Building BIM model generation method, system and storage medium based on point cloud segmentation

Abstract

The present invention discloses a method, system and storage medium for generating a building BIM model based on point cloud segmentation, and relates to the technical field of building BIM models. The method uses a point cloud analysis method to obtain point cloud positioning features; a feature generation method is used based on the point cloud positioning features to obtain a building model, and the point cloud positioning features are supplemented to obtain perfect features; a building BIM model is obtained based on the perfect features and the positioning acquisition method; the present invention is used to solve the problem in the existing method for generating a building BIM model based on point cloud data that, when the building components are special and the point cloud data cannot be effectively extracted, the extracted point cloud data cannot effectively generate the corresponding building components due to insufficient extraction of the point cloud data, thereby resulting in low accuracy of the building components and discrepancy between the modeling and the actual situation.

Description

Technical Field

[0001] The present invention relates to the technical field of building BIM models, and in particular to a method, system and storage medium for generating a building BIM model based on point cloud segmentation. Background Art

[0002] The architectural BIM model is a digital tool for engineering applications that contains rich architectural information and can simulate the construction of a building on a computer. The BIM model digitally expresses the physical and functional characteristics of a building in the form of a 3D model, covering the entire process of design, construction, and operation. Point cloud data refers to a set of vectors in a three-dimensional coordinate system. Each point contains three-dimensional coordinates (X, Y, Z) and can carry additional information such as RGB, reflection intensity, and timestamps. Point cloud segmentation is a key technology in computer vision and three-dimensional data processing, mainly used to divide unstructured point cloud data into subsets with semantic or instance meaning.

[0003] Existing methods for generating building BIM models based on point cloud data usually extract point cloud data in a certain area of ​​the model and point cloud data of a certain plane from the point cloud data, and obtain a geometric model based on the extracted point cloud data and obtain a BIM model through model analysis. Although this improved method can improve the efficiency of generating building components, when the building components are special and it is impossible to obtain effective areas and planes, the extracted point cloud data will not be able to effectively generate the corresponding building components due to insufficient extraction of point cloud data, resulting in low accuracy of building components and problems of modeling not being consistent with reality. For example, in the patent application with publication number CN116108526A, a method and apparatus for generating BIM models of building components based on point cloud data are disclosed. This solution is to select the initial end cutting plane of the original point cloud data, use the point cloud data between the initial end cutting planes as sub-point cloud data, and obtain multiple regional point cloud data based on the sub-point cloud data, so as to obtain a geometric model and its corresponding BIM model. Other improvements for generating building BIM models based on point cloud data are usually improvements in the recognition of point cloud data. They still cannot solve the problem that when the building components are special and the point cloud data cannot be effectively extracted, the point cloud data cannot be effectively extracted due to insufficient extraction of the point cloud data, resulting in the low accuracy of the building components and the modeling is inconsistent with the actual problem. In view of this, it is necessary to improve the existing method for generating building BIM models based on point cloud data. Summary of the Invention

[0004] The present invention aims to solve, at least to a certain extent, one of the technical problems in the prior art. By proposing a method, system and storage medium for generating a building BIM model based on point cloud segmentation, the present invention is used to solve the problem in the existing method for generating a building BIM model based on point cloud data that, when the building components are special and the point cloud data cannot be effectively extracted, the point cloud data cannot be effectively extracted due to insufficient extraction of the point cloud data, resulting in low accuracy of the building components and discrepancy between the modeling and the actual situation.

[0005] To achieve the above objectives, in a first aspect, the present application provides a method for generating a building BIM model based on point cloud segmentation, comprising the following steps:

[0006] Obtain point cloud data of multiple buildings and multiple building BIM models generated based on the point cloud data; use point cloud analysis methods to analyze all point cloud data and all building BIM models, and obtain point cloud positioning features based on the analysis results;

[0007] Based on the point cloud positioning features and point cloud data, a feature generation method is used to obtain a built model, and the built model is compared with the point cloud model corresponding to the point cloud data. Based on the comparison results, the point cloud positioning features are supplemented to obtain a perfect feature;

[0008] Based on the perfect feature and positioning acquisition method, the point cloud positioning points in the point cloud data corresponding to the model to be generated are obtained, and the point cloud positioning points are used to generate the building BIM model corresponding to the point cloud data.

[0009] Furthermore, point cloud data of multiple buildings and multiple building BIM models generated based on the point cloud data are obtained; all point cloud data and all building BIM models are analyzed using a point cloud analysis method, and point cloud positioning features are obtained based on the analysis results, including:

[0010] Obtain multiple building BIM models generated based on point cloud data and record them as point cloud models; obtain the point cloud data corresponding to each point cloud model; point cloud analysis methods include:

[0011] For any point cloud data: record the point in the point cloud model corresponding to the point cloud data as a model point; obtain the reflection intensity and RGB value of all model points, and record the model point at the vertex of any plane in the point cloud model as a plane vertex;

[0012] Establish a plane rectangular coordinate system and record it as the preliminary screening coordinate system, where the coordinate points on the X-axis of the preliminary screening coordinate system from the coordinate origin to the right are filled in with the coordinates of each plane vertex in sequence, and the unit of the Y-axis is percentage or constant;

[0013] When the unit of the Y-axis is a percentage, the preliminary screening coordinate system is punctuated based on the reflection intensity corresponding to each plane vertex, and the curve obtained by fitting all the punctuation points is recorded as the reflection vertex curve; when the unit of the Y-axis is a constant, the preliminary screening coordinate system is punctuated based on the color mean corresponding to each plane vertex, and the curve obtained by fitting all the punctuation points is recorded as the color vertex curve, where the color mean is the average of the three values ​​in the RGB values ​​of the plane vertex.

[0014] Furthermore, the point cloud analysis method also includes:

[0015] The closed interval formed by the minimum and maximum values ​​of the ordinate in the reflection vertex curve is recorded as the reflection vertex interval; the interval formed by the minimum and maximum values ​​of the ordinate in the color vertex curve is recorded as the color vertex interval;

[0016] Place the reflection vertex curve and the color vertex curve in the same preliminary screening coordinate system. When the reflection vertex curve and the color vertex curve have an intersection, execute method V. When the reflection vertex curve and the color vertex curve do not have an intersection, scale the Y axis corresponding to the color vertex curve proportionally until the reflection vertex curve and the color vertex curve have an intersection, and then execute method V.

[0017] Further, method V comprises:

[0018] The preliminary screening coordinate system at this time is recorded as the partitioning coordinate system; for any point A of the reflection vertex curve in the partitioning coordinate system, the horizontal coordinate of point A is marked as X1; when the point with the horizontal coordinate X1 in the color vertex curve is above point A, point A is recorded as the upper reflection point; when the point with the horizontal coordinate X1 in the color vertex curve is below point A, point A is recorded as the lower reflection point; when the point with the horizontal coordinate X1 in the color vertex curve coincides with point A, point A is recorded as the reflection dividing point;

[0019] The curve formed by all the reflection upper sites in the reflection vertex curve is recorded as the reflection upper curve, and the open interval formed by the horizontal coordinates of the leftmost point and the rightmost point of each reflection upper curve is recorded as the reflection upper interval; the curve formed by all the reflection lower sites in the reflection vertex curve is recorded as the reflection lower curve, and the open interval formed by the horizontal coordinates of the leftmost point and the rightmost point of each reflection lower curve is recorded as the reflection lower interval.

[0020] Furthermore, method V further includes:

[0021] For any reflection superposition interval: the open interval formed by the ordinates of the highest point and the lowest point of the reflection superposition curve in the reflection superposition interval is recorded as the upper value interval of the reflection vertex interval, and the open interval formed by the ordinates of the highest point and the lowest point of the color vertex interval in the reflection superposition interval is recorded as the lower value interval of the color vertex interval;

[0022] For any reflection inferior interval: the open interval formed by the ordinates of the highest point and the lowest point of the reflection inferior curve in the reflection inferior interval is recorded as the lower value interval of the reflection vertex interval, and the open interval formed by the ordinates of the highest point and the lowest point of the color vertex interval in the reflection inferior interval is recorded as the upper value interval of the color vertex interval;

[0023] The intervals in the color vertex interval that are recorded as both the upper value interval and the lower value interval are recorded as color mixing intervals; the intervals in the reflection vertex interval that are recorded as both the upper value interval and the lower value interval are recorded as reflection mixing intervals.

[0024] Furthermore, the point cloud analysis method also includes:

[0025] Obtain the color vertex intervals and reflection vertex intervals corresponding to all point cloud data, and after executing method V, record the intersection of the color mixing intervals corresponding to all color vertex intervals as the color feature interval, and record the intersection of the reflection mixing intervals corresponding to all reflection vertex intervals as the reflection feature interval;

[0026] For any color mixing interval that is not recorded as a color feature interval: use the interval sorting algorithm to obtain the interval parameters of the color mixing interval. The interval sorting algorithm is: , where F is the interval parameter, c is the number of point cloud data, G i H is the length of the upper value interval corresponding to the color mixing interval in the i-th point cloud data in the X-axis, j The length of the lower value interval corresponding to the color mixing interval in the point cloud data in the X-axis;

[0027] When the interval parameter of the color mixing interval is greater than 0, the color mixing interval is re-recorded as an upper value interval; when the interval parameter of the color mixing interval is less than 0, the color mixing interval is re-recorded as a lower value interval; when the interval parameter of the color mixing interval is equal to 0, the color mixing interval is re-recorded as a color feature interval;

[0028] For any reflection mixed interval that is not recorded as a reflection feature interval: based on the method of re-recording the color mixed interval into the upper value interval, the lower value interval and the color feature interval, use the interval sorting algorithm to re-record the reflection mixed interval into the upper value interval, the lower value interval and the reflection feature interval;

[0029] The color vertex interval containing the upper value interval, the lower value interval and the color feature interval and the reflection vertex interval containing the upper value interval, the lower value interval and the reflection feature interval are recorded as point cloud positioning features.

[0030] Furthermore, the feature generation method includes:

[0031] Randomly obtain a point cloud model and its corresponding point cloud data; obtain the point cloud positioning points in the point cloud data using the positioning acquisition method based on the point cloud positioning features;

[0032] The positioning acquisition method is as follows: obtain the reflection intensity and color mean of all points in the point cloud data. When any point α satisfies the following conditions: the reflection intensity is in the upper value interval of the reflection vertex interval and the color mean is in the lower value interval of the color vertex interval; the reflection intensity is in the lower value interval of the reflection vertex interval and the color mean is in the upper value interval of the color vertex interval; or the reflection intensity is in the reflection feature interval of the reflection vertex interval and the color mean is in the color feature interval of the color vertex interval, the point α is recorded as the point cloud positioning point.

[0033] Obtain all point cloud positioning points in the point cloud data, and build a building BIM model based on all point cloud positioning points, which is recorded as the built model; when the built model is exactly the same as the point cloud model corresponding to the point cloud data, the point cloud positioning features are recorded as the perfect features;

[0034] When the built model is not exactly the same as the point cloud model corresponding to the point cloud data, the points corresponding to the point cloud data in the area of ​​the built model that is different from the point cloud model are recorded as supplementary points, and based on the analysis method of the point cloud analysis method for analyzing the model points, the supplementary points are analyzed using the point cloud analysis method, and the intersection of the obtained point cloud positioning feature and the existing point cloud positioning feature is recorded as the latest point cloud positioning feature.

[0035] Furthermore, based on the comparison results, the point cloud positioning features are supplemented to obtain the following improved features:

[0036] When the latest point cloud positioning feature exists, the latest point cloud positioning feature is processed based on the feature analysis method until the perfect feature is obtained.

[0037] In a second aspect, the present application also provides a building BIM model generation system based on point cloud segmentation, including a point cloud feature analysis module, a point cloud feature supplement module, and a BIM model generation module;

[0038] The point cloud feature analysis module is used to obtain point cloud data of multiple buildings and multiple building BIM models generated based on the point cloud data; all point cloud data and all building BIM models are analyzed using the point cloud analysis method, and point cloud positioning features are obtained based on the analysis results;

[0039] The point cloud feature supplement module is used to obtain the construction model based on the point cloud positioning features and the feature generation method of the point cloud data, and compare the construction model with the point cloud model corresponding to the point cloud data. Based on the comparison results, the point cloud positioning features are supplemented to obtain the perfect features;

[0040] The BIM model generation module is used to obtain point cloud positioning points in the point cloud data corresponding to the model to be generated based on the perfect features and positioning acquisition method, and use the point cloud positioning points to generate a building BIM model corresponding to the point cloud data.

[0041] In a third aspect, the present application provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the above method are performed.

[0042] Beneficial effects of the present invention: The present application first obtains point cloud data of multiple buildings and multiple building BIM models generated based on the point cloud data; uses a point cloud analysis method to analyze all point cloud data and all building BIM models, and obtains point cloud positioning features based on the analysis results. The advantage of this is that by using the point cloud analysis method to obtain point cloud positioning features, it is possible to obtain features corresponding to key points constituting the building BIM model in the point cloud data based on the existing generated data of the building BIM model generated by the point cloud data, that is, cloud positioning features corresponding to plane vertices, which helps to filter the existing point cloud data in subsequent analysis through the improved features obtained by supplementing the cloud positioning features, ensuring that the filtered point cloud data can accurately generate the required BIM model. At the same time, since less point cloud data needs to be analyzed after filtering, the purpose of improving the efficiency of BIM model generation can still be achieved.

[0043] This application also uses a feature generation method based on point cloud positioning features and point cloud data to obtain a built model, and compares the built model with the point cloud model corresponding to the point cloud data, and supplements the point cloud positioning features based on the comparison results to obtain perfect features; finally, based on the perfect features and the positioning acquisition method, the point cloud positioning points in the point cloud data corresponding to the model to be generated are obtained, and the point cloud positioning points are used to generate a building BIM model corresponding to the point cloud data. The advantage of this is that the point cloud positioning features are supplemented and perfect features are obtained based on the feature generation method, which can ensure that when the BIM model is generated based on the perfect features and the positioning acquisition method, the obtained point cloud positioning points can generate the BIM model more accurately, thereby improving the accuracy of building components and ensuring that the modeling is consistent with actual needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a principle block diagram of the system of the present invention;

[0045] Figure 2 is a flow chart of the steps of the method of the present invention;

[0046] Figure 3 Schematic diagram of the preliminary screening coordinate system and the division coordinate system of the present invention;

[0047] Figure 4 Schematic diagram of the structure of the electronic device of the present invention. DETAILED DESCRIPTION

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0049] Example 1, please refer to Figure 1 As shown, the present application provides a building BIM model generation system based on point cloud segmentation, including a point cloud feature analysis module, a point cloud feature supplement module and a BIM model generation module;

[0050] The point cloud feature analysis module is used to obtain point cloud data of multiple buildings and multiple building BIM models generated based on the point cloud data; all point cloud data and all building BIM models are analyzed using the point cloud analysis method, and point cloud positioning features are obtained based on the analysis results;

[0051] The point cloud feature analysis module includes a point cloud feature analysis unit. The point cloud feature analysis unit is configured with a point cloud feature analysis strategy. The point cloud feature analysis strategy includes:

[0052] Obtain multiple building BIM models generated based on point cloud data and record them as point cloud models; obtain point cloud data corresponding to each point cloud model;

[0053] The point cloud analysis method includes: for any point cloud data: recording the point in the point cloud model corresponding to the point cloud data as a model point; obtaining the reflection intensity and RGB value of all model points, and recording the model point at the vertex of any plane in the point cloud model as a plane vertex among all model points;

[0054] In the specific implementation process, since the subsequent acquisition of point cloud positioning features is based on the data of plane vertices, when there are special components or special sections in the actual building model to be generated, the plane vertices can be added, deleted, or modified to ensure that the point cloud positioning features obtained through analysis can meet the component requirements of the actual building, and reduce the number of updates of the point cloud positioning features when obtaining the perfect features, thereby improving the accuracy and efficiency of the model when generating the BIM model based on point cloud data;

[0055] Establish a plane rectangular coordinate system and record it as the preliminary screening coordinate system, where the coordinate points on the X-axis of the preliminary screening coordinate system from the coordinate origin to the right are filled in with the coordinates of each plane vertex in sequence, and the unit of the Y-axis is percentage or constant;

[0056] When the unit of the Y-axis is a percentage, the reflection intensity corresponding to each plane vertex is punctuated in the preliminary screening coordinate system, and the curve obtained by fitting all the punctuation points is recorded as the reflection vertex curve; when the unit of the Y-axis is a constant, the color mean corresponding to each plane vertex is punctuated in the preliminary screening coordinate system, and the curve obtained by fitting all the punctuation points is recorded as the color vertex curve, where the color mean is the average of the three values ​​in the RGB value of the plane vertex;

[0057] In the specific implementation process, for example, during a data analysis, when the RGB of a plane vertex is obtained as (255, 15, 0), it can be calculated that the color mean of the plane vertex is 90;

[0058] The closed interval formed by the minimum and maximum values ​​of the ordinate in the reflection vertex curve is recorded as the reflection vertex interval; the interval formed by the minimum and maximum values ​​of the ordinate in the color vertex curve is recorded as the color vertex interval;

[0059] In the specific implementation process, for example, during a data analysis, the initial screening coordinate system is obtained as follows Figure 3 As shown, the coordinate system in PP1 is the preliminary screening coordinate system, curve QQ1 is the reflection vertex curve, and curve QQ2 is the color vertex curve. Then, through analysis, it can be obtained that [yy1, yy2] is the reflection vertex interval, and [yy3, yy4] is the color vertex interval. Since there is no intersection between the reflection vertex interval and the color vertex interval in PP1, the Y axis corresponding to the color vertex curve is scaled proportionally to adjust the curve QQ2 to QQ3 in PP2. At the same time, the coordinate system in PP2 is the partitioning coordinate system.

[0060] Place the reflection vertex curve and the color vertex curve in the same preliminary screening coordinate system. When the reflection vertex curve and the color vertex curve have an intersection, execute method V. When the reflection vertex curve and the color vertex curve do not have an intersection, scale the Y axis corresponding to the color vertex curve proportionally until the reflection vertex curve and the color vertex curve have an intersection, and then execute method V.

[0061] Method V includes: recording the preliminary screening coordinate system at this time as the partitioning coordinate system; for any point A on the reflection vertex curve in the partitioning coordinate system, marking the abscissa of point A as X1; when the point with abscissa X1 in the color vertex curve is above point A, recording point A as the upper reflection point; when the point with abscissa X1 in the color vertex curve is below point A, recording point A as the lower reflection point; when the point with abscissa X1 in the color vertex curve coincides with point A, recording point A as the reflection splitting point;

[0062] The curve formed by all the reflection upper sites in the reflection vertex curve is recorded as the reflection upper curve, and the open interval formed by the horizontal coordinates of the leftmost point and the rightmost point of each reflection upper curve is recorded as the reflection upper interval; the curve formed by all the reflection lower sites in the reflection vertex curve is recorded as the reflection lower curve, and the open interval formed by the horizontal coordinates of the leftmost point and the rightmost point of each reflection lower curve is recorded as the reflection lower interval;

[0063] For any reflection superposition interval: the open interval formed by the ordinates of the highest point and the lowest point of the reflection superposition curve in the reflection superposition interval is recorded as the upper value interval of the reflection vertex interval, and the open interval formed by the ordinates of the highest point and the lowest point of the color vertex interval in the reflection superposition interval is recorded as the lower value interval of the color vertex interval;

[0064] In a specific implementation, the color vertex interval is [50, 100], and the ordinates of the highest point and the lowest point of a reflection upper interval are 55 and 52, respectively. Then, (52, 55) in the color vertex interval can be recorded as the lower value interval of the color vertex interval. In this embodiment, all points in the reflection vertex curve are recorded as reflection upper points, reflection lower points, or reflection split points. Therefore, after analysis, the color vertex interval and the reflection vertex interval can be completely divided into upper value intervals or lower value intervals to ensure the integrity of the data analysis.

[0065] For any reflection inferior interval: the open interval formed by the ordinates of the highest point and the lowest point of the reflection inferior curve in the reflection inferior interval is recorded as the lower value interval of the reflection vertex interval, and the open interval formed by the ordinates of the highest point and the lowest point of the color vertex interval in the reflection inferior interval is recorded as the upper value interval of the color vertex interval;

[0066] The intervals in the color vertex interval that are both recorded as the upper value interval and the lower value interval are recorded as color mixing intervals; the intervals in the reflection vertex interval that are both recorded as the upper value interval and the lower value interval are recorded as reflection mixing intervals;

[0067] In the specific implementation process, for example, during a data processing, there is an upper value interval (53,55) and a lower value interval (54,56) in the color vertex interval, then (54,55) can be recorded as the color mixing interval, and the interval (53,54] and the interval [55,56] are still the corresponding upper value interval and lower value interval.

[0068] The point cloud analysis method further includes: obtaining color vertex intervals and reflection vertex intervals corresponding to all point cloud data, and after executing method V, recording the intersection of color mixing intervals corresponding to all color vertex intervals as a color feature interval, and recording the intersection of reflection mixing intervals corresponding to all reflection vertex intervals as a reflection feature interval;

[0069] In the specific implementation process, the color mixed interval that is not recorded as the color feature interval and the reflection mixed interval that is not recorded as the reflection feature interval should be reclassified to ensure the integrity of the data analysis. Therefore, the interval parameters are obtained to achieve the reclassification of the above intervals.

[0070] For any color mixing interval that is not recorded as a color feature interval: use the interval sorting algorithm to obtain the interval parameters of the color mixing interval. The interval sorting algorithm is: , where F is the interval parameter, c is the number of point cloud data, G i H is the length of the upper value interval corresponding to the color mixing interval in the i-th point cloud data in the X-axis, j The length of the lower value interval corresponding to the color mixing interval in the point cloud data in the X-axis;

[0071] In a specific implementation process, for example, during a data processing, in the point cloud data corresponding to a color mixing interval that is not recorded as a color feature interval, the upper value interval corresponding to the color mixing interval in the X-axis has an interval length of 2, 5, and 1, respectively, and the lower value interval corresponding to the color mixing interval in the X-axis has an interval length of 1, 2, and 1.5, respectively. Then, through calculation, it can be obtained that the interval parameter is 3.5, indicating that the interval length of the color feature interval as the upper value interval is larger, and the color mixing interval can be re-recorded as the upper value interval;

[0072] When the interval parameter of the color mixing interval is greater than 0, the color mixing interval is re-recorded as an upper value interval; when the interval parameter of the color mixing interval is less than 0, the color mixing interval is re-recorded as a lower value interval; when the interval parameter of the color mixing interval is equal to 0, the color mixing interval is re-recorded as a color feature interval;

[0073] For any reflection mixed interval that is not recorded as a reflection feature interval: based on the method of re-recording the color mixed interval into the upper value interval, the lower value interval and the color feature interval, use the interval sorting algorithm to re-record the reflection mixed interval into the upper value interval, the lower value interval and the reflection feature interval;

[0074] The color vertex interval containing the upper value interval, the lower value interval and the color feature interval and the reflection vertex interval containing the upper value interval, the lower value interval and the reflection feature interval are recorded as point cloud positioning features.

[0075] The point cloud feature supplement module is used to obtain the construction model based on the point cloud positioning features and the feature generation method of the point cloud data, and compare the construction model with the point cloud model corresponding to the point cloud data. Based on the comparison results, the point cloud positioning features are supplemented to obtain the perfect features;

[0076] The point cloud feature supplementation module includes a point cloud feature supplementation unit. The point cloud feature supplementation unit is configured with a point cloud feature supplementation strategy. The point cloud feature supplementation strategy includes:

[0077] The feature generation method includes: randomly obtaining a point cloud model and its corresponding point cloud data; obtaining point cloud positioning points in the point cloud data using a positioning acquisition method based on point cloud positioning features;

[0078] The positioning acquisition method is as follows: obtain the reflection intensity and color mean of all points in the point cloud data. When any point α satisfies the following conditions: the reflection intensity is in the upper value interval of the reflection vertex interval and the color mean is in the lower value interval of the color vertex interval; the reflection intensity is in the lower value interval of the reflection vertex interval and the color mean is in the upper value interval of the color vertex interval; or the reflection intensity is in the reflection feature interval of the reflection vertex interval and the color mean is in the color feature interval of the color vertex interval, the point α is recorded as the point cloud positioning point.

[0079] In the specific implementation process, for example, during a data processing, if the reflection intensity of point α is in the upper range of the reflection vertex range and the color mean of point α is in the upper range of the color vertex range, it means that point α does not meet the screening conditions of the plane vertex in the point cloud analysis method. Therefore, point α does not have a high application requirement when building the BIM model compared with other points. Therefore, there is no need to analyze the data of point α when generating the BIM model based on point cloud data;

[0080] Obtain all point cloud positioning points in the point cloud data, and build a building BIM model based on all point cloud positioning points, which is recorded as the built model; when the built model is exactly the same as the point cloud model corresponding to the point cloud data, the point cloud positioning features are recorded as the perfect features;

[0081] When the built model is not exactly the same as the point cloud model corresponding to the point cloud data, the points corresponding to the point cloud data in the area of ​​the built model that is different from the point cloud model are recorded as supplementary points, and based on the analysis method of the point cloud analysis method for analyzing the model points, the supplementary points are analyzed using the point cloud analysis method, and the intersection of the obtained point cloud positioning feature and the existing point cloud positioning feature is recorded as the latest point cloud positioning feature.

[0082] The point cloud feature supplementation strategy also includes, when the latest point cloud positioning feature exists, processing the latest point cloud positioning feature based on the feature analysis method until a perfect feature is obtained.

[0083] The BIM model generation module is used to obtain point cloud positioning points in the point cloud data corresponding to the model to be generated based on the perfect features and positioning acquisition method, and use the point cloud positioning points to generate a building BIM model corresponding to the point cloud data.

[0084] Example 2, please refer to Figure 2As shown, the present application also provides a method for generating a building BIM model based on point cloud segmentation, comprising the following steps:

[0085] Step S1, obtaining point cloud data of multiple buildings and multiple building BIM models generated based on the point cloud data; analyzing all the point cloud data and all the building BIM models using a point cloud analysis method, and obtaining point cloud positioning features based on the analysis results;

[0086] Step S1 includes: step S101, obtaining multiple building BIM models generated based on point cloud data, and recording them as point cloud models; obtaining point cloud data corresponding to each point cloud model;

[0087] Step S102, the point cloud analysis method includes: Step S1021, for any point cloud data: record the point in the point cloud model corresponding to the point cloud data as a model point; obtain the reflection intensity and RGB value of all model points, and record the model point that is a vertex of any plane in the point cloud model among all model points as a plane vertex;

[0088] Step S1022: Establish a plane rectangular coordinate system and record it as a preliminary screening coordinate system, wherein the coordinate points on the X-axis of the preliminary screening coordinate system from the coordinate origin to the right are filled in with the coordinates of each plane vertex in sequence, and the unit of the Y-axis is a percentage or a constant;

[0089] Step S1023: When the unit of the Y-axis is a percentage, the points are punctuated in the preliminary screening coordinate system based on the reflection intensity corresponding to each plane vertex, and the curve obtained by fitting all the punctuated points is recorded as the reflection vertex curve. When the unit of the Y-axis is a constant, the points are punctuated in the preliminary screening coordinate system based on the color mean corresponding to each plane vertex, and the curve obtained by fitting all the punctuated points is recorded as the color vertex curve, where the color mean is the average of the three values ​​of the RGB values ​​of the plane vertex.

[0090] Step S1024: record the closed interval formed by the minimum and maximum values ​​of the ordinates in the reflection vertex curve as a reflection vertex interval; record the interval formed by the minimum and maximum values ​​of the ordinates in the color vertex curve as a color vertex interval;

[0091] Step S1025: Place the reflection vertex curve and the color vertex curve in the same preliminary screening coordinate system. When the reflection vertex curve and the color vertex curve have an intersection, execute method V. If the reflection vertex curve and the color vertex curve do not have an intersection, scale the Y axis corresponding to the color vertex curve proportionally until the reflection vertex curve and the color vertex curve have an intersection, then execute method V.

[0092] Method V includes: step VV1: recording the preliminary screening coordinate system at this time as the partitioning coordinate system; for any point A on the reflection vertex curve in the partitioning coordinate system, marking the abscissa of point A as X1; when the point with abscissa X1 in the color vertex curve is above point A, recording point A as the upper reflection point; when the point with abscissa X1 in the color vertex curve is below point A, recording point A as the lower reflection point; when the point with abscissa X1 in the color vertex curve coincides with point A, recording point A as the reflection splitting point;

[0093] Step VV2: Record the curve formed by all the reflection upper sites in the reflection vertex curve as the reflection upper curve, and record the open interval formed by the horizontal coordinates of the leftmost point and the rightmost point of each reflection upper curve as the reflection upper interval; record the curve formed by all the reflection lower sites in the reflection vertex curve as the reflection lower curve, and record the open interval formed by the horizontal coordinates of the leftmost point and the rightmost point of each reflection lower curve as the reflection lower interval;

[0094] Step VV3: For any reflection superposition interval: record the open interval formed by the ordinates of the highest point and the lowest point of the reflection superposition curve in the reflection superposition interval as the upper value interval of the reflection vertex interval, and record the open interval formed by the ordinates of the highest point and the lowest point of the color vertex interval in the reflection superposition interval as the lower value interval of the color vertex interval;

[0095] Step VV4: For any reflection subordinate interval: record the open interval formed by the ordinates of the highest point and the lowest point of the reflection subordinate curve in the reflection subordinate interval as the lower value interval of the reflection vertex interval; record the open interval formed by the ordinates of the highest point and the lowest point of the color vertex interval in the reflection subordinate interval as the upper value interval of the color vertex interval;

[0096] Step VV5: The intervals in the color vertex interval that are recorded as both the upper value interval and the lower value interval are recorded as color mixing intervals; the intervals in the reflection vertex interval that are recorded as both the upper value interval and the lower value interval are recorded as reflection mixing intervals.

[0097] The point cloud analysis method further includes: step S1026, obtaining color vertex intervals and reflection vertex intervals corresponding to all point cloud data, and after executing method V, recording the intersection of color mixing intervals corresponding to all color vertex intervals as a color feature interval, and recording the intersection of reflection mixing intervals corresponding to all reflection vertex intervals as a reflection feature interval;

[0098] Step S1027: For any color mixing interval that is not recorded as a color feature interval, an interval sorting algorithm is used to obtain interval parameters of the color mixing interval. The interval sorting algorithm is: , where F is the interval parameter, c is the number of point cloud data, G iH is the length of the upper value interval corresponding to the color mixing interval in the i-th point cloud data in the X-axis, j The length of the lower value interval corresponding to the color mixing interval in the point cloud data in the X-axis;

[0099] Step S1028: When the interval parameter of the color mixing interval is greater than 0, the color mixing interval is re-recorded as an upper value interval; when the interval parameter of the color mixing interval is less than 0, the color mixing interval is re-recorded as a lower value interval; when the interval parameter of the color mixing interval is equal to 0, the color mixing interval is re-recorded as a color feature interval;

[0100] Step S1029: for any reflection mixed interval that is not recorded as a reflection characteristic interval: based on the method of re-recording the color mixed interval as an upper value interval, a lower value interval, and a color characteristic interval, use the interval sorting algorithm to re-record the reflection mixed interval as an upper value interval, a lower value interval, and a reflection characteristic interval;

[0101] The color vertex interval containing the upper value interval, the lower value interval and the color feature interval and the reflection vertex interval containing the upper value interval, the lower value interval and the reflection feature interval are recorded as point cloud positioning features.

[0102] Step S2, obtaining a built model using a feature generation method based on the point cloud positioning features and the point cloud data, and comparing the built model with the point cloud model corresponding to the point cloud data, supplementing the point cloud positioning features based on the comparison results to obtain a perfect feature;

[0103] Step S201, the feature generation method includes: step S2011, randomly obtaining a point cloud model and its corresponding point cloud data; obtaining a point cloud positioning point in the point cloud data using a positioning acquisition method based on the point cloud positioning feature;

[0104] Step S2012: The positioning acquisition method is as follows: obtaining the reflection intensity and color mean of all points in the point cloud data; when any point α satisfies the following conditions: the reflection intensity is within the upper value interval of the reflection vertex interval and the color mean is within the lower value interval of the color vertex interval; the reflection intensity is within the lower value interval of the reflection vertex interval and the color mean is within the upper value interval of the color vertex interval; or the reflection intensity is within the reflection feature interval of the reflection vertex interval and the color mean is within the color feature interval of the color vertex interval, the point α is recorded as a point cloud positioning point;

[0105] Step S2013: Acquire all point cloud positioning points in the point cloud data, and build a building BIM model based on all the point cloud positioning points, which is recorded as a built model; when the built model is exactly the same as the point cloud model corresponding to the point cloud data, record the point cloud positioning features as perfect features;

[0106] In step S2014, when the built model is not exactly the same as the point cloud model corresponding to the point cloud data, the points corresponding to the point cloud data in the area of ​​the built model that is different from the point cloud model are recorded as supplementary points, and based on the analysis method of the point cloud analysis method for analyzing the model points, the supplementary points are analyzed using the point cloud analysis method, and the intersection of the obtained point cloud positioning feature and the existing point cloud positioning feature is recorded as the latest point cloud positioning feature.

[0107] Step S2 also includes: step S202, when the latest point cloud positioning feature exists, processing the latest point cloud positioning feature based on the feature analysis method until a perfect feature is obtained.

[0108] Step S3: obtaining point cloud positioning points in the point cloud data corresponding to the model to be generated based on the perfect feature and positioning acquisition method, and generating a building BIM model corresponding to the point cloud data using the point cloud positioning points.

[0109] Example 3, please refer to Figure 4 As shown, Figure 4 A schematic diagram of the structure of an electronic device is provided, which may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps of the method for generating a building BIM model based on point cloud segmentation are executed to implement the following functions: first, point cloud data of multiple buildings and multiple building BIM models generated based on the point cloud data are obtained; all point cloud data and all building BIM models are analyzed using a point cloud analysis method, and point cloud positioning features are obtained based on the analysis results; then, a construction model is obtained using a feature generation method based on the point cloud positioning features and the point cloud data, and the construction model is compared with the point cloud model corresponding to the point cloud data. Based on the comparison results, the point cloud positioning features are supplemented to obtain improved features; finally, point cloud positioning points in the point cloud data corresponding to the model to be generated are obtained based on the improved features and the positioning acquisition method, and the building BIM model corresponding to the point cloud data is generated using the point cloud positioning points.

[0110] In addition, the logical instructions in the above-mentioned memory can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0111] Example 4. The present application also provides a computer-readable storage medium. The present application provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps in the above-mentioned method for generating a building BIM model based on point cloud segmentation are executed to achieve the following functions: first, point cloud data of multiple buildings and multiple building BIM models generated based on the point cloud data are obtained; all point cloud data and all building BIM models are analyzed using a point cloud analysis method, and point cloud positioning features are obtained based on the analysis results; then, a feature generation method is used based on the point cloud positioning features and the point cloud data to obtain a built model, and the built model is compared with the point cloud model corresponding to the point cloud data, and the point cloud positioning features are supplemented based on the comparison results to obtain a perfect feature; finally, point cloud positioning points in the point cloud data corresponding to the model to be generated are obtained based on the perfect feature and the positioning acquisition method, and the point cloud positioning points are used to generate a building BIM model corresponding to the point cloud data.

[0112] Through the description of the above embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the essence of the above technical solutions or the portion that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for enabling a computer device (such as a personal computer, server, or network device) to execute the methods described in various embodiments or certain portions of the embodiments.

[0113] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for generating a building BIM model based on point cloud segmentation, characterized in that: The steps include: Obtain point cloud data of multiple buildings and multiple building BIM models generated based on the point cloud data; use point cloud analysis methods to analyze all point cloud data and all building BIM models, and obtain point cloud positioning features based on the analysis results; Acquire multiple building BIM models generated based on point cloud data, and record them as point cloud models, and obtain point cloud data corresponding to each point cloud model; wherein, the point cloud analysis method includes: for any point cloud data: record the point corresponding to the point cloud data in the point cloud model as a model point; obtain the reflection intensity and RGB value of all model points, and record the model points at the vertices of any plane in the point cloud model among all model points as plane vertices; establish a plane rectangular coordinate system, and record it as a preliminary screening coordinate system, wherein the coordinate points in the X-axis of the preliminary screening coordinate system from the coordinate origin to the right are filled with the coordinates of each plane vertex in turn, and the unit of the Y-axis is a percentage or a constant; when the unit of the Y-axis is a percentage, punctuate the preliminary screening coordinate system based on the reflection intensity corresponding to each plane vertex, and record the curve obtained by fitting all the punctuation points as a reflection vertex curve; when the unit of the Y-axis is a constant, punctuate the preliminary screening coordinate system based on the color mean corresponding to each plane vertex, and record the curve obtained by fitting all the punctuation points as a color vertex curve, wherein the color mean is the average of the three values ​​in the RGB value of the plane vertex; Based on the point cloud positioning features and point cloud data, a feature generation method is used to obtain a built model, and the built model is compared with the point cloud model corresponding to the point cloud data. Based on the comparison results, the point cloud positioning features are supplemented to obtain a perfect feature; Based on the perfect feature and positioning acquisition method, the point cloud positioning points in the point cloud data corresponding to the model to be generated are obtained, and the point cloud positioning points are used to generate the building BIM model corresponding to the point cloud data.

2. The method for generating a building BIM model based on point cloud segmentation according to claim 1, characterized in that: Point cloud analysis also includes: The closed interval formed by the minimum and maximum values ​​of the ordinate in the reflection vertex curve is recorded as the reflection vertex interval; the interval formed by the minimum and maximum values ​​of the ordinate in the color vertex curve is recorded as the color vertex interval; Place the reflection vertex curve and the color vertex curve in the same preliminary screening coordinate system. When the reflection vertex curve and the color vertex curve have an intersection, execute method V. When the reflection vertex curve and the color vertex curve do not have an intersection, scale the Y axis corresponding to the color vertex curve proportionally until the reflection vertex curve and the color vertex curve have an intersection, and then execute method V.

3. The method for generating a building BIM model based on point cloud segmentation according to claim 2, characterized in that: Method V includes: The preliminary screening coordinate system at this time is recorded as the partitioning coordinate system; for any point A of the reflection vertex curve in the partitioning coordinate system, the horizontal coordinate of point A is marked as X1; when the point with the horizontal coordinate X1 in the color vertex curve is above point A, point A is recorded as the upper reflection point; when the point with the horizontal coordinate X1 in the color vertex curve is below point A, point A is recorded as the lower reflection point; when the point with the horizontal coordinate X1 in the color vertex curve coincides with point A, point A is recorded as the reflection dividing point; The curve formed by all the reflection upper sites in the reflection vertex curve is recorded as the reflection upper curve, and the open interval formed by the horizontal coordinates of the leftmost point and the rightmost point of each reflection upper curve is recorded as the reflection upper interval; the curve formed by all the reflection lower sites in the reflection vertex curve is recorded as the reflection lower curve, and the open interval formed by the horizontal coordinates of the leftmost point and the rightmost point of each reflection lower curve is recorded as the reflection lower interval.

4. The method for generating a building BIM model based on point cloud segmentation according to claim 3, characterized in that: Method V further includes: For any reflection superposition interval: the open interval formed by the ordinates of the highest point and the lowest point of the reflection superposition curve in the reflection superposition interval is recorded as the upper value interval of the reflection vertex interval, and the open interval formed by the ordinates of the highest point and the lowest point of the color vertex interval in the reflection superposition interval is recorded as the lower value interval of the color vertex interval; For any reflection inferior interval: the open interval formed by the ordinates of the highest point and the lowest point of the reflection inferior curve in the reflection inferior interval is recorded as the lower value interval of the reflection vertex interval, and the open interval formed by the ordinates of the highest point and the lowest point of the color vertex interval in the reflection inferior interval is recorded as the upper value interval of the color vertex interval; The intervals in the color vertex interval that are recorded as both the upper value interval and the lower value interval are recorded as color mixing intervals; the intervals in the reflection vertex interval that are recorded as both the upper value interval and the lower value interval are recorded as reflection mixing intervals.

5. The method for generating a building BIM model based on point cloud segmentation according to claim 4, characterized in that: Point cloud analysis also includes: Obtain the color vertex intervals and reflection vertex intervals corresponding to all point cloud data, and after executing method V, record the intersection of the color mixing intervals corresponding to all color vertex intervals as the color feature interval, and record the intersection of the reflection mixing intervals corresponding to all reflection vertex intervals as the reflection feature interval; For any color mixing interval that is not recorded as a color feature interval: use the interval sorting algorithm to obtain the interval parameters of the color mixing interval. The interval sorting algorithm is: , where F is the interval parameter, c is the number of point cloud data, G i H is the length of the upper value interval corresponding to the color mixing interval in the i-th point cloud data in the X-axis, j The length of the lower value interval corresponding to the color mixing interval in the point cloud data in the X-axis; When the interval parameter of the color mixing interval is greater than 0, the color mixing interval is re-recorded as an upper value interval; when the interval parameter of the color mixing interval is less than 0, the color mixing interval is re-recorded as a lower value interval; when the interval parameter of the color mixing interval is equal to 0, the color mixing interval is re-recorded as a color feature interval; For any reflection mixed interval that is not recorded as a reflection feature interval: based on the method of re-recording the color mixed interval into the upper value interval, the lower value interval and the color feature interval, use the interval sorting algorithm to re-record the reflection mixed interval into the upper value interval, the lower value interval and the reflection feature interval; The color vertex interval containing the upper value interval, the lower value interval and the color feature interval and the reflection vertex interval containing the upper value interval, the lower value interval and the reflection feature interval are recorded as point cloud positioning features.

6. The method for generating a building BIM model based on point cloud segmentation according to claim 5, characterized in that: Feature generation methods include: Randomly obtain a point cloud model and its corresponding point cloud data; obtain a point cloud positioning point in the point cloud data using a positioning acquisition method based on the point cloud positioning feature; wherein the positioning acquisition method is: obtain the reflection intensity and color mean of all points in the point cloud data, and when any point α satisfies the following conditions: the reflection intensity is in the upper value interval of the reflection vertex interval and the color mean is in the lower value interval of the color vertex interval, the reflection intensity is in the lower value interval of the reflection vertex interval and the color mean is in the upper value interval of the color vertex interval, or the reflection intensity is in the reflection feature interval of the reflection vertex interval and the color mean is in the color feature interval of the color vertex interval, the point α is recorded as a point cloud positioning point; Obtain all point cloud positioning points in the point cloud data, and build a building BIM model based on all point cloud positioning points, which is recorded as the built model; when the built model is exactly the same as the point cloud model corresponding to the point cloud data, the point cloud positioning features are recorded as the perfect features; When the built model is not exactly the same as the point cloud model corresponding to the point cloud data, the points corresponding to the point cloud data in the area of ​​the built model that is different from the point cloud model are recorded as supplementary points, and based on the analysis method of the point cloud analysis method for analyzing the model points, the supplementary points are analyzed using the point cloud analysis method, and the intersection of the obtained point cloud positioning feature and the existing point cloud positioning feature is recorded as the latest point cloud positioning feature.

7. The method for generating a building BIM model based on point cloud segmentation according to claim 6, wherein: Based on the comparison results, the point cloud positioning features are supplemented, and the improved features include: When the latest point cloud positioning feature exists, the latest point cloud positioning feature is processed based on the feature analysis method until the perfect feature is obtained.

8. A building BIM model generation system based on point cloud segmentation, used to implement the building BIM model generation method based on point cloud segmentation according to any one of claims 1 to 7, characterized in that: Including point cloud feature analysis module, point cloud feature supplement module and BIM model generation module; The point cloud feature analysis module is used to obtain point cloud data of multiple buildings and multiple building BIM models generated based on the point cloud data; all point cloud data and all building BIM models are analyzed using the point cloud analysis method, and point cloud positioning features are obtained based on the analysis results; The point cloud feature supplement module is used to obtain the construction model based on the point cloud positioning features and the feature generation method of the point cloud data, and compare the construction model with the point cloud model corresponding to the point cloud data. Based on the comparison results, the point cloud positioning features are supplemented to obtain the perfect features; The BIM model generation module is used to obtain point cloud positioning points in the point cloud data corresponding to the model to be generated based on the perfect features and positioning acquisition method, and use the point cloud positioning points to generate a building BIM model corresponding to the point cloud data.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are executed.

Images