Intelligent identification method and device for historical building diseases

Abstract

The present invention discloses an intelligent identification method and device for historical building defects, the method comprising: obtaining point cloud data corresponding to a target historical building and segmenting it to obtain point cloud data of a target building component; determining the defect dimension type corresponding to the target building component and performing a defect identification operation on the target building component based on the defect dimension type to obtain a corresponding defect identification result; and determining an overall defect identification result based on the defect identification results of all target building components corresponding to the target historical building. It can be seen that the present invention can segment the point cloud data of the target historical building, identify the point cloud data of the segmented target building component to obtain a corresponding defect identification result, and further obtain an overall defect identification result, which is conducive to improving the accuracy and efficiency of defect identification of the target building component, and thus improving the accuracy and efficiency of defect identification of the target historical building.

Description

Technical Field

[0001] The present invention relates to the technical field of historical building protection, and in particular to an intelligent identification method and device for historical building diseases. Background Art

[0002] Due to various factors, historical buildings often have various diseases. In the existing technology, the diseases of historical buildings can only be confirmed by naked eye observation. This disease identification method is not only subjective, but also inaccurate and inefficient, which is not conducive to the precise protection and scientific research of ancient buildings. It can be seen that it is particularly important to provide an intelligent identification solution for historical building diseases to improve the accuracy and efficiency of historical building disease identification. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method and device for intelligently identifying defects in historical buildings, which can improve the accuracy and efficiency of defect identification of target historical buildings.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses an intelligent identification method for historical building diseases, the method comprising:

[0005] Obtain point cloud data corresponding to the target historical building;

[0006] Segmenting the point cloud data corresponding to the target historical building to obtain point cloud data of a plurality of target building components to be identified corresponding to the target historical building;

[0007] For each of the target building components, determining the defect dimension type corresponding to the target building component; the defect dimension type includes two-dimensional defects and three-dimensional defects;

[0008] For each of the target building components, based on the point cloud data corresponding to the target building component and the corresponding defect dimension type, a defect identification operation is performed on the target building component to obtain a defect identification result of the target building component;

[0009] Based on the disease identification results of all target building components corresponding to the target historical building, an overall disease identification result corresponding to the target historical building is determined.

[0010] As an optional implementation manner, in the first aspect of the present invention, for each of the target building components, based on the point cloud data corresponding to the target building component and the corresponding defect dimension type, performing a defect identification operation on the target building component to obtain a defect identification result of the target building component includes:

[0011] For each of the target building components, when the defect dimension type corresponding to the target building component is a two-dimensional defect, a target two-dimensional projection view corresponding to the target building component is determined based on the point cloud data corresponding to the target building component, and the target two-dimensional projection view is a plan view of the perspective to be detected corresponding to the target building component whose defect dimension type is a two-dimensional defect; the target two-dimensional projection view corresponding to the target building component is input into a pre-trained two-dimensional defect recognition model to perform a defect recognition operation, and obtain a two-dimensional defect model recognition result corresponding to the target building component; based on the two-dimensional defect model recognition result corresponding to the target building component, a defect recognition result corresponding to the target building component is determined.

[0012] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0013] For each of the target building components, when the defect dimension type corresponding to the target building component is a three-dimensional defect, based on the point cloud data corresponding to the target building component, a target two-dimensional projection view of a plurality of viewing angles corresponding to the target building component is determined; for each target two-dimensional projection view corresponding to the target building component, the target two-dimensional projection view is input into the two-dimensional defect recognition model to perform a defect recognition operation, and a two-dimensional defect model recognition result corresponding to the target two-dimensional projection view is obtained;

[0014] For each of the target building components, an intermediate defect recognition result corresponding to the target building component is determined according to the two-dimensional defect model recognition results of all target two-dimensional projection views corresponding to the target building component; it is judged whether the intermediate defect recognition result corresponding to the target building component meets the preset intermediate defect recognition conditions; if so, the point cloud data corresponding to the target building component is input into a pre-trained three-dimensional defect recognition model to perform a defect recognition operation to obtain a three-dimensional defect model recognition result corresponding to the target building component; based on the three-dimensional defect model recognition result corresponding to the target building component, the defect recognition result corresponding to the target building component is determined.

[0015] As an optional embodiment, in the first aspect of the present invention, the target building components whose damage dimension type is three-dimensional damage include beams and columns;

[0016] And, the method further comprises:

[0017] When the target building component includes beams and columns, based on the defect identification result corresponding to the target building component, it is judged whether the target building component has a column bending defect; when the target building component has a column bending defect, based on the point cloud data corresponding to the target building component, the target building component is segmented to obtain a plurality of component partition point clouds corresponding to the target building component; the center of each component partition point cloud corresponding to the target building component is determined; based on the center of each component partition point cloud corresponding to the target building component, the center trajectory of the target building component is determined; based on the center trajectory of the target building component, it is judged whether the center trajectory of the target building component meets the preset beam-column center trajectory condition; if not, the target building component is determined as the first target defective component.

[0018] As an optional embodiment, in the first aspect of the present invention, the target building component whose defect dimension type is two-dimensional defect includes a sill wall;

[0019] And, the method further comprises:

[0020] When the target building component includes a sill wall, judging whether the target building component has crack damage based on the damage identification result corresponding to the target building component;

[0021] When crack damage exists in the target building component, the damage information of the crack damage corresponding to the target building component is determined based on the two-dimensional projection view corresponding to the target building component; the damage information includes the number of cracks, the size of cracks, the width of cracks and the area of ​​cracks corresponding to the target building component; it is judged whether the damage information of the crack damage corresponding to the target building component meets the preset crack damage condition; if so, the target building component is determined as the second target defective component.

[0022] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0023] Determine the regional environmental characteristics corresponding to the target historical building; the regional environmental characteristics include regional climate characteristics and regional surface characteristics; based on the regional environmental characteristics corresponding to the target historical building, determine the regional environmental parameters corresponding to the target historical building;

[0024] Determine a number of similar historical buildings corresponding to the target historical building; for each target building component, compare and analyze the disease identification result of the target building component in the target historical building with the disease identification result of the target building component in each of the similar historical buildings to obtain the relative disease parameter of the target building component in the target historical building; determine the overall relative disease parameter corresponding to the target historical building based on the relative disease parameters of all the target building components in the target historical building;

[0025] Determining the overall disease parameters corresponding to the target historical building based on the overall disease identification result corresponding to the target historical building;

[0026] Based on the overall damage parameters, the corresponding overall relative damage parameters and the corresponding regional environmental parameters corresponding to the target historical building, the building protection grade parameters corresponding to the target historical building are determined.

[0027] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0028] Determining a component type of each target building component of the target historic building;

[0029] For each of the target building components, based on the component type and the defect identification result of the target building component, determine whether the target building component needs to be repaired; if the target building component needs to be repaired, determine the point cloud data of the non-defective building component corresponding to the target building component from a predetermined building component point cloud database; based on the point cloud data corresponding to the target building component, determine the size information corresponding to the target building component; based on the size information corresponding to the target building component, perform an optimization operation on the point cloud data of the non-defective building component corresponding to the target building component to obtain the point cloud data of the target non-defective building component corresponding to the target building component;

[0030] Based on the point cloud data of the target building components that do not need to perform repair operations corresponding to the target historical building, and the point cloud data of the target non-defective building components corresponding to the target building components that need to perform repair operations, the predicted repair point cloud data corresponding to the target historical building is determined.

[0031] The second aspect of the present invention discloses an intelligent device for identifying defects in historical buildings, the device comprising:

[0032] An acquisition module is used to obtain point cloud data corresponding to the target historical building;

[0033] A segmentation module, used to segment the point cloud data corresponding to the target historical building to obtain point cloud data of a plurality of target building components to be identified corresponding to the target historical building;

[0034] A first determination module is used to determine, for each target building component, a defect dimension type corresponding to the target building component; the defect dimension type includes two-dimensional defects and three-dimensional defects;

[0035] an identification module, configured to perform a defect identification operation on each target building component based on the point cloud data corresponding to the target building component and the corresponding defect dimension type, to obtain a defect identification result of the target building component;

[0036] The second determination module is used to determine the overall disease identification result corresponding to the target historical building based on the disease identification results of all target building components corresponding to the target historical building.

[0037] As an optional implementation, in the second aspect of the present invention, the identification module includes:

[0038] The first identification submodule is used to determine, for each of the target building components, a target two-dimensional projection view corresponding to the target building component based on the point cloud data corresponding to the target building component when the defect dimension type corresponding to the target building component is a two-dimensional defect, wherein the target two-dimensional projection view is a plan view of a perspective to be detected corresponding to the target building component whose defect dimension type is a two-dimensional defect; input the target two-dimensional projection view corresponding to the target building component into a pre-trained two-dimensional defect recognition model to perform a defect recognition operation to obtain a two-dimensional defect model recognition result corresponding to the target building component; and determine a defect recognition result corresponding to the target building component based on the two-dimensional defect model recognition result corresponding to the target building component.

[0039] As an optional implementation, in the second aspect of the present invention, the identification module further includes:

[0040] The second recognition submodule is used for, for each of the target building components, when the defect dimension type corresponding to the target building component is a three-dimensional defect, determining the target two-dimensional projection views of several viewing angles corresponding to the target building component based on the point cloud data corresponding to the target building component; for each target two-dimensional projection view corresponding to the target building component, inputting the target two-dimensional projection view into the two-dimensional defect recognition model to perform a defect recognition operation, and obtaining a two-dimensional defect model recognition result corresponding to the target two-dimensional projection view; for each of the target building components, determining an intermediate defect recognition result corresponding to the target building component according to the two-dimensional defect model recognition results of all target two-dimensional projection views corresponding to the target building component; judging whether the intermediate defect recognition result corresponding to the target building component meets a preset intermediate defect recognition condition, and if so, inputting the point cloud data corresponding to the target building component into a pre-trained three-dimensional defect recognition model to perform a defect recognition operation, and obtaining a three-dimensional defect model recognition result corresponding to the target building component; and determining the defect recognition result corresponding to the target building component based on the three-dimensional defect model recognition result corresponding to the target building component.

[0041] As an optional embodiment, in the second aspect of the present invention, the target building components whose damage dimension type is three-dimensional damage include beams and columns;

[0042] And, the identification module also includes:

[0043] The first judgment submodule is used for judging whether the target building component has a column bending defect based on the defect identification result corresponding to the target building component when the target building component includes a beam and a column; when the target building component has a column bending defect, segmenting the target building component based on the point cloud data corresponding to the target building component to obtain a plurality of component partition point clouds corresponding to the target building component; determining the center of each component partition point cloud corresponding to the target building component; determining the center trajectory of the target building component based on the center of each component partition point cloud corresponding to the target building component; judging whether the center trajectory of the target building component meets the preset beam and column center trajectory condition based on the center trajectory of the target building component; if not, determining the target building component as the first target defective component.

[0044] As an optional embodiment, in the second aspect of the present invention, the target building component whose defect dimension type is two-dimensional defect includes a sill wall;

[0045] And, the identification module also includes:

[0046] The second judgment submodule is used to judge whether the target building component has crack disease based on the disease identification result corresponding to the target building component when the target building component includes a sill wall; when the target building component has crack disease, determine the disease information of the crack disease corresponding to the target building component based on the two-dimensional projection view corresponding to the target building component; the disease information includes the number of cracks, crack size, crack width and crack area of ​​the crack disease corresponding to the target building component; judge whether the disease information of the crack disease corresponding to the target building component meets the preset crack disease condition; if so, determine the target building component as the second target diseased component.

[0047] As an optional implementation, in the second aspect of the present invention, the device further includes:

[0048] A grading module is used to determine the regional environmental characteristics corresponding to the target historical building; the regional environmental characteristics include regional climate characteristics and regional surface characteristics; based on the regional environmental characteristics corresponding to the target historical building, determine the regional environmental parameters corresponding to the target historical building; determine a number of similar historical buildings corresponding to the target historical building; for each target building component, compare and analyze the disease identification result of the target building component in the target historical building with the disease identification result of the target building component in each of the similar historical buildings to obtain the relative disease parameter of the target building component in the target historical building; based on the relative disease parameters of all the target building components in the target historical building, determine the overall relative disease parameter corresponding to the target historical building; based on the overall disease identification result corresponding to the target historical building, determine the overall disease parameter corresponding to the target historical building; based on the overall disease parameter corresponding to the target historical building, the corresponding overall relative disease parameter and the corresponding regional environmental parameter, determine the building protection grade parameter corresponding to the target historical building.

[0049] As an optional implementation, in the second aspect of the present invention, the device further includes:

[0050] The prediction module is used to determine the component type of each target building component of the target historical building; for each target building component, based on the component type of the target building component and the defect identification result, determine whether the target building component needs to be repaired; if the target building component needs to be repaired, determine the point cloud data of the non-defective building component corresponding to the target building component from a predetermined building component point cloud database; based on the point cloud data corresponding to the target building component, determine the size information corresponding to the target building component; based on the size information corresponding to the target building component, perform an optimization operation on the point cloud data of the non-defective building component corresponding to the target building component to obtain the point cloud data of the target non-defective building component corresponding to the target building component; based on the point cloud data of the target building component that does not need to be repaired corresponding to the target historical building and the point cloud data of the target non-defective building component corresponding to the target building component that needs to be repaired, determine the predicted repair point cloud data corresponding to the target historical building.

[0051] The third aspect of the present invention discloses another intelligent identification system for historical building defects, the system comprising:

[0052] A memory storing executable program code;

[0053] a processor coupled to the memory;

[0054] The processor calls the executable program code stored in the memory to execute the steps of the intelligent identification method for historical building diseases disclosed in the first aspect of the present invention.

[0055] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps in the intelligent identification method of historical building diseases disclosed in the first aspect of the present invention.

[0056] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0057] The present invention obtains point cloud data corresponding to the target historical building and performs segmentation to obtain point cloud data of the target building component; determines the defect dimension type corresponding to the target building component and performs a defect identification operation on the target building component based on the defect dimension type to obtain a corresponding defect identification result; and determines an overall defect identification result based on the defect identification results of all target building components corresponding to the target historical building. It can be seen that the present invention can segment the point cloud data of the target historical building, identify the segmented point cloud data of the target building component to obtain a corresponding defect identification result, and further obtain an overall defect identification result, which is conducive to improving the defect identification accuracy of the target building component, and then improving the defect identification accuracy of the target historical building. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0059] Figure 1 It is a flow chart of an intelligent identification method for historical building defects disclosed in an embodiment of the present invention;

[0060] Figure 2 It is a schematic diagram of the beam-column center trajectory condition disclosed in an embodiment of the present invention;

[0061] Figure 3 It is a structural schematic diagram of an intelligent identification device for historical building defects disclosed in an embodiment of the present invention;

[0062] Figure 4 It is a structural schematic diagram of an intelligent identification system for historical building defects disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0064] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or terminal including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or terminals.

[0065] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0066] The present invention discloses an intelligent identification method and device for historical building defects. The method described in the embodiment of the present invention can segment the point cloud data of the target historical building, identify the segmented point cloud data of the target building components to obtain the corresponding defect identification results, and further obtain the overall defect identification results, which is conducive to improving the accuracy of defect identification of the target building components, and further improves the accuracy of defect identification of the target historical building. The following are detailed descriptions.

[0067] Embodiment 1

[0068] See also Figure 1 , Figure 1 1 is a flow chart of an intelligent identification method for historical building defects disclosed in an embodiment of the present invention. Figure 1 The described method can be applied to any intelligent identification scenario of historical building defects, and the embodiments of the present invention are not limited thereto. Figure 1 As shown, the intelligent identification method of historical building diseases includes the following operations:

[0069] 101. Obtain point cloud data corresponding to the target historical building;

[0070] In an embodiment of the present invention, point cloud data of the target historical building can be collected by a three-dimensional laser scanner. After pre-processing such as denoising, smoothing, and alignment, the collected massive data is integrated and processed to obtain the precise three-dimensional dimensions of each component of the historical building. A BIM model of the historical building is established through modeling software. The specific method is not limited in the embodiment of the present invention.

[0071] 102. Segment the point cloud data corresponding to the target historical building to obtain point cloud data of a plurality of target building components to be identified corresponding to the target historical building;

[0072] In the embodiment of the present invention, the segmentation of point cloud data can be performed by using PointNet to use MLP to extract the features of each point, and the global features are combined with the local point features point by point on the basis of global feature aggregation to generate a classification result for each point, and finally a category label is predicted for each point; the segmentation of point cloud data can also be performed by customization, and the specific method is not limited in the embodiment of the present invention.

[0073] 103. For each target building component, determine a defect dimension type corresponding to the target building component; the defect dimension type includes two-dimensional defects and three-dimensional defects;

[0074] In the embodiments of the present invention, it is understandable that the defects of some target building components such as sill walls are mainly manifested in the plane; while the defects of some target building components such as beams, columns, brackets, etc. are mainly manifested in the three-dimensional angle.

[0075] 104. For each target building component, based on the point cloud data corresponding to the target building component and the corresponding defect dimension type, a defect identification operation is performed on the target building component to obtain a defect identification result of the target building component;

[0076] In the embodiment of the present invention, it can be understood that the defect identification result can include whether the target building component has a defect, and can also include parameters such as the specific size and type of the defect, which is not limited in the embodiment of the present invention.

[0077] 105. Based on the disease identification results of all target building components corresponding to the target historical building, determine the overall disease identification result corresponding to the target historical building.

[0078] In the embodiment of the present invention, it can be understood that the overall defect identification result can be the superposition of the defect identification results of each target building component, and can also be further analyzed based on the connection relationship between different target building components, etc., which is not limited in the embodiment of the present invention.

[0079] It can be seen that the implementation of the embodiment of the present invention can obtain the point cloud data corresponding to the target historical building and perform segmentation to obtain the point cloud data of the target building components; determine the defect dimension type corresponding to the target building components and perform a defect identification operation on the target building components based on the defect dimension type to obtain the corresponding defect identification result; based on the defect identification results of all target building components corresponding to the target historical building, determine the overall defect identification result, which is conducive to improving the defect identification accuracy of the target building components, and then improve the defect identification accuracy of the target historical building.

[0080] In an optional embodiment, for each target building component, based on the point cloud data corresponding to the target building component and the corresponding defect dimension type, performing a defect identification operation on the target building component to obtain a defect identification result of the target building component may include:

[0081] For each target building component, when the defect dimension type corresponding to the target building component is a two-dimensional defect, a target two-dimensional projection view corresponding to the target building component is determined based on the point cloud data corresponding to the target building component, the target two-dimensional projection view being a plan view of a perspective to be detected corresponding to the target building component whose defect dimension type is a two-dimensional defect; the target two-dimensional projection view corresponding to the target building component is input into a pre-trained two-dimensional defect recognition model to perform a defect recognition operation, and obtain a two-dimensional defect model recognition result corresponding to the target building component; based on the two-dimensional defect model recognition result corresponding to the target building component, a defect recognition result corresponding to the target building component is determined.

[0082] In this optional embodiment, it is understood that the target two-dimensional projection view can select the direct view of the target building component that can most clearly show the defect, which is determined by the point cloud data corresponding to the direct view, or can be customized, and the specific method is not limited in the embodiment of the present invention. The pre-trained two-dimensional defect recognition model can be a CNN model based on deep learning, or a model trained based on AlexNet, VGG, GoogleNet, ResNet, ResNetXt, etc., or it can be a point cloud directly rendered into a view and feature learning is performed using traditional image convolution, which is not limited in the embodiment of the present invention.

[0083] It can be seen that the implementation of this optional embodiment can determine the target two-dimensional projection view based on the corresponding point cloud data when the defect dimension type corresponding to the target building component is a two-dimensional defect, and input the target two-dimensional projection view into the two-dimensional defect recognition model to perform defect recognition to obtain a defect recognition result, which is beneficial to improve the determination accuracy of the defect recognition result corresponding to the target building component, and thereby improve the accuracy of defect recognition of the target historical building.

[0084] In another optional embodiment, the method may further include:

[0085] For each target building component, when the defect dimension type corresponding to the target building component is a three-dimensional defect, based on the point cloud data corresponding to the target building component, a target two-dimensional projection view of several viewing angles corresponding to the target building component is determined; for each target two-dimensional projection view corresponding to the target building component, the target two-dimensional projection view is input into the two-dimensional defect recognition model to perform a defect recognition operation, and a two-dimensional defect model recognition result corresponding to the target two-dimensional projection view is obtained;

[0086] For each target building component, an intermediate defect recognition result corresponding to the target building component is determined according to the two-dimensional defect model recognition results of all target two-dimensional projection views corresponding to the target building component; it is judged whether the intermediate defect recognition result corresponding to the target building component meets the preset intermediate defect recognition conditions; if so, the point cloud data corresponding to the target building component is input into a pre-trained three-dimensional defect recognition model to perform a defect recognition operation to obtain a three-dimensional defect model recognition result corresponding to the target building component; based on the three-dimensional defect model recognition result corresponding to the target building component, the defect recognition result corresponding to the target building component is determined.

[0087] In this optional embodiment, for example, if the target building component is a beam, the target two-dimensional projection views of several perspectives can be multiple perspective images corresponding to the beam, and the perspective images are determined by the point cloud data corresponding to the beam, or can be specified in other ways, and the specific way is not limited in the embodiment of the present invention. Among them, the pre-trained three-dimensional defect recognition model can be obtained by training PointNet or PointNet++ based on a multi-layer perceptron, or by training PointCNN based on a convolutional neural network, or by training based on a graph convolutional neural network or an attention mechanism, and the specific way is not limited in the embodiment of the present invention.

[0088] It can be seen that the implementation of this optional embodiment can determine the target two-dimensional projection views of several perspectives based on the corresponding point cloud data when the defect dimension type corresponding to the target building component is a three-dimensional defect, and input them into the two-dimensional defect recognition model to perform defect recognition. If the defect recognition result meets the conditions, the point cloud data corresponding to the target building component is input into the three-dimensional defect recognition model to perform defect recognition, which is beneficial to improve the determination accuracy of the defect recognition result corresponding to the target building component, and thereby improve the accuracy of defect recognition of the target historical building.

[0089] In yet another optional embodiment, the target building components whose defect dimension type is three-dimensional defect include beams and columns;

[0090] And, the method may further include:

[0091] When the target building component includes beams and columns, based on the defect identification result corresponding to the target building component, it is judged whether the target building component has a column bending defect; when the target building component has a column bending defect, based on the point cloud data corresponding to the target building component, the target building component is segmented to obtain a plurality of component partition point clouds corresponding to the target building component; the center of each component partition point cloud corresponding to the target building component is determined; based on the center of each component partition point cloud corresponding to the target building component, the center trajectory of the target building component is determined; based on the center trajectory of the target building component, it is judged whether the center trajectory of the target building component meets the preset beam-column center trajectory condition; if not, the target building component is determined as the first target defective component.

[0092] In this optional embodiment, it is understood that if Figure 2 The figure is a schematic diagram of the beam-column center trajectory condition disclosed in an embodiment of the present invention. The center trajectory condition may refer to the center trajectory being an approximate straight line. If the center trajectory of the target building component is not an approximate straight line but an arc with a large curvature, it can be considered that the center trajectory of the target building component does not meet the preset beam-column center trajectory condition; the beam-column center trajectory condition may also be set in other ways, and the specific way is not limited in the embodiment of the present invention.

[0093] It can be seen that the implementation of this optional embodiment can determine whether the target building component has a column bending disease based on the disease identification result of the target building component when the target building component includes beams and columns; if it does, further analyze the center trajectory of the circle; if the center trajectory does not meet the conditions, it is determined as the first target diseased component, which is conducive to further improving the accuracy of the analysis of the disease of the target building component, and then improving the accuracy of disease identification of the target historical building.

[0094] In yet another optional embodiment, the target building component whose defect dimension type is a two-dimensional defect includes a sill wall;

[0095] And, the method may further include:

[0096] When the target building component includes a sill wall, judging whether the target building component has crack damage based on the damage identification result corresponding to the target building component;

[0097] When a target building component has crack damage, the damage information of the crack damage corresponding to the target building component is determined based on the two-dimensional projection view corresponding to the target building component; the damage information includes the number of cracks, the size of cracks, the width of cracks and the area of ​​cracks corresponding to the target building component; it is judged whether the damage information of the crack damage corresponding to the target building component meets the preset crack damage condition; if so, the target building component is determined as the second target defective component.

[0098] In this optional embodiment, it can be understood that the crack disease condition can be any one of the number of cracks, crack size, crack width and crack area, or each of which reaches a corresponding threshold value, and the specific method is not limited in the embodiment of the present invention.

[0099] It can be seen that the implementation of this optional embodiment can determine whether the target building component has crack disease based on the disease identification result of the target building component when the target building component includes a sill wall; if it does, the disease information of the crack disease corresponding to the target building component is further determined, and if the disease information meets the conditions, it is determined as the second target diseased component, which is conducive to further improving the accuracy of the analysis of the target building component diseases, and then improving the accuracy of disease identification of the target historical building.

[0100] In yet another optional embodiment, the method may further include:

[0101] Determine the regional environmental characteristics corresponding to the target historical building; the regional environmental characteristics include regional climate characteristics and regional surface characteristics; based on the regional environmental characteristics corresponding to the target historical building, determine the regional environmental parameters corresponding to the target historical building;

[0102] Determine a number of similar historical buildings corresponding to the target historical building; for each target building component, compare and analyze the damage identification result of the target building component in the target historical building with the damage identification result of the target building component in each similar historical building to obtain the relative damage parameter of the target building component in the target historical building; determine the overall relative damage parameter corresponding to the target historical building based on the relative damage parameters of all target building components in the target historical building;

[0103] Based on the overall disease identification results corresponding to the target historical building, determine the overall disease parameters corresponding to the target historical building;

[0104] Based on the overall damage parameters, the corresponding overall relative damage parameters and the corresponding regional environmental parameters corresponding to the target historical building, the building protection grade parameters corresponding to the target historical building are determined.

[0105] In this optional embodiment, it can be understood that the building protection grade parameters can be used to determine whether the historical building is the focus of attention, key protection or regular inspection, the regional climate characteristics can include temperature conditions, humidity conditions, wind conditions, etc., and the regional surface characteristics can include soil conditions, terrain conditions, etc., which are not limited in this embodiment of the present invention.

[0106] It can be seen that the implementation of this optional embodiment can determine the regional environmental parameters based on the regional environmental characteristics corresponding to the target historical building, determine the overall relative disease parameters based on a number of similar historical buildings corresponding to the target historical building, determine the corresponding overall disease parameters based on the overall disease identification results corresponding to the target historical building, and further determine the building protection grade parameters corresponding to the target historical building, which is conducive to improving the accuracy of determining the building protection grade parameters, and thereby improving the accuracy and efficiency of protecting historical buildings.

[0107] In yet another optional embodiment, the method may further include:

[0108] determining the component type of each target building component of the target historic building;

[0109] For each target building component, based on the component type of the target building component and the defect identification result, determine whether the target building component needs to be repaired; if the target building component needs to be repaired, determine the point cloud data of the non-defective building component corresponding to the target building component from a predetermined building component point cloud database; based on the point cloud data corresponding to the target building component, determine the size information corresponding to the target building component; based on the size information corresponding to the target building component, perform an optimization operation on the point cloud data of the non-defective building component corresponding to the target building component to obtain the point cloud data of the target non-defective building component corresponding to the target building component;

[0110] Based on the point cloud data of target building components that do not require repair operations corresponding to the target historical building, and the point cloud data of target non-defective building components that require repair operations corresponding to the target building components, the predicted repair point cloud data corresponding to the target historical building is determined.

[0111] In this optional embodiment, it is understood that the optimization operation is performed on the point cloud data of the non-damaged building component corresponding to the target building component in order to make the non-damaged building component corresponding to the target building component more compatible with the target building component in terms of size, etc. The predicted repair point cloud data can generate and display a model of the historical building before it is damaged or a repaired model.

[0112] It can be seen that the implementation of this optional embodiment can determine whether a repair operation needs to be performed based on the component type of the target building component and the defect identification result. If necessary, the point cloud data of the corresponding non-defective building component is determined and an optimization operation is performed on it. The corresponding predicted repair point cloud data is determined based on the point cloud data of the target non-defective building component corresponding to the optimized target building component and the point cloud data of the target building component that does not need to be repaired, which is beneficial to improving the determination accuracy of the corresponding predicted repair point cloud data, and thereby improving the accuracy and efficiency of the repair of historical buildings.

[0113] Embodiment 2

[0114] See also Figure 3 , Figure 3 1 is a schematic diagram of the structure of an intelligent identification device for historical building defects disclosed in an embodiment of the present invention. Figure 3 The described device can be applied to any intelligent identification scenario of historical building defects, and the embodiments of the present invention are not limited thereto. Figure 3 As shown, the intelligent identification device for historical building diseases may include:

[0115] An acquisition module 201 is used to acquire point cloud data corresponding to a target historical building;

[0116] The segmentation module 202 is used to segment the point cloud data corresponding to the target historical building to obtain point cloud data of a plurality of target building components to be identified corresponding to the target historical building;

[0117] The first determination module 203 is used to determine, for each target building component, the type of defect dimension corresponding to the target building component; the defect dimension type includes two-dimensional defects and three-dimensional defects;

[0118] The identification module 204 is used to perform a defect identification operation on each target building component based on the point cloud data corresponding to the target building component and the corresponding defect dimension type to obtain a defect identification result of the target building component;

[0119] The second determination module 205 is used to determine the overall disease identification result corresponding to the target historical building based on the disease identification results of all target building components corresponding to the target historical building.

[0120] It can be seen that the device described in the embodiment of the present invention can obtain the point cloud data corresponding to the target historical building and perform segmentation to obtain the point cloud data of the target building components; determine the defect dimension type corresponding to the target building components and perform a defect identification operation on the target building components based on the defect dimension type to obtain the corresponding defect identification result; determine the overall defect identification result based on the defect identification results of all target building components corresponding to the target historical building, which is conducive to improving the defect identification accuracy of the target building components, and then improving the defect identification accuracy of the target historical building.

[0121] In an optional embodiment, the identification module 204 may include:

[0122] The first identification submodule is used to determine, for each target building component, a target two-dimensional projection view corresponding to the target building component based on the point cloud data corresponding to the target building component when the defect dimension type corresponding to the target building component is a two-dimensional defect, the target two-dimensional projection view being a plan view of a perspective to be detected corresponding to the target building component with a defect dimension type of two-dimensional disease; input the target two-dimensional projection view corresponding to the target building component into a pre-trained two-dimensional defect recognition model to perform a defect recognition operation to obtain a two-dimensional defect model recognition result corresponding to the target building component; and determine a defect recognition result corresponding to the target building component based on the two-dimensional defect model recognition result corresponding to the target building component.

[0123] It can be seen that the implementation of this optional embodiment can determine the target two-dimensional projection view based on the corresponding point cloud data when the defect dimension type corresponding to the target building component is a two-dimensional defect, and input the target two-dimensional projection view into the two-dimensional defect recognition model to perform defect recognition to obtain a defect recognition result, which is beneficial to improve the determination accuracy of the defect recognition result corresponding to the target building component, and thereby improve the accuracy of defect recognition of the target historical building.

[0124] In another optional embodiment, the identification module 204 may further include:

[0125] The second recognition submodule is used for, for each target building component, when the defect dimension type corresponding to the target building component is a three-dimensional defect, determining the target two-dimensional projection views of several viewing angles corresponding to the target building component based on the point cloud data corresponding to the target building component; for each target two-dimensional projection view corresponding to the target building component, inputting the target two-dimensional projection view into the two-dimensional defect recognition model to perform a defect recognition operation, and obtaining a two-dimensional defect model recognition result corresponding to the target two-dimensional projection view; for each target building component, determining the intermediate defect recognition result corresponding to the target building component according to the two-dimensional defect model recognition results of all target two-dimensional projection views corresponding to the target building component; judging whether the intermediate defect recognition result corresponding to the target building component meets a preset intermediate defect recognition condition, and if so, inputting the point cloud data corresponding to the target building component into a pre-trained three-dimensional defect recognition model to perform a defect recognition operation, and obtaining a three-dimensional defect model recognition result corresponding to the target building component; and determining the defect recognition result corresponding to the target building component based on the three-dimensional defect model recognition result corresponding to the target building component.

[0126] It can be seen that the implementation of this optional embodiment can determine the target two-dimensional projection views of several perspectives based on the corresponding point cloud data when the defect dimension type corresponding to the target building component is a three-dimensional defect, and input them into the two-dimensional defect recognition model to perform defect recognition. If the defect recognition result meets the conditions, the point cloud data corresponding to the target building component is input into the three-dimensional defect recognition model to perform defect recognition, which is beneficial to improve the determination accuracy of the defect recognition result corresponding to the target building component, and thereby improve the accuracy of defect recognition of the target historical building.

[0127] In yet another optional embodiment, the target building components whose defect dimension type is three-dimensional defect include beams and columns;

[0128] And, the identification module 204 may also include:

[0129] The first judgment submodule is used to judge whether the target building component has a column bending defect based on the defect identification result corresponding to the target building component when the target building component includes a beam and a column; when the target building component has a column bending defect, segment the target building component based on the point cloud data corresponding to the target building component to obtain a plurality of component partition point clouds corresponding to the target building component; determine the center of each component partition point cloud corresponding to the target building component; determine the center trajectory of the target building component based on the center of each component partition point cloud corresponding to the target building component; judge whether the center trajectory of the target building component meets the preset beam-column center trajectory condition based on the center trajectory of the target building component; if not, determine the target building component as the first target defective component.

[0130] It can be seen that the implementation of this optional embodiment can determine whether the target building component has a column bending disease based on the disease identification result of the target building component when the target building component includes beams and columns; if it does, further analyze the center trajectory of the circle; if the center trajectory does not meet the conditions, it is determined as the first target diseased component, which is conducive to further improving the accuracy of the analysis of the disease of the target building component, and then improving the accuracy of disease identification of the target historical building.

[0131] In yet another optional embodiment, the target building component whose defect dimension type is a two-dimensional defect includes a sill wall;

[0132] And, the identification module 204 may also include:

[0133] The second judgment submodule is used to judge whether the target building component has crack disease based on the disease identification result corresponding to the target building component when the target building component includes a sill wall; when the target building component has crack disease, determine the disease information of the crack disease corresponding to the target building component based on the two-dimensional projection view corresponding to the target building component; the disease information includes the number of cracks, the size of cracks, the width of cracks and the area of ​​cracks corresponding to the target building component; judge whether the disease information of the crack disease corresponding to the target building component meets the preset crack disease condition; if so, determine the target building component as the second target diseased component.

[0134] It can be seen that the implementation of this optional embodiment can determine whether the target building component has crack disease based on the disease identification result of the target building component when the target building component includes a sill wall; if it does, the disease information of the crack disease corresponding to the target building component is further determined, and if the disease information meets the conditions, it is determined as the second target diseased component, which is conducive to further improving the accuracy of the analysis of the target building component diseases, and then improving the accuracy of disease identification of the target historical building.

[0135] In yet another optional embodiment, the device may further include:

[0136] The grading module is used to determine the regional environmental characteristics corresponding to the target historical building; the regional environmental characteristics include regional climate characteristics and regional surface characteristics; based on the regional environmental characteristics corresponding to the target historical building, determine the regional environmental parameters corresponding to the target historical building; determine a number of similar historical buildings corresponding to the target historical building; for each target building component, compare and analyze the disease identification result of the target building component in the target historical building with the disease identification result of the target building component in each similar historical building to obtain the relative disease parameter of the target building component in the target historical building; based on the relative disease parameters of all target building components in the target historical building, determine the overall relative disease parameters corresponding to the target historical building; based on the overall disease identification result corresponding to the target historical building, determine the overall disease parameters corresponding to the target historical building; based on the overall disease parameters corresponding to the target historical building, the corresponding overall relative disease parameters and the corresponding regional environmental parameters, determine the building protection grade parameters corresponding to the target historical building.

[0137] It can be seen that the implementation of this optional embodiment can determine the regional environmental parameters based on the regional environmental characteristics corresponding to the target historical building, determine the overall relative disease parameters based on a number of similar historical buildings corresponding to the target historical building, determine the corresponding overall disease parameters based on the overall disease identification results corresponding to the target historical building, and further determine the building protection grade parameters corresponding to the target historical building, which is conducive to improving the accuracy of determining the building protection grade parameters, and thereby improving the accuracy and efficiency of protecting historical buildings.

[0138] In yet another optional embodiment, the device may further include:

[0139] The prediction module is used to determine the component type of each target building component of the target historical building; for each target building component, based on the component type of the target building component and the defect identification result, determine whether the target building component needs to be repaired; if the target building component needs to be repaired, determine the point cloud data of the non-defective building component corresponding to the target building component from a predetermined building component point cloud database; based on the point cloud data corresponding to the target building component, determine the size information corresponding to the target building component; based on the size information corresponding to the target building component, perform an optimization operation on the point cloud data of the non-defective building component corresponding to the target building component to obtain the point cloud data of the target non-defective building component corresponding to the target building component; based on the point cloud data of the target building component that does not need to be repaired corresponding to the target historical building and the point cloud data of the target non-defective building component corresponding to the target building component that needs to be repaired, determine the predicted repair point cloud data corresponding to the target historical building.

[0140] It can be seen that the implementation of this optional embodiment can determine whether a repair operation needs to be performed based on the component type of the target building component and the defect identification result. If necessary, the point cloud data of the corresponding non-defective building component is determined and an optimization operation is performed on it. The corresponding predicted repair point cloud data is determined based on the point cloud data of the target non-defective building component corresponding to the optimized target building component and the point cloud data of the target building component that does not need to be repaired, which is beneficial to improving the determination accuracy of the corresponding predicted repair point cloud data, and thereby improving the accuracy and efficiency of the repair of historical buildings.

[0141] Embodiment 3

[0142] See also Figure 4 , Figure 4 FIG. 1 is a schematic diagram of the structure of another intelligent identification system for historical building defects disclosed in an embodiment of the present invention. Figure 4 The intelligent identification system for the historical building defects shown may include:

[0143] A memory 301 storing executable program codes;

[0144] a processor 302 coupled to the memory 301;

[0145] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the intelligent identification method for historical building diseases described in the first embodiment of the present invention.

[0146] Embodiment 4

[0147] The embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps of intelligent identification of historical building diseases described in the first embodiment of the present invention.

[0148] Embodiment 5

[0149] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps in the intelligent identification method for historical building diseases described in Example 1.

[0150] The system embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative labor.

[0151] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0152] Finally, it should be noted that the intelligent identification method and device for historical building diseases disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent identification method for historical building defects, characterized in that: The method comprises: Obtain point cloud data corresponding to the target historical building; Segmenting the point cloud data corresponding to the target historical building to obtain point cloud data of a plurality of target building components to be identified corresponding to the target historical building; For each of the target building components, determining the defect dimension type corresponding to the target building component; the defect dimension type includes two-dimensional defects and three-dimensional defects; For each of the target building components, when the defect dimension type corresponding to the target building component is a two-dimensional defect, based on the point cloud data corresponding to the target building component, a target two-dimensional projection view corresponding to the target building component is determined, wherein the target two-dimensional projection view is a plane view of a to-be-detected viewing angle corresponding to the target building component whose defect dimension type is a two-dimensional defect; the target two-dimensional projection view corresponding to the target building component is input into a pre-trained two-dimensional defect recognition model to perform a defect recognition operation, and obtain a two-dimensional defect model recognition result corresponding to the target building component; based on the two-dimensional defect model recognition result corresponding to the target building component, a defect recognition result corresponding to the target building component is determined; Based on the disease identification results of all target building components corresponding to the target historical building, an overall disease identification result corresponding to the target historical building is determined.

2. The intelligent identification method for historical building defects according to claim 1, characterized in that: The method further comprises: For each of the target building components, when the defect dimension type corresponding to the target building component is a three-dimensional defect, based on the point cloud data corresponding to the target building component, a target two-dimensional projection view of a plurality of viewing angles corresponding to the target building component is determined; for each target two-dimensional projection view corresponding to the target building component, the target two-dimensional projection view is input into the two-dimensional defect recognition model to perform a defect recognition operation, and a two-dimensional defect model recognition result corresponding to the target two-dimensional projection view is obtained; For each of the target building components, an intermediate defect recognition result corresponding to the target building component is determined according to the two-dimensional defect model recognition results of all target two-dimensional projection views corresponding to the target building component; it is judged whether the intermediate defect recognition result corresponding to the target building component meets the preset intermediate defect recognition conditions; if so, the point cloud data corresponding to the target building component is input into a pre-trained three-dimensional defect recognition model to perform a defect recognition operation to obtain a three-dimensional defect model recognition result corresponding to the target building component; based on the three-dimensional defect model recognition result corresponding to the target building component, the defect recognition result corresponding to the target building component is determined.

3. The intelligent identification method for historical building defects as claimed in claim 2, characterized in that: The target building components whose damage dimension type is three-dimensional damage include beams and columns; And, the method further comprises: When the target building component includes beams and columns, based on the defect identification result corresponding to the target building component, it is judged whether the target building component has a column bending defect; when the target building component has a column bending defect, based on the point cloud data corresponding to the target building component, the target building component is segmented to obtain a plurality of component partition point clouds corresponding to the target building component; the center of each component partition point cloud corresponding to the target building component is determined; based on the center of each component partition point cloud corresponding to the target building component, the center trajectory of the target building component is determined; based on the center trajectory of the target building component, it is judged whether the center trajectory of the target building component meets the preset beam-column center trajectory condition; if not, the target building component is determined as the first target defective component.

4. The intelligent identification method for historical building defects as claimed in claim 3, characterized in that: The target building components whose damage dimension type is two-dimensional damage include sill walls; And, the method further comprises: When the target building component includes a sill wall, judging whether the target building component has crack damage based on the damage identification result corresponding to the target building component; When crack damage exists in the target building component, the damage information of the crack damage corresponding to the target building component is determined based on the two-dimensional projection view corresponding to the target building component; the damage information includes the number of cracks, the size of cracks, the width of cracks and the area of ​​cracks corresponding to the target building component; it is judged whether the damage information of the crack damage corresponding to the target building component meets the preset crack damage condition; if so, the target building component is determined as the second target defective component.

5. The intelligent identification method for historical building defects according to claim 1, characterized in that: The method further comprises: Determine the regional environmental characteristics corresponding to the target historical building; the regional environmental characteristics include regional climate characteristics and regional surface characteristics; based on the regional environmental characteristics corresponding to the target historical building, determine the regional environmental parameters corresponding to the target historical building; Determine a number of similar historical buildings corresponding to the target historical building; for each target building component, compare and analyze the disease identification result of the target building component in the target historical building with the disease identification result of the target building component in each of the similar historical buildings to obtain the relative disease parameter of the target building component in the target historical building; determine the overall relative disease parameter corresponding to the target historical building based on the relative disease parameters of all the target building components in the target historical building; Determining the overall disease parameters corresponding to the target historical building based on the overall disease identification result corresponding to the target historical building; Based on the overall damage parameters, the corresponding overall relative damage parameters and the corresponding regional environmental parameters corresponding to the target historical building, the building protection grade parameters corresponding to the target historical building are determined.

6. The intelligent identification method for historical building defects according to claim 1, characterized in that: The method further comprises: Determining a component type of each target building component of the target historic building; For each of the target building components, based on the component type and the defect identification result of the target building component, determine whether the target building component needs to be repaired; if the target building component needs to be repaired, determine the point cloud data of the non-defective building component corresponding to the target building component from a predetermined building component point cloud database; based on the point cloud data corresponding to the target building component, determine the size information corresponding to the target building component; based on the size information corresponding to the target building component, perform an optimization operation on the point cloud data of the non-defective building component corresponding to the target building component to obtain the point cloud data of the target non-defective building component corresponding to the target building component; Based on the point cloud data of the target building components that do not need to perform repair operations corresponding to the target historical building, and the point cloud data of the target non-defective building components corresponding to the target building components that need to perform repair operations, the predicted repair point cloud data corresponding to the target historical building is determined.

7. An intelligent identification device for historical building defects, characterized in that: The device comprises: An acquisition module is used to obtain point cloud data corresponding to the target historical building; A segmentation module, used to segment the point cloud data corresponding to the target historical building to obtain point cloud data of a plurality of target building components to be identified corresponding to the target historical building; A first determination module is used to determine, for each target building component, a defect dimension type corresponding to the target building component; the defect dimension type includes two-dimensional defects and three-dimensional defects; an identification module, configured to perform a defect identification operation on each target building component based on the point cloud data corresponding to the target building component and the corresponding defect dimension type, to obtain a defect identification result of the target building component; A second determination module is used to determine the overall disease identification result corresponding to the target historical building based on the disease identification results of all target building components corresponding to the target historical building; The identification module comprises: The first identification submodule is used to determine, for each of the target building components, a target two-dimensional projection view corresponding to the target building component based on the point cloud data corresponding to the target building component when the defect dimension type corresponding to the target building component is a two-dimensional defect, wherein the target two-dimensional projection view is a plan view of a perspective to be detected corresponding to the target building component whose defect dimension type is a two-dimensional defect; input the target two-dimensional projection view corresponding to the target building component into a pre-trained two-dimensional defect recognition model to perform a defect recognition operation to obtain a two-dimensional defect model recognition result corresponding to the target building component; and determine a defect recognition result corresponding to the target building component based on the two-dimensional defect model recognition result corresponding to the target building component.

8. An intelligent identification system for historical building defects, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent identification method for historical building diseases as described in any one of claims 1-6.

9. A computer storage medium, characterized in that The computer storage medium stores computer instructions, which, when called, are used to execute the intelligent identification method for historical building diseases as described in any one of claims 1-6.

Images