A building window effective area calculation method and system based on a BIM model

Abstract

The application relates to a building window effective area calculation method and system based on a BIM model, and relates to the technical field of building windows. The method comprises the following steps: acquiring a plurality of images of a current room in a building; the room comprises a plurality of building windows; selecting one image from the images of the same building window taken from different angles to determine whether the type of the building window can be identified; extracting the image of the building window based on the images of the same building window taken from different angles and the identified type of the building window to obtain a building window image; identifying the geometric information of the building window based on the building window image; importing the identified type of the window and the geometric information into a BIM model to obtain corresponding window components; calling corresponding window effective opening area algorithms based on the type of the building window and the parameters of the window components to perform calculation, so that the effective area of the current building window is obtained; performing effective area calculation on each building window of the current room; and summing up the total building window effective area of the current room to obtain the total building window effective area of the current room.

Description

Technical Field

[0001] The present application relates to the technical field of BIM models, and in particular to a method and system for calculating the effective area of ​​building windows based on the BIM model. Background Art

[0002] With the widespread adoption of Building Information Modeling (BIM) technology, the design, construction, and management efficiency of the construction industry has been significantly improved. BIM not only provides detailed 3D geometric information but also integrates the attribute data of building components, enabling management and optimization of the entire building lifecycle.

[0003] Traditional methods for calculating the effective area of ​​building windows typically rely on manual measurement and recording, a time-consuming and labor-intensive process prone to human error. Furthermore, manual measurement is particularly challenging for complex or inaccessible building windows. In recent years, advances in image processing and machine learning have made image recognition-based methods a viable solution. These methods take photos of buildings and then use computer vision to identify and analyze the types and sizes of windows, thereby calculating the effective opening area of ​​these windows.

[0004] While existing image recognition-based technologies have improved the automation level of building window area calculation to a certain extent, they still have some limitations. For example, images from a single angle may not fully reflect the actual state of a building window, which can lead to errors in the calculation of building window area. Summary of the Invention

[0005] In order to at least partially solve the above technical problems, the present application provides a method and system for calculating the effective area of ​​building windows based on a BIM model.

[0006] In a first aspect, the present application provides a method for calculating the effective area of ​​building windows based on a BIM model, which adopts the following technical solution.

[0007] A method for calculating the effective area of ​​building windows based on a BIM model, comprising:

[0008] S101. Acquire several images of a current room in a building; the room includes several building windows;

[0009] S102, select one of the images of the same building window taken from different angles to determine whether the type of the building window can be identified; if yes, execute S103; if not, select another image of the same building window to identify the type of the building window until the type of the building window is identified; the type of the building window includes: casement window, top-hung window, center-hung window, bottom-hung window, sliding window and side-hung window;

[0010] S103, extract the image of the building window based on the images of the same building window taken from different angles and the identified type of the building window to obtain a building window image;

[0011] S104, identify the geometric information of the building window based on the building window image; the geometric information includes: window frame size, sash opening direction and sash opening angle;

[0012] S105, import the identified type of the window and the geometric information into a BIM model to obtain a corresponding window component;

[0013] S106, call a corresponding window effective opening area algorithm based on the type of the building window and the parameters of the window component to calculate the effective area of the current building window;

[0014] S107, calculate the effective area of each building window of the current room, and obtain the total building window effective area of the current room by summarizing the sum of the building window effective areas of the current room.

[0015] Optionally, the calculation of the effective area of the current building window based on the type of the building window and the parameters of the window component includes:

[0016] The calculation of the effective area of the current building window based on the type of the building window and the parameters of the window component includes:

[0017] If the type is one of casement window, top-hung window, center-hung window or bottom-hung window, it is determined whether the opening angle is greater than 70 degrees; if yes, the window effective opening area is equal to the area of the sash IfcSash; otherwise, the calculation formula is: window effective opening area = area of sash IfcSash * sin a, a represents the opening angle;

[0018] If the type is sliding window, the installation position of the sliding window is obtained; if the installation position is the roof, the calculation formula is: window effective opening area = min((perimeter of sash IfcSash * 0.5) * sliding distance, area of sash IfcSash);

[0019] If the installation location is an external wall, the calculation formula is: window effective opening area = min((perimeter of the window sash IfcSash * 0.25) * sliding distance, area of the window sash IfcSash);

[0020] If the type is a side-hung window, it is determined whether the side-hung window has a neighboring matching side-hung window, and if so, the window effective opening area is equal to the area of the window sash IfcSash * 0.5, otherwise the window effective opening area is equal to the area of the window sash IfcSash.

[0021] Optionally, an image of the same building window taken from multiple different angles is selected to determine whether the type of the building window can be identified, including:

[0022] An image of the building window taken from different angles is randomly selected from the collected images;

[0023] The selected image is identified for the type of the building window using a pre-trained machine learning model;

[0024] If the result output by the machine learning model shows that the type of the building window is successfully identified and the confidence exceeds a predetermined threshold, the type of the building window is obtained; wherein the confidence calculation formula is: C = ω1 × P max + ω2 × (1-H(P)) + ω3 × (1-σ 2 ); wherein C is the confidence; ω1, ω2 and ω3 are weight coefficients; P max is the probability of the most likely class output by the machine learning model; H(P) is the entropy of the probability distribution; σ 2 is the standard deviation of multiple prediction results;

[0025] If the identification is not successful or the confidence is lower than the predetermined threshold, another image is replaced.

[0026] Optionally, based on the multiple images of the same building window taken from different angles and the identified type of the building window, an image of the building window is extracted to obtain a building window image, including:

[0027] The clarity score and the angle score of each image of the multiple images of the same building window taken from different angles are calculated; wherein the angle score is determined based on the identified type of the building window, and specifically includes: determining an observation angle range according to the obtained type of the building window; calculating the position deviation of the center of the building window in the image from the center of the image and the inclination angle of the building window in the image for each image; obtaining the angle score based on the matching degree of the position deviation and the inclination angle with the observation angle range; the calculation formula of the angle score is: wherein S a is the angle score; the matching observation range is: [A min , A max ]. A is an actual observed angle; D is a center position deviation, T is a tilt angle; D max is a maximum allowed position deviation; T max is a maximum allowed tilt angle;

[0028] selecting an image with a highest total score as a main image based on the definition score and the angle score;

[0029] extracting feature points from images of the same building window taken from different angles;

[0030] finding a feature point correspondence between the main image and other images using a feature matching algorithm;

[0031] calculating an essential matrix and an intrinsic matrix based on the feature point correspondence;

[0032] registering the main image using the essential matrix and the intrinsic matrix;

[0033] extracting an image of the building window based on the registered main image to obtain a building window image.

[0034] Optionally, finding the feature point correspondence between the main image and other images using the feature matching algorithm includes:

[0035] extracting feature points in the main image and other images;

[0036] describing a local area around each feature point to obtain a feature point descriptor;

[0037] calculating Euclidean distances between the main image feature point descriptor and all other image feature point descriptors;

[0038] selecting K closest feature points as matching points.

[0039] Optionally, calculating the essential matrix and the intrinsic matrix based on the feature point correspondence includes:

[0040] selecting an inlier set from the matching feature point pairs;

[0041] calculating the essential matrix based on the matching points in the inlier set;

[0042] obtaining camera intrinsic matrices of the main image and other images;

[0043] calculating the intrinsic matrix based on the camera intrinsic matrices.

[0044] Optionally, selecting the inlier set from the matching feature point pairs includes:

[0045] S601: initializing a maximum iteration number, a threshold distance, and a minimum inlier ratio;

[0046] S602, randomly select a minimum number of point pairs from the matched feature point pairs;

[0047] S603, calculate a preliminary fundamental matrix F based on the selected point pairs;

[0048] S604, for all matched feature point pairs, calculate the re-projection error of each point pair under the fundamental matrix F;

[0049] S605, mark the point pairs with re-projection error less than a preset threshold as inliers;

[0050] S606, record the number of inliers in the current iteration and the corresponding inlier set;

[0051] S607, determine whether the number of inliers in the current iteration exceeds the maximum number of inliers recorded before, if so, update the maximum number of inliers and the optimal inlier set;

[0052] S608, determine whether the maximum number of iterations is reached, if not, return to step S602 to continue iteration;

[0053] S609, if the maximum number of iterations is reached, output the final inlier set as the screened inlier set.

[0054] In a second aspect, the application provides a building window effective area calculation system based on a BIM model, which adopts the following technical scheme.

[0055] A building window effective area calculation system based on a BIM model, comprising:

[0056] A first processing module acquires a plurality of images of a current room in a building; the room comprises a plurality of building windows;

[0057] A second processing module is configured to: select one of a plurality of images of the same building window taken from different angles to determine whether the type of the building window can be identified; the type of the building window includes: casement window, top-hung window, center-hung window, bottom-hung window, sliding window, and side-hung window;

[0058] A third processing module extracts a building window image based on the plurality of images of the same building window taken from different angles and the identified type of the building window to obtain a building window image;

[0059] A fourth processing module is configured to: identify geometric information of the building window based on the building window image; the geometric information includes: window frame size, window sash opening direction, and window sash opening angle;

[0060] A fifth processing module is configured to: import the identified type of the window and the geometric information into a BIM model to obtain a corresponding window component;

[0061] The sixth processing module is configured to: based on the type of the building window and the parameters of the window component, call a corresponding window effective opening area algorithm to calculate the effective area of the current building window.

[0062] The seventh processing module is configured to: perform effective area calculation on each building window of the current room, and aggregate the sum of the building window effective areas of the current room to obtain the total building window effective area of the current room.

[0063] In a third aspect, the present application discloses an electronic device, comprising a memory and a processor, and the memory stores a computer program loaded and executed by the processor to execute any of the above methods.

[0064] In a fourth aspect, the present application discloses a computer readable storage medium, which stores a computer program capable of being loaded and executed by a processor to execute any of the above methods. BRIEF DESCRIPTION OF DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiment or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0066] Fig. 1 is a flow chart of a building window effective area calculation method based on a BIM model according to an embodiment of the present application;

[0067] Fig. 2 is a system block diagram of a building window effective area calculation system based on a BIM model according to an embodiment of the present application;

[0068] In the figure, 201 is a first processing module; 202 is a second processing module; 203 is a third processing module; 204 is a fourth processing module; 205 is a fifth processing module; 206 is a sixth processing module; and 207 is a seventh processing module. DETAILED DESCRIPTION

[0069] The present application will be further described below in combination with the drawings and specific embodiments: Figs. 1-2 and specific embodiments:

[0070] The present application discloses a building window effective area calculation method based on a BIM model, comprising the following steps:

[0071] S101, acquiring a plurality of images of a current room in a building; the room comprises a plurality of building windows;

[0072] S102, select one of the images of the same building window taken from different angles to determine whether the type of the building window can be identified; if yes, execute S103; if not, select another image of the same building window to identify the type of the building window until the type of the building window is identified; the type of the building window includes: casement window, top-hung window, center-hung window, bottom-hung window, sliding window and side-hung window;

[0073] S103, extract the image of the building window based on the images of the same building window taken from different angles and the identified type of the building window to obtain a building window image;

[0074] S104, identify the geometric information of the building window based on the building window image; the geometric information includes: window frame size, window sash opening direction and window sash opening angle.

[0075] Specifically, the edge detection algorithm can be used to extract the edge contour of the window frame, window sash and the like; for the building window structure with obvious corner points, the corner point detection algorithm is used to determine whether the pixel point in the image is a corner point by calculating the gray level change of the pixel point in each direction and the autocorrelation matrix, so as to identify the corner points of the window frame and the corner points of the window sash opening. Window frame size determination: according to the extracted window frame edge information, the corresponding proportional relationship between the image pixel size and the actual size is calibrated in advance, the number of pixels is counted along the horizontal and vertical directions of the window frame edge, and then the actual length unit is converted according to the proportion, and the length and width of the window frame are obtained. Window sash opening direction determination: analyze the relative position between the window sash and the window frame and the edge change. If the window sash edge has a significant translation relative to the window frame edge in the horizontal direction and moves to one side, it can be determined that the opening direction is a side-hung window; if the window sash edge has a rotation change around an axis point relative to the window frame edge, the position of the rotation axis and the turning trend of the window sash are analyzed based on the detected corner point position information to determine the corresponding opening direction of the top-hung window, center-hung window or bottom-hung window. Window sash opening angle calculation: for the window sash with rotation opening, the opening angle value of the window sash relative to the window frame is calculated based on the edge point coordinates, corner point coordinates and the like according to the angle change of the window sash edge relative to the window frame reference line (such as the horizontal or vertical edge of the window frame) before and after opening. In some embodiments, the existing machine learning-based prediction technology can also be used to obtain the geometric information in the building window image, which is not specially limited in the present application.

[0076] S105, import the identified window type and geometric information into the BIM model to obtain the corresponding window component;

[0077] S106, call the corresponding window effective opening area algorithm based on the type of the building window and the parameters of the window component to calculate the effective area of the current building window;

[0078] S107, calculating the effective area of each architectural window of the current room, summarizing the sum of the effective areas of the architectural windows of the current room to obtain the total effective area of the architectural windows of the current room.

[0079] Specifically, BIM model (Building Information Modeling) is a building design tool based on three-dimensional digital technology. It allows architects, engineers, and project team members to create and manage building data in a virtual environment, thereby improving design efficiency. Architectural window refers to an opening on a building for lighting, ventilation, or providing a view, usually composed of a window frame and an openable window sash. According to the opening mode, it can be divided into types such as casement window, top-hung window, center-hung window, bottom-hung window, horizontal sliding window and side-hung window. The sash of the casement window is connected to one side of the frame by a hinge and can be rotated outward or inward to open. The top-hung window opens by flipping the sash from the bottom up, with the top fixed to the window frame. The sash of the center-hung window opens from the middle position, and the upper and lower parts can rotate in different directions, suitable for situations where ventilation and light entering need to be controlled simultaneously. The bottom-hung window is the opposite of the top-hung window, and the opening mode of the architectural window is to flip from the top down, with the bottom fixed, commonly used in scenarios where rain needs to be prevented and indoor ventilation needs to be maintained. The sash of the horizontal sliding window can slide left and right or up and down, suitable for places with limited space. The side-hung window, also known as the sliding window, has the sash sliding along a direction perpendicular to the wall, usually with two or more sashes that can move relative to each other to open the architectural window. The effective opening area of the window refers to the effective area that the architectural window can actually use for ventilation, which depends on the opening mode and opening degree of the architectural window.

[0080] Specifically, a plurality of images of the current room in the building are obtained, one or more images of the same architectural window taken from different angles are selected for type recognition, and after successfully identifying the type of the architectural window, the architectural window image is extracted and optimized based on the multi-view image and the known type. The identified window type and geometric information are imported into the BIM model, so that each architectural window can be represented in a digital form. Finally, according to the specific type of the architectural window and its parameterized description in the BIM, the corresponding algorithm is called to calculate the effective opening area, and the total value is obtained by summarizing the effective areas of all architectural windows in the room. Compared with the prior art of directly identifying the parameter information of the architectural window through image recognition, the present application identifies the type of the architectural window first, selects the main image according to the type of the architectural window and performs image registration, thereby improving the accuracy of the geometric parameters obtained by identifying the architectural window image and improving the accuracy of the calculation of the effective area of the architectural window.

[0081] In other embodiments, the building image is taken by a drone, and the above method further comprises:

[0082] Obtaining geographical position data of all buildings whose building window areas are to be calculated;

[0083] Selecting a building closest to the starting point of the unmanned aerial vehicle as the first station;

[0084] Starting from the current building, determining whether there is another building adjacent to the current building and not yet visited, if there is, adding the building to the current inspection path and marking the building as visited, then setting the building as a new starting point and repeating the above steps, if there is not, completing the current inspection path and recording the path information;

[0085] Increasing the number of path numbers M, selecting a building closest to the initial position and not yet visited as the starting point of a new path, and returning to the previous step to continue execution, and continuing the cycle until all buildings are included in the inspection path;

[0086] According to the actual area of each building and the path information, obtaining the total inspection time required for the inspection;

[0087] According to the total inspection time and the endurance time of a single unmanned aerial vehicle, calculating the number of unmanned aerial vehicles required;

[0088] Uploading the determined inspection path and related building information to the unmanned aerial vehicle control system;

[0089] The control system instructs the unmanned aerial vehicle to take off according to the received data, and starts the inspection task according to the predetermined path; during the inspection process, the unmanned aerial vehicle takes images of the building, and when an architectural window is identified, multiple images are taken at different angles.

[0090] Specifically, when updating a city, the effective area of architectural windows of a large number of buildings needs to be calculated. In the present application, geographical position data of all buildings whose building window areas are to be calculated is obtained, and a building closest to the starting point of the unmanned aerial vehicle is selected as the first station. Starting from the current building, it is determined whether there is another building adjacent to the current building and not yet visited. If there is, the building is added to the current inspection path and marked as visited, and then it is set as a new starting point to continue the same steps. If there is not, the configuration of the current inspection path is completed and the related information is recorded. The number of path numbers M is increased, and a building closest to the initial position and not yet visited is selected as the starting point of a new path, and the above process is repeated until all buildings are included in the inspection path. According to the actual area of each building and the path information, the number of unmanned aerial vehicles required is calculated. Then, the planned inspection path and related building information are uploaded to the unmanned aerial vehicle control system, and the system instructs the unmanned aerial vehicle to take off according to the received data, and starts the inspection task according to the predetermined path. During the inspection process, when the unmanned aerial vehicle identifies an architectural window, multiple images are taken at different angles, improving the accuracy of window type and geometric information identification and improving work efficiency.

[0091] As a specific embodiment of the building window effective area calculation method based on the BIM model, the effective area of the current building window is calculated by calling the corresponding window effective opening area algorithm based on the type of the building window and the parameters of the window components, including:

[0092] The calculation based on the type and the parameters of the window components calling the corresponding window effective opening area algorithm includes:

[0093] If the type is one of the casement window, top-hung window, center-hung window or bottom-hung window, it is determined whether the opening angle is greater than 70 degrees, if yes, the window effective opening area is equal to the area of the sash IfcSash; otherwise, the calculation formula is expressed as: window effective opening area = area of sash IfcSash * sin α, α represents the opening angle;

[0094] If the type is a sliding window, the installation position of the sliding window is obtained, if the installation position is a roof, the calculation formula is expressed as: window effective opening area = min((perimeter of sash IfcSash * 0.5 * sliding distance, area of sash IfcSash);

[0095] If the installation position is an external wall, the calculation formula is expressed as: window effective opening area = min((perimeter of sash IfcSash * 0.25) * sliding distance, area of sash IfcSash);

[0096] If the type is a side-hung window, it is determined whether the side-hung window has a neighboring matching side-hung window, if yes, the window effective opening area is equal to the area of the sash IfcSash * 0.5, otherwise, the window effective opening area is equal to the area of the sash IfcSash.

[0097] As a specific embodiment of the building window effective area calculation method based on the BIM model, an image of the same building window is photographed from multiple different angles, and one of the images is selected to determine whether the type of the building window can be identified, including:

[0098] A selected image is randomly selected from the collected images of the building window photographed from different angles;

[0099] A pre-trained machine learning model is used to identify the type of the building window from the selected image;

[0100] If the result output by the machine learning model shows that the type of the building window is successfully identified and the confidence exceeds a predetermined threshold, the type of the building window is obtained; wherein the confidence calculation formula is: C = ω1 × P max + ω2 × (1-H(P)) + ω3 × (1-σ 2); wherein C is the confidence; ω1, ω2 and ω3 are weight coefficients; P max is the probability of the most likely class output by the machine learning model; H(P) is the entropy of the probability distribution; σ 2 is the standard deviation of multiple prediction results.

[0101] If the recognition fails or the confidence is lower than a predetermined threshold, another image is replaced.

[0102] Specifically, one of the images of the building window taken from different angles is randomly selected, and a pre-trained machine learning model is used to identify the type of the building window, combined with a confidence evaluation mechanism to ensure the reliability of the identification result. If the probability of the most likely class output by the model is high, the entropy of the probability distribution is low, and the standard deviation of multiple prediction results is small, the calculated confidence C will be high, indicating that the identification is not only accurate but also stable. Once the confidence exceeds a predetermined threshold, it is considered that the type of the building window has been successfully identified. If the requirement is not met, another image is replaced to try again until an image that can provide a high enough confidence is found. By considering the maximum probability, entropy and standard deviation of the model prediction, the success rate of window type identification is improved.

[0103] As a specific embodiment of a method for calculating the effective area of a building window based on a BIM model, the image of the building window is obtained based on multiple images of the same building window taken from different angles and the identified type of the building window, comprising:

[0104] The clarity score and angle score of each image of the multiple images of the same building window taken from different angles are calculated; wherein the angle score is determined based on the identified type of the building window, specifically including: determining the observation angle range according to the obtained type of the building window; calculating the position deviation of the center of the building window in the image from the center of the image and the tilt angle of the building window in the image for each image; obtaining the angle score based on the matching degree of the position deviation and the tilt angle with the observation angle range; the calculation formula of the angle score is: wherein S a is the angle score; the matching observation range is: [A min , A max ]; A is the actually observed angle; D is the center position deviation, and T is the tilt angle; D max is the maximum allowed position deviation; T max is the maximum allowed tilt angle;

[0105] The image with the highest total score is selected as the main image based on the clarity score and the angle score.

[0106] Extract feature points from images of the same building window taken from different angles;

[0107] Find the correspondence of feature points between the main image and other images using a feature matching algorithm;

[0108] Calculate the fundamental matrix and essential matrix based on the correspondence of feature points;

[0109] Register the main image using the fundamental matrix and essential matrix;

[0110] Extract the building window image based on the registered main image.

[0111] Specifically, in this application, the angle score determines the observation angle range based on the identified building window type, and is calculated in combination with the positional deviation of the window center in the image from the image center and the tilt angle. The image with the highest total score is selected as the main image based on the clarity score and the angle score, feature points are extracted from the images taken from different angles, and the correspondence of feature points between the main image and other images is found using a feature matching algorithm, and then the fundamental matrix and essential matrix are calculated. Register the main image to make the finally extracted building window image more accurate and complete.

[0112] As one of the implementation manners of the building window effective area calculation method based on the BIM model, the correspondence of feature points between the main image and other images is found using a feature matching algorithm, including:

[0113] Extract feature points in the main image and other images;

[0114] Describe the local area around each feature point to obtain the descriptor of the feature point;

[0115] Calculate the Euclidean distance between the feature point descriptor of the main image and the feature point descriptors of all other images;

[0116] Select the K nearest feature points as matching points.

[0117] As one of the implementation manners of the building window effective area calculation method based on the BIM model, the fundamental matrix and essential matrix are calculated based on the correspondence of feature points, including:

[0118] Select the inlier set from the matched feature point pairs;

[0119] Calculate the fundamental matrix based on the matching points in the inlier set;

[0120] Obtain the camera intrinsic matrix of the main image and other images;

[0121] Calculate the essential matrix based on the camera intrinsic matrix.

[0122] As one of the implementation manners of the building window effective area calculation method based on the BIM model, an inlier set is screened from matched feature point pairs, including:

[0123] S601: initializing a maximum iteration number, a threshold distance, and a minimum inlier ratio;

[0124] S602: randomly selecting a minimum number of point pairs from the matched feature point pairs;

[0125] S603: calculating a preliminary fundamental matrix F based on the selected point pairs;

[0126] S604: calculating a re-projection error of each point pair under the fundamental matrix F for all matched feature point pairs;

[0127] S605: marking the point pair with a re-projection error less than a preset threshold as an inlier;

[0128] S606: recording the number of inliers in the current iteration and the corresponding inlier set;

[0129] S607: determining whether the number of inliers in the current iteration exceeds the maximum inlier number recorded before, and if yes, updating the maximum inlier number and the optimal inlier set;

[0130] S608: determining whether the maximum iteration number is reached, and if not, returning to step S602 to continue iteration;

[0131] S609: if the maximum iteration number is reached, outputting the final inlier set as the screened inlier set.

[0132] The application further provides a building window effective area calculation system based on a BIM model, including:

[0133] A first processing module 201 acquires a plurality of images of a current room in a building; the room includes a plurality of building windows;

[0134] A second processing module 202 is configured to: select one of a plurality of images of the same building window taken from different angles to determine whether the type of the building window can be identified; the type of the building window includes: a casement window, a top-hung window, a center-hung window, a bottom-hung window, a sliding sash window, and a side-hung window;

[0135] A third processing module 203 extracts a building window image based on the plurality of images of the same building window taken from different angles and the identified type of the building window to obtain the building window image;

[0136] A fourth processing module 204 is configured to: identify geometric information of the building window based on the building window image; the geometric information includes: a window frame size, a sash opening direction, and a sash opening angle;

[0137] The fifth processing module 205 is configured to: import the identified window type and geometric information into a BIM model to obtain a corresponding window component;

[0138] The sixth processing module 206 is configured to: call a corresponding window effective opening area algorithm based on the type of the building window and the parameters of the window component to calculate the effective area of the current building window.

[0139] The seventh processing module 207 is configured to: calculate the effective area of each building window of the current room, and obtain the total building window effective area of the current room by summing up the total of the building window effective areas of the current room.

[0140] The embodiment of the present application further discloses an electronic device.

[0141] Specifically, the device includes a memory and a processor, and the memory stores a computer program capable of being loaded and executed by the processor to perform any one of the above-mentioned building window effective area calculation methods based on a BIM model.

[0142] The embodiment of the present application further discloses a computer readable storage medium. Specifically, the computer readable storage medium stores a computer program capable of being loaded and executed by the processor to perform any one of the above-mentioned building window effective area calculation methods based on a BIM model. The computer readable storage medium may, for example, include a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various storage program codes.

[0143] It should be noted that: the above embodiments are only used to illustrate the present application and not to limit the technical solutions described in the present application. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that the skilled in the art can still modify or equivalently replace the present application, and all technical solutions and improvements which do not deviate from the spirit and scope of the present application should be covered in the scope of claims of the present application.

Claims

1. A method for calculating the effective area of ​​building windows based on a BIM model, characterized in that: include: S101, obtaining several images of the current room in the building; said room including a number of architectural windows; S102. Select one of the images of the same building window taken from multiple different angles to determine whether the type of the building window can be identified, including: randomly selecting an image from the collected building window images taken from different angles; using a pre-trained machine learning model to identify the type of the building window in the selected image; if the result output by the machine learning model shows that the building window type is successfully identified and the confidence level exceeds a predetermined threshold, the type of the building window is obtained; wherein the confidence level is calculated as: C = ω1 × P max +ω2×(1-H(P))+ω3×(1-σ 2 ); where C is the confidence level; ω1, ω2 and ω3 are weight coefficients; P max is the probability of the most likely category output by the machine learning model; H(P) is the entropy of the probability distribution; σ 2 is the standard deviation of multiple prediction results; if recognition fails or the confidence level is lower than a predetermined threshold, another image is replaced; if successful, S103 is executed; if not, another image of the same building window is selected to identify the building window type until the building window type is identified; the building window types include: casement window, top-hung window, center-hung window, bottom-hung window, sliding window and side-sliding window; S103, extracting an image of the building window based on multiple images of the same building window taken at different angles and the identified building window type to obtain a building window image; S104, identifying geometric information of the building window based on the building window image; the geometric information includes: window frame size, window sash opening direction and window sash opening angle; S105, importing the identified window type and geometric information into the BIM model to obtain corresponding window components; S106. Based on the type of the building window and the parameters of the window components, the corresponding window effective opening area algorithm is called to calculate the effective area of ​​the current building window, including: if the type is one of a casement window, a top-hung window, a center-hung window, or a bottom-hung window, then determining whether the opening angle is greater than 70 degrees. If so, the window effective opening area is equal to the area of ​​the window sash IfcSash; otherwise, the calculation formula is expressed as: window effective opening area = area of ​​the window sash IfcSash * sinα, where α represents the opening angle; if the type is a sliding window, then obtaining the installation location of the sliding window. If the installation location is the roof, the calculation formula is as follows: The calculation formula is: Window Effective Opening Area = min((Circumference of sash IfcSash * 0.5) * Sliding Distance, Area of ​​sash IfcSash); If the installation location is an exterior wall, the calculation formula is: Window Effective Opening Area = min((Circumference of sash IfcSash * 0.25) * Sliding Distance, Area of ​​sash IfcSash); If the type is a side-sliding window, determine whether the side-sliding window has an adjacent side-sliding window. If so, the window effective opening area is equal to the area of ​​the window sash IfcSash * 0.5; otherwise, the window effective opening area is equal to the area of ​​the window sash IfcSash. S107: Calculate the effective area of ​​each building window in the current room, summarize the total effective area of ​​the building windows in the current room, and obtain the total effective area of ​​the building windows in the current room.

2. The method for calculating the effective area of ​​building windows based on the BIM model according to claim 1, characterized in that: The image of the building window is extracted based on multiple images of the same building window taken at different angles and the identified building window type to obtain the building window image, including: Calculate the clarity score and angle score of each of multiple images of the same building window taken from different angles; the angle score is determined based on the identified building window type, specifically including: determining the observation angle range based on the obtained building window type; calculating, for each image, the position deviation between the center position of the building window in the image and the image center, as well as the tilt angle of the building window in the image; and obtaining the angle score based on the degree of match between the position deviation and the tilt angle and the observation angle range. The angle score calculation formula is: Among them, S a Score the angle; the matching observation range is: [A min , A max ]; A is the actual observed angle; D is the center position deviation, T is the tilt angle; D max is the maximum position deviation allowed; T max is the maximum permissible tilt angle; Selecting the image with the highest total score as the main image based on the clarity score and the angle score; Extract feature points from images of the same building window taken from different angles; Use feature matching algorithms to find the correspondence between feature points in the main image and other images; Calculate the basic matrix and essential matrix based on the corresponding relationship of feature points; Register the main image using the fundamental matrix and the essential matrix; The image of the building window is extracted based on the registered main image to obtain the building window image.

3. The method for calculating the effective area of ​​building windows based on the BIM model according to claim 2, characterized in that: Use feature matching algorithms to find the correspondence between feature points in the main image and other images, including: Extract feature points from the main image and other images; Describe the local area around each feature point to obtain the descriptor of the feature point; Calculate the Euclidean distance between the main image feature point descriptor and all other image feature point descriptors; Select the K closest feature points as matching points.

4. The method for calculating the effective area of ​​building windows based on the BIM model according to claim 3 is characterized in that: Calculate the basic matrix and essential matrix based on the corresponding relationship of feature points, including: Filter out the inlier point set from the matched feature point pairs; Calculate the fundamental matrix based on the matching point pairs in the internal point set; Get the camera intrinsic parameter matrix of the main image and other images; Calculate the intrinsic matrix based on the camera intrinsic parameter matrix.

5. The method for calculating the effective area of ​​building windows based on the BIM model according to claim 4 is characterized in that: Filter out the inlier set from the matched feature point pairs, including: S601: Initialize the maximum number of iterations, threshold distance and minimum inlier ratio; S602, randomly selecting a minimum number of point pairs from the matched feature point pairs; S603, calculating a preliminary fundamental matrix F based on the selected point pairs; S604: For all matched feature point pairs, calculate the reprojection error of each point pair under the basic matrix F; S605, marking the point pairs whose reprojection errors are less than a preset threshold as inliers; S606, record the number of inliers and the corresponding inlier set in the current iteration; S607: Determine whether the number of inliers in the current iteration exceeds the maximum number of inliers recorded previously. If so, update the maximum number of inliers and the optimal inlier set. S608: Determine whether the maximum number of iterations has been reached. If not, return to step S602 to continue iterating. S609: If the maximum number of iterations is reached, output the final inlier set as the screened inlier set.

6. A building window effective area calculation system based on BIM model, characterized in that: include: A first processing module acquires a plurality of images of a current room in a building; the room includes a plurality of building windows; The second processing module is used to: select one of the images of the same building window taken from multiple different angles to determine whether the type of the building window can be identified, including: randomly selecting an image from the collected building window images taken from different angles; using a pre-trained machine learning model to identify the type of the building window in the selected image; if the result output by the machine learning model shows that the building window type is successfully identified and the confidence level exceeds a predetermined threshold, the type of the building window is obtained; wherein the confidence level is calculated as: C = ω1 × P max +ω2×(1-H(P))+ω3×(1-σ 2 ); where C is the confidence level; ω1, ω2 and ω3 are weight coefficients; P max is the probability of the most likely category output by the machine learning model; H(P) is the entropy of the probability distribution; σ 2 is the standard deviation of multiple prediction results; if the recognition fails or the confidence level is lower than a predetermined threshold, another image is replaced; the types of building windows include: casement windows, top-hung windows, center-hung windows, bottom-hung windows, sliding windows, and side-sliding windows; The third processing module extracts the image of the building window based on multiple images of the same building window taken at different angles and the identified building window type to obtain a building window image; A fourth processing module is configured to: identify geometric information of the building window based on the building window image; the geometric information includes: window frame size, window sash opening direction, and window sash opening angle; A fifth processing module is configured to: import the identified window type and geometric information into the BIM model to obtain corresponding window components; The sixth processing module is used to: call the corresponding window effective opening area algorithm based on the type of building window and the parameters of the window component to calculate the effective area of ​​the current building window, including: if the type is one of a casement window, a top-hung window, a center-hung window or a bottom-hung window, then determine whether the opening angle is greater than 70 degrees. If so, the window effective opening area is equal to the area of ​​the window sash IfcSash; otherwise, the calculation formula is expressed as: window effective opening area = area of ​​window sash IfcSash * sinα, α represents the opening angle; if the type is a sliding window, then obtain the installation position of the sliding window. If the installation position is the roof, calculate The formula is: Window Effective Opening Area = min((Circumference of sash IfcSash * 0.5) * Sliding Distance, Area of ​​sash IfcSash); If the installation location is an exterior wall, the calculation formula is: Window Effective Opening Area = min((Circumference of sash IfcSash * 0.25) * Sliding Distance, Area of ​​sash IfcSash); If the type is a side-sliding window, determine whether the side-sliding window has an adjacent side-sliding window. If so, the window effective opening area is equal to the area of ​​the window sash IfcSash * 0.5; otherwise, the window effective opening area is equal to the area of ​​the window sash IfcSash. The seventh processing module is used to calculate the effective area of ​​each building window in the current room, summarize the total effective area of ​​the building windows in the current room, and obtain the total effective area of ​​the building windows in the current room.

7. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program according to any one of claims 1 to 5 and is loaded and executed by the processor.

8. A method for calculating the effective area of ​​building windows in a functional space, characterized in that: include: Get all window components in the functional space; The effective area of ​​each window component is calculated respectively using the method described in any one of claims 1 to 5.

Images