Historical building damage degree evaluation system

Abstract

The invention discloses a historical building damage degree evaluation system, and the system comprises a photo obtaining module which is used for obtaining initial photos of a building wall surface according to a set sequence; the photo splicing module is used for splicing the initial photos according to the obtained sequence to obtain photos to be evaluated; the evaluation model module is used for outputting an evaluation result according to the input to-be-evaluated photo; and the damage degree evaluation module is used for calculating the plurality of related evaluation results to obtain a damage degree result. According to the historical building damage degree evaluation system, the cost during picture collection can be well reduced, the professional requirement during picture collection is reduced, and the overall quality of a picture formed by splicing a plurality of pictures is also good, so that the overall recognition effect is improved.

Description

Technical Field

[0001] The invention relates to the technical field of historical building repair, and in particular to a historical building damage degree assessment system. Background Art

[0002] Historical buildings can well reflect the local historical features and local characteristics. Therefore, the protection and repair of historical buildings are gradually increasing. Before repairing historical buildings, it is necessary to evaluate the degree of damage to historical buildings in order to give better suggestions for repair. At present, many judgments on the degree of damage are based on some neural network models. For objects with large areas such as building walls, during the image acquisition process, if you want to obtain photos of a single wall, on the one hand, the requirements for the acquisition equipment are too high and the construction cost is high. On the other hand, the technical requirements for the collector are too high, and the overall quality of the acquired pictures will be biased, thus affecting the overall recognition effect. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a historical building damage degree assessment system, which can greatly reduce the cost of image collection and reduce the professional requirements for photo collection. The overall quality of the photos formed by splicing several pictures is also very good, thereby improving the overall recognition effect.

[0004] The present invention provides a historical building damage degree assessment system, comprising:

[0005] A photo acquisition module, used to acquire initial photos of the building wall in a set order;

[0006] A photo stitching module, used for stitching the initial photos in the order in which they are acquired to obtain photos to be evaluated;

[0007] An evaluation model module is used to output evaluation results based on the input photos to be evaluated;

[0008] The damage degree assessment module is used to calculate a number of related assessment results to obtain a damage degree result.

[0009] In one embodiment, the photo acquisition module includes:

[0010] A division submodule, used for dividing the building wall into a plurality of areas and marking the plurality of areas;

[0011] The photographing submodule is used to set an acquisition sequence according to the mark, and acquire the initial photo of the building wall according to the set sequence, wherein the initial photo includes the mark information.

[0012] In one embodiment, the photo stitching module includes:

[0013] A marking information acquisition submodule is used to acquire the marking information on the initial photo;

[0014] The splicing submodule is used to splice the initial photos according to the acquired marking information to obtain the photos to be evaluated.

[0015] In one embodiment, the damage assessment module includes:

[0016] A search submodule, used for searching, based on one of the evaluation results, an evaluation result related to the evaluation result;

[0017] The calculation submodule is used to determine the weight corresponding to each evaluation result, and calculate the damage degree result according to the corresponding weight and the evaluation result.

[0018] In one embodiment, the training process of the evaluation model module includes:

[0019] Acquire a training image dataset, wherein the image dataset includes a plurality of training photos;

[0020] The training photos are input into the initial model for training to obtain the evaluation model.

[0021] In one embodiment, the image data set includes weathered building wall images, plant and moss covered building wall images, peeling building wall images, defective building wall images, and polluted building wall images.

[0022] The historical building damage degree assessment system provided by the present invention can greatly reduce the cost of picture collection and the professional requirements for picture collection. The overall quality of the picture formed by splicing several pictures is also very good, thereby improving the overall recognition effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 This is a system block diagram of the historical building damage degree assessment system provided by the present invention. DETAILED DESCRIPTION

[0025] The specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the description 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.

[0026] In the description of the present invention, unless otherwise clearly specified and limited, the terms "set", "install", "connection" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0027] The directions or positional relationships indicated by terms such as “upper”, “lower”, “left”, “right”, “front”, “back”, “top”, “bottom”, “inside” and “outside” are based on the directions or positional relationships shown in the accompanying drawings, or are the directions or positional relationships in which the inventive product is usually placed when used. They are only for the convenience of description and simplified description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as a limitation on the present invention.

[0028] The terms "first", "second", "third", etc. are merely used to distinguish elements of similar nature, and do not indicate or imply relative importance or a particular order.

[0029] The terms "comprises," "comprising," or any other variations thereof, are intended to cover a non-exclusive inclusion of the elements listed and may also include additional elements not expressly listed.

[0030] Embodiment 1

[0031] See also Figure 1 The historical building damage degree assessment system provided by the present invention comprises the following steps:

[0032] The photo acquisition module 1 is used to acquire initial photos of the building wall in a set order.

[0033] It can be known that the photo acquisition module 1 may include:

[0034] The division submodule is used to divide the wall of the building into several areas and mark the several areas.

[0035] It is understandable that a coordinate system can be established with the center point of the building wall as the origin, and then a number of grids can be divided based on the coordinate system. Markings can be made with numbers, and of course, the marks are virtual marks.

[0036] The photographing submodule is used to set an acquisition sequence according to the mark, and acquire an initial photo of the building wall according to the set sequence, wherein the initial photo includes the mark information.

[0037] It is understandable that the photos can be taken in sequence from top to bottom and from left to right until one of the walls of the building is completely photographed.

[0038] The photo stitching module 2 is used to stitch the initial photos in the order in which they are acquired to obtain the photos to be evaluated.

[0039] It is understandable that the above-mentioned photo stitching module 2 may include:

[0040] The tag information acquisition submodule is used to obtain the tag information on the initial photo.

[0041] It is understandable that the initial photos are sorted and spliced ​​according to the marking information, and the photo splicing module can be some image processing software on the market.

[0042] The stitching submodule is used to stitch the initial photos according to the acquired marking information to obtain the photos to be evaluated.

[0043] It can be known that after being arranged in order, the initial photos are spliced ​​to form a photo of a completed wall. Because the walls of historical buildings are generally relatively large, this form of method is used to obtain pictures of the walls of historical buildings.

[0044] The evaluation model module 3 is used to output the evaluation result according to the input photo to be evaluated.

[0045] It can be understood that the training process of the evaluation model module 3 includes:

[0046] A training image dataset is obtained, wherein the image dataset includes a plurality of training photos.

[0047] It can be known that the image data set may include weathered building wall images, plant and moss covered building wall images, peeling building wall images, defective building wall images, and polluted building wall images.

[0048] Among them, pictures of weathered building walls and pictures of damaged building walls can include the following types: surface weathering or damage depth less than 5 mm, wall damage or weathering depth of 5 mm to 20 mm, serious wall damage or weathering depth greater than 20 mm, less than 50 mm, and damage or weathering depth greater than 50 mm. Pictures of building walls covered with plants and mosses can include plant roots invading the wall, moss covering the wall, and peeling building wall pictures can include single surface peeling area ≤0.1m 2 、Single surface layer peeling area>0.1m 2 Or the peeling area exceeds 10% of the plastering area, and the peeling area of ​​the surface layer is greater than 0.3m 2 Or the peeling area exceeds 30% of the plastering area. The image data can also include pictures of building walls in a hollow state and pictures of building walls with crack types. Pictures of building walls with crack types can include crack width ≤ 0.3mm and crack width > 0.3mm. There are also some common additional iron parts, human pollution (including graffiti and oil stains, etc.) and pictures of building walls in an alkali-reversion state.

[0049] The training photos are fed into the initial model for training to obtain the evaluation model.

[0050] It can be understood that the training process can be to divide the above-mentioned training photos into a training set and a test set. The training set is used to train the initial model, and the test set can be used to test the trained model, and finally a trained evaluation model is obtained. The initial model can be some common neural network models.

[0051] The damage degree assessment module 4 is used to calculate a number of related assessment results to obtain a damage degree result.

[0052] It is understandable that the above-mentioned damage degree assessment module 4 may include:

[0053] The search submodule is used to search for evaluation results related to one of the evaluation results based on the evaluation results.

[0054] It is understandable that the evaluation result may include the information of the wall corresponding to the evaluation result, and the wall information related to the evaluation result is searched according to the wall information until all the wall information related to the evaluation result is searched out.

[0055] The calculation submodule is used to determine the weight corresponding to each evaluation result, and calculate the damage degree result according to the corresponding weight and the evaluation result.

[0056] It is understandable that corresponding weights can be assigned according to the importance of different wall surfaces, and the product of the weights and the corresponding evaluation results can be calculated. After adding several products and finding the average, the final result is the damage degree result.

[0057] Embodiment 2

[0058] This embodiment provides a method for assessing the degree of damage to a historical building, comprising the following steps:

[0059] Obtain initial photos of the building walls in a set order;

[0060] splicing the initial photos in the order in which they were acquired to obtain photos to be evaluated;

[0061] Output evaluation results based on the input photos to be evaluated;

[0062] Several related assessment results are calculated to obtain the damage extent result.

[0063] From the above description, it can be known that the historical building damage degree assessment system provided by the present invention can greatly reduce the cost of picture collection and reduce the professional requirements for picture collection. The overall quality of the photos formed by splicing several pictures is also very good, thereby improving the overall recognition effect.

[0064] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. A system for assessing the degree of damage to historical buildings, characterized in that: include: A photo acquisition module, used to acquire initial photos of the building wall in a set order; A photo stitching module, used for stitching the initial photos in the order in which they are acquired to obtain photos to be evaluated; An evaluation model module, used for outputting evaluation results based on the input photos to be evaluated; The damage degree assessment module is used to calculate a number of related assessment results to obtain a damage degree result.

2. The historical building damage assessment system according to claim 1, characterized in that: The photo acquisition module includes: A division submodule, used for dividing the building wall into a plurality of areas and marking the plurality of areas; The photographing submodule is used to set an acquisition sequence according to the mark, and acquire the initial photo of the building wall according to the set sequence, wherein the initial photo includes the mark information.

3. The historical building damage assessment system according to claim 2, characterized in that: The photo stitching module includes: A marking information acquisition submodule is used to acquire the marking information on the initial photo; The splicing submodule is used to splice the initial photos according to the acquired marking information to obtain the photos to be evaluated.

4. The historical building damage assessment system according to claim 1, characterized in that: The damage assessment module includes: A search submodule, used for searching, based on one of the evaluation results, an evaluation result related to the evaluation result; The calculation submodule is used to determine the weight corresponding to each evaluation result, and calculate the damage degree result according to the corresponding weight and the evaluation result.

5. The historical building damage assessment system according to claim 1, characterized in that: The training process of the evaluation model module includes: Acquire a training image dataset, wherein the image dataset includes a plurality of training photos; The training photos are input into the initial model for training to obtain the evaluation model.

6. The historical building damage assessment system according to claim 5, characterized in that: The image data set includes weathered building wall images, plant and moss covered building wall images, peeling building wall images, damaged building wall images and polluted building wall images.

Images