A method, system and storage medium for collecting and planning building basic data

Abstract

The present invention discloses a method, system and storage medium for collecting and planning basic data of a building. In a construction cycle, basic image data of the building is obtained, and image enhancement is performed on the first image data and the second image data respectively; a three-dimensional model is constructed from multiple angles based on the first enhanced image data and the second enhanced image data to generate multiple three-dimensional building models; through construction plan data, multiple comparative construction models under the corresponding construction cycle are obtained, and a model-by-model comparative analysis and difference degree analysis are performed on multiple three-dimensional building models and multiple BIM comparative construction models to obtain difference information data, and a deviation curve graph is generated through the difference information data; the deviation curve graph is compared with the expected deviation curve, and a comprehensive evaluation and early warning of the construction progress of the building are performed through the analysis results. Through the present invention, rapid comparison and accurate early warning of construction conditions can be effectively achieved, and high-level information analysis and building data planning can be achieved.

Description

Technical Field

[0001] The present invention relates to the field of data collection and analysis, and more specifically, to a method, system and storage medium for building foundation data collection and planning. Background Art

[0002] With the rapid development of the information age, the acquisition and planning analysis of basic building image data has become a key link in improving building management efficiency, optimizing resource allocation, and analyzing construction warnings. However, traditional building image data acquisition and planning processing methods have problems such as low processing efficiency and insufficient warning analysis. Therefore, it is necessary to develop a basic building data acquisition and planning method. Summary of the invention

[0003] The present invention overcomes the defects of the prior art and proposes a method, system and storage medium for collecting and planning building basic data.

[0004] A first aspect of the present invention provides a method for collecting and planning basic building data, comprising:

[0005] Acquire building foundation image data at preset angles within a construction cycle;

[0006] Based on the mean brightness of the image, data division is performed on the building basic image data to form first image data and second image data;

[0007] Extracting the outline features and color features of the building from the first image data and the second image data respectively to obtain building feature data, and training the building feature data through a GAN generation model to generate enhanced feature data;

[0008] Performing cluster analysis and characteristic defect area marking on the first image data and the second image data, and performing image feature enhancement on the first image data and the second image data based on the enhanced feature data according to the DCA feature fusion algorithm, and obtaining first enhanced image data and second enhanced image data;

[0009] Based on the first enhanced image data and the second enhanced image data, a three-dimensional model is constructed from multiple angles, wherein the construction mode is based on a BIM data format and is sorted based on a time dimension to generate multiple three-dimensional building models;

[0010] Through the construction plan data, multiple BIM comparison construction models in the corresponding construction period are obtained, and the multiple three-dimensional building models are compared and analyzed with the multiple BIM comparison construction models one by one to obtain the difference information data, and the deviation curve graph is generated through the difference information data;

[0011] The deviation curve is compared with the expected deviation curve, and the construction progress of the building is comprehensively evaluated and warned based on the analysis results.

[0012] In this solution, the building basic image data at a preset angle is obtained within a construction cycle, specifically:

[0013] Based on a preset angle, basic image data of the construction site is obtained through a preset camera device;

[0014] The corresponding angle information is recorded and stored in the basic image data, and the basic image data obtained from multiple preset angles are integrated to form the building basic image data.

[0015] In this solution, the building basic image data is divided based on the mean brightness of the image to form the first image data and the second image data, specifically:

[0016] Sort the building basic image data according to the time dimension of acquisition;

[0017] Extract pixel information from each image in the building basic image data, perform brightness statistics based on the pixel information, and calculate the average brightness of each image to obtain the average brightness of each image;

[0018] Based on the comparison and screening between the mean brightness and the preset brightness, images with brightness lower than the preset brightness are statistically marked to obtain first image data, and images with brightness higher than the preset brightness are statistically marked to obtain second image data.

[0019] In this solution, the first image data and the second image data are respectively subjected to building contour feature extraction and color feature extraction to obtain building feature data, and the building feature data is trained through a GAN generation model to generate enhanced feature data, specifically:

[0020] Based on the PCA analysis method, color feature extraction and contour feature extraction are performed on the first image data and the second image data respectively, and first building feature data and second building feature data are obtained;

[0021] The first building feature data and the second building feature data both include color features and outline features;

[0022] Constructing a generative model based on GAN, wherein the generative model includes a generator and a discriminator;

[0023] The first building feature data and the second building feature data are standardized and sequentially imported into the generator for data training. During the training process, the generator and the discriminator are evaluated for results and parameters are optimized until the discriminator and the generator reach Nash equilibrium.

[0024] Based on the trained generation model, a preset amount of data is simulated and generated to obtain feature-added data.

[0025] In this solution, cluster analysis and feature defect area marking are performed on the first image data and the second image data, and image feature enhancement is performed on the first image data and the second image data based on the enhanced feature data according to the DCA feature fusion algorithm, and first enhanced image data and second enhanced image data are obtained, specifically:

[0026] Performing K-means-based clustering grouping on the first building feature data to obtain multiple groups of feature data;

[0027] Quantize multiple sets of feature data, perform similarity analysis with enhanced feature data based on standard Euclidean distance, and select defect feature data groups based on similarity thresholds;

[0028] Based on the building feature data in the defect feature data group, perform corresponding feature extraction region marking and image marking from the first image data, and obtain first defect region information;

[0029] Performing clustering and defect area analysis on the second building feature data, and obtaining second defect area information;

[0030] Based on the first defect area information, integrating the feature data of the corresponding area from the first building feature data to obtain current feature data;

[0031] Based on the DCA feature fusion algorithm, the current feature data and the enhanced feature data are convolved and fused in a preset convolutional neural network, and the obtained fused feature data is used to overwrite the current feature data to form the first enhanced image data;

[0032] Based on the second defect area information, the DCA feature fusion algorithm is used to perform feature fusion enhancement on the corresponding defect area to form second enhanced image data.

[0033] In this solution, the three-dimensional model is constructed from multiple angles based on the first enhanced image data and the second enhanced image data. The construction mode is based on the BIM data format and is sorted based on the time dimension to generate multiple three-dimensional building models, specifically:

[0034] Based on the time dimension, the first enhanced image data and the second enhanced image data are integrated to form enhanced basic image data;

[0035] The enhanced basic image data is used to build a three-dimensional model from multiple angles. The construction process is based on the BIM software platform and data format, and multiple three-dimensional building models are obtained.

[0036] In this solution, the construction plan data is used to obtain multiple BIM comparison construction models in the corresponding construction period, and multiple three-dimensional building models are compared and analyzed with multiple BIM comparison construction models one by one to obtain difference information data. The deviation curve diagram is generated through the difference information data, specifically:

[0037] Through the construction plan data, multiple BIM comparison construction models corresponding to the construction period are obtained;

[0038] Through the BIM platform, multiple 3D building models are compared and analyzed with multiple BIM comparison construction models one by one. The analysis process includes difference calculation analysis. By selecting a 3D building model and a corresponding BIM comparison construction model to calculate the structural difference and appearance difference, the two obtained differences are weighted averaged to obtain a comprehensive difference.

[0039] Through multiple comparison and analysis processes, difference information data is obtained;

[0040] The difference information data includes a plurality of comprehensive difference degrees;

[0041] Data fitting based on linear regression is performed according to the difference information data to form a deviation curve graph.

[0042] In this scheme, the deviation curve is compared and analyzed with the expected deviation curve, and the construction progress of the building is comprehensively evaluated and warned based on the analysis results, specifically:

[0043] Through the construction plan data, the deviation curves of N construction cycles are analyzed, the N deviation curves are compared with the preset deviation curves to evaluate the construction deviation values, and the construction quality evaluation information and construction early warning information are generated;

[0044] Send construction quality assessment information and construction warning information to the preset terminal device.

[0045] The second aspect of the present invention further provides a building basic data collection and planning system, the system comprising: a memory, a processor, the memory comprising a building basic data collection and planning program, the building basic data collection and planning program when executed by the processor to implement the following steps:

[0046] Acquire building foundation image data at preset angles within a construction cycle;

[0047] Based on the mean brightness of the image, data division is performed on the building basic image data to form first image data and second image data;

[0048] Extracting the outline features and color features of the building from the first image data and the second image data respectively to obtain building feature data, and training the building feature data through a GAN generation model to generate enhanced feature data;

[0049] Performing cluster analysis and characteristic defect area marking on the first image data and the second image data, and performing image feature enhancement on the first image data and the second image data based on the enhanced feature data according to the DCA feature fusion algorithm, and obtaining first enhanced image data and second enhanced image data;

[0050] Based on the first enhanced image data and the second enhanced image data, a three-dimensional model is constructed from multiple angles, wherein the construction mode is based on a BIM data format and is sorted based on a time dimension to generate multiple three-dimensional building models;

[0051] Through the construction plan data, multiple BIM comparison construction models in the corresponding construction period are obtained, and the multiple three-dimensional building models are compared and analyzed with the multiple BIM comparison construction models one by one to obtain the difference information data, and the deviation curve graph is generated through the difference information data;

[0052] The deviation curve is compared with the expected deviation curve, and the construction progress of the building is comprehensively evaluated and warned based on the analysis results.

[0053] The third aspect of the present invention also provides a computer-readable storage medium, which includes a building basic data collection and planning program. When the building basic data collection and planning program is executed by a processor, the steps of the building basic data collection and planning method as described in any one of the above items are implemented.

[0054] The present invention discloses a method, system and storage medium for collecting and planning basic data of a building. In a construction cycle, basic image data of the building is obtained, and image enhancement is performed on the first image data and the second image data respectively; a three-dimensional model is constructed from multiple angles based on the first enhanced image data and the second enhanced image data to generate multiple three-dimensional building models; through construction plan data, multiple comparative construction models under the corresponding construction cycle are obtained, and a model-by-model comparative analysis and difference degree analysis are performed on multiple three-dimensional building models and multiple BIM comparative construction models to obtain difference information data, and a deviation curve graph is generated through the difference information data; the deviation curve graph is compared with the expected deviation curve, and a comprehensive evaluation and early warning of the construction progress of the building are performed through the analysis results. Through the present invention, rapid comparison and accurate early warning of construction conditions can be effectively achieved, and high-level information analysis and building data planning can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1A flow chart of a building basic data collection and planning method according to the present invention is shown;

[0056] Figure 2 A block diagram of a building basic data collection and planning system of the present invention is shown. DETAILED DESCRIPTION

[0057] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0058] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0059] Figure 1 A flow chart of a building basic data collection and planning method of the present invention is shown.

[0060] like Figure 1 As shown, the first aspect of the present invention provides a method for collecting and planning basic building data, comprising:

[0061] S102, acquiring building foundation image data at a preset angle within a construction cycle;

[0062] S104, dividing the building basic image data based on the mean brightness of the image to form first image data and second image data;

[0063] S106, extracting the outline features and color features of the building from the first image data and the second image data respectively to obtain building feature data, and training the building feature data through a GAN generation model to generate enhanced feature data;

[0064] S108, performing cluster analysis and feature defect area marking on the first image data and the second image data, and performing image feature enhancement on the first image data and the second image data based on the enhanced feature data according to the DCA feature fusion algorithm, and obtaining first enhanced image data and second enhanced image data;

[0065] S110, constructing a three-dimensional model from multiple angles based on the first enhanced image data and the second enhanced image data, wherein the construction mode is based on a BIM data format and the data are sorted based on a time dimension to generate a plurality of three-dimensional building models;

[0066] S112, obtaining multiple BIM comparison construction models in a corresponding construction period through the construction plan data, performing model-to-model comparison analysis and difference analysis on the multiple three-dimensional building models and the multiple BIM comparison construction models, obtaining difference information data, and generating a deviation curve graph through the difference information data;

[0067] S114, compare and analyze the deviation curve with the expected deviation curve, and conduct a comprehensive assessment and early warning of the construction progress of the building through the analysis results.

[0068] It should be noted that the preset angles include a plurality of construction site angles, each of which includes at least one camera device, and basic image data of the building is acquired through each camera device.

[0069] It is worth mentioning that when conducting building appearance analysis and construction progress assessment, the existing technology is generally based on manual experience or is limited to the assessment of construction results, and lacks assessment of construction defects in the intermediate process. In the present invention, by collecting construction building image data from multiple angles and generating corresponding BIM models for comparative analysis, construction assessment analysis can be performed in an information-based mode, reducing analysis errors caused by manual analysis, and performing data planning analysis and building quality assessment more accurately.

[0070] According to an embodiment of the present invention, obtaining building basic image data at a preset angle within a construction cycle is specifically as follows:

[0071] Based on a preset angle, basic image data of the construction site is obtained through a preset camera device;

[0072] The corresponding angle information is recorded and stored in the basic image data, and the basic image data obtained from multiple preset angles are integrated to form the building basic image data.

[0073] It should be noted that the three-dimensional model of the building can be restored through architectural image data from multiple angles, and the three-dimensional model can be stored and analyzed based on the BIM data format.

[0074] According to an embodiment of the present invention, the data of the basic building image data is divided based on the mean brightness of the image to form the first image data and the second image data, specifically:

[0075] Sort the building basic image data according to the time dimension of acquisition;

[0076] Extract pixel information from each image in the building basic image data, perform brightness statistics based on the pixel information, and calculate the average brightness of each image to obtain the average brightness of each image;

[0077] Based on the comparison and screening between the mean brightness and the preset brightness, images with brightness lower than the preset brightness are statistically marked to obtain first image data, and images with brightness higher than the preset brightness are statistically marked to obtain second image data.

[0078] It should be noted that the pixel information includes RBG information, brightness, spatial arrangement and other information. In the basic image of the building site, due to the influence of light during the day and at night, there is a difference in the brightness of the two image data obtained. Furthermore, the building outlines, building colors and other features of the two will be affected to a certain extent, resulting in inaccurate three-dimensional modeling. Therefore, it is necessary to perform corresponding data division based on image brightness analysis. Subsequently, corresponding feature enhancement can be performed for high-brightness images and low-brightness images. In addition, it is worth mentioning that in the prior art, in the analysis of basic building images, there is often a lack of corresponding defect analysis, such as color defects and contour defects. This may be subject to the influence of light, and there is a certain loss when performing feature analysis on the collected images.

[0079] According to an embodiment of the present invention, the first image data and the second image data are respectively subjected to building contour feature extraction and color feature extraction to obtain building feature data, and the building feature data is trained through a GAN generation model to generate enhanced feature data, specifically:

[0080] Based on the PCA analysis method, color feature extraction and contour feature extraction are performed on the first image data and the second image data respectively, and first building feature data and second building feature data are obtained;

[0081] The first building feature data and the second building feature data both include color features and outline features;

[0082] Constructing a generative model based on GAN, wherein the generative model includes a generator and a discriminator;

[0083] The first building feature data and the second building feature data are standardized and sequentially imported into the generator for data training. During the training process, the generator and the discriminator are evaluated for results and parameters are optimized until the discriminator and the generator reach Nash equilibrium.

[0084] Based on the trained generation model, a preset amount of data is simulated and generated to obtain feature-added data.

[0085] It should be noted that the data are imported in sequence for training, and the training process includes two stages, which are respectively for the training process of the first building feature data and the second building feature data. Since both data have relevant important features, they need to be trained separately to obtain high-quality simulation feature data.

[0086] According to an embodiment of the present invention, cluster analysis and feature defect area marking are performed on the first image data and the second image data, and image feature enhancement is performed on the first image data and the second image data based on the enhanced feature data according to the DCA feature fusion algorithm, and first enhanced image data and second enhanced image data are obtained, specifically:

[0087] Performing K-means-based clustering grouping on the first building feature data to obtain multiple groups of feature data;

[0088] Quantize multiple sets of feature data, perform similarity analysis with enhanced feature data based on standard Euclidean distance, and select defect feature data groups based on similarity thresholds;

[0089] Based on the building feature data in the defect feature data group, perform corresponding feature extraction region marking and image marking from the first image data, and obtain first defect region information;

[0090] Performing clustering and defect area analysis on the second building feature data, and obtaining second defect area information;

[0091] Based on the first defect area information, integrating the feature data of the corresponding area from the first building feature data to obtain current feature data;

[0092] Based on the DCA feature fusion algorithm, the current feature data and the enhanced feature data are convolved and fused in a preset convolutional neural network, and the obtained fused feature data is used to overwrite the current feature data to form the first enhanced image data;

[0093] Based on the second defect area information, the DCA feature fusion algorithm is used to perform feature fusion enhancement on the corresponding defect area to form second enhanced image data.

[0094] It should be noted that the first and second image data include multiple images, and corresponding feature data can be extracted from each image to integrate the corresponding building feature data. In the similarity analysis between the standard Euclidean distance and the enhanced feature data, the larger the distance value, the lower the similarity, and each group is compared with the enhanced feature data, and the defect feature data group is screened out based on the similarity threshold, that is, the similarity is lower than the threshold and marked as a defect group. The defect area analysis of the second building feature data is the same as the analysis process of the first building feature data.

[0095] The present invention can quickly and accurately screen out relevant areas or images with defects by clustering and grouping feature data, and subsequently perform feature enhancement based on the defective areas, effectively increasing the accuracy of three-dimensional modeling of basic image data. It has strong practicality and is of great significance for subsequent image conversion into three-dimensional models for construction analysis and appearance three-dimensional difference analysis.

[0096] According to an embodiment of the present invention, the three-dimensional model is constructed from multiple angles based on the first enhanced image data and the second enhanced image data, the construction mode is based on the BIM data format, and is sorted based on the time dimension to generate multiple three-dimensional building models, specifically:

[0097] Based on the time dimension, the first enhanced image data and the second enhanced image data are integrated to form enhanced basic image data;

[0098] The enhanced basic image data is used to build a three-dimensional model from multiple angles. The construction process is based on the BIM software platform and data format, and multiple three-dimensional building models are obtained.

[0099] It should be noted that, since the data is generally collected multiple times, the collected data (basic image data) can be used to construct multiple BIM building models in three dimensions, and the changing conditions of the building construction can also be analyzed accordingly.

[0100] According to an embodiment of the present invention, the construction plan data is used to obtain multiple BIM comparison construction models in the corresponding construction period, and multiple three-dimensional building models are compared and analyzed with multiple BIM comparison construction models one by one to obtain difference information data, and a deviation curve graph is generated through the difference information data, specifically:

[0101] Through the construction plan data, multiple BIM comparison construction models corresponding to the construction period are obtained;

[0102] Through the BIM platform, multiple 3D building models are compared and analyzed with multiple BIM comparison construction models one by one. The analysis process includes difference calculation analysis. By selecting a 3D building model and a corresponding BIM comparison construction model to calculate the structural difference and appearance difference, the two obtained differences are weighted averaged to obtain a comprehensive difference.

[0103] Through multiple comparison and analysis processes, difference information data is obtained;

[0104] The difference information data includes a plurality of comprehensive difference degrees;

[0105] Data fitting based on linear regression is performed according to the difference information data to form a deviation curve graph.

[0106] It should be noted that the number of the multiple three-dimensional building models and the multiple BIM comparison construction models is consistent, and the number of three-dimensional building models is controlled by the frequency of collecting image data and modeling. In the calculation of structural differences and appearance differences by selecting a three-dimensional building model and a corresponding BIM comparison construction model, two models are selected for each difference calculation. If there are N three-dimensional building models and N BIM comparison construction models, N comprehensive differences are finally obtained. In the calculation of structural differences and appearance differences, structural differences include difference analysis of the plane layout, component space layout, and component quantity in the model, and appearance differences include difference analysis of overall size, building floor height, geometric structure, etc.

[0107] The BIM platform is a BIM-based software analysis platform that can perform certain data analysis on BIM building data.

[0108] According to an embodiment of the present invention, the deviation curve graph is compared and analyzed with the expected deviation curve, and a comprehensive evaluation and early warning of the construction progress of the building are performed based on the analysis results, specifically:

[0109] Through the construction plan data, the deviation curves of N construction cycles are analyzed, the N deviation curves are compared with the preset deviation curves to evaluate the construction deviation values, and the construction quality evaluation information and construction early warning information are generated;

[0110] Send construction quality assessment information and construction warning information to the preset terminal device.

[0111] It should be noted that the deviation curve of the N construction cycles is specifically a deviation curve for comprehensive analysis of the N construction cycles that have been constructed in history, so as to warn of related construction processes in the later period. The preset deviation curve is a curve obtained by the user through reasonable deviation analysis based on the existing building construction process or construction plan, which has a comparative analysis function.

[0112] The construction plan data includes information on multiple construction cycles, BIM comparison construction models, construction progress, cost information, importance and priority of each construction area, and other information.

[0113] According to an embodiment of the present invention, the preset deviation curve graph further includes:

[0114] According to the construction plan data, multiple BIM comparison construction models within a construction period are selected, and the multiple BIM comparison construction models are marked as comparison models;

[0115] Based on the construction plan data, obtaining key construction areas and non-key construction areas within the construction period;

[0116] Marking regions based on the key construction region and the non-key construction region from the comparison model to form a first region and a second region;

[0117] According to the construction plan data, the expected maximum deviation information of the BIM structure is obtained, and based on the expected maximum deviation information of the BIM structure, the building structure simulation change analysis is performed on the first area and the second area respectively, and a preprocessing comparison model after the structure change is obtained;

[0118] Perform difference calculation analysis on the contrast model and the preprocessing contrast model, and the analysis process calculates the difference between the first area and the second area respectively, and obtains two difference values ​​respectively;

[0119] Based on the first area, the second area and the preset construction proportion, a weighted average calculation is performed on the two difference values ​​to obtain an expected difference;

[0120] The expected differences of multiple comparison models are calculated and analyzed, and all the expected differences are subjected to linear regression change analysis based on the construction period to form a preset deviation curve.

[0121] It should be noted that the preset construction weight is a weight value pre-set by the user, and the weight is assigned based on factors such as the construction difficulty and importance of key construction areas and non-key construction areas. The weight of key construction areas is greater than that of non-key construction areas. Furthermore, in the weighted average calculation of the two difference values, the weight assigned to the difference of the first area is greater than that of the second area. The preset deviation curve is a curve that can be quickly compared and analyzed. In large-scale and complex construction, the setting of this curve is an important task. In the present invention, based on the expected BIM deviation information, the relevant models are simulated and changed, and the expected deviation value with certain reference significance and comparative analysis function is generated in combination with the importance of the construction area, and a linear change analysis is performed based on the construction time dimension, thereby obtaining the corresponding overall expected deviation curve (preset deviation curve), so as to realize the subsequent rapid deviation analysis and early warning of the building model formed by the basic image.

[0122] Figure 2 A block diagram of a building basic data collection and planning system of the present invention is shown.

[0123] The second aspect of the present invention further provides a building basic data collection and planning system 2, the system comprising: a memory 21, a processor 22, the memory comprising a building basic data collection and planning program, the building basic data collection and planning program when executed by the processor to implement the following steps:

[0124] Acquire building foundation image data at preset angles within a construction cycle;

[0125] Based on the mean brightness of the image, data division is performed on the building basic image data to form first image data and second image data;

[0126] Extracting the outline features and color features of the building from the first image data and the second image data respectively to obtain building feature data, and training the building feature data through a GAN generation model to generate enhanced feature data;

[0127] Performing cluster analysis and characteristic defect area marking on the first image data and the second image data, and performing image feature enhancement on the first image data and the second image data based on the enhanced feature data according to the DCA feature fusion algorithm, and obtaining first enhanced image data and second enhanced image data;

[0128] Based on the first enhanced image data and the second enhanced image data, a three-dimensional model is constructed from multiple angles, wherein the construction mode is based on a BIM data format and is sorted based on a time dimension to generate multiple three-dimensional building models;

[0129] Through the construction plan data, multiple BIM comparison construction models in the corresponding construction period are obtained, and the multiple three-dimensional building models are compared and analyzed with the multiple BIM comparison construction models one by one to obtain the difference information data, and the deviation curve graph is generated through the difference information data;

[0130] The deviation curve is compared with the expected deviation curve, and the construction progress of the building is comprehensively evaluated and warned based on the analysis results.

[0131] It should be noted that the preset angles include a plurality of construction site angles, each of which includes at least one camera device, and basic image data of the building is acquired through each camera device.

[0132] It is worth mentioning that when conducting building appearance analysis and construction progress assessment, the existing technology is generally based on manual experience or is limited to the assessment of construction results, and lacks assessment of construction defects in the intermediate process. In the present invention, by collecting construction building image data from multiple angles and generating corresponding BIM models for comparative analysis, construction assessment analysis can be performed in an information-based mode, reducing analysis errors caused by manual analysis, and performing data planning analysis and building quality assessment more accurately.

[0133] According to an embodiment of the present invention, obtaining building basic image data at a preset angle within a construction cycle is specifically as follows:

[0134] Based on a preset angle, basic image data of the construction site is obtained through a preset camera device;

[0135] The corresponding angle information is recorded and stored in the basic image data, and the basic image data obtained from multiple preset angles are integrated to form the building basic image data.

[0136] It should be noted that the three-dimensional model of the building can be restored through architectural image data from multiple angles, and the three-dimensional model can be stored and analyzed based on the BIM data format.

[0137] According to an embodiment of the present invention, the data of the basic building image data is divided based on the mean brightness of the image to form the first image data and the second image data, specifically:

[0138] Sort the building basic image data according to the time dimension of acquisition;

[0139] Extract pixel information from each image in the building basic image data, perform brightness statistics based on the pixel information, and calculate the average brightness of each image to obtain the average brightness of each image;

[0140] Based on the comparison and screening between the mean brightness and the preset brightness, images with brightness lower than the preset brightness are statistically marked to obtain first image data, and images with brightness higher than the preset brightness are statistically marked to obtain second image data.

[0141] It should be noted that the pixel information includes RBG information, brightness, spatial arrangement and other information. In the basic image of the building site, due to the influence of light during the day and at night, there is a difference in the brightness of the two image data obtained. Furthermore, the building outlines, building colors and other features of the two will be affected to a certain extent, resulting in inaccurate three-dimensional modeling. Therefore, it is necessary to perform corresponding data division based on image brightness analysis. Subsequently, corresponding feature enhancement can be performed for high-brightness images and low-brightness images. In addition, it is worth mentioning that in the prior art, in the analysis of basic building images, there is often a lack of corresponding defect analysis, such as color defects and contour defects. This may be subject to the influence of light, and there is a certain loss when performing feature analysis on the collected images.

[0142] According to an embodiment of the present invention, the first image data and the second image data are respectively subjected to building contour feature extraction and color feature extraction to obtain building feature data, and the building feature data is trained through a GAN generation model to generate enhanced feature data, specifically:

[0143] Based on the PCA analysis method, color feature extraction and contour feature extraction are performed on the first image data and the second image data respectively, and first building feature data and second building feature data are obtained;

[0144] The first building feature data and the second building feature data both include color features and outline features;

[0145] Constructing a generative model based on GAN, wherein the generative model includes a generator and a discriminator;

[0146] The first building feature data and the second building feature data are standardized and sequentially imported into the generator for data training. During the training process, the generator and the discriminator are evaluated for results and parameters are optimized until the discriminator and the generator reach Nash equilibrium.

[0147] Based on the trained generation model, a preset amount of data is simulated and generated to obtain feature-added data.

[0148] It should be noted that the data are imported in sequence for training, and the training process includes two stages, which are respectively for the training process of the first building feature data and the second building feature data. Since both data have relevant important features, they need to be trained separately to obtain high-quality simulation feature data.

[0149] According to an embodiment of the present invention, cluster analysis and feature defect area marking are performed on the first image data and the second image data, and image feature enhancement is performed on the first image data and the second image data based on the enhanced feature data according to the DCA feature fusion algorithm, and first enhanced image data and second enhanced image data are obtained, specifically:

[0150] Performing K-means-based clustering grouping on the first building feature data to obtain multiple groups of feature data;

[0151] Quantize multiple sets of feature data, perform similarity analysis with enhanced feature data based on standard Euclidean distance, and select defect feature data groups based on similarity thresholds;

[0152] Based on the building feature data in the defect feature data group, perform corresponding feature extraction region marking and image marking from the first image data, and obtain first defect region information;

[0153] Performing clustering and defect area analysis on the second building feature data, and obtaining second defect area information;

[0154] Based on the first defect area information, integrating the feature data of the corresponding area from the first building feature data to obtain current feature data;

[0155] Based on the DCA feature fusion algorithm, the current feature data and the enhanced feature data are convolved and fused in a preset convolutional neural network, and the obtained fused feature data is used to overwrite the current feature data to form the first enhanced image data;

[0156] Based on the second defect area information, the DCA feature fusion algorithm is used to perform feature fusion enhancement on the corresponding defect area to form second enhanced image data.

[0157] It should be noted that the first and second image data include multiple images, and corresponding feature data can be extracted from each image to integrate the corresponding building feature data. In the similarity analysis between the standard Euclidean distance and the enhanced feature data, the larger the distance value, the lower the similarity, and each group is compared with the enhanced feature data, and the defect feature data group is screened out based on the similarity threshold, that is, the similarity is lower than the threshold and marked as a defect group. The defect area analysis of the second building feature data is the same as the analysis process of the first building feature data.

[0158] The present invention can quickly and accurately screen out relevant areas or images with defects by clustering and grouping feature data, and subsequently perform feature enhancement based on the defective areas, effectively increasing the accuracy of three-dimensional modeling of basic image data. It has strong practicality and is of great significance for subsequent image conversion into three-dimensional models for construction analysis and appearance three-dimensional difference analysis.

[0159] According to an embodiment of the present invention, the three-dimensional model is constructed from multiple angles based on the first enhanced image data and the second enhanced image data, the construction mode is based on the BIM data format, and is sorted based on the time dimension to generate multiple three-dimensional building models, specifically:

[0160] Based on the time dimension, the first enhanced image data and the second enhanced image data are integrated to form enhanced basic image data;

[0161] The enhanced basic image data is used to build a three-dimensional model from multiple angles. The construction process is based on the BIM software platform and data format, and multiple three-dimensional building models are obtained.

[0162] It should be noted that, since the data is generally collected multiple times, the collected data (basic image data) can be used to construct multiple BIM building models in three dimensions, and the changing conditions of the building construction can also be analyzed accordingly.

[0163] According to an embodiment of the present invention, the construction plan data is used to obtain multiple BIM comparison construction models in the corresponding construction period, and multiple three-dimensional building models are compared and analyzed with multiple BIM comparison construction models one by one to obtain difference information data, and a deviation curve graph is generated through the difference information data, specifically:

[0164] Through the construction plan data, multiple BIM comparison construction models corresponding to the construction period are obtained;

[0165] Through the BIM platform, multiple 3D building models are compared and analyzed with multiple BIM comparison construction models one by one. The analysis process includes difference calculation analysis. By selecting a 3D building model and a corresponding BIM comparison construction model to calculate the structural difference and appearance difference, the two obtained differences are weighted averaged to obtain a comprehensive difference.

[0166] Through multiple comparison and analysis processes, difference information data is obtained;

[0167] The difference information data includes a plurality of comprehensive difference degrees;

[0168] Data fitting based on linear regression is performed according to the difference information data to form a deviation curve graph.

[0169] It should be noted that the number of the multiple three-dimensional building models and the multiple BIM comparison construction models is consistent, and the number of three-dimensional building models is controlled by the frequency of collecting image data and modeling. In the calculation of structural differences and appearance differences by selecting a three-dimensional building model and a corresponding BIM comparison construction model, two models are selected for each difference calculation. If there are N three-dimensional building models and N BIM comparison construction models, N comprehensive differences are finally obtained. In the calculation of structural differences and appearance differences, structural differences include difference analysis of the plane layout, component space layout, and component quantity in the model, and appearance differences include difference analysis of overall size, building floor height, geometric structure, etc.

[0170] The BIM platform is a BIM-based software analysis platform that can perform certain data analysis on BIM building data.

[0171] According to an embodiment of the present invention, the deviation curve graph is compared and analyzed with the expected deviation curve, and a comprehensive evaluation and early warning of the construction progress of the building are performed based on the analysis results, specifically:

[0172] Through the construction plan data, the deviation curves of N construction cycles are analyzed, the N deviation curves are compared with the preset deviation curves to evaluate the construction deviation values, and the construction quality evaluation information and construction early warning information are generated;

[0173] Send construction quality assessment information and construction warning information to the preset terminal device.

[0174] It should be noted that the deviation curve of the N construction cycles is specifically a deviation curve for comprehensive analysis of the N construction cycles that have been constructed in history, so as to warn of related construction processes in the later period. The preset deviation curve is a curve obtained by the user through reasonable deviation analysis based on the existing building construction process or construction plan, which has a comparative analysis function.

[0175] The construction plan data includes information on multiple construction cycles, BIM comparison construction models, construction progress, cost information, importance and priority of each construction area, and other information.

[0176] According to an embodiment of the present invention, the preset deviation curve graph further includes:

[0177] According to the construction plan data, multiple BIM comparison construction models within a construction period are selected, and the multiple BIM comparison construction models are marked as comparison models;

[0178] Based on the construction plan data, obtaining key construction areas and non-key construction areas within the construction period;

[0179] Marking regions based on the key construction region and the non-key construction region from the comparison model to form a first region and a second region;

[0180] According to the construction plan data, the expected maximum deviation information of the BIM structure is obtained, and based on the expected maximum deviation information of the BIM structure, the building structure simulation change analysis is performed on the first area and the second area respectively, and a preprocessing comparison model after the structure change is obtained;

[0181] Perform difference calculation analysis on the contrast model and the preprocessing contrast model, and the analysis process calculates the difference between the first area and the second area respectively, and obtains two difference values ​​respectively;

[0182] Based on the first area, the second area and the preset construction proportion, a weighted average calculation is performed on the two difference values ​​to obtain an expected difference;

[0183] The expected differences of multiple comparison models are calculated and analyzed, and all the expected differences are subjected to linear regression change analysis based on the construction period to form a preset deviation curve.

[0184] It should be noted that the preset construction weight is a weight value pre-set by the user, and the weight is assigned based on factors such as the construction difficulty and importance of key construction areas and non-key construction areas. The weight of key construction areas is greater than that of non-key construction areas. Furthermore, in the weighted average calculation of the two difference values, the weight assigned to the difference of the first area is greater than that of the second area. The preset deviation curve is a curve that can be quickly compared and analyzed. In large-scale and complex construction, the setting of this curve is an important task. In the present invention, based on the expected BIM deviation information, the relevant models are simulated and changed, and the expected deviation value with certain reference significance and comparative analysis function is generated in combination with the importance of the construction area, and a linear change analysis is performed based on the construction time dimension, thereby obtaining the corresponding overall expected deviation curve (preset deviation curve), so as to realize the subsequent rapid deviation analysis and early warning of the building model formed by the basic image.

[0185] The third aspect of the present invention also provides a computer-readable storage medium, which includes a building basic data collection and planning program. When the building basic data collection and planning program is executed by a processor, the steps of the building basic data collection and planning method as described in any one of the above items are implemented.

[0186] The present invention discloses a method, system and storage medium for collecting and planning basic data of a building. In a construction cycle, basic image data of the building is obtained, and image enhancement is performed on the first image data and the second image data respectively; a three-dimensional model is constructed from multiple angles based on the first enhanced image data and the second enhanced image data to generate multiple three-dimensional building models; through construction plan data, multiple comparative construction models under the corresponding construction cycle are obtained, and a model-by-model comparative analysis and difference degree analysis are performed on multiple three-dimensional building models and multiple BIM comparative construction models to obtain difference information data, and a deviation curve graph is generated through the difference information data; the deviation curve graph is compared with the expected deviation curve, and a comprehensive evaluation and early warning of the construction progress of the building are performed through the analysis results. Through the present invention, rapid comparison and accurate early warning of construction conditions can be effectively achieved, and high-level information analysis and building data planning can be achieved.

[0187] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0188] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0189] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0190] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0191] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0192] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A building basic data collection and planning method, characterized in that: include: Acquire building foundation image data at preset angles within a construction cycle; Based on the mean brightness of the image, data division is performed on the building basic image data to form first image data and second image data; Extracting the outline features and color features of the building from the first image data and the second image data respectively to obtain building feature data, and training the building feature data through a GAN generation model to generate enhanced feature data; Performing cluster analysis and characteristic defect area marking on the first image data and the second image data, and performing image feature enhancement on the first image data and the second image data based on the enhanced feature data according to the DCA feature fusion algorithm, and obtaining first enhanced image data and second enhanced image data; Based on the first enhanced image data and the second enhanced image data, a three-dimensional model is constructed from multiple angles, wherein the construction mode is based on a BIM data format and is sorted based on a time dimension to generate multiple three-dimensional building models; Through the construction plan data, multiple BIM comparison construction models in the corresponding construction period are obtained, and the multiple three-dimensional building models are compared and analyzed with the multiple BIM comparison construction models one by one to obtain the difference information data, and the deviation curve graph is generated through the difference information data; Compare and analyze the deviation curve with the expected deviation curve, and use the analysis results to conduct a comprehensive assessment and early warning of the building's construction progress; The cluster analysis and characteristic defect area marking are performed on the first image data and the second image data, and the image features of the first image data and the second image data are enhanced based on the enhanced feature data according to the DCA feature fusion algorithm, and the first enhanced image data and the second enhanced image data are obtained, specifically: Performing K-means-based clustering grouping on the first building feature data to obtain multiple groups of feature data; Quantize multiple sets of feature data, perform similarity analysis with enhanced feature data based on standard Euclidean distance, and select defect feature data groups based on similarity thresholds; Based on the building feature data in the defect feature data group, perform corresponding feature extraction region marking and image marking from the first image data, and obtain first defect region information; Performing clustering and defect area analysis on the second building feature data, and obtaining second defect area information; Based on the first defect area information, integrating the feature data of the corresponding area from the first building feature data to obtain current feature data; Based on the DCA feature fusion algorithm, the current feature data and the enhanced feature data are convolved and fused in a preset convolutional neural network, and the obtained fused feature data is used to overwrite the current feature data to form the first enhanced image data; Based on the second defect area information, the DCA feature fusion algorithm is used to perform feature fusion enhancement on the corresponding defect area to form second enhanced image data.

2. A building basic data collection and planning method according to claim 1, characterized in that: The method of obtaining the building basic image data at a preset angle during a construction cycle is specifically as follows: Based on a preset angle, basic image data of the construction site is obtained through a preset camera device; The corresponding angle information is recorded and stored in the basic image data, and the basic image data obtained from multiple preset angles are integrated to form the building basic image data.

3. A building basic data collection and planning method according to claim 1, characterized in that: The data division of the building basic image data based on the mean brightness of the image to form the first image data and the second image data is specifically as follows: Sort the building basic image data according to the time dimension of acquisition; Extract pixel information from each image in the building basic image data, perform brightness statistics based on the pixel information, and calculate the average brightness of each image to obtain the average brightness of each image; Based on the comparison and screening between the mean brightness and the preset brightness, images with brightness lower than the preset brightness are statistically marked to obtain first image data, and images with brightness higher than the preset brightness are statistically marked to obtain second image data.

4. A building basic data collection and planning method according to claim 3, characterized in that: The first image data and the second image data are respectively subjected to building contour feature extraction and color feature extraction to obtain building feature data, and the building feature data is trained through a GAN generation model to generate enhanced feature data, specifically: Based on the PCA analysis method, color feature extraction and contour feature extraction are performed on the first image data and the second image data respectively, and first building feature data and second building feature data are obtained; The first building feature data and the second building feature data both include color features and outline features; Constructing a generative model based on GAN, wherein the generative model includes a generator and a discriminator; The first building feature data and the second building feature data are standardized and sequentially imported into the generator for data training. During the training process, the generator and the discriminator are evaluated for results and parameters are optimized until the discriminator and the generator reach Nash equilibrium. Based on the trained generation model, a preset amount of data is simulated and generated to obtain enhanced feature data.

5. A building basic data collection and planning method according to claim 1, characterized in that: The three-dimensional model is constructed from multiple angles based on the first enhanced image data and the second enhanced image data, the construction mode is based on the BIM data format, and is sorted based on the time dimension to generate multiple three-dimensional building models, specifically: Based on the time dimension, the first enhanced image data and the second enhanced image data are integrated to form enhanced basic image data; The enhanced basic image data is used to build a three-dimensional model from multiple angles. The building process is based on the BIM software platform and data format, and multiple three-dimensional building models are obtained.

6. A building basic data collection and planning method according to claim 5, characterized in that: The construction plan data is used to obtain multiple BIM comparison construction models in the corresponding construction period, and multiple three-dimensional building models are compared and analyzed with the multiple BIM comparison construction models one by one to obtain difference information data, and a deviation curve chart is generated through the difference information data, specifically: Through the construction plan data, multiple BIM comparison construction models corresponding to the construction period are obtained; Through the BIM platform, multiple 3D building models are compared and analyzed with multiple BIM comparison construction models one by one. The analysis process includes difference calculation analysis. By selecting a 3D building model and a corresponding BIM comparison construction model to calculate the structural difference and appearance difference, the two obtained differences are weighted averaged to obtain a comprehensive difference. Through multiple comparison and analysis processes, difference information data is obtained; The difference information data includes a plurality of comprehensive difference degrees; Data fitting based on linear regression is performed according to the difference information data to form a deviation curve graph.

7. A building basic data collection and planning method according to claim 6, characterized in that: The deviation curve is compared and analyzed with the expected deviation curve, and the construction progress of the building is comprehensively evaluated and warned based on the analysis results, specifically: Through the construction plan data, the deviation curves of N construction cycles are analyzed, the N deviation curves are compared with the preset deviation curves to evaluate the construction deviation values, and the construction quality evaluation information and construction early warning information are generated; Send construction quality assessment information and construction warning information to the preset terminal device.

8. A building basic data collection and planning system, characterized in that: The system includes: a memory and a processor. The memory includes a building basic data collection and planning program. When the building basic data collection and planning program is executed by the processor, the following steps are implemented: Acquire building foundation image data at preset angles within a construction cycle; Based on the mean brightness of the image, data division is performed on the building basic image data to form first image data and second image data; Extracting the outline features and color features of the building from the first image data and the second image data respectively to obtain building feature data, and training the building feature data through a GAN generation model to generate enhanced feature data; Performing cluster analysis and characteristic defect area marking on the first image data and the second image data, and performing image feature enhancement on the first image data and the second image data based on the enhanced feature data according to the DCA feature fusion algorithm, and obtaining first enhanced image data and second enhanced image data; Based on the first enhanced image data and the second enhanced image data, a three-dimensional model is constructed from multiple angles, wherein the construction mode is based on a BIM data format and is sorted based on a time dimension to generate multiple three-dimensional building models; Through the construction plan data, multiple BIM comparison construction models in the corresponding construction period are obtained, and the multiple three-dimensional building models are compared and analyzed with the multiple BIM comparison construction models one by one to obtain the difference information data, and the deviation curve graph is generated through the difference information data; Compare and analyze the deviation curve with the expected deviation curve, and use the analysis results to conduct a comprehensive assessment and early warning of the building's construction progress; The cluster analysis and characteristic defect area marking are performed on the first image data and the second image data, and the image features of the first image data and the second image data are enhanced based on the enhanced feature data according to the DCA feature fusion algorithm, and the first enhanced image data and the second enhanced image data are obtained, specifically: Performing K-means-based clustering grouping on the first building feature data to obtain multiple groups of feature data; Quantize multiple sets of feature data, perform similarity analysis with enhanced feature data based on standard Euclidean distance, and select defect feature data groups based on similarity thresholds; Based on the building feature data in the defect feature data group, perform corresponding feature extraction region marking and image marking from the first image data, and obtain first defect region information; Performing clustering and defect area analysis on the second building feature data, and obtaining second defect area information; Based on the first defect area information, integrating the feature data of the corresponding area from the first building feature data to obtain current feature data; Based on the DCA feature fusion algorithm, the current feature data and the enhanced feature data are convolved and fused in a preset convolutional neural network, and the obtained fused feature data is used to overwrite the current feature data to form the first enhanced image data; Based on the second defect area information, the DCA feature fusion algorithm is used to perform feature fusion enhancement on the corresponding defect area to form second enhanced image data.

Images