A method, device, equipment and storage medium for calculating overlap of three-dimensional models

Abstract

The present application provides a method, device, equipment and storage medium for calculating the overlap of a three-dimensional model, and relates to the field of drone technology. The method obtains the model height range of multiple sub-areas in the target area; calculates the two-dimensional overlap of each sub-area in multiple planes according to the area of ​​each sub-area in multiple planes and the image overlap area of ​​multiple planes; wherein the multiple planes are planes corresponding to multiple heights within the model height range of each sub-area; determines the overlapping direction category of each sub-area in multiple planes according to the center position of each sub-area in multiple planes and the image center position of each sub-area in multiple planes; calculates the three-dimensional overlap of each sub-area in each plane according to the two-dimensional overlap of each plane and the corresponding overlapping direction category. Thus, the quantitative information and vector information of the overlap are calculated, and the reconstruction quality of the model can be analyzed more accurately, which is applicable to a wide range of scenarios.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle technology, and in particular to a method, device, equipment and storage medium for calculating the overlap of a three-dimensional model. Background Art

[0002] With the rise of real-life 3D and smart city construction, high-precision 3D models have received widespread attention. UAV photogrammetry uses sensors mounted on the UAV flight platform to obtain images of objects in the experimental area from multiple angles, and uses 3D modeling algorithms to quickly reconstruct a 3D model of the experimental area.

[0003] The terrain and objects in three-dimensional space are complex and diverse, including elements with complex spatial structures at multiple levels and angles, such as buildings. Therefore, multi-angle data acquisition is required to restore a complete three-dimensional model. From the currently widely used five-lens oblique photogrammetry, single-lens circumnavigation flight, to close-up photogrammetry and optimal view photogrammetry, there are many aerial data acquisition modes for data acquisition for three-dimensional model reconstruction. For the collected data, the data quality can be further analyzed by calculating the overlap of the model area.

[0004] However, in the existing methods, the overlap calculated is the overlap of two-dimensional planes. The applicability of two-dimensional overlap to three-dimensional models, especially to three-dimensional elements such as buildings, is poor, and the reconstruction quality cannot be guaranteed. Therefore, there is an urgent need for an overlap calculation method suitable for three-dimensional models. Summary of the invention

[0005] The purpose of the present invention is to provide a method, device, equipment and storage medium for calculating the overlap of a three-dimensional model in order to address the shortcomings of the above-mentioned prior art, so as to solve the problem that the overlap calculated in the prior art has poor applicability.

[0006] To achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:

[0007] In a first aspect, an embodiment of the present application provides a method for calculating the degree of overlap of a three-dimensional model, the method comprising:

[0008] Get the model height ranges of multiple sub-areas in the target area;

[0009] According to the area of ​​each sub-region in multiple planes and the image overlap area of ​​the multiple planes, respectively calculate the two-dimensional overlap degree of each sub-region in the multiple planes; wherein the multiple planes are planes corresponding to multiple heights within the model height range of each sub-region;

[0010] Determine the overlapping direction category of each sub-region in the multiple planes according to the center position of each sub-region in the multiple planes and the center position of the image of each sub-region in the multiple planes;

[0011] According to the two-dimensional overlap degree of each plane and the corresponding overlap direction category, the three-dimensional overlap degree of each sub-region on each plane is calculated.

[0012] Optionally, obtaining model height ranges of multiple sub-areas in the target area includes:

[0013] Performing spatial region segmentation on the target region to obtain the multiple sub-regions;

[0014] The model height ranges of the multiple sub-areas are determined according to the height information of the model in the target area.

[0015] Optionally, the performing spatial region segmentation on the target region to obtain the multiple sub-regions includes:

[0016] According to the outline of the target area and the preset sub-area segmentation condition, the target area is spatially segmented to obtain the multiple sub-areas.

[0017] Optionally, the sub-region segmentation condition includes: a preset minimum segmentation area of ​​the sub-region, and a preset minimum number of connection points of the sub-region;

[0018] The step of performing spatial region segmentation on the target region according to the contour of the target region and the preset sub-region segmentation condition to obtain the multiple sub-regions includes:

[0019] According to the outline of the target area, the minimum segmentation area of ​​the sub-area, and the minimum number of connection points of the sub-area, the target area is spatially segmented to obtain the multiple sub-areas, the area of ​​each sub-area is greater than or equal to the minimum segmentation area of ​​the sub-area, and the number of connection points of each sub-area is greater than or equal to the minimum number of connection points.

[0020] Optionally, determining the model height ranges of the plurality of sub-areas according to the height information of the model in the target area includes:

[0021] Determine the maximum height of each sub-region and the minimum height of each sub-region according to the height information of the model;

[0022] According to the maximum height of each sub-region and the minimum height of each sub-region, a model height range of each sub-region is obtained.

[0023] Optionally, determining the overlapping direction category of each sub-region in the multiple planes according to the center position of each sub-region in the multiple planes and the center position of the image of each sub-region in the multiple planes respectively includes:

[0024] Determine the overlapping direction of each sub-region on the multiple planes according to the center position of each sub-region on the multiple planes and the center position of the image;

[0025] The overlapping direction category is calculated according to the overlapping direction.

[0026] Optionally, the method further comprises:

[0027] Calculating the cumulative two-dimensional overlap of each sub-region on each plane according to the multiple two-dimensional overlaps of each plane, wherein the multiple two-dimensional overlaps are two-dimensional overlaps obtained based on multiple images of each sub-region on each plane;

[0028] According to the number of the multiple overlapping direction categories of each plane and the accumulated two-dimensional overlap degree, the model quality evaluation parameter of each sub-region in each plane is obtained, wherein the multiple overlapping direction categories are overlapping direction categories obtained based on the multiple images respectively.

[0029] In a second aspect, an embodiment of the present application provides a device for calculating the degree of overlap of a three-dimensional model, the device comprising:

[0030] An acquisition module, used to obtain model height ranges of multiple sub-areas in a target area;

[0031] A first calculation module is used to calculate the two-dimensional overlap of each sub-region on the multiple planes according to the area of ​​each sub-region on the multiple planes and the image overlap area of ​​the multiple planes; wherein the multiple planes are planes corresponding to multiple heights within the model height range of each sub-region;

[0032] A determination module, used to determine the overlapping direction category of each sub-region in the multiple planes according to the center position of each sub-region in the multiple planes and the center position of the image of each sub-region in the multiple planes;

[0033] The second calculation module is used to calculate the three-dimensional overlap degree of each sub-region on each plane according to the two-dimensional overlap degree of each plane and the corresponding overlap direction category.

[0034] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a storage medium, wherein the processor and the storage medium are communicatively connected via a bus, the storage medium stores program instructions executable by the processor, and the processor calls the program stored in the storage medium to execute the steps of the method for calculating the degree of overlap of a three-dimensional model as described in any one of the first aspects above.

[0035] In a fourth aspect, an embodiment of 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 of the method for calculating the degree of overlap of a three-dimensional model as described in any one of the above-mentioned first aspects are executed.

[0036] Compared with the prior art, this application has the following beneficial effects:

[0037] The embodiment of the present application provides a method, device, equipment and storage medium for calculating the overlap of a three-dimensional model. The method obtains the model height range of multiple sub-areas in the target area; calculates the two-dimensional overlap of each sub-area in multiple planes according to the area of ​​each sub-area in multiple planes and the image coverage area of ​​multiple planes; wherein the multiple planes are planes corresponding to multiple heights within the model height range of each sub-area; determines the overlap direction category of each sub-area in multiple planes according to the center position of each sub-area in multiple planes and the image center position of each sub-area in multiple planes; calculates the three-dimensional overlap of each sub-area in each plane according to the two-dimensional overlap of each plane and the corresponding overlap direction category. Thus, the quantitative information and vector information of the overlap are calculated, and the reconstruction quality of the model can be analyzed more accurately, which is applicable to a wide range of scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 A schematic diagram of a flow chart of a method for calculating the degree of overlap of a three-dimensional model provided in an embodiment of the present application;

[0040] Figure 2 A schematic flow chart of a method for determining a model height range of a sub-region according to a target region provided in an embodiment of the present application;

[0041] Figure 3 A schematic flow chart of a method for determining model height ranges of multiple sub-areas provided in an embodiment of the present application;

[0042] Figure 4 A flowchart of a method for determining overlapping direction categories provided in an embodiment of the present application;

[0043] Figure 5 A schematic diagram of a flow chart of another method for calculating the degree of overlap of a three-dimensional model provided in an embodiment of the present application;

[0044] Figure 6 A schematic diagram of a device for calculating the degree of overlap of a three-dimensional model provided in an embodiment of the present application;

[0045] Figure 7 A schematic diagram of an electronic device provided in an embodiment of the present application.

[0046] Icons: 601 - acquisition module, 602 - first calculation module, 603 - determination module, 604 - second calculation module, 701 - processor, 702 - storage medium. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0048] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0049] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0050] In addition, the terms “first”, “second”, etc., if used, are merely used to distinguish between the descriptions and should not be understood as indicating or implying relative importance.

[0051] It should be noted that, in the absence of conflict, the features in the embodiments of the present invention may be combined with each other.

[0052] In order to make the overlap degree more adaptable to various scenarios, the present application provides a method, device, equipment and storage medium for calculating the overlap degree of a three-dimensional model, and the calculated overlap degree is more suitable for three-dimensional scenes.

[0053] The following is an explanation of a method for calculating the overlap of a three-dimensional model provided in an embodiment of the present application through a specific example. This embodiment uses the height information of the model calculated by the connection points (i.e., sparse point cloud) obtained by sparse reconstruction in the three-dimensional reconstruction algorithm as an example for explanation. In actual applications, other elevation data can also be used to calculate the height information of the model, which is not limited in the present application. Figure 1 The flowchart of a method for calculating the overlap of a three-dimensional model provided in an embodiment of the present application is shown in FIG. The method can be executed by a desktop computer, a laptop computer, etc. having a computing function, and is not limited here. Figure 1 As shown, the method includes:

[0054] S101, obtaining model height ranges of multiple sub-areas in a target area.

[0055] The target area is photographed by a drone, and the three-dimensional coordinate information of multiple connection points in the target area is obtained using a three-dimensional reconstruction algorithm. Based on the three-dimensional coordinate information of multiple connection points in the target area, the height information of the entire target area is obtained, and then the model height range of multiple sub-areas in the target area can be obtained. For example, the target area can be a block, which includes multiple buildings, and a building can be a sub-area.

[0056] For example, the connection points are feature points on objects in the target area, such as the corners of a house. The connection points of the three-dimensional model can be obtained by processing the image using a three-dimensional reconstruction algorithm. The connection points record the coordinate information of the object in the three-dimensional space, and the corresponding height information can be determined through the three-dimensional coordinate information of the connection points.

[0057] S102 , calculating the two-dimensional overlap of each sub-region in the multiple planes according to the area of ​​each sub-region in the multiple planes and the image overlap area of ​​the multiple planes.

[0058] Among them, the multiple planes are planes corresponding to multiple heights within the model height range of each sub-area. In the actual calculation of overlap, the model height range of the sub-area is divided into multiple heights, each height corresponds to a plane of the sub-area. If it is divided into k categories, the corresponding height distribution H is recorded. Ri ={H ri1 , H ri2 ,,,H rik}, each sub-area has k planes. For example, in a building, different heights correspond to different floors, and each floor is a different plane, that is, different heights correspond to different planes. There is no restriction on the specific height range splitting method, which can be evenly divided or split according to other preset methods.

[0059] Construct the minimum circumscribed rectangle R of the plane according to the coordinates of the connecting points of each plane MBR Construct the projection quadrilateral Q of each plane according to the coordinates of the four corner points in the projection of the drone image on each plane j . Project the quadrilateral Q j With the minimum enclosing rectangle R MBR The intersection area and the minimum enclosing rectangle R MBR The ratio of the areas is taken as the two-dimensional overlap of the plane.

[0060] For example, the specific projected quadrilateral Q j The construction method is: the drone image set is I = {i1, i2, ..., i n}, known image i i The internal and external orientation element information and the minimum height H1 of the model area are used to calculate the object space projection coordinates of the image corner points using the photogrammetry collinear equation formula, and the maximum object space projection quadrilateral Q of the image is constructed using the four corner points. j The specific minimum enclosing rectangle R MBR The construction method is: obtain the maximum horizontal coordinate and minimum horizontal coordinate on the horizontal axis, and the maximum vertical coordinate and minimum vertical coordinate on the vertical axis of the plane connection point coordinates. Construct the coordinates of the four boundary points based on the maximum horizontal coordinate, minimum horizontal coordinate, maximum vertical coordinate, and minimum vertical coordinate to determine the minimum enclosing rectangle R MBR .

[0061] S103 , determining the overlapping direction category of each sub-region in the multiple planes respectively according to the center position of each sub-region in the multiple planes and the center position of the image of each sub-region in the multiple planes.

[0062] Get the minimum enclosing rectangle R of each plane MBR , and determine the minimum enclosing rectangle R MBR The center position of is the center position of the plane. Get the projection quadrilateral Q of the sub-region on each plane j , determine the projected quadrilateral Q j The center position of the plane is taken as the image center position of the plane. The overlapping direction category of the sub-region in each plane is determined according to the center position coordinates of the plane and the corresponding image center position coordinates. And the overlapping direction category of each sub-region in multiple planes is determined in turn. For example, the overlapping direction category is the direction category of the overlapping area. If the plane is divided into four parts with the center position of the plane as the center, there are four overlapping direction categories: the first direction, the second direction, the third direction, and the fourth direction.

[0063] S104 , calculating the three-dimensional overlapping degree of each sub-region in each plane according to the two-dimensional overlapping degree of each plane and the corresponding overlapping direction category.

[0064] The two-dimensional overlap is taken as the quantity in the three-dimensional overlap of the plane. The overlapping direction category corresponding to the plane characterizes the directional characteristics of the overlap, which is taken as the vector in the three-dimensional overlap of the plane. Then each sub-region contains both the quantitative information of the overlap and the vector information of the overlap in the three-dimensional overlap of each plane. The quantitative information and the vector information more accurately reflect the characteristics of the three-dimensional model. The calculated overlap improves the reconstruction quality of the three-dimensional model and is applicable to almost all three-dimensional models.

[0065] Specifically, the three-dimensional overlap is OD ijk , O.D. ijk =(O ijk , D ijk ). Among them, O ijk is the two-dimensional overlap, D ijk Overlap direction category.

[0066] In summary, in this embodiment, by obtaining the model height range of multiple sub-regions in the target area; according to the area of ​​each sub-region in multiple planes and the image overlapping area of ​​multiple planes, the two-dimensional overlap of each sub-region in multiple planes is calculated respectively; wherein the multiple planes are planes corresponding to multiple heights within the model height range of each sub-region; according to the center position of each sub-region in multiple planes and the image center position of each sub-region in multiple planes, the overlapping direction category of each sub-region in multiple planes is determined respectively; according to the two-dimensional overlap of each plane and the corresponding overlapping direction category, the three-dimensional overlap of each sub-region in each plane is calculated. Thus, the quantitative information and vector information of the overlap are calculated, and the reconstruction quality of the model can be analyzed more accurately, which is applicable to a wide range of scenarios.

[0067] Figure 2 A flow chart of a method for determining a model height range of a sub-region according to a target region provided in an embodiment of the present application. Figure 2 As shown, in S101, the model height ranges of multiple sub-areas in the target area are obtained, including:

[0068] S201, performing spatial region segmentation on the target region to obtain multiple sub-regions.

[0069] When a drone shoots a target area, if the target area is large, the calculated three-dimensional overlap accuracy is low, which is not conducive to the subsequent use of overlap for model reconstruction. Therefore, the target area is spatially divided into multiple sub-areas, and each sub-area is used as the calculation object, so that the three-dimensional overlap information can be obtained more accurately.

[0070] S202: Determine model height ranges of multiple sub-areas based on height information of the model in the target area.

[0071] The coordinate information of the 3D model in the target area is obtained, and the coordinate information includes the height information of the 3D model. The corresponding model height range is determined according to the model height information of the sub-area. The model height ranges of multiple sub-areas are determined in sequence. For example, the height information H of the 3D model is counted according to the coordinate information of the 3D model, and H = {H1, H2,,, H m}, that is, the three-dimensional model has m types of height information.

[0072] In summary, in this embodiment, the target area is spatially segmented to obtain multiple sub-areas, and the model height ranges of the multiple sub-areas are determined according to the height information of the model in the target area. Thus, the target area is segmented into multiple sub-areas, which improves the calculation accuracy of the overlap degree.

[0073] Furthermore, in another embodiment, in S201, the target area is spatially segmented to obtain a plurality of sub-areas, including:

[0074] According to the contour of the target area and the preset sub-area segmentation conditions, the target area is spatially segmented to obtain multiple sub-areas.

[0075] Determine the two-dimensional contour of the target area parallel to the horizontal plane. Segment the two-dimensional contour according to the preset sub-region segmentation condition to obtain multiple sub-region two-dimensional contours. While segmenting the two-dimensional contour, the three-dimensional target object in the two-dimensional contour is also spatially segmented to obtain the sub-region two-dimensional contour and the three-dimensional target object in the sub-region two-dimensional contour. The target area is spatially segmented to obtain multiple sub-regions, making the region segmentation more convenient. For example, the target area is a block, and the block is spatially segmented to obtain a sub-region in the block and the building in the sub-region. Among them, the preset sub-region segmentation condition can be set according to the segmentation requirements and is not limited here.

[0076] After multiple sub-regions are obtained through segmentation, each sub-region may be labeled to construct a spatial index.

[0077] For example, the outline of the target area can be the minimum circumscribed rectangle R MBR , according to the preset sub-region segmentation conditions, the minimum enclosing rectangle R MBR The specific minimum enclosing rectangle R MBR The construction method is: obtain the maximum horizontal coordinate and minimum horizontal coordinate on the horizontal axis, and the maximum vertical coordinate and minimum vertical coordinate on the vertical axis of the plane connection point coordinates. Construct the coordinates of the four boundary points based on the maximum horizontal coordinate, minimum horizontal coordinate, maximum vertical coordinate, and minimum vertical coordinate to determine the minimum enclosing rectangle R MBR It should be noted here that the minimum enclosing rectangle R MBRThis is just an example of the target area contour and is not limited here. Other contours of the target area may also be used for segmentation.

[0078] In summary, in this embodiment, the target region is spatially segmented according to the contour of the target region and the preset sub-region segmentation conditions to obtain multiple sub-regions, thereby making the region segmentation more convenient.

[0079] Furthermore, in another embodiment, the sub-region segmentation condition includes: a preset sub-region minimum segmentation area S min , and the minimum number of connection points N of the preset sub-area min ;

[0080] According to the contour of the target area and the preset sub-area segmentation conditions, the target area is segmented into multiple sub-areas, including:

[0081] According to the contour of the target area and the minimum segmentation area S of the sub-region min , and the minimum number of connection points N in the sub-region min , perform spatial region segmentation on the target area to obtain multiple sub-regions, and the area of ​​each sub-region is greater than or equal to the minimum segmentation area S of the sub-region min , and the number of connection points in each sub-area is greater than or equal to the minimum number of connection points N Min .

[0082] By determining the minimum segmentation area S of the sub-region min , making the spatial region segmentation as accurate as possible without dividing the sub-regions into very small parts; by determining the minimum number of connection points N min Makes the segmentation area more accurate.

[0083] For example, the minimum segmentation area S of the sub-region can be determined according to the contour area min , for example, one twentieth of the contour area is taken as the minimum segmentation area S min , or the minimum segmentation area S of the sub-region can be set according to the characteristics of the target region min The minimum enclosing rectangle R of the target area can be MBR As the outline of the target area, according to the minimum segmentation area S min , and the minimum number of connection points N in the sub-region min The minimum enclosing rectangle R of the target area MBR to split.

[0084] In summary, in this embodiment, according to the contour of the target area, the minimum segmentation area of ​​the sub-area, and the minimum number of connection points N of the sub-area min, perform spatial region segmentation on the target area to obtain multiple sub-regions, the area of ​​each sub-region is greater than or equal to the minimum segmentation area of ​​the sub-region, and the number of connection points in each sub-region is greater than or equal to the minimum number of connection points N min . Thus, the segmentation accuracy of the target area is improved.

[0085] Figure 3 A flow chart of a method for determining model height ranges of multiple sub-areas provided in an embodiment of the present application. Figure 3 As shown, in S202, according to the height information of the model in the target area, determining the model height ranges of the multiple sub-areas includes:

[0086] S301. Determine the maximum height and the minimum height of each sub-region according to the height information of the model.

[0087] Get the coordinate information of all connection points in the sub-area, which contains the height information of the 3D model. Get the height information of all connection points according to the coordinate information of all connection points in the sub-area. Count the height information of all connection points in the sub-area, and determine the maximum height and minimum height of the sub-area. And determine the maximum height and minimum height of each sub-area.

[0088] S302: Obtain a model height range of each sub-region according to the maximum height of each sub-region and the minimum height of each sub-region.

[0089] After determining the maximum height of each sub-area and the minimum height of each sub-area, the range between the maximum height and the minimum height can be used as the model height range for subsequent further processing.

[0090] In summary, in this embodiment, the maximum height and the minimum height of each sub-region are determined according to the height information of the model; and the model height range of each sub-region is obtained according to the maximum height and the minimum height of each sub-region. Thus, the model height range of the sub-region is more accurate.

[0091] Figure 4 A flowchart of a method for determining overlapping direction categories provided in an embodiment of the present application. Figure 4 As shown, in S103, the overlapping direction categories of each sub-region in the multiple planes are determined according to the center position of each sub-region in the multiple planes and the center position of the image of each sub-region in the multiple planes, including:

[0092] S401 , determining the overlapping direction of each sub-region in the multiple planes according to the center position of each sub-region in the multiple planes and the center position of the image.

[0093] Get the minimum enclosing rectangle R of each plane MBR , determine the minimum enclosing rectangle R MBR The center position of the plane is the center position of the plane. Let the coordinates of the center position of the plane be C ik =(X i , Y i , H ik ); Get the projection quadrilateral Q of the sub-region on each plane j , determine the projected quadrilateral Q j The center position of the image is taken as the center position of the image of the plane, and the coordinates of the image center position are set as S j =(X si , Y sj , Z sj ). The overlap direction vector of the plane can be determined by the center position coordinates of the plane and the center position coordinates of the image. The specific overlap direction vector V ijk The calculation method of is shown in the following formula (1):

[0094] V ijk =(X si -X i , Y sj -Y i , Z sj -H ik ) (1)

[0095] The overlapping direction vector is a vector that can represent the overlapping direction on each plane.

[0096] S402: Calculate overlapping direction categories according to the overlapping directions.

[0097] According to the overlapping direction vector, the angle between the overlapping direction vector and multiple coordinate axes in the preset three-dimensional coordinate system can be calculated. A preset two-dimensional coordinate system is determined in the preset three-dimensional coordinate system, and a preset coordinate axis is determined in the preset two-dimensional coordinate system. The angle with the positive direction of the preset coordinate axis is divided into n categories, such as n=4, n=8, etc., and each category of angle corresponds to an angle range. According to the angle between the overlapping direction vector and the positive direction of the preset coordinate axis, the angle range in which it is located is determined, and the angle category, that is, the overlapping direction category, is determined according to the angle range in which it is located. For example: the first category of direction, the second category of direction, the third category of direction, and the fourth category of direction. Among them, the preset three-dimensional coordinate system is a three-dimensional rectangular coordinate system obtained by coordinate transformation of the target area photographed by the drone.

[0098] For example, the following is an example in which the preset two-dimensional coordinate system is the XOY coordinate system and the preset coordinate axis is the X axis. The angle between the overlapping direction vector and the X axis in the XOY coordinate system is calculated as shown in the following formula (2):

[0099]

[0100] According to the preset requirements of the three-dimensional model, the angle θ ijk Divide into n categories to determine the overlapping direction category D ijk , specific D ijk The classification calculation method is shown in the following formula (3):

[0101]

[0102] The overlapping direction category is determined by the angle between the overlapping direction vector and the preset three-dimensional coordinate system, so that the overlapping direction category is more suitable for the three-dimensional model, and the calculation accuracy of the three-dimensional overlap is improved. The above is only an example, and calculation can also be performed through other preset two-dimensional coordinate systems in the preset three-dimensional coordinate system, which is not limited here.

[0103] In summary, in this embodiment, the overlapping direction of each sub-region in multiple planes is determined according to the center position of each sub-region in multiple planes and the center position of the image; and the overlapping direction category is calculated according to the overlapping direction. Thus, the overlapping direction category is accurately determined by the angle between the overlapping direction vector and the preset three-dimensional coordinate system.

[0104] Figure 5 A schematic diagram of a flow chart of another method for calculating the overlap of a three-dimensional model provided in an embodiment of the present application. Figure 5 As shown, the method also includes:

[0105] S105 . Calculate the cumulative two-dimensional overlap of each sub-region on each plane according to the multiple two-dimensional overlaps of each plane.

[0106] Among them, the multiple two-dimensional overlaps are the two-dimensional overlaps obtained based on multiple images of each sub-area on each plane. When the drone shoots the target area, it will shoot from multiple different directions to obtain more comprehensive target area feature information. Then, for each plane, there will be multiple images shot from different directions. Each shot image will have a corresponding projection quadrilateral Q j , according to each projected quadrilateral Q j and the minimum circumscribed rectangle R of the plane MBR The corresponding two-dimensional overlap can be calculated, and each plane will have multiple two-dimensional overlaps.

[0107] By adding up the multiple 2D overlaps of each plane, the cumulative 2D overlap of each sub-area on each plane can be calculated. The cumulative 2D overlap of a plane represents the overlap of multiple shots taken by the drone, and can better reflect the overlapping situation of the shots taken on the plane.

[0108] S106 , obtaining a model quality evaluation parameter of each sub-region in each plane according to the number of multiple overlapping direction categories and the accumulated two-dimensional overlap degree in each plane.

[0109] Among them, the multiple overlapping direction categories are overlapping direction categories obtained based on multiple images. The drone shoots the target area from multiple different directions, and each shot image obtained has not only a corresponding two-dimensional overlap, but also a corresponding overlapping direction category. If there are n types of overlapping direction categories, the more overlapping direction categories the drone shoots multiple times, the more comprehensive the shooting direction is, and the poorer the shooting quality is; the fewer overlapping direction categories the drone shoots multiple times, the more single the shooting direction is, and the poorer the shooting quality is.

[0110] Therefore, the threshold of the number of direction categories nmin can be set according to the actual needs of 3D model reconstruction. For a plane, if the number of direction categories exceeds the threshold nmin, the model quality can be considered good. For example, if there are n overlapping direction categories, the threshold of the number of direction categories nmin can be set to any value between 0.5n-0.9n, and the specific threshold is not limited.

[0111] In addition to setting the direction category quantity threshold nmin to evaluate the model quality, you can also set the cumulative two-dimensional overlap threshold omin. For a plane, if the cumulative two-dimensional overlap exceeds the threshold omin, it can be considered that the model quality is good. For example, the cumulative two-dimensional overlap omin can be set to any value between 2 and 10, and the specific threshold is not limited.

[0112] The corresponding overlapping direction category quality evaluation parameter is obtained according to the number of overlapping direction categories of each plane, and the corresponding cumulative two-dimensional overlap quality evaluation parameter is obtained according to the cumulative two-dimensional overlap of each plane. According to the overlapping direction category quality evaluation parameter and the cumulative two-dimensional overlap quality evaluation parameter of each plane, the model quality evaluation parameter of each sub-region in each plane is obtained comprehensively. The model quality evaluation parameters obtained by comprehensively considering the overlapping direction category and the cumulative two-dimensional overlap of each plane are more accurate and objective.

[0113] In summary, in this embodiment, the cumulative two-dimensional overlap of each sub-region on each plane is calculated according to the multiple two-dimensional overlaps of each plane; the model quality evaluation parameter of each sub-region on each plane is obtained according to the number of multiple overlapping direction categories and the cumulative two-dimensional overlap of each plane. Thus, the model quality evaluation parameter obtained by comprehensively considering the overlapping direction category and the cumulative two-dimensional overlap of each plane is more accurate and objective.

[0114] The following is a description of a three-dimensional model overlap calculation device, equipment, and storage medium provided by the present application. The specific implementation process and technical effects are described above and will not be repeated below.

[0115] Figure 6 A schematic diagram of a three-dimensional model overlap calculation device provided in an embodiment of the present application, such as Figure 6 As shown, the computing device may include:

[0116] An acquisition module 601 is used to acquire model height ranges of multiple sub-areas in a target area;

[0117] A first calculation module 602 is used to calculate the two-dimensional overlap of each sub-region on the multiple planes according to the area of ​​each sub-region on the multiple planes and the image overlap area of ​​the multiple planes; wherein the multiple planes are planes corresponding to multiple heights within the model height range of each sub-region;

[0118] A determination module 603, configured to determine the overlapping direction category of each sub-region in the multiple planes according to the center position of each sub-region in the multiple planes and the center position of the image of each sub-region in the multiple planes;

[0119] The second calculation module 604 is used to calculate the three-dimensional overlap degree of each sub-region on each plane according to the two-dimensional overlap degree of each plane and the corresponding overlap direction category.

[0120] Furthermore, the acquisition module 601 is specifically configured to perform spatial region segmentation on the target region to obtain the multiple sub-regions; and determine model height ranges of the multiple sub-regions according to height information of the model in the target region.

[0121] Furthermore, the acquisition module 601 is specifically configured to perform spatial region segmentation on the target region according to the contour of the target region and a preset sub-region segmentation condition to obtain the multiple sub-regions.

[0122] Furthermore, the acquisition module 601 is specifically used to perform spatial region segmentation on the target area according to the contour of the target area and the preset sub-region segmentation conditions to obtain the multiple sub-regions, including: performing spatial region segmentation on the target area according to the contour of the target area, the minimum segmentation area of ​​the sub-region, and the minimum number of connection points of the sub-region to obtain the multiple sub-regions, the area of ​​each sub-region is greater than or equal to the minimum segmentation area of ​​the sub-region, and the number of connection points of each sub-region is greater than or equal to the minimum number of connection points.

[0123] Furthermore, the acquisition module 601 is specifically used to determine the maximum height of each sub-area and the minimum height of each sub-area according to the height information of the model; and obtain the model height range of each sub-area according to the maximum height of each sub-area and the minimum height of each sub-area.

[0124] Furthermore, the determination module 603 is specifically used to determine the overlapping direction of each sub-region in the multiple planes according to the center position of each sub-region in the multiple planes and the center position of the image; and calculate the overlapping direction category according to the overlapping direction.

[0125] Furthermore, the second calculation module 604 is specifically used to calculate the cumulative two-dimensional overlap of each sub-region in each plane according to the multiple two-dimensional overlaps of each plane, wherein the multiple two-dimensional overlaps are respectively the two-dimensional overlaps obtained based on the multiple images of each sub-region in each plane; and obtain the model quality evaluation parameters of each sub-region in each plane according to the number of multiple overlapping direction categories in each plane and the cumulative two-dimensional overlap, wherein the multiple overlapping direction categories are respectively the overlapping direction categories obtained based on the multiple images.

[0126] The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more digital singnal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0127] Figure 7 A schematic diagram of an electronic device provided in an embodiment of the present application, which electronic device may be a device with computing and processing functions.

[0128] The electronic device includes: a processor 701 and a storage medium 702. The processor 701 and the storage medium 702 are connected via a bus.

[0129] The storage medium 702 is used to store programs, and the processor 701 calls the programs stored in the storage medium 702 to execute the above method embodiment. The specific implementation method and technical effect are similar and will not be repeated here.

[0130] Optionally, the present invention also provides a program product, such as a computer-readable storage medium, comprising a program, which is used to execute the above method embodiment when executed by a processor.

[0131] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or 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 interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0134] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (English: Read-Only Memory, abbreviated: ROM), random access memory (English: Random Access Memory, abbreviated: RAM), disk or optical disk and other media that can store program codes.

Claims

1. A method for calculating the overlap of a three-dimensional model, characterized in that: The method comprises: Get the model height ranges of multiple sub-areas in the target area; According to the area of ​​each sub-region in multiple planes and the image overlap area of ​​the multiple planes, respectively calculate the two-dimensional overlap degree of each sub-region in the multiple planes; wherein the multiple planes are planes corresponding to multiple heights within the model height range of each sub-region; Determine the overlapping direction category of each sub-region in the multiple planes according to the center position of each sub-region in the multiple planes and the center position of the image of each sub-region in the multiple planes; Calculating the three-dimensional overlapping degree of each sub-region on each plane according to the two-dimensional overlapping degree of each plane and the corresponding overlapping direction category; The step of determining the overlapping direction category of each sub-region in the multiple planes according to the center position of each sub-region in the multiple planes and the center position of the image of each sub-region in the multiple planes comprises: Determine the overlapping direction of each sub-region on the multiple planes according to the center position of each sub-region on the multiple planes and the center position of the image; The overlapping direction category is calculated according to the overlapping direction.

2. The method according to claim 1, characterized in that The step of obtaining the model height ranges of multiple sub-areas in the target area includes: Performing spatial region segmentation on the target region to obtain the multiple sub-regions; The model height ranges of the multiple sub-areas are determined according to the height information of the model in the target area.

3. The method according to claim 2, characterized in that The spatial region segmentation of the target region to obtain the multiple sub-regions includes: According to the outline of the target area and the preset sub-area segmentation condition, the target area is spatially segmented to obtain the multiple sub-areas.

4. The method according to claim 3, characterized in that The sub-region segmentation conditions include: a preset minimum segmentation area of ​​the sub-region, and a preset minimum number of connection points of the sub-region; The step of performing spatial region segmentation on the target region according to the contour of the target region and the preset sub-region segmentation condition to obtain the multiple sub-regions includes: According to the outline of the target area, the minimum segmentation area of ​​the sub-area, and the minimum number of connection points of the sub-area, the target area is spatially segmented to obtain the multiple sub-areas, the area of ​​each sub-area is greater than or equal to the minimum segmentation area of ​​the sub-area, and the number of connection points of each sub-area is greater than or equal to the minimum number of connection points.

5. The method according to claim 2, characterized in that: The determining, according to the height information of the model in the target area, the model height ranges of the plurality of sub-areas includes: Determine the maximum height of each sub-region and the minimum height of each sub-region according to the height information of the model; According to the maximum height of each sub-region and the minimum height of each sub-region, a model height range of each sub-region is obtained.

6. The method according to claim 1, characterized in that The method further comprises: Calculating the cumulative two-dimensional overlap of each sub-region on each plane according to the multiple two-dimensional overlaps of each plane, wherein the multiple two-dimensional overlaps are two-dimensional overlaps obtained based on multiple images of each sub-region on each plane; According to the number of the multiple overlapping direction categories of each plane and the accumulated two-dimensional overlap degree, the model quality evaluation parameter of each sub-region in each plane is obtained, wherein the multiple overlapping direction categories are overlapping direction categories obtained based on the multiple images respectively.

7. A device for calculating the degree of overlap of a three-dimensional model, characterized in that: The device comprises: An acquisition module, used to obtain model height ranges of multiple sub-areas in the target area; A first calculation module is used to calculate the two-dimensional overlap of each sub-region on the multiple planes according to the area of ​​each sub-region on the multiple planes and the image overlap area of ​​the multiple planes; wherein the multiple planes are planes corresponding to multiple heights within the model height range of each sub-region; A determination module, used to determine the overlapping direction category of each sub-region in the multiple planes according to the center position of each sub-region in the multiple planes and the center position of the image of each sub-region in the multiple planes; A second calculation module, used for calculating the three-dimensional overlap degree of each sub-region on each plane according to the two-dimensional overlap degree of each plane and the corresponding overlap direction category; A determination module, specifically configured to determine the overlapping direction of each sub-region on the multiple planes according to the center position of each sub-region on the multiple planes and the center position of the image; The overlapping direction category is calculated according to the overlapping direction.

8. An electronic device, characterized in that: include: A processor and a storage medium, wherein the processor and the storage medium are connected to each other via a bus communication, the storage medium stores program instructions executable by the processor, and the processor calls the program stored in the storage medium to execute the steps of the method for calculating the degree of overlap of a three-dimensional model as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for calculating the degree of overlap of a three-dimensional model as claimed in any one of claims 1 to 6 are executed.

Images