Oblique photography model singulation method and apparatus, electronic device, and storage medium

Abstract

Embodiments of the present application disclose a tilt photography model singulation method and device, electronic equipment and a storage medium. The method comprises: obtaining a target tilt photography model to be processed and terrain data corresponding to the target tilt photography model; segmenting the target tilt photography model into at least one model block according to the terrain data; obtaining an outer contour corresponding to the at least one model block through a projection technology; and cutting the target tilt photography model according to the outer contour corresponding to the at least one model block to obtain at least one independent model. In the embodiments of the present application, after the tilt photography model is segmented by using the terrain data, the interference information in the model is deleted, the outer contour of the model block is obtained by using the projection technology, and then the original tilt photography model is cut based on the outer contour to obtain a single model. The efficiency of model singulation is improved, and the accuracy of model singulation is also improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of maps, in particular to a tilt photography model singulation method and device, electronic equipment and storage medium. BACKGROUND

[0002] With the wide use of tilt photography technology, the area covered by the tilt photography model building is getting larger and larger. After loading the tilt photography model into the map application, if you want to view the properties of a certain element (such as a certain building) in the tilt photography model, you need to perform singulation processing on the tilt photography model so that the element becomes a separate model.

[0003] Currently, when performing singulation processing on the tilt photography model, the point cloud data of the model is mainly obtained, the point cloud data is divided by unit distance grid, the number of point clouds in the unit grid is calculated, the building outline is determined according to the number, and then the singulation of the tilt photography model is realized based on the building outline. However, this method still has some shortcomings: it depends on point cloud data, and the accuracy and efficiency of the tilt photography model singulation are low. SUMMARY

[0004] The embodiments of the present application provide a tilt photography model singulation method, device, electronic equipment and storage medium to improve the accuracy and efficiency of model singulation.

[0005] In a first aspect, the embodiments of the present application provide a tilt photography model singulation method, comprising:

[0006] obtaining a target tilt photography model to be processed and terrain data corresponding to the target tilt photography model;

[0007] segmenting the target tilt photography model into at least one model block according to the terrain data;

[0008] obtaining an outer contour corresponding to the at least one model block through projection technology;

[0009] cutting the target tilt photography model according to the outer contour corresponding to the at least one model block to obtain at least one independent model

[0010] In a second aspect, the embodiments of the present application provide a tilt photography model singulation device, comprising:

[0011] a model obtaining module configured to obtain a target tilt photography model to be processed and terrain data corresponding to the target tilt photography model;

[0012] a first segmentation module configured to segment the target tilt photography model into at least one model block according to the terrain data;

[0013] an outer contour acquisition module configured to acquire an outer contour corresponding to each model block by using a projection technology;

[0014] a second segmentation module configured to cut the target oblique photography model according to the outer contour corresponding to each model block to obtain at least one independent model.

[0015] In a third aspect, an electronic device is provided, which includes:

[0016] one or more processors;

[0017] a storage device configured to store one or more programs,

[0018] When the one or more programs are executed by the one or more processors, the one or more processors implement the oblique photography model individualization method according to any embodiment of the present application.

[0019] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program. When the program is executed by a processor, the oblique photography model individualization method according to any embodiment of the present application is implemented.

[0020] In the embodiments of the present application, after the terrain data is used to remove the interference information on the ground in the model, a plurality of model blocks are obtained. Then, the original oblique photography model is cut according to the outer contour of each model block, so that the independent model (i.e., the individualized model) is obtained. Compared with the point cloud calculation method, the model individualization efficiency and accuracy are improved. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1a is a flowchart of the oblique photography model individualization method according to the first embodiment of the present application;

[0022] Figure 1b is an effect diagram of a top view of the target oblique photography model segmented into at least one model block according to the first embodiment of the present application;

[0023] Figure 2a is a flowchart of the oblique photography model individualization method according to the second embodiment of the present application;

[0024] Figure 2b is a side view of the oblique photography model after the elevation surface is lifted according to the second embodiment of the present application;

[0025] Figure 3 is a flowchart of the oblique photography model individualization method according to the third embodiment of the present application;

[0026] Figure 4aThis is a flowchart illustrating the oblique photography model individualization method according to the fourth embodiment of this application;

[0027] Figure 4b This is an image of the effect of generating a second type of rectangular border corresponding to the side view projection outer contour according to a preset number of vertices in the fourth embodiment of this application;

[0028] Figure 4c This is a rendering of the side view projection outer contour and the corresponding convex hull contour according to the fourth embodiment of this application.

[0029] Figure 5 This is a schematic diagram of the oblique photography model unitization device according to the fifth embodiment of this application;

[0030] Figure 6 This is a schematic diagram of the structure of an electronic device according to the sixth embodiment of this application. Detailed Implementation

[0031] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the present application are shown in the drawings, not all structures.

[0032] Figure 1a This is a flowchart of the oblique photogrammetry model individualization method according to the first embodiment of this application. This embodiment can be applied to the case where electronic devices such as servers perform individualization of oblique photogrammetry models imported into a map engine. The method can be executed by an oblique photogrammetry model individualization device, which can be implemented in software and / or hardware and can be integrated into electronic devices, such as servers or other computer devices.

[0033] like Figure 1a As shown, the oblique photogrammetry model individualization method specifically includes the following process:

[0034] S101. Obtain the target oblique photogrammetry model to be processed, and the terrain data corresponding to the target oblique photogrammetry model.

[0035] Oblique photogrammetry is a high-tech field that has developed in the international surveying and mapping industry in recent years. It has overturned the previous limitation that orthophotos could only be taken from a vertical angle. It can acquire images from five different angles, including a vertical angle and four oblique angles, by mounting multiple sensors on the same flight platform. The acquired photos are then submitted to a cloud server. The cloud server uses an algorithm workflow consisting of SFM (Structure from Motion) + MVS (Multi View Stereo) + Mesh + Texture to automatically construct a three-dimensional model, i.e., an oblique photogrammetry model, from the acquired images.

[0036] The target oblique photography model to be processed refers to the oblique photography model that needs to be individualized; the terrain data corresponding to the target oblique photography model refers to the terrain data within the range of the target oblique photography model. The terrain data refers to the data that can represent the undulation of the Earth's surface, that is, the data with elevation information.

[0037] S102. Based on the terrain data, the target oblique photography model is divided into at least one model block.

[0038] Because the oblique photogrammetry model, after being imported into the engine, is organized and presented as triangular faces like a regular 3D model, all the model buildings appear as one continuous mass, making it impossible to distinguish roads, green belts, buildings, vehicles, etc. To quickly remove interfering ground data, this embodiment uses imported terrain data to delete the triangular faces on the surface of the oblique photogrammetry model that form roads, green belts, vehicles, lakes, etc., thereby achieving segmentation of the target oblique photogrammetry model and obtaining at least one model block. The model block can be exemplarily a model of a building, a tall tree, or a tower. See also... Figure 1b It shows a top view of a target oblique photogrammetric model divided into at least one model block based on terrain data, where 1 represents the top view of a building model block and the others are top views of non-building model blocks.

[0039] It should be noted that after dividing the target oblique photogrammetry model into at least one model block based on the terrain data, the resulting model block does not have ground data, and even the resulting building model block is a model block that lacks some underlying building data. In other words, the resulting at least one model block is incomplete, so further operations are needed to divide it into complete independent models.

[0040] S103. Obtain the outer contour corresponding to at least one model block through projection technology.

[0041] In one optional implementation, obtaining the outer contour corresponding to at least one model block using projection technology includes: performing vertical projection processing on at least one model block, and determining the vertically projected outer contour corresponding to at least one model block based on the projection result. Specifically, performing vertical projection processing on the model block involves projecting the top view of the model block onto the bottom surface, and then obtaining the vertically projected outer contour of the model block through contour recognition.

[0042] S104. Based on the outer contour corresponding to at least one model block, cut the target oblique photography model to obtain at least one independent model.

[0043] After obtaining the outer contour of at least one model block, since the outer contour of the model block contains coordinate position information, the complete individual model corresponding to the model block can be cut out from the initial target oblique photography model according to the outer contour of the model block, so that the obtained individual model has ground information and can be used as an independent model.

[0044] In one optional implementation, the target oblique photogrammetry model is cut according to the outer contour of each of at least one model block to obtain at least one independent model. This includes: vertically cutting the target oblique photogrammetry model according to the vertical projection outer contour corresponding to at least one model block. Specifically, the independent model to be cut is determined based on the coordinate position information carried in the vertical projection outer contour. The vertical projection outer contour is then aligned with the top view of the independent model to be segmented, and the vertical projection outer contour is cut along a vertically downward direction to obtain an independent model with ground information. The at least one independent model includes building models and non-building models, with non-building models exemplarily being models of tall trees or iron towers.

[0045] In this embodiment, after removing interference information on the ground in the model using terrain data, multiple model blocks are obtained. Then, based on the outer contour of each model block, the original oblique photogrammetry model is cut to obtain individual models (i.e., the individualized models). Compared with point cloud computing, this not only improves the efficiency of model individualization but also improves the accuracy of model individualization.

[0046] Figure 2a This is a flowchart of the oblique photography model individualization method according to the second embodiment of this application. This embodiment is an optimization based on the above embodiment. See [link to flowchart]. Figure 2a The method includes:

[0047] S201. Obtain the target oblique photogrammetry model to be processed, and the terrain data corresponding to the target oblique photogrammetry model.

[0048] S202. Based on the terrain data, delete the triangular faces in the target oblique photography model that are lower than the preset height value to obtain at least one model block.

[0049] In this embodiment of the application, in order to improve the efficiency of deleting surface interference data in the oblique photography model, optionally, the triangular faces in the target oblique photography model that are lower than a preset height value are deleted according to the terrain data.

[0050] In one alternative implementation, based on terrain data, triangular faces below a height threshold in the target oblique photogrammetry model are deleted to obtain at least one model block, including S2021-S2023:

[0051] S2021. Generate an elevation surface based on the elevation data included in the terrain data.

[0052] Among them, elevation data is exemplified by contour lines that describe the undulations of the earth's surface.

[0053] S2022. Raise the elevation surface to a preset height value and compare the height of the raised elevation surface with that of the target oblique photogrammetry model.

[0054] In this embodiment of the application, to avoid errors caused by changes during urban road repairs, a height range can be set, i.e., a pre-set height value. The entire elevation surface is raised or lowered by a certain height along the vertical direction. The pre-set height value can optionally be set based on the height of non-buildings. For example, the pre-set height value is 3 meters, raising the entire elevation surface by 3 meters along the vertical direction. The height of the raised elevation surface is then compared with the target oblique photography model. See also [example description]. Figure 2b It shows a side view of the target oblique photogrammetric model after the elevation surface has been raised, where curve 1 represents the elevation surface after the elevation has been raised, rectangle 22 represents the target oblique photogrammetric model, and elevation surface 3 represents the elevation surface before the elevation has been raised.

[0055] S2023. Delete the triangular faces in the target oblique photography model whose height is lower than the height of the raised elevation surface to obtain at least one model block.

[0056] See Figure 2bTo quickly remove surface information from the oblique photogrammetry model, the model's triangular faces below the elevation surface can be directly removed. This allows for the removal of triangular faces that make up objects such as roads, grasslands, lakes, and low shrubs, as well as triangular faces on buildings less than 3 meters above the ground. In practice, all triangular faces in the oblique photogrammetry model can be traversed, their heights determined, and those below a preset height value deleted. This yields at least one model block. It's important to note that since the heights of buildings and towers in the oblique photogrammetry model exceed the preset height, at least one model block will inevitably remain after deleting triangular faces below the preset height. Furthermore, because triangular faces within a certain height range are deleted based on terrain data, the resulting at least one model block is incomplete and cannot be directly used as an independent model; further processing is needed to create a single model block.

[0057] S203. Obtain the outer contour corresponding to at least one model block through projection technology.

[0058] Optionally, at least one model block is subjected to vertical projection processing, and the vertical projection outer contour corresponding to at least one model block is determined based on the projection result.

[0059] S204. Based on the outer contour corresponding to at least one model block, cut the target oblique photography model to obtain at least one independent model.

[0060] Optionally, the target oblique photography model is vertically cut according to the vertical projection outer contour corresponding to at least one model block to obtain at least one independent model. For details, please refer to the above embodiments, which will not be repeated here.

[0061] Furthermore, to avoid cutting directly onto the model surface and causing model loss, in one optional implementation, the target oblique photography model is cut according to the outer contour corresponding to at least one model block to obtain at least one independent model. This includes: expanding the outer contour corresponding to at least one model block, the expansion distance of which can be set according to actual needs and is not specifically limited here; and cutting the target oblique photography model according to the expanded outer contour of each model block to obtain at least one independent model.

[0062] In this embodiment, based on terrain data, all triangular faces within a certain height range above the ground surface are deleted, thus avoiding the influence of ground information on the individual model. Furthermore, when cutting individual models based on their outer contours, the outer contours are extended to prevent cutting directly onto the model surface and causing model loss.

[0063] Figure 3This is a flowchart of the oblique photography model individualization method according to the third embodiment of this application. This embodiment is an optimization based on the above embodiment. See [link to flowchart]. Figure 3 The method includes:

[0064] S301. Obtain the target oblique photogrammetry model to be processed, and the terrain data corresponding to the target oblique photogrammetry model.

[0065] S302. Based on the terrain data, the target oblique photography model is divided into at least one model block.

[0066] S303. Obtain the outer contour corresponding to at least one model block through projection technology.

[0067] S304. For any model block, generate a first-class rectangular border corresponding to the outer contour based on the vertex position of the outer contour.

[0068] S305. Determine whether the width of the first type of rectangular border is less than the preset width threshold. If so, discard the model block and its corresponding outer contour.

[0069] The oblique photogrammetry model, after removing the road surface, is divided into multiple model blocks. Each block may contain buildings, tall trees, poles, towers, etc. The top view of each model block can be projected onto the bottom plane, and the outer contour information of each block is obtained through contour recognition. Since some model blocks (such as those including poles or billboards) are not required by the user, these blocks need to be deleted in advance and do not require further processing. Specifically, for the outer contour of any model block, a first-type rectangular border is generated based on the vertex position of the outer contour. The first-type rectangular border is the smallest bounding rectangle of the outer contour. Since the width of the first-type rectangular border corresponding to the outer contour of model blocks including poles or billboards is small, a width threshold can be set in advance. If the width of the first-type rectangular border is determined to be less than the preset width threshold, the model block and its corresponding outer contour are discarded.

[0070] S306. Based on the outer contour corresponding to at least one model block, cut the target oblique photography model to obtain at least one independent model.

[0071] In this embodiment, some unnecessary model blocks and their corresponding outer contours can be discarded by comparing the width of the outer rectangle of the model block's outer contour with a preset width threshold, thereby reducing the number of outer contours and thus reducing the number of independent models extracted subsequently, thereby improving the efficiency of oblique photogrammetry model individualization.

[0072] Figure 4 is a flowchart of the oblique photogrammetry model individualization method according to the fourth embodiment of this application. This embodiment is an optimization based on the above embodiments. Referring to Figure 4, the method includes:

[0073] S401. Obtain the target oblique photogrammetry model to be processed, and the terrain data corresponding to the target oblique photogrammetry model.

[0074] S402. Based on the terrain data, the target oblique photography model is divided into at least one model block.

[0075] S403. Obtain the outer contour corresponding to at least one model block through projection technology.

[0076] S404. For any model block, generate a first-class rectangular border corresponding to the outer contour based on the vertex position of the outer contour.

[0077] S405. Determine whether the width of the first type of rectangular border is less than the preset width threshold. If so, discard the model block and its corresponding outer contour.

[0078] S406. Based on the outer contour corresponding to at least one model block, cut the target oblique photography model to obtain at least one independent model.

[0079] At least one independent model includes both building models and non-building models. Examples of non-building models include models of tall trees or iron towers. Depending on the actual needs, building models may be selected from at least one independent model, optionally according to S407-S408.

[0080] S407. For any independent model, obtain the side view projection outline of the independent model in at least two directions.

[0081] Optionally, for any independent model, a side view projection (i.e., horizontal projection) can be performed on the independent model in at least two directions, such as a horizontal projection in front of the independent model and a horizontal projection on the right or left side of the independent model, to obtain the side view projection outline in at least two directions.

[0082] S408. Determine whether the independent model is a building model based on the outer contour projected from the side view.

[0083] Since the horizontal projections of building models are all rectangles, building models can be identified by judging whether their outer contours are approximately rectangular. Therefore, in one optional implementation, determining whether an independent model is a building model based on the side view projection outer contour includes: determining a preset number of vertices on the side view projection outer contour, and generating a second type of rectangular border corresponding to the side view projection outer contour based on the preset number of vertices, wherein the second type of rectangular border refers to the smallest bounding rectangle determined based on the preset number of vertices on the side view projection outer contour; determining the area difference between the area enclosed by the second type of rectangular border and the area enclosed by the side view projection outer contour, and if the area difference is less than a preset area threshold, then the independent model is determined to be a building model.

[0084] For example, see Figure 4b The diagram illustrates the effect of generating a second type of rectangular border corresponding to the side view projection outline based on a preset number of vertices. The preset number of vertices is 10. Border 1 is the side view projection outline, and border 2 is the second type of rectangular border corresponding to the side view projection outline. If the area difference between the areas enclosed by border 1 and border 2 is less than a preset area threshold, then the independent model corresponding to border 1 is determined to be a building model.

[0085] Furthermore, to improve comparison efficiency, a comparison model can be pre-trained based on the aforementioned comparison method. During training, a large number of building, tree, pole, or tower model outlines are used as training samples, with building outlines as positive samples and others as negative samples. The model's training parameters are the preset number of outline vertices and area thresholds. Specifically, the training samples can be sequentially input into the comparison model, and the preset number of vertices and area thresholds can be continuously adjusted based on the comparison results output by the model until training is complete. Subsequently, the side view projection outline can be directly input into the comparison model, and the output of the comparison model can quickly determine whether an independent model is a building model.

[0086] Furthermore, if an independent model is a tree, but the trees within the independent model are connected, making the side view projection outline of the independent model approximately rectangular, and the area difference between this outline and the second type of rectangular border is less than the area threshold, the independent model may be incorrectly identified as a building model. Therefore, to avoid this situation, for independent models identified as building models, the following verification method can be used: Obtain the side view projection outline of the independent model and the corresponding convex hull outline, where the convex hull outline is the convex polygon with the smallest area enclosing the side view projection outline, and a convex polygon is a polygon without any concave points; calculate the convex defects of the side view projection outline and the convex hull outline, and verify the accuracy of the independent model being a building model based on these convex defects, where the convex defect refers to the distance between the concave point of the side view projection outline and the convex hull outline.

[0087] Furthermore, the side view projection outline includes at least one recessed point; correspondingly, verifying whether the independent model is accurately a building model based on the protruding defects includes: adding the protruding defects at at least one recessed point; if the accumulated value of the protruding defects is greater than a defect threshold, then it is determined that the independent model is not a building model. For example, see... Figure 4c It shows the rendering of the outer contour of the side view projection and the corresponding convex hull contour. The outer contour of the vertically filled area is the outer contour of the side view projection, which includes four recessed points A, B, C, and D. Figure 4c The outermost contour is the convex hull contour corresponding to the outer contour of the side view projection. h1 is equal to the distance from the concave point A to the convex hull contour, that is, h1 is the protruding defect at the concave point A. Similarly, h2 is the protruding defect at the concave point B, h3 is the protruding defect at the concave point C, and h4 is the protruding defect at the concave point D. If the sum of h1, h2, h3 and h4 is greater than the defect threshold, then the independent model is determined to be not a building model.

[0088] Furthermore, the identified building models can be stored in a database so that during subsequent manual inspections, if trees or towers that were mistakenly identified as building models are found, their contours can be extracted as training samples. This allows for further training of the comparison model based on the new samples. In other words, adjusting the set parameters of the number of vertices and the area threshold will make the trained comparison model more accurate.

[0089] In this embodiment of the application, the purpose of accurately identifying the required building model from at least one independent model can be achieved by using an approximate outline to approximate a rectangle and by calculating protrusion defects.

[0090] Figure 5 This is a schematic diagram of the oblique photogrammetry model individualization device according to the fifth embodiment of this application. This embodiment is applicable to situations where oblique photogrammetry models imported into a map engine are individualized by electronic devices such as servers. See also... Figure 5 The device includes:

[0091] The model acquisition module 501 is used to acquire the target oblique photogrammetry model to be processed, and the terrain data corresponding to the target oblique photogrammetry model;

[0092] The first segmentation module 502 is used to segment the target oblique photography model into at least one model block based on terrain data.

[0093] The first outer contour acquisition module 503 is used to acquire the outer contour of at least one model block through projection technology.

[0094] The second segmentation module 504 is used to cut the target oblique photography model according to the outer contour corresponding to at least one model block to obtain at least one independent model.

[0095] Based on the above embodiments, optionally, the first segmentation module includes:

[0096] The first segmentation unit is used to delete the triangular faces below a preset height value in the target oblique photography model based on terrain data, so as to obtain at least one model block.

[0097] Based on the above embodiments, optionally, the first segmentation unit includes:

[0098] The surface generation sub-unit is used to generate elevation surfaces based on the elevation data included in the terrain data.

[0099] The height comparison subunit is used to raise the elevation surface by a preset height value and compare the height of the raised elevation surface with the target oblique photogrammetry model.

[0100] The delete sub-unit is used to delete the triangular faces in the target oblique photography model whose height is lower than the height of the elevation surface after lifting, so as to obtain at least one model block.

[0101] Based on the above embodiments, optionally, the first outer contour acquisition module is specifically used for:

[0102] Perform vertical projection processing on at least one model block, and determine the vertical projection outer contour corresponding to at least one model block based on the projection result.

[0103] Correspondingly, the second segmentation module is also used for:

[0104] Based on the vertical projection outer contour corresponding to at least one model block, the target oblique photography model is vertically cut to obtain at least one independent model.

[0105] Optionally, based on the above embodiments, the second segmentation module is further configured to:

[0106] Expand the outer contour corresponding to at least one model block;

[0107] Based on the outer contour of the expanded model block, the target oblique photography model is cut to obtain at least one independent model.

[0108] Based on the above embodiments, the apparatus may optionally further include:

[0109] The border generation module is used to generate a first type of rectangular border corresponding to the outer contour of any model block after obtaining the outer contour corresponding to at least one model block, based on the vertex position of the outer contour.

[0110] The discard module is used to determine whether the width of the first type of rectangular border is less than a preset width threshold. If so, the model block and its corresponding outer contour are discarded.

[0111] Based on the above embodiments, the apparatus may optionally further include:

[0112] The second outer contour acquisition module is used to acquire the side view projection outer contour of any independent model in at least two directions.

[0113] The judgment module is used to determine whether an independent model is a building model based on the outer contour projected from the side view.

[0114] Based on the above embodiments, optionally, the determination module is used for:

[0115] A preset number of vertices are determined on the outer contour of the side view projection, and a second type of rectangular border corresponding to the outer contour of the side view projection is generated based on the preset number of vertices.

[0116] Determine the area difference between the area enclosed by the second type of rectangular border and the area enclosed by the outer contour of the side view projection. If the area difference is less than the preset area threshold, then the independent model is determined to be a building model.

[0117] Based on the above embodiments, the apparatus may optionally further include:

[0118] The acquisition module is used to acquire the side view projection outline and the corresponding convex hull outline of the independent model after determining that the independent model is a building model. The convex hull outline refers to the convex polygon with the smallest area that encloses the side view projection outline.

[0119] The verification module is used to calculate the protrusion defects of the outer contour and convex hull contour of the side view projection, and to verify whether the independent model is an accurate building model based on the protrusion defects; where the protrusion defect refers to the distance between the concave point of the outer contour of the side view projection and the convex hull contour.

[0120] Based on the above embodiments, optionally, the outer contour of the side view projection includes at least one recessed point;

[0121] Correspondingly, the verification module is also used for:

[0122] Add up the protruding defects at at least one depression point. If the cumulative value of the protruding defects is greater than the defect threshold, then the independent model is determined not to be a building model.

[0123] The oblique photogrammetry model individualization device provided in this application embodiment can execute the oblique photogrammetry model individualization method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of the method execution.

[0124] Figure 6 This is a schematic diagram of the structure of an electronic device provided in the sixth embodiment of this application. Figure 6 The structure shown in this application embodiment includes an electronic device comprising one or more processors 602 and a memory 601; the processors 602 in this electronic device may be one or more. Figure 6 Taking a processor 602 as an example; memory 601 is used to store one or more programs; the one or more programs are executed by the one or more processors 602, so that the one or more processors 602 implement the oblique photogrammetry model individualization method as described in any one of the embodiments of this application.

[0125] The electronic device may also include an input device 603 and an output device 604.

[0126] The processor 602, memory 601, input device 603, and output device 604 in this electronic device can be connected via a bus or other means. Figure 6 Taking the example of a connection between China and Israel via a bus.

[0127] The memory 601 in this electronic device serves as a computer-readable storage medium, capable of storing one or more programs. These programs can be software programs, computer-executable programs, or modules, such as the program instructions / modules corresponding to the application control method provided in this embodiment. The processor 602 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 601, thereby implementing the oblique photography model individualization method described in the above method embodiments.

[0128] Memory 601 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device. Furthermore, memory 601 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, memory 601 may further include memory remotely located relative to processor 602, which can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0129] Input device 603 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the electronic device. Output device 604 may include display devices such as a display screen.

[0130] Furthermore, when one or more programs included in the aforementioned electronic device are executed by one or more processors 602, the programs perform the following operations:

[0131] Acquire the target oblique photogrammetry model to be processed, and the corresponding terrain data of the target oblique photogrammetry model;

[0132] Based on the terrain data, the target oblique photogrammetry model is divided into at least one model block;

[0133] At least one model block's outer contour is obtained using projection technology;

[0134] Based on the outer contour corresponding to at least one model block, the target oblique photography model is cut to obtain at least one independent model.

[0135] Of course, those skilled in the art will understand that when one or more programs included in the above-mentioned electronic device are executed by one or more processors 602, the programs can also perform related operations in the application control method provided in any embodiment of this application.

[0136] One embodiment of this application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, performs a method for isolating oblique photogrammetry models, the method comprising:

[0137] Acquire the target oblique photogrammetry model to be processed, and the corresponding terrain data of the target oblique photogrammetry model;

[0138] Based on the terrain data, the target oblique photogrammetry model is divided into at least one model block;

[0139] At least one model block's outer contour is obtained using projection technology;

[0140] Based on the outer contour corresponding to at least one model block, the target oblique photography model is cut to obtain at least one independent model.

[0141] Optionally, when executed by a processor, the program can also be used to perform the methods provided in any embodiment of this application.

[0142] The computer storage medium in this application embodiment can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be—but is not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable CD-ROM, optical storage device, magnetic storage device, or any suitable combination thereof. The computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0143] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit programs for use by or in connection with an instruction execution system, apparatus, or device.

[0144] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, radio frequency (RF), etc., or any suitable combination thereof.

[0145] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (e.g., including local area networks (LANs) or wide area networks (WANs)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0146] Note that the above are merely preferred embodiments and the technical principles employed in this application. Those skilled in the art will understand that this application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the appended claims.

Claims

1. A method of monomerizing a tilt photography model, characterized by, The method comprises: acquiring a target oblique photography model to be processed and terrain data corresponding to the target oblique photography model; generating an elevation surface according to elevation data included in the terrain data; lifting the elevation surface by a preset height value, and comparing the lifted elevation surface with the target oblique photography model in height; deleting triangular faces in the target oblique photography model that are lower in height than the lifted elevation surface to obtain at least one model block, the model block not including ground data; acquiring an outer contour corresponding to the at least one model block through projection technology; cutting the target oblique photography model according to the outer contour corresponding to the at least one model block to obtain at least one independent model, the independent model having ground information and including a building model and a non-building model; after obtaining the at least one independent model, the method further comprises: for any independent model, acquiring a side view projection contour of the independent model in at least two directions; determining a preset number of vertices on the side view projection contour, and generating a second type of rectangular frame corresponding to the side view projection contour according to the preset number of vertices; determining an area difference value between an area of the second type of rectangular frame and an area of the side view projection contour, and determining that the independent model is a building model if the area difference value is less than a preset area threshold.

2. The method of claim 1, wherein, acquiring the outer contour corresponding to the at least one model block through projection technology comprises: performing vertical projection processing on the at least one model block, and determining a vertical projection contour corresponding to the at least one model block according to a projection result; correspondingly, cutting the target oblique photography model according to the outer contour corresponding to the at least one model block to obtain the at least one independent model comprises: performing vertical cutting on the target oblique photography model according to the vertical projection contour corresponding to the at least one model block to obtain the at least one independent model.

3. The method of claim 1, wherein, cutting the target oblique photography model according to the outer contour corresponding to the at least one model block to obtain the at least one independent model comprises: extending the outer contour corresponding to the at least one model block; cutting the target oblique photography model according to the outer contour of the extended model block to obtain the at least one independent model.

4. The method of claim 1, wherein, after acquiring the outer contour corresponding to the at least one model block, the method further comprises: for the outer contour corresponding to any model block, generating a first type of rectangular frame corresponding to the outer contour according to a vertex position of the outer contour; determining whether a width of the first type of rectangular frame is less than a preset width threshold, and discarding the model block and the outer contour corresponding to the model block if the width is less than the preset width threshold.

5. The method of claim 1, wherein, after determining that the independent model is a building model, the method further comprises: acquiring a side view projection contour of the independent model and a convex hull contour corresponding to the side view projection contour, wherein the convex hull contour refers to a convex polygon with a minimum area that encloses the side view projection contour; Calculate a convex defect of the side view projection outer contour and the convex hull contour, and verify whether the independent model is an accurate building model according to the convex defect; wherein the convex defect refers to a distance between a concave point of the side view projection outer contour and the convex hull contour.

6. The method of claim 5, wherein, Wherein, The side view projection outer contour comprises at least one concave point; Correspondingly, verifying whether the independent model is an accurate building model according to the convex defect comprises: Adding the convex defects at the at least one concave point, and if an accumulated value of the convex defects is greater than a defect threshold value, determining that the independent model is not a building model.

7. A tilt photography model individualization apparatus characterized by comprising: Comprise: A model acquisition module, configured to acquire a target oblique photography model to be processed and terrain data corresponding to the target oblique photography model; A first segmentation module, comprising a first segmentation unit, The first segmentation unit comprises: A curved surface generation subunit, configured to generate an elevation curved surface according to elevation data included in the terrain data; A height comparison subunit, configured to lift the elevation curved surface by a preset height value, and compare heights of the lifted elevation curved surface and the target oblique photography model; A deletion subunit, configured to delete a triangular face in the target oblique photography model whose height is lower than a height of the lifted elevation curved surface, to obtain at least one model block, wherein the model block does not include ground data; An outer contour acquisition module, configured to acquire an outer contour corresponding to the at least one model block by using a projection technology; A second segmentation module, configured to cut the target oblique photography model according to the outer contour corresponding to the at least one model block, to obtain at least one independent model, wherein the independent model has ground information and comprises a building model and a non-building model; The device further comprises: A second outer contour acquisition module, configured to acquire side view projection outer contours of an independent model in at least two directions for any independent model; A judgment module, configured to determine a preset number of vertices on the side view projection outer contour, and generate a second type of rectangular frame corresponding to the side view projection outer contour according to the preset number of vertices; determine an area difference value between an area of the second type of rectangular frame and an area of the side view projection outer contour, and if the area difference value is less than a preset area threshold value, determine that the independent model is a building model.

8. An electronic device, comprising: Comprise: One or more processors; A storage device, configured to store one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the oblique photography model monomerization method according to any one of claims 1-6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the oblique photography model monomerization method according to any one of claims 1-6.

Images