BIM-image recognition ancient building activation and repair method and device based on cooperation of unmanned aerial vehicle

Abstract

This application relates to the field of ancient building restoration, and discloses a method and apparatus for the revitalization and restoration of ancient buildings based on UAV collaboration using BIM-image recognition. The method includes: determining multiple detection levels of the ancient building to be restored based on BIM information; determining the detection order of the multiple detection levels of the detection areas, and acquiring multiple images of the detection areas corresponding to the multiple detection levels according to the detection order; determining revitalization and restoration suggestions for the ancient building to be restored based on the BIM information and the multiple images of the detection areas using an ancient building revitalization and restoration model; acquiring a first image of the first detection level of the detection area using a UAV, and determining a second detection level of the detection area among the multiple detection levels of the detection areas using the BIM information and the first image of the detection area. This application can improve the auxiliary effect of BIM information and UAV-acquired images on the restoration of ancient buildings.

Description

Technical Field

[0001] This application relates to the field of ancient building restoration technology, and more specifically, to a method and apparatus for the revitalization and restoration of ancient buildings based on UAV-assisted BIM-image recognition. Background Technology

[0002] Ancient building restoration is a complex and highly specialized task. The standard process typically includes the following steps: First, a thorough on-site survey and mapping are required, primarily relying on manual labor using tools such as measuring tapes and total stations to obtain the building's geometric dimensions and component locations, as well as to identify and record defects. This process is time-consuming, labor-intensive, and has limited accuracy. Based on this, the restoration team combines historical document research, traditional technique analysis, and expert experience to diagnose the building's structural problems, the degree of material deterioration, and its core historical value. Next, a restoration design plan is developed, determining the restoration materials and techniques (such as splicing wooden columns, patching brick walls, and repainting). Finally, the construction phase begins, where traditional craftsmen carry out the restoration work according to the design plan, requiring continuous on-site supervision and quality control. This ancient building restoration process is highly dependent on the craftsmen's experience and subjective judgment, lacking efficiency and comprehensiveness in information acquisition, and making it difficult to achieve visualized previewing and precise quantitative control of the restoration process.

[0003] With technological advancements, Building Information Modeling (BIM) and UAV aerial surveying technology have begun to be applied in the field of ancient building restoration, but significant limitations still exist. On the one hand, although BIM technology can construct three-dimensional information models of buildings, current applications typically focus on converting point cloud models from traditional surveying or simple reverse engineering into BIM models, mainly for visualization or structural information management. This fails to deeply integrate the unique form, historical information, and detailed defects of ancient buildings for intelligent analysis and restoration plan deduction. On the other hand, UAV systems can efficiently acquire high-resolution imagery and three-dimensional point cloud data, but in current practice, this data is often only used to generate visualization models or create survey drawings. It cannot automatically and accurately identify subtle damage, material degradation types and degrees of key components (such as brackets and corbels), or monitor structural deformation in real time during the restoration process. Essentially, current applications mostly treat BIM information or drone-collected images as static, isolated "data warehouses," which can only mechanically assist human judgment. BIM information and drone-collected images have not achieved effective collaborative integration, and the intelligent and proactive assistance provided to actual repair operations in terms of accuracy, efficiency, security, and preservation of historical authenticity remains limited. Summary of the Invention

[0004] The purpose of this application is to provide a method and device for the revitalization and restoration of ancient buildings based on UAV collaboration using BIM-image recognition. This method solves the technical problem that BIM information and images collected by UAVs have poor auxiliary effects on the restoration of ancient buildings, and achieves the technical effect of improving the auxiliary effects of BIM information and images collected by UAVs on the restoration of ancient buildings.

[0005] This application provides a method for the revitalization and restoration of ancient buildings based on UAV-assisted BIM-image recognition. The method includes: acquiring BIM information of the ancient building to be restored; determining multiple detection levels of the ancient building to be restored based on the BIM information; determining the detection order of the multiple detection levels of the detection areas, and acquiring multiple images of the detection areas corresponding to the multiple detection levels according to the detection order; and determining revitalization and restoration suggestions for the ancient building to be restored based on the BIM information and the multiple images of the detection areas using an ancient building revitalization and restoration model. The determination of the detection order of the multiple detection levels of the detection areas includes: acquiring a first image of the detection area corresponding to the first detection level of the detection area using a UAV, and determining a second detection level of the detection area among the multiple detection levels of the detection areas using the BIM information and the first image of the detection area, wherein the first detection level is greater than the second detection level.

[0006] In one possible implementation, a second detection level detection area is determined from multiple detection level detection areas using BIM information and a first detection area image. This includes: determining first edge regions in different directions corresponding to the first detection area image and the BIM information based on their corresponding positions in the BIM information; determining the structural matching degree between the first edge regions and the BIM information in different directions as the first edge region matching degree; wherein, multiple first edge regions are located in the circumferential direction of the first detection area image, and each first edge region is an edge region with a preset proportion of the edge of the first detection area image; determining the maximum first edge region matching degree among the structural matching degrees in different directions, and determining the detection area closest to the first edge region corresponding to the maximum first edge region matching degree as the detection area for the second detection level.

[0007] In another possible implementation, determining the structural matching degree between the first edge region and BIM information in different directions, as the first edge region matching degree, includes: determining the structural misalignment types between the first edge region and BIM information in different directions, and obtaining the matching degree adjustment factor corresponding to each structural misalignment type; wherein, the structural misalignment types include structural damage misalignment, corrosion misalignment, and contaminant misalignment; and determining the product of the structural matching degree between the first edge region and BIM information in different directions and the matching degree adjustment factor as the first edge region matching degree.

[0008] In another possible implementation, the matching degree adjustment factor for contaminant misalignment is 1.0 to 1.5; the matching degree adjustment factor for corrosion misalignment is 0.8 to 1.0; and the matching degree adjustment factor for structural damage misalignment is 0.5 to 0.8.

[0009] In another possible implementation, determining the structural matching degree between the first edge region and BIM information in different directions as the first edge region matching degree also includes: determining the area of ​​the first edge region corresponding to the first edge region; when the area of ​​the first edge region is less than a preset area of ​​the first edge region, determining the first extension region of the first edge region in different directions, and determining the first extension region weight index corresponding to the first extension region in different directions as the first extension region weight index of the first edge region in different directions; wherein, the area of ​​the first extension region is 50% to 150% of the area of ​​the first edge region, and the first extension region weight index includes the weight index corresponding to the structural type of the first extension region; determining the product of the structural matching degree between the first edge region and BIM information in different directions, the matching degree adjustment factor, and the first extension region weight index as the first edge region matching degree.

[0010] In another possible implementation, determining the structural matching degree between the first edge region and BIM information in different directions as the first edge region matching degree also includes: when the area of ​​the first edge region is greater than or equal to a preset first edge region area, determining the first edge region weight index corresponding to the first edge region; wherein, the first edge region weight index includes the weight index corresponding to the structural type of the first edge region; and determining the product of the structural matching degree between the first edge region and BIM information in different directions, the matching degree adjustment factor, and the first edge region weight index as the first edge region matching degree.

[0011] In another possible implementation, based on BIM information, multiple inspection areas for the ancient building to be restored are determined, including: acquiring the structural type indicators and data integrity corresponding to the BIM information of multiple inspection areas respectively, and determining the product of the structural type indicators and data integrity corresponding to the BIM information of multiple inspection areas as the priority indicators for the multiple inspection areas respectively; sorting the multiple inspection areas according to the priority indicators from largest to smallest to determine the inspection level of the multiple inspection areas of the ancient building to be restored.

[0012] In another possible implementation, the method further includes: determining the dispersion index corresponding to each area to be inspected; wherein the dispersion index characterizes the degree of distance dispersion between each area to be inspected and other areas to be inspected, and the larger the dispersion index, the greater the degree of distance dispersion between the area to be inspected and other areas to be inspected; determining the product of the structural type index, data integrity and distance dispersion corresponding to the BIM information of multiple areas to be inspected, respectively, as the priority index of the areas to be inspected corresponding to the multiple areas to be inspected.

[0013] In another possible implementation, the method further includes: obtaining the data integrity corresponding to the BIM information of multiple areas to be detected; determining the structural matching degree of the first edge area and the BIM information in different directions, and determining the product of the structural matching degree and the data integrity of the first edge area and the BIM information in different directions as the matching degree of the first edge area.

[0014] This application also provides a BIM-image recognition-based ancient building revitalization and restoration system based on drone collaboration, including a unit for performing the method described in any of the preceding claims.

[0015] The beneficial effects of the embodiments in this application compared with the prior art are:

[0016] This application provides a method for the revitalization and restoration of ancient buildings based on UAV-assisted BIM-image recognition. The method includes: acquiring BIM information of the ancient building to be restored; determining multiple detection levels of the ancient building to be restored based on the BIM information; determining the detection order of the multiple detection levels of the detection areas, and acquiring multiple images of the detection areas corresponding to the multiple detection levels according to the detection order; and determining revitalization and restoration suggestions for the ancient building to be restored based on the BIM information and the multiple images of the detection areas using an ancient building revitalization and restoration model. Determining the detection order of the multiple detection levels of the detection areas includes: acquiring a first image of the detection area corresponding to the first detection level of the detection area using a UAV, and determining a second detection level of the detection area among the multiple detection levels of the detection areas using the BIM information and the first image of the detection area, where the first detection level is higher than the second detection level. The method in this application can efficiently and accurately utilize BIM information and UAV image information to revitalize and restore ancient buildings, improving the restoration efficiency of ancient buildings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating the first method for revitalizing and restoring ancient buildings based on UAV collaboration using BIM-image recognition, as provided in this application embodiment;

[0019] Figure 2 A schematic diagram of the workflow for determining the detection order of multiple detection levels of regions to be detected, provided in an embodiment of this application;

[0020] Figure 3 A flowchart illustrating the second method for revitalizing and restoring ancient buildings based on UAV collaboration using BIM-image recognition, as provided in this application embodiment;

[0021] Figure 4 This is a schematic diagram of the logical structure of a BIM-image recognition-based ancient building revitalization and restoration system based on UAV collaboration, provided in an embodiment of this application. Detailed Implementation

[0022] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0023] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0024] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0025] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0026] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0027] Currently, when Building Information Modeling (BIM) and UAV aerial surveying technology are applied to the field of ancient building restoration, BIM information and images collected by UAVs have not been effectively integrated, and the intelligent and proactive assistance provided to actual restoration operations in terms of accuracy, efficiency, safety, and preservation of historical authenticity remains limited.

[0028] Based on the above reasons, this application provides a BIM-image recognition-based method for the revitalization and restoration of ancient buildings using UAV collaboration. The method includes: acquiring BIM information of the ancient building to be restored; determining multiple detection levels of the ancient building to be restored based on the BIM information; determining the detection order of the multiple detection levels of the detection areas, and acquiring multiple images of the detection areas corresponding to the multiple detection levels according to the detection order; and determining revitalization and restoration suggestions for the ancient building to be restored based on the BIM information and the multiple images of the detection areas using an ancient building revitalization and restoration model. Specifically, determining the detection order of the multiple detection levels of the detection areas includes: acquiring a first image of the detection area corresponding to the first detection level of the detection area using a UAV, and determining a second detection level of the detection area among the multiple detection levels of the detection areas using the BIM information and the first image of the detection area, where the first detection level is higher than the second detection level. The method in this application can efficiently and accurately utilize BIM information and UAV image information to revitalize and restore ancient buildings, improving the restoration efficiency of ancient buildings.

[0029] In some scenarios, the BIM-image recognition method for the revitalization and restoration of ancient buildings based on drone collaboration, as described in this application, can be applied to the revitalization and restoration of ancient buildings. Revitalization and restoration refers to giving historical buildings new uses that meet modern needs through functional updates, spatial transformation, or technological intervention, while protecting their original appearance and structural safety, thereby improving the revitalization and restoration effect of ancient buildings.

[0030] The following specific examples illustrate a method for the revitalization and restoration of ancient buildings based on UAV-cooperative BIM-image recognition provided in this application.

[0031] Figure 1 A flowchart illustrating the first BIM-image recognition-based method for the revitalization and restoration of ancient buildings based on UAV collaboration, as provided in this application embodiment, is shown below. Figure 1 As shown, the BIM-image recognition method for the revitalization and restoration of ancient buildings based on UAV collaboration includes S110 to S120, and S110 to S120 will be explained in detail below.

[0032] S110. Obtain BIM information for the ancient building to be restored. Based on the BIM information, determine the inspection areas for multiple inspection levels of the ancient building to be restored.

[0033] In this implementation method, the BIM information of the ancient building to be restored can be obtained. The BIM information can include the complete three-dimensional model data and component attribute information of the ancient building, which can provide basic data support for subsequent inspection. Through the BIM information, the structural characteristics and restoration needs of the ancient building can be fully understood.

[0034] For example, BIM information can be BIM information from historical inspection results or BIM information obtained from recent surveys of ancient buildings. BIM information may not match drone images due to measurement errors or changes in the structure of ancient buildings.

[0035] After obtaining BIM information, the areas to be inspected at multiple inspection levels of the ancient building to be restored can be determined based on the BIM information. Different inspection levels correspond to different priority inspection sequences. By using a specific inspection sequence, the inspection accuracy can be improved, thereby improving the restoration effect of the ancient building.

[0036] S120. Determine the detection order of the areas to be detected at multiple detection levels, and acquire multiple images of the areas to be detected corresponding to the multiple detection levels according to the detection order. Using the ancient building revitalization and restoration model, based on BIM information and multiple images of the areas to be detected, determine the ancient building revitalization and restoration suggestions corresponding to the ancient building to be restored; wherein, determining the detection order of the areas to be detected at multiple detection levels includes: acquiring the first image of the area to be detected corresponding to the first detection level using a drone, and determining the area to be detected at the second detection level among the areas to be detected at multiple detection levels using BIM information and the first image of the area to be detected, wherein the first detection level is greater than the second detection level.

[0037] In this implementation, the detection order of the regions to be detected at multiple detection levels can be determined first. Then, the corresponding images of multiple regions to be detected can be acquired according to the detection order. When determining the images of the regions to be detected, detailed image data of each detection level can be acquired through a high-definition camera mounted on a drone. This image data will serve as the basis for subsequent analysis.

[0038] Figure 2 This application provides a schematic diagram of a first method for determining the detection order of regions to be detected at multiple detection levels, as illustrated in the embodiments of this application. Figure 2 As shown, when determining the detection order of multiple detection levels of the areas to be detected, it can be determined in the following way: First, the image of the first area to be detected corresponding to the first detection level can be obtained by drone. Then, by combining BIM information and the image of the first area to be detected, the area to be detected at the second detection level can be determined among the areas to be detected at multiple detection levels. This progressive detection method can gradually improve the detection accuracy. By iterating, the areas to be detected at subsequent multiple detection levels can be determined step by step.

[0039] It should be noted that different detection levels can be represented by numbers, with the first detection level being higher than the second detection level.

[0040] After obtaining multiple images of the areas to be inspected corresponding to multiple inspection levels, the ancient building revitalization and restoration model can be used to determine the overall revitalization and restoration suggestions for the ancient building to be restored based on BIM information and multiple images of the overall structure of the ancient building detected by drones. Then, the ancient building can be restored according to the revitalization and restoration suggestions.

[0041] For example, the ancient building revitalization and restoration model can be an image recognition model based on deep learning. The ancient building revitalization and restoration model can be trained with a large number of ancient building restoration cases and can accurately identify various types of damage and propose restoration solutions.

[0042] For example, when restoring an ancient pagoda, the ancient building revitalization and restoration model can identify the degree of weathering of the bricks and the condition of structural cracks, and provide targeted suggestions for restoration materials and construction plans. For the problem of insect infestation in wooden components, the ancient building revitalization and restoration model can suggest appropriate anti-corrosion treatment methods.

[0043] The beneficial effects of the above implementation method are that, during the inspection process, the inspection areas of multiple inspection levels of the ancient building to be restored are first determined according to the BIM information. Then, during the inspection process, the inspection areas of subsequent inspection levels are accurately determined based on the BIM information and the images of the inspection areas. This allows for dynamic adjustment of the inspection areas, improves the inspection accuracy of the inspection areas, enhances the accuracy of the ancient building revitalization and restoration recommendations, and improves the reliability of the ancient building restoration plan.

[0044] The beneficial effects of the above implementation method are that, by using BIM information and the image of the first area to be inspected, the area to be inspected at the second inspection level can be determined from among the areas to be inspected at multiple inspection levels. This allows for the precise determination of the next area to be inspected by combining BIM information and the image of the area to be inspected, thus improving the scientific rigor of the inspection of the area image. The progressive inspection sequence design can dynamically adjust the focus of subsequent inspections based on the results of previous inspections, concentrating inspection resources on the most needed areas. This adaptive inspection strategy significantly improves the scientific rigor and economy of the inspection work.

[0045] In some implementations, in S120 above, the second detection level detection area is determined from the detection areas of multiple detection levels using BIM information and the first detection area image, including S121 to S122. S121 to S122 will be explained in detail below.

[0046] S121. Based on the corresponding position of the first region image to be detected in the BIM information, determine the first edge regions in different directions corresponding to the first region image to be detected and the BIM information. Determine the structural matching degree between the first edge regions and the BIM information in different directions, as the first edge region matching degree. Wherein, multiple first edge regions are defined in the circumferential direction of the first region image to be detected, and each first edge region is an edge region with a preset proportion of the edge of the first region image to be detected.

[0047] In this implementation, the first detection area image and BIM information can be registered according to the registration algorithm. After registration, the corresponding position of the first detection area image in the BIM information can be determined, and then the first edge regions in different directions corresponding to the first detection area image and BIM information can be determined.

[0048] For example, the first edge region is an edge region of a preset proportion of the edge of the first detection area image. Multiple first edge regions are distributed in the circumferential direction of the first detection area image. In this way, the correspondence between the image edge and the BIM model can be comprehensively analyzed, and the areas that need to be detected by UAV images in the BIM model can be determined.

[0049] In the scenario of ancient building restoration, for example, when a drone captures a partial image of the roof of an ancient building, the surrounding edge areas of the image can be extracted as the first edge area. These edge areas contain connection feature information with the corresponding structure in the BIM model. By analyzing these edge areas, we can better understand the positional relationship of the local image in the overall building and the detection requirements.

[0050] In this implementation, after determining the first edge regions in different directions corresponding to the first region to be detected image and BIM information, the structural matching degree between the first edge regions and BIM information in different directions can be further determined as the first edge region matching degree.

[0051] For example, the structural matching degree can be calculated based on the similarity between the texture features, geometry, etc. of the edge region and the corresponding structure in the BIM model. The higher the matching degree, the more accurate the correspondence between the edge region and the BIM model in that direction.

[0052] S122. Determine the maximum first edge region matching degree among the structural matching degrees in different directions, and determine the detection region that is closest to the first edge region corresponding to the maximum first edge region matching degree, as the detection region of the second detection level.

[0053] After obtaining the structural matching degree in different directions, the maximum first edge region matching degree in different directions can be determined, and the detection area closest to the first edge region corresponding to the maximum first edge region matching degree can be determined as the detection area of ​​the second detection level. This method prioritizes the direction with the highest matching degree for further detection to ensure the reliability of the detection.

[0054] For example, when inspecting the walls of ancient buildings, if the eastern edge area has the highest matching degree with the BIM model, then the adjacent eastern area is selected as the next inspection area. This matching degree-based selection method can effectively improve the targeting of the inspection.

[0055] The beneficial effect of the above implementation method is that, firstly, the first edge region corresponding to the first region to be detected in the BIM information is determined, and then the first edge region with the largest structural matching degree is determined according to the structural matching degree between the first edge region and the BIM information in different directions. Then, other regions to be detected corresponding to the first edge region are detected, which improves the detection accuracy of the regions to be detected.

[0056] The beneficial effect of the above implementation method is that by fusing UAV images to continue detection in the direction of the first edge region with the greatest structural matching degree with BIM information, the detection accuracy of the cooperation between UAV images and BIM information is improved.

[0057] The beneficial effect of the above implementation method is that by adopting a multi-directional edge region matching method, it can adapt to image acquisition under different angles and lighting conditions. Even when the image quality is not ideal in some directions, the optimal detection direction can be selected through matching degree analysis, thereby improving the robustness of the method.

[0058] In some implementations, in S121 above, the structural matching degree between the first edge region and the BIM information in different directions is determined as the first edge region matching degree, including S121a to S121b. S121a to S121b will be explained in detail below.

[0059] S121a. Determine the structural misalignment types of the first edge region and BIM information in different directions, and obtain the matching degree adjustment factor corresponding to each structural misalignment type. The structural misalignment types include structural damage misalignment, corrosion misalignment, and contaminant misalignment.

[0060] In this implementation method, the structural misalignment types of the first edge area and BIM information in different directions can be determined. The structural misalignment types include three main types: structural damage misalignment, corrosion misalignment, and contaminant misalignment. These types reflect different forms of damage that may occur to ancient buildings during long-term use.

[0061] For each type of structural misalignment, a corresponding matching degree adjustment factor can be obtained. The matching degree adjustment factor is a parameter value set according to the severity of different types of structural misalignment and the degree of influence on the overall structural matching degree.

[0062] S121b. Determine the product of the structural matching degree and matching degree adjustment factor of the first edge region and BIM information in different directions, and use it as the matching degree of the first edge region.

[0063] After obtaining the matching degree adjustment factor, the product of the structural matching degree and the matching degree adjustment factor of the first edge region and BIM information in different directions can be calculated as the final matching degree of the first edge region. This calculation process takes into account the differential impact of different types of structural misalignment on the overall matching degree, and can then improve the accuracy of comprehensive structural detection of ancient buildings based on different types of structural misalignment using UAV images and BIM information.

[0064] For example, during the revitalization and restoration of an ancient temple, the edge area of ​​the eaves captured by a drone was misaligned compared with the BIM model. Through analysis, it was determined that some of the misalignment was due to corrosion caused by wood decay, and some was due to pollutants caused by bird droppings. The system will automatically apply different matching degree adjustment factors to calculate based on the different types of misalignment.

[0065] The beneficial effect of the above implementation method is that, firstly, the matching degree adjustment factor corresponding to the structural misalignment type in different directions of the first edge region and BIM information is obtained, and the matching degree adjustment factor is adjusted according to the matching degree adjustment factor. This can adjust the structural matching degree corresponding to structural misalignment caused by different reasons, thereby improving the scientific nature of the detection of the cooperation between UAV images and BIM information.

[0066] The beneficial effect of the above implementation method is that by distinguishing between three different types of structural misalignment—structural damage misalignment, corrosion misalignment, and contaminant misalignment—and setting a specific matching degree adjustment factor for each type, it is possible to more accurately reflect the degree of influence of different types of structural misalignment on the overall matching degree.

[0067] The beneficial effect of the above implementation method is that by combining the original structural matching degree and the matching degree adjustment factor in a product manner, differentiated processing of different types of structural misalignment is achieved, making the final matching degree assessment more scientific and reasonable.

[0068] In some implementations, the matching degree adjustment factor for contaminant misalignment is 1.0 to 1.5. The matching degree adjustment factor for corrosion misalignment is 0.8 to 1.0. The matching degree adjustment factor for structural damage misalignment is 0.5 to 0.8.

[0069] In the process of revitalizing and restoring ancient buildings, different matching degree adjustment factors can be set for different types of structural misalignment defects. The matching degree adjustment factor for pollutant misalignment is set to 1.0 to 1.5, the matching degree adjustment factor for corrosion misalignment is set to 0.8 to 1.0, and the matching degree adjustment factor for structural damage misalignment is set to 0.5 to 0.8. This setting method takes into account the different degrees of impact of different defect types on the structural integrity of ancient buildings.

[0070] In this implementation, contaminants have the least impact on the structure, so a higher matching degree adjustment factor is assigned; while structural damage has the greatest impact on building stability, so a lower matching degree adjustment factor is assigned; when inspecting the walls of ancient buildings, the misalignment caused by surface contaminants can be quickly matched and treated first, and then more serious corrosion and structural damage problems can be addressed step by step.

[0071] In the practice of ancient building restoration, this tiered approach is particularly suitable for historically significant wooden structures. For example, when inspecting an ancient temple, one can first address image discrepancies caused by surface dust and stains, then tackle corrosion on the wood surface, and finally address structural damage at beam-column joints, ensuring the scientific rigor and accuracy of the inspection process.

[0072] The beneficial effects of the above implementation method are that the matching degree adjustment factors corresponding to corrosion misalignment, contaminant misalignment, and structural damage misalignment decrease sequentially. Priority is given to structural detection of contaminant misalignment with less structural impact using a combination of UAV images and BIM information. Finally, structural damage misalignment with greater structural impact is detected using a combination of UAV images and BIM information. This reduces the amount of error propagation when conducting structural detection of ancient buildings and improves the accuracy of structural detection of ancient buildings using a combination of UAV images and BIM information.

[0073] The beneficial effect of the above implementation method is that, through this progressive detection sequence, the transmission and accumulation of errors during the detection process can be effectively controlled. When minor defects are dealt with first, more accurate benchmark data can be established, providing a reliable reference for subsequent processing of serious defects, thereby improving the overall detection accuracy.

[0074] In some implementations, S121 above, determining the structural matching degree of the first edge region and BIM information in different directions as the first edge region matching degree, also includes S121c to S121d.

[0075] S121c. Determine the area of ​​the first edge region corresponding to the first edge region. When the area of ​​the first edge region is less than the preset area of ​​the first edge region, determine the first extension region of the first edge region in different directions, and determine the weight index of the first extension region corresponding to the first extension region in different directions, as the weight index of the first extension region of the first edge region in different directions. The area of ​​the first extension region is 50% to 150% of the area of ​​the first edge region, and the weight index of the first extension region includes the weight index corresponding to the structural type of the first extension region.

[0076] In this implementation, the area of ​​the first edge region corresponding to the first edge region can be determined. The area of ​​the first edge region reflects the dimensional characteristics of the edge structure of the ancient building to be detected. Quantifying the area parameter helps to evaluate the reliability of the structural detection.

[0077] After obtaining the area of ​​the first edge region, if the area of ​​the first edge region is smaller than the preset area of ​​the first edge region, it indicates that the area of ​​the first edge region is too small to be used to evaluate the structural importance of the first edge region. In this case, the first extension region of the first edge region in different directions can be determined. The area of ​​the first extension region is 50% to 150% of the area of ​​the first edge region. By appropriately expanding the detection range, the accuracy of structural evaluation of small edge regions can be improved.

[0078] After obtaining the first extension regions in different directions, the weight index of the first extension region corresponding to the first extension region in different directions can be determined. The weight index of the first extension region characterizes the importance of the first extension region and serves as the weight index of the first extension region of the first edge region in different directions.

[0079] For example, the weight index of the first extended area includes the weight index corresponding to the structural type of the first extended area. Different structural types can be set with different weight values. For example, the weight index of load-bearing walls can be higher than that of decorative structures. By introducing structural type weights, the differences in importance of different structures in building safety can be reflected.

[0080] S121d. Determine the product of the structural matching degree of the first edge region and BIM information in different directions, the matching degree adjustment factor and the weight index of the first extended region, as the matching degree of the first edge region.

[0081] In this implementation, the product of the structural matching degree of the first edge region and BIM information in different directions, the matching degree adjustment factor, and the weight index of the first extended region can be determined as the matching degree of the first edge region. The scientificity and reliability of the matching degree of the first edge region can be improved by multi-factor comprehensive calculation.

[0082] For example, when inspecting the eaves of ancient buildings, if the area of ​​the first edge region of the eaves is small, the first extension region can be determined along the extension direction of the eaves. The weight index of the first extension region can be determined according to the structural type of the eaves. The structural matching degree can be calculated by combining the eaves design parameters in the BIM information, and finally a more accurate evaluation result of the eaves structure can be obtained.

[0083] The beneficial effect of the above implementation method is that it can prioritize the subsequent detection based on UAV images and BIM information according to structural importance, thereby improving the structural protection effect of ancient buildings during subsequent restoration and enhancing the reliability of the restoration plan.

[0084] The beneficial effect of the above implementation method is that when the area of ​​the first edge region is small, the first extension region is determined for the first edge region. Based on the structural matching degree, matching degree adjustment factor and weight degree of the first extension region and BIM information in different directions, the priority of structural detection based on UAV images and BIM information is determined, avoiding inaccurate evaluation due to the small size of the first edge region, and improving the scientific nature of structural protection and restoration of ancient buildings.

[0085] The beneficial effect of the above implementation method is that by comprehensively calculating the structural matching degree, matching degree adjustment factor and extended area weight index, a multi-dimensional evaluation system can be established, which takes into account both the matching degree of structural geometric features and the differences in the importance of structural functions, providing a more comprehensive decision-making basis for the revitalization and restoration of ancient buildings.

[0086] In some implementations, S121 above determines the structural matching degree of the first edge region and BIM information in different directions as the first edge region matching degree, and also includes S121e to S121f. S121e to S121f will be explained in detail below.

[0087] S121e: When the area of ​​the first edge region is greater than or equal to the preset area of ​​the first edge region, determine the weight index of the first edge region corresponding to the first edge region. The weight index of the first edge region includes the weight index corresponding to the structural type of the first edge region.

[0088] When determining the structural matching degree between the first edge region and BIM information in different directions, if the area of ​​the first edge region reaches or exceeds the preset area of ​​the first edge region, it indicates that the area of ​​the first edge region is large enough to evaluate the structural importance of the first edge region. At this time, the weight index of the first edge region can be further determined. The weight index of the first edge region reflects the importance of the structural type of the first edge region in the overall building. For example, the weight index of key structures such as load-bearing walls, beams and columns will be higher than that of decorative structures.

[0089] S121f: Determine the product of the structural matching degree of the first edge region and BIM information in different directions, the matching degree adjustment factor and the weight index of the first edge region, as the matching degree of the first edge region.

[0090] When the area of ​​the first edge region reaches or exceeds the preset area of ​​the first edge region, the structural matching degree of the first edge region and BIM information in different directions can be obtained. The matching degree adjustment factor and the weight index of the first edge region are then combined and multiplied to obtain the final matching degree of the first edge region. This calculation method can more accurately reflect the degree of matching between the region and the BIM model and its structural importance.

[0091] For example, in the restoration of ancient buildings, the matching degree calculation of large-area wall structures can be more accurate, providing a more reliable basis for subsequent restoration decisions.

[0092] The beneficial effect of the above implementation method is that it can prioritize subsequent inspections based on UAV images and BIM information according to structural importance, thereby improving the structural protection effect of ancient buildings during subsequent restoration.

[0093] The beneficial effect of the above implementation method is that when the area of ​​the first edge region is large, the first extension region is determined for the first edge region. Based on the structural matching degree, matching degree adjustment factor and weight degree of the first extension region and BIM information in different directions, the priority of structural detection based on UAV images and BIM information is determined, avoiding inaccurate evaluation when the first edge region is small, and improving the scientific nature of structural protection and restoration of ancient buildings.

[0094] The beneficial effect of the above implementation method is that by setting area threshold conditions, over-calculation of small areas can be avoided, thus improving calculation efficiency. At the same time, more accurate matching degree calculation can be performed on larger areas that meet the conditions, ensuring the reliability of the detection results.

[0095] Figure 3 A flowchart illustrating the second method for revitalizing and restoring ancient buildings based on UAV collaboration using BIM-image recognition, as provided in this application embodiment, is shown below. Figure 3 As shown, in S110 above, based on BIM information, multiple inspection areas of the ancient building to be restored are determined, including S111 to S112. S111 to S112 will be explained in detail below.

[0096] S111. Obtain the structural type index and data integrity corresponding to the BIM information of multiple areas to be inspected, and determine the product of the structural type index and data integrity corresponding to the BIM information of multiple areas to be inspected, as the priority index of the areas to be inspected.

[0097] In this implementation, the structural type index and data completeness corresponding to the BIM information of multiple areas to be inspected can be obtained. The structural type index reflects the importance of the area to be inspected in the overall structure of the ancient building, and the data completeness indicates the completeness and accuracy of the BIM information of the area. By obtaining these two parameters, the inspection value of each area to be inspected can be preliminarily assessed.

[0098] For example, data completeness may include indicators of the completeness of information such as structural dimensions, material properties, and historical repair records.

[0099] After obtaining the structural type index and data completeness of BIM information for multiple areas to be inspected, the product of the structural type index and data completeness corresponding to the BIM information of each area to be inspected can be determined as the priority index for each area to be inspected. This product calculation method can comprehensively consider both structural importance and data quality, avoiding the bias caused by a single index evaluation.

[0100] S112. Sort multiple areas to be inspected in descending order of priority index to determine the inspection level of multiple areas of the ancient building to be restored.

[0101] After obtaining the priority index of the area to be inspected, the higher the priority index, the more priority the area needs to be inspected. Specifically, multiple areas to be inspected can be sorted in descending order of priority index to determine the inspection level of multiple areas of the ancient building to be restored. This sorting method ensures that high-priority areas can get inspection opportunities earlier, providing a reliable basis for subsequent restoration work.

[0102] For example, the detection levels can be divided into multiple levels according to actual needs.

[0103] For example, when restoring an ancient Ming and Qing dynasty building, one can first obtain BIM information on key components such as beam-column joints, walls, and roofs. For load-bearing beam-column joints, although their structural type index is high, if the BIM data is severely missing, their priority index may be lower than that of secondary walls with complete data. In this way, the inspection sequence can be scientifically arranged.

[0104] The beneficial effect of the above implementation method is that the detection priority of multiple areas to be detected is determined according to the structural type indicators and data completeness corresponding to the BIM information of multiple areas to be detected. In the case of incomplete BIM information, areas with high structural importance and high data completeness are prioritized for detection, which improves the scientific nature of the detection order of the areas to be detected and improves the reliability of the ancient building restoration plan.

[0105] In some implementations, the above method also includes S113 to S114, which will be explained in detail below.

[0106] S113. Determine the dispersion index corresponding to each area to be detected. The dispersion index characterizes the degree of distance dispersion between each area to be detected and other areas to be detected. The larger the dispersion index, the greater the degree of distance dispersion between the area to be detected and other areas to be detected.

[0107] In the process of revitalizing and restoring ancient buildings, the dispersion index corresponding to each area to be tested can be determined. The dispersion index can reflect the spatial distribution characteristics between the area to be tested and other areas to be tested. When the dispersion index value is large, it indicates that the spatial distance between the area to be tested and other areas is far and the distribution is relatively scattered.

[0108] For example, when testing an ancient building complex, the dispersion index of different building units such as the main hall, side halls, and corridors can be calculated. The main hall may be located in the center of the building complex, and its dispersion index is relatively small; while the dispersion index of side halls or independent pavilions located on the edge will be larger, which reflects their degree of dispersion in spatial distribution.

[0109] S114. Determine the product of the structural type index, data integrity, and distance dispersion degree corresponding to the BIM information of multiple areas to be inspected, and use it as the priority index of the multiple areas to be inspected.

[0110] After determining the dispersion index, the product of structural type index, data integrity, and distance dispersion can be calculated by combining the BIM information of the area to be inspected. This yields the priority index for each area to be inspected. The structural type index reflects the importance level of building components, the data integrity indicates the completeness of the BIM model in the area, and the distance dispersion reflects the spatial distribution characteristics.

[0111] In the practice of ancient building restoration, for example, when inspecting a Ming and Qing dynasty house, priority can be given to inspecting the roof beam frame area, which is more dispersed and structurally important. These areas are often the key load-bearing parts of the building and are located in the upper space of the building, making them more difficult to inspect. This priority sorting method can ensure that the inspection work covers the key parts while taking into account the rationality of the spatial distribution.

[0112] The beneficial effect of the above implementation method is that, based on the distance dispersion of multiple areas to be detected, the detection order of multiple areas to be detected is further sorted, and the areas to be detected with higher distance dispersion of ancient buildings are given priority. In subsequent detection, the overall coverage of all areas to be detected of ancient buildings can be gradually improved, thereby improving the detection accuracy of ancient buildings and the reliability of ancient building restoration plans.

[0113] In some implementations, the above method also includes S121g to S121h, which will be described in detail below.

[0114] S121g: Obtain the data completeness corresponding to the BIM information of multiple areas to be inspected.

[0115] During the revitalization and restoration of ancient buildings, drones can be used to collect BIM information corresponding to multiple areas to be inspected. The data completeness of BIM information reflects the completeness of the building information in that area. Data completeness can be calculated by assessing the proportion of missing elements in the BIM model.

[0116] S121h: Determine the structural matching degree of the first edge region and BIM information in different directions, and determine the product of the structural matching degree and data integrity of the first edge region and BIM information in different directions as the matching degree of the first edge region.

[0117] For each area to be detected, the structural matching degree between its first edge area and BIM information in different directions can be determined. The structural matching degree can measure the degree of agreement between the actual building edge contour collected by the UAV and the theoretical edge contour in the BIM model. The structural matching degree in different directions can comprehensively evaluate the deformation of the building structure.

[0118] In this implementation, the structural matching degree of the first edge region and BIM information in different directions can be multiplied by the data integrity of the BIM information in that region to obtain the matching degree of the first edge region. The matching degree of the first edge region comprehensively considers the matching degree between the actual detection data and the theoretical model as well as the reliability of the original data.

[0119] For example, when restoring an ancient temple, even if the edge matching degree of a certain area is high, if the BIM data of the first edge area is severely missing, the matching degree of the first edge area will also be reduced accordingly, thereby reducing the detection priority of the first edge area.

[0120] The beneficial effect of the above implementation method is that when using UAV images and BIM information to inspect ancient buildings, the matching degree of the first edge area is adjusted by the data integrity corresponding to the BIM information, and the priority inspection area is determined according to the matching degree of the first edge area, which improves the data integrity and accuracy of the inspection of ancient buildings and improves the reliability of the ancient building restoration plan.

[0121] The beneficial effect of the above implementation method is that when the completeness of BIM data in a certain area is low, even if the structural matching degree calculation result is good, the matching degree of its first edge area will be reduced accordingly, thereby avoiding making wrong judgments based on incomplete data.

[0122] This application also provides a BIM-image recognition-based ancient building revitalization and restoration system based on drone collaboration, including a unit for performing the method described in any of the preceding claims.

[0123] Figure 4 A schematic diagram of the logical structure of a BIM-image recognition-based ancient building revitalization and restoration system based on UAV collaboration is provided for an embodiment of this application, as shown below. Figure 4 As shown, the system 1 of this embodiment includes a processing unit 11, a storage unit 12, and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12, and the transceiver unit 13 cooperate with each other to implement the above-described method. The beneficial effects of the embodiments of this application have been described in the above-described method and will not be repeated here.

[0124] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0125] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0126] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0127] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0128] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0129] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0130] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0131] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A BIM-image recognition-based method for the revitalization and restoration of ancient buildings based on UAV collaboration, characterized in that, The method includes: Obtain BIM information of the ancient building to be restored; based on the BIM information, determine the inspection areas of the ancient building to be restored at multiple inspection levels; The detection order of the areas to be detected at multiple detection levels is determined, and images of multiple areas to be detected at multiple detection levels are obtained according to the detection order; based on the BIM information and multiple images of the areas to be detected, the ancient building revitalization and restoration suggestions are determined according to the ancient building revitalization and restoration model. Among them, determining the detection order of the areas to be detected at multiple detection levels includes: acquiring the image of the first area to be detected corresponding to the area to be detected at the first detection level through a drone, and determining the area to be detected at the second detection level among the areas to be detected at multiple detection levels through BIM information and the image of the first area to be detected, wherein the first detection level is greater than the second detection level; Using BIM information and the image of the first area to be inspected, the area to be inspected at the second inspection level is determined from the areas to be inspected at multiple inspection levels, including: Based on the corresponding position of the first region image to be detected in the BIM information, the first edge regions in different directions corresponding to the first region image to be detected and the BIM information are determined; the structural matching degree between the first edge region and the BIM information in different directions is determined as the matching degree of the first edge region; wherein, multiple first edge regions are in the circumferential direction of the first region image to be detected, and the first edge region is an edge region with a preset proportion of the edge of the first region image to be detected. Determine the maximum first edge region matching degree among the structural matching degrees in different directions, and determine the detection region that is closest to the first edge region corresponding to the maximum first edge region matching degree, as the detection region of the second detection level; Based on BIM information, areas to be inspected at multiple inspection levels for the ancient building to be restored were identified, including: Obtain the structural type index and data integrity corresponding to the BIM information of multiple areas to be inspected, and determine the product of the structural type index and data integrity corresponding to the BIM information of multiple areas to be inspected, as the priority index of the areas to be inspected. The multiple areas to be inspected are sorted in descending order of priority index to determine the inspection level of the multiple areas of the ancient building to be restored.

2. The method as described in claim 1, characterized in that, Determine the structural matching degree between the first edge region and BIM information in different directions, as the matching degree of the first edge region, including: Determine the structural misalignment types of the first edge region and BIM information in different directions, and obtain the matching degree adjustment factor corresponding to each structural misalignment type; among which, the structural misalignment types include structural damage misalignment, corrosion misalignment, and contaminant misalignment; The product of the structural matching degree and the matching degree adjustment factor of the first edge region and BIM information in different directions is determined as the matching degree of the first edge region.

3. The method as described in claim 2, characterized in that, The matching degree adjustment factor for contaminant misalignment is 1.0 to 1.5; the matching degree adjustment factor for corrosion misalignment is 0.8 to 1.0; and the matching degree adjustment factor for structural damage misalignment is 0.5 to 0.

8.

4. The method as described in claim 3, characterized in that, Determining the structural matching degree between the first edge region and BIM information in different directions, as the matching degree of the first edge region, also includes: Determine the area of ​​the first edge region corresponding to the first edge region; when the area of ​​the first edge region is less than the preset area of ​​the first edge region, determine the first extension region of the first edge region in different directions, and determine the first extension region weight index corresponding to the first extension region in different directions, as the first extension region weight index of the first edge region in different directions; wherein, the area of ​​the first extension region is 50% to 150% of the area of ​​the first edge region, and the first extension region weight index includes the weight index corresponding to the structure type of the first extension region. The product of the structural matching degree of the first edge region and BIM information in different directions, the matching degree adjustment factor, and the weight index of the first extended region is determined as the matching degree of the first edge region.

5. The method as described in claim 4, characterized in that, Determining the structural matching degree between the first edge region and BIM information in different directions, as the matching degree of the first edge region, also includes: When the area of ​​the first edge region is greater than or equal to the preset area of ​​the first edge region, the weight index of the first edge region corresponding to the first edge region is determined; wherein, the weight index of the first edge region includes the weight index corresponding to the structure type of the first edge region; The product of the structural matching degree of the first edge region and BIM information in different directions, the matching degree adjustment factor, and the weight index of the first edge region is determined as the matching degree of the first edge region.

6. The method as described in claim 5, characterized in that, The method further includes: Determine the dispersion index corresponding to each area to be detected; whereby the dispersion index characterizes the degree of distance dispersion between each area to be detected and other areas to be detected. The larger the dispersion index, the greater the degree of distance dispersion between the area to be detected and other areas to be detected. The product of the structural type index, data completeness, and distance dispersion of the BIM information of multiple areas to be inspected is determined and used as the priority index for each area to be inspected.

7. The method as described in claim 6, characterized in that, The method further includes: Obtain the data completeness of BIM information for multiple areas to be inspected; Determine the structural matching degree between the first edge region and BIM information in different directions, and determine the product of the structural matching degree and data integrity of the first edge region and BIM information in different directions as the matching degree of the first edge region.

8. A BIM-image recognition-based system for the revitalization and restoration of ancient buildings based on UAV collaboration, characterized in that, Includes a unit for performing the method according to any one of claims 1 to 7.

Images