Method and system for generating three-dimensional building with embossment based on unmanned aerial vehicle

Abstract

The invention discloses an unmanned aerial vehicle-based three-dimensional building generation method and system with an embossment, and relates to the technical field of data processing, and the method comprises the steps: obtaining a building image, which is collected by an unmanned aerial vehicle and is related to a target building, and generating a corresponding basic point cloud model according to the building image; determining a target area with an embossment on the target building, and determining an arrangement area and corresponding position information of the embossment; determining a compensation acquisition route of the unmanned aerial vehicle according to a preset rule, the arrangement area of the embossment, the corresponding position information and the target area, and controlling the unmanned aerial vehicle to perform image acquisition on the target area according to the compensation acquisition route to obtain a compensation image; and generating a corresponding compensation point cloud model according to the compensation image, and fusing the basic point cloud model and the compensation point cloud model to obtain a three-dimensional model of the target building. The problem that in the prior art, the accuracy is low when three-dimensional models of three-dimensional buildings with embossments are generated is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for generating a three-dimensional building with relief based on an unmanned aerial vehicle. Background Art

[0002] At present, many buildings use sculptures or reliefs to express the image of people or depict some historical scenes. These sculptures not only increase the artistic sense of the building, but also convey a spirit through visual language.

[0003] However, the building often does not follow the traditional regular geometric form, but adopts a more free and symbolic design, such as slopes, curves, asymmetric structures, etc. This makes it difficult to directly apply the traditional 3D reconstruction method based on regular geometry. The complex details of the building (such as carvings, decorations, etc.) and the irregular form make it more difficult to capture accurate architectural details. As a result, the accuracy of the generated 3D model is low. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method and system for generating a three-dimensional building with relief based on a drone, aiming to solve the problem of low accuracy in the prior art when generating a three-dimensional model of a three-dimensional building with relief.

[0005] An object of the present invention is to provide a method for generating a three-dimensional building with relief based on a drone, the method comprising: Acquire a building image of a target building collected by a drone, and generate a corresponding basic point cloud model according to the building image; Determine a target area on the target building where a relief is provided, and determine a layout area and corresponding position information of the relief; Determine the compensation acquisition route of the drone according to the arrangement area of ​​the relief and the corresponding position information and the target area according to a preset rule, and control the drone to acquire an image of the target area according to the compensation acquisition route to obtain a compensation image; A corresponding compensation point cloud model is generated according to the compensation image, and the basic point cloud model and the compensation point cloud model are fused to obtain a three-dimensional model of the target building.

[0006] Furthermore, in the above-mentioned method for generating a three-dimensional building with relief based on a drone, the step of determining the compensation acquisition route of the drone according to the arrangement area and corresponding position information of the relief and the target area according to a preset rule comprises: Obtaining the center points of the target area and the layout area respectively, and obtaining a reference point for determining the viewpoint of the drone according to the center points; A reference line perpendicular to the surface of the target area is extended outward from the reference point, and the field of view width or field of view height of the drone is determined according to a preset rule according to either the length or the width of the layout area; Determine the vertical distance between the drone and the target area according to the field of view width or field of view height of the drone and the focal length of the drone camera, and determine the first viewpoint of the drone according to the vertical distance and the reference line; The first viewpoint is translated along the target area in a longitudinal and transverse interval so that the field of view of the drone covers the target area and the overlap between each different field of view is within a preset range to obtain the remaining viewpoints; A compensation acquisition route of the UAV is determined according to the first viewpoint and the remaining viewpoints. Furthermore, in the above-mentioned method for generating a three-dimensional building with relief based on a drone, the step of obtaining a reference point for determining the viewpoint of the drone according to the center point comprises: When the center points of the target area and the layout area coincide, any center point is used as the reference point; When the center points of the target area and the layout area do not coincide, a line connecting the two center points is obtained and a midpoint of the line connecting the two center points is used as the reference point.

[0007] Furthermore, in the above-mentioned method for generating a three-dimensional building with relief based on a drone, the calculation formula of the vertical distance is: ; in, FOV is the UAV’s field of view width or field of view height, f is the focal length of the drone camera, S is the width or height of the corresponding drone's camera sensor.

[0008] Furthermore, in the above-mentioned method for generating a three-dimensional building with relief based on a drone, the step of determining the field of view width or field of view height of the drone according to a preset rule according to any one of the length or width of the layout area comprises: respectively obtaining the area sizes of the target area and the layout area, determining the ratio of the area of ​​the target area to the area of ​​the layout area, and determining the corresponding adjustment factor according to the ratio; The length or width of the arrangement area is adjusted according to the adjustment factor to obtain the field of view width or field of view height of the UAV.

[0009] Furthermore, in the above-mentioned method for generating a three-dimensional building with relief based on a drone, the steps of determining a target area on the target building where the relief is provided, and determining the arrangement area and corresponding position information of the relief include: Determine a building surface on which a relief is provided on the target building, obtain coordinates of outer boundary points of the building surface, and determine the target area according to a rectangular area enclosed by the coordinates of the outer boundary points; The coordinate information of the outer boundary points of the relief is obtained, and the layout area of ​​the relief and the corresponding position information are determined according to the rectangular area enclosed by the coordinate information of the outer boundary points.

[0010] Furthermore, in the above-mentioned method for generating a three-dimensional building with relief based on a drone, the step of fusing the basic point cloud model and the compensation point cloud model to obtain the three-dimensional model of the target building comprises: The feature points of the basic point cloud model and the compensation point cloud model are respectively extracted using an ISS feature point detection algorithm, and the feature points are described using a 3DSC algorithm; The SAC-IA algorithm is used to roughly align the feature points, and then the ICP algorithm is used to precisely align the feature points to obtain the fused target point cloud model. The target point cloud model is processed by triangulation and texture mapping in sequence to obtain a three-dimensional model of the target building.

[0011] Another object of the present invention is to provide a drone-based three-dimensional building generation system with relief, the system comprising: The acquisition module is used to obtain the building image of the target building collected by the drone, and generate a corresponding basic point cloud model according to the building image; A determination module, used to determine a target area on the target building where a relief is provided, and to determine a layout area and corresponding position information of the relief; A control module, used to determine a compensation acquisition route of the drone according to a layout area of ​​the relief and corresponding position information and a target area according to a preset rule, and control the drone to acquire an image of the target area according to the compensation acquisition route to obtain a compensation image; The fusion module is used to generate a corresponding compensation point cloud model according to the compensation image, and fuse the basic point cloud model and the compensation point cloud model to obtain a three-dimensional model of the target building.

[0012] Another object of the present invention is to provide a readable storage medium having a computer program stored thereon, wherein the program implements the steps of the above method when executed by a processor.

[0013] Another object of the present invention is to provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above method when executing the program.

[0014] The present invention obtains the building image of the target building collected by the drone, generates the corresponding basic point cloud model according to the building image; determines the target area with relief on the target building, and determines the layout area and corresponding position information of the relief; determines the compensation collection route of the drone according to the layout area and corresponding position information of the relief and the target area according to the preset rules, controls the drone to collect images of the target area according to the compensation collection route to obtain the compensation image; generates the corresponding compensation point cloud model according to the compensation image, and fuses the basic point cloud model and the compensation point cloud model to obtain the three-dimensional model of the target building. First, the target building is preliminarily collected to generate the basic point cloud model, and then the compensation collection route is used to collect the specific details of the relief to generate the compensation point cloud model, and the two are fused to obtain the final three-dimensional model. The problem of low accuracy in generating three-dimensional models of three-dimensional buildings with reliefs in the prior art is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a method for generating a three-dimensional building with relief based on a drone in the first embodiment of the present invention; Figure 2 This is a structural block diagram of a drone-based three-dimensional building generation system with relief in the third embodiment of the present invention.

[0016] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0017] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0018] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0020] Embodiment 1 See also Figure 1 , shown is a method for generating a three-dimensional building with relief based on a drone in the first embodiment of the present invention, the method comprising steps S10 to S13.

[0021] Step S10, obtaining a building image of the target building collected by the drone, and generating a corresponding basic point cloud model according to the building image.

[0022] Among them, the overall situation of the target building is firstly collected to obtain a basic building image. Generally, a large number of building images with a certain degree of overlap will be collected, so that the corresponding basic point cloud model can be generated according to the building image. For example, in order to capture the overall situation of the target building, a large amount of image data can be collected by controlling the drone at the top or in the inclined direction of the target building, and the initial point cloud model can be generated using the collected image data. Specifically, after a large number of images are collected, the point cloud model can be generated by dense image matching, by extracting feature points in the image, and finding corresponding relationships in different images through these feature points. By comparing these feature points, the relative position and posture of the camera can be inferred, and the algorithm is used to estimate the movement trajectory and position of the camera by analyzing images from different angles. This process will generate a preliminary three-dimensional point cloud and the camera position corresponding to each image. From the matching information between the camera and the image, a sparse point cloud model can be reconstructed to represent the key points in the scene, and then a multi-view stereo reconstruction algorithm (MVS) is used to further extract more pixels from the image based on the preliminary generated sparse point cloud to generate a denser point cloud. For example, image matching is achieved based on current image matching algorithms such as SIFT, SURF, and ORB. Therefore, how to generate a corresponding point cloud model based on a building image is understandable to those skilled in the art and will not be elaborated here.

[0023] Step S11, determining a target area where a relief is provided on the target building, and determining a layout area and corresponding position information of the relief.

[0024] Among them, when collecting images of buildings with reliefs, in order to obtain the overall situation of the target building, the distance of drone collection is relatively far, which makes it impossible to accurately collect the fine details of the relief area. Therefore, it is necessary to obtain the features of the relief area more finely. Specifically, the target area with reliefs on the target building and the layout area and position information of the reliefs are determined, wherein the target area refers to an area of ​​a building surface on the target building where the reliefs are arranged, and the layout area is the specific area occupied by the relief on the building surface. For example, the building surface with reliefs on the target building can be determined first, and the outer boundary point coordinates of the building surface can be obtained. The target area is determined according to the rectangular area enclosed by the coordinates of the outer boundary points; and the layout area is determined by obtaining the coordinate information of the outer boundary points of the relief, and determining the layout area of ​​the relief and the corresponding position information according to the rectangular area enclosed by the coordinate information of the outer boundary points, wherein the coordinates (position information) of the outer boundary points can be obtained by manual measurement or by a positioning device. In specific implementation, the target area, the layout area and the corresponding position information can be obtained according to the generated basic point cloud model, or by separately collecting an image of a certain face of the target building with the relief, and determining the target area, the layout area and the corresponding position information according to image recognition.

[0025] Step S12, determining the compensation acquisition route of the drone according to the layout area of ​​the relief and the corresponding position information and the target area according to a preset rule, and controlling the drone to acquire an image of the target area according to the compensation acquisition route to obtain a compensated image.

[0026] Specifically, in order to capture the relief in more detail, the compensation acquisition route of the UAV is determined according to the layout area of ​​the relief and the target area, and the UAV is controlled to capture the target area according to the compensation acquisition route to obtain a compensated image, wherein the compensation acquisition route is generally opposite to the layout area of ​​the relief and can capture a clearer relief image.

[0027] Step S13, generating a corresponding compensation point cloud model according to the compensation image, and fusing the basic point cloud model and the compensation point cloud model to obtain a three-dimensional model of the target building.

[0028] Among them, in order to enable the basic point cloud model and the compensation point cloud model to be perfectly integrated, in the embodiment of the present invention, a method combining coarse alignment and fine alignment is adopted. First, a coarse alignment is performed to make the basic point cloud model and the compensation point cloud model have a better initial position. After the coarse alignment, the positions of the two building point clouds are basically consistent, which reduces the complexity of the subsequent similarity calculation of the alignment points. Finally, a fine alignment is performed to obtain the corresponding fused target point cloud model. For example, the ISS feature point detection algorithm can be used to extract the feature points of the basic point cloud model and the compensation point cloud model respectively, and the 3DSC algorithm can be used to describe the feature points; the SAC-IA algorithm is used to perform coarse alignment of the feature points, and then the ICP algorithm is used to perform fine alignment to obtain the fused target point cloud model.

[0029] Furthermore, the target point cloud model is processed by triangulation and texture mapping in turn to obtain a three-dimensional model of the target building. Specifically, buildings can be composed of irregular triangular meshes. After the fusion process in the previous step, a high-density point cloud will be formed, and these point clouds can form multiple triangular meshes. After the point cloud data is used to construct a triangular mesh, a large number of irregular triangular networks will be generated, but they can only reflect the surface morphology of the building and cannot accurately identify the color, appearance and other features of the building. Therefore, texture mapping technology is needed to supplement the color and appearance of the building on the three-dimensional mesh to obtain the final three-dimensional model.

[0030] In summary, a method for generating a three-dimensional building with relief based on a drone in the above-mentioned embodiment of the present invention generates a corresponding basic point cloud model according to the building image by acquiring a building image of a target building collected by a drone; determining a target area with relief on the target building, and determining the layout area and corresponding position information of the relief; determining the compensation acquisition route of the drone according to the layout area and corresponding position information of the relief and the target area according to a preset rule, and controlling the drone to perform image acquisition on the target area according to the compensation acquisition route to obtain a compensation image; generating a corresponding compensation point cloud model according to the compensation image, and fusing the basic point cloud model and the compensation point cloud model to obtain a three-dimensional model of the target building. First, a preliminary image acquisition is performed on the target building to generate a basic point cloud model, and then the compensation acquisition route is used to collect the specific detail information of the relief in a targeted manner to generate a compensation point cloud model, and the two are fused to obtain the final three-dimensional model. The problem of low accuracy in generating three-dimensional models of three-dimensional buildings with reliefs in the prior art is solved.

[0031] Embodiment 2 This embodiment also proposes a method for generating a three-dimensional building with relief based on a drone. The difference between the method for generating a three-dimensional building with relief based on a drone in this embodiment and the method for generating a three-dimensional building with relief based on a drone in the first embodiment is that: The step of determining the compensation acquisition route of the drone according to the arrangement area of ​​the relief and the corresponding position information and the target area according to the preset rules includes: Obtaining the center points of the target area and the layout area respectively, and obtaining a reference point for determining the viewpoint of the drone according to the center points; A reference line perpendicular to the surface of the target area is extended outward from the reference point, and the field of view width or field of view height of the drone is determined according to a preset rule according to either the length or the width of the layout area; Determine the vertical distance between the drone and the target area according to the field of view width or field of view height of the drone and the focal length of the drone camera, and determine the first viewpoint of the drone according to the vertical distance and the reference line; The remaining viewpoints are obtained according to the translation of the first viewpoint along the target area in a longitudinal and transverse interval so that the field of view of the drone covers the target area and the overlap between each different field of view is within a preset range; A compensation acquisition route of the UAV is determined according to the first viewpoint and the remaining viewpoints. The viewpoint is the position where the drone collects the compensation image. Specifically, the center point of the target area and the layout area is obtained to determine the reference point of the drone viewpoint, so as to ensure that the collected compensation image can obtain high-quality detail information. In the specific implementation, when the center point of the target area and the layout area coincide, any center point is used as the reference point; when the center point of the target area and the rectangular area does not coincide, the line connecting the two center points is obtained and the midpoint of the line connecting the two center points is used as the reference point. Determining the reference point means determining the location information of the drone shooting, and then combining the distance information of the drone from the building, a viewpoint can be determined. Specifically, the reference line of the drone viewpoint is determined by the reference point, and the width or height of the drone's field of view is determined. The vertical distance information of the drone from the building is determined according to the width or height of the field of view, so as to obtain the first viewpoint on the reference line.

[0032] Exemplarily, the vertical distance is calculated as: ; in, FOV is the UAV’s field of view width or field of view height, f is the focal length of the drone camera, S is the width or height of the corresponding drone's camera sensor.

[0033] Among them, the field of view width or field of view height of the drone can be set according to the actual situation. In addition, in some preferred embodiments of the present invention, in order to further improve the accuracy of the obtained compensation image, the field of view width or field of view height of the drone can be determined according to any one of the length or width of the layout area. Since the fine features of the relief are to be obtained, the field of view width or field of view height of the drone can be determined according to the length or width of the layout area, thereby ensuring that the drone can capture more accurate fine features of the relief. For example, the field of view width or field of view height of the drone is obtained by reducing the length or width of the layout area according to a preset ratio. In addition, the camera's field of view width or field of view height can also be determined based on the current sizes of the target area and the layout area. Specifically, the area sizes of the target area and the layout area are obtained, and the corresponding adjustment factor is determined based on the area ratio. The length or width of the layout area is reduced and adjusted based on the adjustment factor to obtain the corresponding field of view width and field of view height, or the field of view width and field of view height obtained in advance by the length or width of the layout area are adjusted based on the adjustment factor. Among them, the adjustment factor can establish a mapping table of corresponding area ratios and adjustment factors based on empirical values ​​or big data analysis, so as to find the corresponding adjustment factor according to the mapping table. The purpose of this is to ensure that the field of view area matches the layout area, and to ensure that the compensated image obtains more detailed technical features as much as possible.

[0034] After obtaining the first viewpoint, the viewpoint can be used as a reference point to determine the remaining viewpoints. Specifically, the first viewpoint is translated at intervals in the horizontal and vertical directions, that is, translated at intervals in the horizontal and vertical directions along the target area, to ensure that the overlap between the compensated image captured after the translation and the previous compensated image is within a preset range, until the target area is completely photographed, thereby obtaining multiple different viewpoints. The compensation collection route of the drone is determined based on these viewpoints, wherein the collection route can be determined by connecting lines in the order in which the viewpoints are determined, or after all the viewpoints are determined, the compensation collection route can be determined by connecting lines in sequence from the upper left corner of the target area.

[0035] In summary, a method for generating a three-dimensional building with relief based on a drone in the above-mentioned embodiment of the present invention generates a corresponding basic point cloud model according to the building image by acquiring a building image of a target building collected by a drone; determining a target area with relief on the target building, and determining the layout area and corresponding position information of the relief; determining the compensation acquisition route of the drone according to the layout area and corresponding position information of the relief and the target area according to a preset rule, and controlling the drone to perform image acquisition on the target area according to the compensation acquisition route to obtain a compensation image; generating a corresponding compensation point cloud model according to the compensation image, and fusing the basic point cloud model and the compensation point cloud model to obtain a three-dimensional model of the target building. First, a preliminary image acquisition is performed on the target building to generate a basic point cloud model, and then the compensation acquisition route is used to collect the specific detail information of the relief in a targeted manner to generate a compensation point cloud model, and the two are fused to obtain the final three-dimensional model. The problem of low accuracy in generating three-dimensional models of three-dimensional buildings with reliefs in the prior art is solved.

[0036] Embodiment 3 See also Figure 2 , shown is a drone-based three-dimensional building generation system with relief proposed in the third embodiment of the present invention, the system comprising: The acquisition module 100 is used to acquire the building image of the target building acquired by the drone, and generate a corresponding basic point cloud model according to the building image; The determination module 200 is used to determine the target area where the relief is provided on the target building, and determine the arrangement area of ​​the relief and the corresponding position information; The control module 300 is used to determine the compensation acquisition route of the drone according to the arrangement area of ​​the relief and the corresponding position information and the target area according to a preset rule, and control the drone to acquire an image of the target area according to the compensation acquisition route to obtain a compensated image; The fusion module 400 is used to generate a corresponding compensated point cloud model according to the compensated image, and fuse the basic point cloud model and the compensated point cloud model to obtain a three-dimensional model of the target building.

[0037] Furthermore, in the above-mentioned drone-based three-dimensional building generation system with relief, the step of determining the compensation acquisition route of the drone according to the arrangement area and corresponding position information of the relief and the target area according to a preset rule comprises: Obtaining the center points of the target area and the layout area respectively, and obtaining a reference point for determining the viewpoint of the drone according to the center points; A reference line perpendicular to the surface of the target area is extended outward from the reference point, and the field of view width or field of view height of the drone is determined according to a preset rule according to either the length or the width of the layout area; Determine the vertical distance between the drone and the target area according to the field of view width or field of view height of the drone and the focal length of the drone camera, and determine the first viewpoint of the drone according to the vertical distance and the reference line; The first viewpoint is translated along the target area in a longitudinal and transverse interval so that the field of view of the drone covers the target area and the overlap between each different field of view is within a preset range to obtain the remaining viewpoints; A compensation acquisition route of the UAV is determined according to the first viewpoint and the remaining viewpoints. Furthermore, in the above-mentioned drone-based three-dimensional building generation system with relief, the step of acquiring a reference point for determining the viewpoint of the drone according to the center point comprises: When the center points of the target area and the layout area coincide, any center point is used as the reference point; When the center points of the target area and the layout area do not coincide, a line connecting the two center points is obtained and a midpoint of the line connecting the two center points is used as the reference point.

[0038] Furthermore, in the above-mentioned drone-based three-dimensional building generation system with relief, the calculation formula of the vertical distance is: ; in, FOV is the UAV’s field of view width or field of view height, f is the focal length of the drone camera, S is the width or height of the corresponding drone's camera sensor.

[0039] Furthermore, in the above-mentioned drone-based three-dimensional building generation system with relief, the step of determining the field of view width or field of view height of the drone according to a preset rule according to any one of the length or width of the layout area comprises: respectively obtaining the area sizes of the target area and the layout area, determining the ratio of the area of ​​the target area to the area of ​​the layout area, and determining the corresponding adjustment factor according to the ratio; The length or width of the arrangement area is adjusted according to the adjustment factor to obtain the field of view width or field of view height of the UAV.

[0040] Furthermore, in the above-mentioned drone-based three-dimensional building generation system with relief, the steps of determining a target area on the target building where the relief is provided, and determining a layout area of ​​the relief and corresponding position information include: Determine a building surface on which a relief is provided on the target building, obtain coordinates of outer boundary points of the building surface, and determine the target area according to a rectangular area enclosed by the coordinates of the outer boundary points; Acquire coordinate information of outer boundary points of the relief, and determine the layout area of ​​the relief and corresponding position information according to a rectangular area enclosed by the coordinate information of the outer boundary points; Furthermore, in the above-mentioned drone-based three-dimensional building generation system with relief, the step of fusing the basic point cloud model and the compensation point cloud model to obtain the three-dimensional model of the target building includes: The feature points of the basic point cloud model and the compensation point cloud model are respectively extracted using an ISS feature point detection algorithm, and the feature points are described using a 3DSC algorithm; The SAC-IA algorithm is used to roughly align the feature points, and then the ICP algorithm is used to precisely align the feature points to obtain the fused target point cloud model. The target point cloud model is processed by triangulation and texture mapping in sequence to obtain a three-dimensional model of the target building.

[0041] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments, and will not be repeated here.

[0042] Embodiment 4 Another aspect of the present invention further provides a readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps of the method described in any one of the above-mentioned embodiments 1 to 2 are implemented.

[0043] Embodiment 5 Another aspect of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the program, the steps of the method described in any one of the above-mentioned embodiments 1 to 2 are implemented.

[0044] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0045] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable storage medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable storage medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0046] More specific examples (a non-exhaustive list) of computer-readable storage media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable storage medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0047] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0048] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0049] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for generating a three-dimensional building with relief based on a drone, characterized in that: The method comprises: Acquire a building image of a target building collected by a drone, and generate a corresponding basic point cloud model according to the building image; Determine a target area on the target building where a relief is provided, and determine a layout area and corresponding position information of the relief; Determine the compensation acquisition route of the drone according to the arrangement area of ​​the relief and the corresponding position information and the target area according to a preset rule, and control the drone to acquire an image of the target area according to the compensation acquisition route to obtain a compensation image; Generate a corresponding compensation point cloud model according to the compensation image, and fuse the basic point cloud model and the compensation point cloud model to obtain a three-dimensional model of the target building; The step of determining the compensation acquisition route of the drone according to the arrangement area of ​​the relief and the corresponding position information and the target area according to the preset rules includes: Obtaining the center points of the target area and the layout area respectively, and obtaining a reference point for determining the viewpoint of the drone according to the center points; A reference line perpendicular to the surface of the target area is extended outward from the reference point, and the field of view width or field of view height of the drone is determined according to a preset rule according to either the length or the width of the layout area; Determine the vertical distance between the drone and the target area according to the field of view width or field of view height of the drone and the focal length of the drone camera, and determine the first viewpoint of the drone according to the vertical distance and the reference line; The first viewpoint is translated along the target area in a longitudinal and transverse interval so that the field of view of the drone covers the target area and the overlap between each different field of view is within a preset range to obtain the remaining viewpoints; A compensation acquisition route of the UAV is determined according to the first viewpoint and the remaining viewpoints.

2. The method for generating a three-dimensional building with relief based on a drone according to claim 1, characterized in that: The step of obtaining a reference point for determining the viewpoint of the drone according to the center point comprises: When the center points of the target area and the layout area coincide, any center point is used as the reference point; When the center points of the target area and the layout area do not coincide, a line connecting the two center points is obtained and a midpoint of the line connecting the two center points is used as the reference point.

3. The method for generating a three-dimensional building with relief based on a drone according to claim 1, characterized in that: The calculation formula of the vertical distance is: ； in, FOV is the UAV’s field of view width or field of view height, f is the focal length of the drone camera, S is the width or height of the corresponding drone's camera sensor.

4. The method for generating a three-dimensional building with relief based on a drone according to claim 1, characterized in that: The step of determining the vision width or the vision height of the drone according to any one of the length or the width of the arrangement area according to a preset rule comprises: respectively obtaining the area sizes of the target area and the layout area, determining the ratio of the area of ​​the target area to the area of ​​the layout area, and determining the corresponding adjustment factor according to the ratio; The length or width of the arrangement area is adjusted according to the adjustment factor to obtain the field of view width or field of view height of the UAV.

5. The method for generating a three-dimensional building with relief based on a drone according to claim 1, characterized in that: The step of determining a target area on the target building where a relief is provided, and determining a layout area and corresponding position information of the relief comprises: Determine a building surface on which a relief is provided on the target building, obtain coordinates of outer boundary points of the building surface, and determine the target area according to a rectangular area enclosed by the coordinates of the outer boundary points; The coordinate information of the outer boundary points of the relief is obtained, and the layout area of ​​the relief and the corresponding position information are determined according to the rectangular area enclosed by the coordinate information of the outer boundary points.

6. The method for generating a three-dimensional building with relief based on a drone according to claim 1, characterized in that: The step of fusing the basic point cloud model and the compensation point cloud model to obtain the three-dimensional model of the target building comprises: The feature points of the basic point cloud model and the compensation point cloud model are respectively extracted using an ISS feature point detection algorithm, and the feature points are described using a 3DSC algorithm; The SAC-IA algorithm is used to roughly align the feature points, and then the ICP algorithm is used to precisely align the feature points to obtain the fused target point cloud model. The target point cloud model is processed by triangulation and texture mapping in sequence to obtain a three-dimensional model of the target building.

7. A three-dimensional building generation system with relief based on drone, characterized in that: A method for generating a three-dimensional building with relief based on a drone according to any one of claims 1 to 6, the system comprising: The acquisition module is used to obtain the building image of the target building collected by the drone, and generate a corresponding basic point cloud model according to the building image; A determination module, used to determine a target area on the target building where a relief is provided, and to determine a layout area and corresponding position information of the relief; A control module, used to determine a compensation acquisition route of the drone according to a layout area of ​​the relief and corresponding position information and a target area according to a preset rule, and control the drone to acquire an image of the target area according to the compensation acquisition route to obtain a compensation image; The fusion module is used to generate a corresponding compensation point cloud model according to the compensation image, and fuse the basic point cloud model and the compensation point cloud model to obtain a three-dimensional model of the target building.

8. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 6 when executing the program.

Images