A method and system for generating a building model for photovoltaic system installation

Abstract

The application discloses a kind of photovoltaic system installation building model generation method and system.Therein, the method includes: determining the two-dimensional map data of the map area where the target building is located, wherein the two-dimensional map data includes the position of the target building;Control aircraft to collect the three-dimensional data of target building, wherein acquisition device is arranged on the aircraft, and the acquisition device is used to collect three-dimensional data, and the three-dimensional data is the geometric data of the outer surface of the target building;According to three-dimensional data, generate the three-dimensional point cloud of target building, wherein the three-dimensional point cloud is the three-dimensional point cloud of the outer surface of the target building;According to the three-dimensional point cloud of building, based on the two-dimensional map data of the target building, establish the three-dimensional building model of building.The application solves the technical problems of low efficiency and low accuracy in the prior art of generating building model only according to two-dimensional map information and building parameters.

Description

Technical Field

[0001] This invention relates to the field of building information, and more specifically, to a method and system for generating building models for photovoltaic system installation. Background Technology

[0002] Building-integrated photovoltaics (BIPV) refers to the installation of solar photovoltaic arrays on the exterior surface of a building's envelope to provide electricity. The integration of photovoltaic arrays with buildings is a common form. Since the integration of photovoltaic arrays with buildings does not occupy additional ground space, it is the best installation method for the widespread application of photovoltaic power generation systems in cities. In particular, before integrating photovoltaic arrays with buildings, it is necessary to fully study issues such as building height, sunlight hours, and shading between buildings. Creating a three-dimensional model of the building can easily achieve these objectives. However, in related technologies, when creating 3D building models, the buildings are simply constructed as square prisms based on their length, width, and height data. This results in the loss of many details in the building model, making it difficult to identify and containing significant errors. In the construction field, there are methods to create internal building models based on actual building data, but the specific building parameters need to be obtained from design parameters or measured manually. However, this is not suitable for creating external surface models of buildings used in building-integrated photovoltaics (BIPV), and it is difficult to achieve ideal results when there are many buildings over a wide area. Currently, no effective solution has been proposed to address this technical problem. Summary of the Invention

[0003] This invention provides a method and apparatus for collecting building information and generating building models using an aircraft, thereby at least solving the technical problems of low efficiency and low accuracy in the prior art where building models are generated solely based on two-dimensional map information and building parameters.

[0004] According to one aspect of the present invention, a method for generating a building model for photovoltaic system installation is provided, comprising: determining two-dimensional map data of a map area where a target building is located, wherein the two-dimensional map data includes the location of the target building; controlling an aircraft to collect three-dimensional data of the target building, wherein the aircraft is equipped with a data acquisition device for collecting the three-dimensional data, the three-dimensional data being geometric data of the outer surface of the target building; generating a three-dimensional point cloud of the target building based on the three-dimensional data, wherein the three-dimensional point cloud is a three-dimensional point cloud of the outer surface of the target building; and establishing a three-dimensional building model of the building based on the three-dimensional point cloud of the building and the two-dimensional map data of the target building.

[0005] Optionally, controlling the aircraft to collect 3D data of the target building includes: determining a collection route for the aircraft to collect data of the target building based on the 2D map data, wherein the target building includes one or more individual buildings, and the collection route is a route for completely collecting the side views of the target building based on a 2D plane; determining the collection altitude of the aircraft based on the collection range of the collection device on the aircraft; controlling the aircraft to traverse the collection route at the collection altitude and collect 3D data of the target building through the collection device; determining whether the 3D data of the target building at the height has been completely collected after the aircraft has completed collecting data according to the collection route; and adjusting the collection altitude of the aircraft and continuing to collect data according to the collection route until the 3D data of the target building has been completely collected if the 3D data of the target building at the height has not been completely collected.

[0006] Optionally, generating a 3D point cloud of the target building based on the 3D data includes: establishing a 3D coordinate system based on the 2D map data; establishing 3D point cloud data of the target building in the 3D coordinate system based on the collected 3D data; and filtering the 3D point cloud data to remove outliers, thereby obtaining the processed 3D point cloud.

[0007] Optionally, establishing a 3D building model of the target building based on the 3D point cloud of the building and the 2D map data of the target building includes: performing a first segmentation on the 3D point cloud, deleting the 3D point cloud portion of the 2D ground in the 3D point cloud, and retaining the 3D point cloud of the target building; performing principal component analysis on the 3D point cloud of the target building to obtain the building point cloud of the target building; performing a second segmentation on the building point cloud to obtain building point clouds of multiple parts of the outer surface of the target building, wherein the multiple parts of the outer surface include planes, curved surfaces, straight lines, and curves; clustering the building point clouds of the multiple parts respectively to obtain multiple part models of the outer surface of the target building; determining the relative positional relationship between the multiple parts based on the 3D coordinates of the building point clouds of the multiple parts; and establishing a 3D building model of the target building based on the multiple part models and the relative positional relationship of the multiple parts.

[0008] Optionally, before clustering the point clouds of multiple parts of the building to obtain multiple part models of the outer surface of the target building, the method further includes: determining whether there are adjacent buildings of the target building using the two-dimensional map data; if there are adjacent buildings of the target building, collecting adjacent three-dimensional data of the adjacent buildings and generating adjacent three-dimensional point clouds; determining the intersection line between the adjacent buildings and the target building based on the adjacent three-dimensional point clouds and the three-dimensional point cloud of the target building, wherein the intersection line and the ground form an adjacent interface; generating an adjacent interface model based on the point cloud of the intersection line and determining the relative positional relationship between the adjacent interface and the target building; establishing a three-dimensional building model of the target building based on multiple part models and the relative positional relationship of the multiple parts includes: establishing a three-dimensional building model of the target building based on multiple part models, the relative positional relationship of the multiple parts, the adjacent interface model, and the relative positional relationship between the adjacent interface and the target building.

[0009] Optionally, the acquisition device is an image acquisition device. Controlling the aircraft to traverse the acquisition route at the acquisition altitude and acquiring 3D data of the target building through the acquisition device includes: controlling the image acquisition device to acquire depth images of the target building from multiple angles at a preset acquisition frequency while the aircraft traverses the acquisition route at the acquisition altitude; and generating 3D data of the building from the multiple depth images. Alternatively, the acquisition device is a ranging device. Controlling the aircraft to traverse the acquisition route at the acquisition altitude and acquiring 3D data of the target building through the acquisition device includes: controlling the ranging device to detect the distance between the building and the aircraft in real time while the aircraft traverses the acquisition route at the acquisition altitude; and generating 3D data of the building based on the aircraft's position on the acquisition route, the aircraft's acquisition altitude, and the real-time distance between the building and the aircraft.

[0010] Optionally, when the acquisition device is an image acquisition device, after establishing a three-dimensional building model of the target building based on multiple partial models and the relative positional relationships of the multiple parts, the method further includes: identifying the contour of the target building in the depth image acquired by the image acquisition device by recognizing the model, wherein the contour includes an outer contour and a boundary line; determining the construction line at the angle corresponding to the three-dimensional building model and the depth image; verifying the generated three-dimensional building model by comparing the contour with the construction line; determining that the three-dimensional building model is unqualified if the similarity between the contour and the construction line does not reach a preset threshold; correcting the construction line according to the contour; and repeatedly verifying and correcting the three-dimensional building model using multiple depth images.

[0011] According to another aspect of the present invention, a building model generation system for photovoltaic system installation is provided, comprising: a determining module, configured to determine two-dimensional map data of a map area where a target building is located, wherein the two-dimensional map data includes the location of the target building; a control module, configured to control an aircraft to collect three-dimensional data of the target building, wherein the aircraft is equipped with a data acquisition device for collecting the three-dimensional data, the three-dimensional data being geometric data of the outer surface of the target building; a generating module, configured to generate a three-dimensional point cloud of the target building based on the three-dimensional data, wherein the three-dimensional point cloud is a three-dimensional point cloud of the outer surface of the target building; and a building module, configured to build a three-dimensional building model of the building based on the three-dimensional point cloud of the building and the two-dimensional map data of the target building.

[0012] According to another aspect of the present invention, a computer storage medium is provided, the computer storage medium storing program instructions, wherein, when the program instructions are executed, the device where the computer storage medium is located controls the execution of any one of the methods described above.

[0013] According to another aspect of the present invention, a processor is provided for running a program, wherein the program, when running, performs the method described in any of the above embodiments.

[0014] In this embodiment of the invention, two-dimensional map data of a map area determining the location of a target building is used, wherein the two-dimensional map data includes the location of the target building; a controlled aircraft is used to collect three-dimensional data of the target building, wherein the aircraft is equipped with a data acquisition device for collecting three-dimensional data, the three-dimensional data being the geometric data of the outer surface of the target building; a three-dimensional point cloud of the target building is generated based on the three-dimensional data, wherein the three-dimensional point cloud is the three-dimensional point cloud of the outer surface of the target building; and a three-dimensional building model of the building is established based on the three-dimensional point cloud of the building and the two-dimensional map data of the target building. By collecting the three-dimensional data of the target building by the aircraft and establishing a three-dimensional building model based on the two-dimensional map data and the three-dimensional data, the purpose of automatically and effectively collecting the three-dimensional data of the target building is achieved, thereby improving the technical effect of improving the efficiency and accuracy of establishing the three-dimensional building model of the target building. This solves the technical problems of low efficiency and low accuracy in the existing technology of generating building models based only on two-dimensional map information and building parameters. In addition, based on the established three-dimensional building model, it is also possible to conveniently study the building height, lighting time, and shading between buildings, thereby helping to realize the integration of photovoltaic arrays with buildings. Attached Figure Description

[0015] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings: Figure 1 This is a flowchart of a method for generating a building model for photovoltaic system installation according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a building model generation system for photovoltaic system installation according to an embodiment of the present invention. Detailed Implementation

[0016] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0017] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0018] According to an embodiment of the present invention, an embodiment of a method for generating a building model for photovoltaic system installation is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0019] Figure 1 This is a flowchart of a method for generating a building model for photovoltaic system installation according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps: Step S101: Determine the two-dimensional map data of the map area where the target building is located, wherein the two-dimensional map data includes the location of the target building; Step S102: Control the aircraft to collect three-dimensional data of the target building. The aircraft is equipped with a data acquisition device for collecting three-dimensional data, which is the geometric data of the outer surface of the target building. Step S103: Generate a three-dimensional point cloud of the target building based on the three-dimensional data, wherein the three-dimensional point cloud is the three-dimensional point cloud of the outer surface of the target building; Step S104: Based on the three-dimensional point cloud of the building and the two-dimensional map data of the target building, establish a three-dimensional building model of the building.

[0020] Through the above steps, a two-dimensional map data of the map area where the target building is located is used, where the two-dimensional map data includes the location of the target building; a controlled aircraft is used to collect three-dimensional data of the target building, where the aircraft is equipped with a data acquisition device for collecting three-dimensional data, which is the geometric data of the outer surface of the target building; a three-dimensional point cloud of the target building is generated based on the three-dimensional data, where the three-dimensional point cloud is the three-dimensional point cloud of the outer surface of the target building; and a three-dimensional building model of the building is established based on the three-dimensional point cloud of the building and the two-dimensional map data of the target building. By collecting the three-dimensional data of the target building by the aircraft and establishing a three-dimensional building model based on the two-dimensional map data and the three-dimensional data, the purpose of automatically and effectively collecting the three-dimensional data of the target building is achieved. This improves the efficiency and accuracy of establishing the three-dimensional building model of the target building, and solves the technical problems of low efficiency and low accuracy in the existing technology of generating building models based only on two-dimensional map information and building parameters.

[0021] The aforementioned aircraft can be a drone or other controllable flight device. It can carry a data acquisition device to collect three-dimensional data of the target building, including its shape and dimensions. The aircraft is connected to a computer terminal, which can be a mobile computer, tablet, or smartphone. The data acquisition device on the aircraft transmits the collected data to the computer terminal in real time via a communication link between the aircraft and the computer terminal. Alternatively, the data acquisition device can transmit the collected data to the computer terminal via a communication relay device. The data acquisition device communicates wirelessly with the communication relay device, while the communication relay device communicates wiredly with the computer terminal, thereby improving the reliability of communication between the data acquisition device and the computer terminal.

[0022] The target building can be a single building, multiple single buildings, or a group of buildings within a region. The two-dimensional map data of the map area determining the location of the target building can be obtained through map software or generated using GPS technology. This two-dimensional map data determines the actual distribution of the target building, and based on this distribution, the aircraft can determine the route for collecting the three-dimensional data of the target building. This allows for automatic and efficient collection of the target building's three-dimensional data, improving the efficiency of building a three-dimensional model of the target building.

[0023] The aforementioned two-dimensional maps include the location of the target building and the surrounding terrain, including topography, ground slope, and ground features such as roads, walkways, vegetation, and trees. When using a drone carrying data collection equipment to collect data from the target building, the interference of terrain conditions on the data collection process must be considered. For example, if there are trees on the ground, the drone should not be allowed to collect data behind the trees, as this will create obstructions and render the collected data invalid. The impact of trees on data collection should be considered and eliminated when determining the data collection route.

[0024] Once the data acquisition path of the aircraft is determined, the aforementioned control system allows the aircraft to acquire 3D data of the target building. This path enables the aircraft to be controlled for data acquisition without human intervention. Control of the aircraft, including linear movement and angular rotation, is based solely on the acquisition path, greatly avoiding the inefficiencies and inaccuracies associated with manual operation. This solves the inefficiency problem of related technologies that rely solely on 2D map information and building parameters to generate building models.

[0025] The aforementioned acquisition device can be an image acquisition device, which determines the three-dimensional data of the target building, including its shape and size, by acquiring depth images of the target building. Alternatively, the acquisition device can be a ranging device, which determines the three-dimensional data of the target building by determining the position of the aircraft and the distance between the acquired target building and the aircraft.

[0026] The aforementioned method of generating a 3D point cloud of a target building from 3D data can be achieved using existing techniques for creating 3D point clouds. Since the 3D data is actually data of the target building's outer surface, the generated 3D point cloud only represents the outer surface and does not include the building's internal structure. Based on this outer surface point cloud, a building model of the target building can be constructed, ensuring that the appearance of the 3D building model matches the appearance of the target building. This solves the accuracy problem of methods that generate building models solely based on 2D map information and building parameters, which suffer from low accuracy.

[0027] Based on the aforementioned 3D point cloud and the 2D map data of the target building, a 3D building model can be built on the 2D map to generate a 3D map. This 3D map not only retains the features of the 2D map but also allows users to view the specific appearance and condition of the building by rotating the viewpoint. For users, this allows for more detailed and accurate comparisons based on the 3D map and the actual situation, greatly improving the user experience.

[0028] Optionally, controlling the aircraft to collect 3D data of the target building includes: determining the collection route for the aircraft to collect the target building based on 2D map data, wherein the target building includes one or more individual buildings, and the collection route is a route for completely collecting the side views of the target building based on a 2D plane; determining the collection altitude of the aircraft based on the collection range of the collection device on the aircraft; controlling the aircraft to traverse the collection route at the collection altitude and collect 3D data of the target building through the collection device; after the aircraft has completed collecting data according to the collection route, determining whether the 3D data of the target building at the height has been completely collected; if the 3D data of the target building at the height has not been completely collected, adjusting the collection altitude of the aircraft and continuing to collect data according to the collection route until the 3D data of the target building has been completely collected.

[0029] Based on 2D map data, the data collection route for the aircraft to collect data on the target building is determined. This route can be a path on the 2D plane that ensures the aircraft can completely collect data on the target building, regardless of altitude. For example, if the building is rectangular on the 2D map, the collection route can be a path that follows the outline of the target building's projection on the 2D map. This ensures that the data collection device onboard the aircraft can effectively collect 3D data of the target building's sides.

[0030] Since the data acquisition route is on a two-dimensional plane, and considering the varying heights of different buildings and the limited acquisition range of the acquisition device on the aircraft, the aircraft's flight altitude will first be determined based on the acquisition range of the acquisition device. Specifically, the acquisition range of the acquisition device can be a circular acquisition range with the maximum acquisition distance as its radius. In this case, the maximum acquisition distance will be used as the aircraft's flight altitude, thereby ensuring that the aircraft gradually acquires the three-dimensional data of the target building from low to high.

[0031] After the flight altitude is determined, the control aircraft traverses the acquisition route at the acquisition altitude, keeping the aircraft's flight altitude constant. The aircraft is guided by the acquisition route and automatically controlled to fly along the acquisition route, acquiring three-dimensional data of the target building through the acquisition device.

[0032] It should be noted that the aforementioned aircraft can also be equipped with a collision avoidance device. This device can detect the presence of obstacles within a certain range around the aircraft in real time. If it is determined that the aircraft will collide with an obstacle while following the data collection route, it will first bypass the obstacle and then continue collecting data along the path. This allows for flexible adjustments based on actual conditions, preventing unexpected situations from occurring during actual operation that could lead to data collection failure or even equipment damage.

[0033] After the aircraft completes the data collection along the collection route, it is determined whether the three-dimensional data of the target building in terms of height has been completely collected. If the three-dimensional data of the target building in terms of height has been collected, it means that the height of the target building is lower than the collection range of the collection device. The three-dimensional data of the target building is collected by the aircraft traversing the collection route.

[0034] If the 3D data of the target building at its height has not been fully acquired, it indicates that the target building's height is higher than the range of the acquisition device. The aircraft's traversal of the acquisition route has not resulted in the acquisition of all the target building's 3D data. The aircraft's acquisition altitude needs to be adjusted, and acquisition should continue along the acquisition route until the target building's 3D data is fully acquired. This ensures complete acquisition of the target building's 3D data, further improving the accuracy of the target building's modeling.

[0035] Optionally, generating a 3D point cloud of the target building based on 3D data includes: establishing a 3D coordinate system based on 2D map data; establishing 3D point cloud data of the target building in the 3D coordinate system based on the collected 3D data; and filtering the 3D point cloud data to remove outliers and obtain the processed 3D point cloud.

[0036] Filtering 3D point cloud data removes outliers, resulting in a processed 3D point cloud. This process improves the accuracy of the 3D point cloud, thereby enhancing the accuracy of generating 3D building models from it and facilitating subsequent data processing.

[0037] Optionally, based on the 3D point cloud of the building and the 2D map data of the target building, a 3D building model is established, including: performing a first segmentation on the 3D point cloud, deleting the 3D point cloud portion of the 2D ground in the 3D point cloud, and retaining the 3D point cloud of the target building; performing principal component analysis on the 3D point cloud of the target building to obtain the building point cloud of the target building; performing a second segmentation on the building point cloud to obtain building point clouds of multiple parts of the outer surface of the target building, wherein the multiple parts of the outer surface include planes, curved surfaces, straight lines, and curves; clustering the building point clouds of the multiple parts respectively to obtain multiple part models of the outer surface of the target building; determining the relative positional relationship between the multiple parts based on the 3D coordinates of the building point clouds of the multiple parts; and establishing a 3D building model of the target building based on the multiple part models and the relative positional relationship of the multiple parts.

[0038] The aforementioned 3D point cloud was determined by the aircraft collecting 3D data of the target building. Therefore, the established 3D point cloud may include some ground building data. Therefore, the 3D point cloud is segmented to delete the 3D point cloud of the 2D ground and retain the 3D point cloud of the target building for subsequent processing.

[0039] Principal component analysis is performed on the 3D point cloud of the target building to obtain the building point cloud. This is equivalent to compressing and clustering the relatively scattered point cloud and simplifying the overly complex shape of the building surface. For example, the target building may have exterior panels, building waistlines, decorative structures, etc., especially decorative structures, such as load-bearing carvings. These details can be omitted to reduce data processing and occupy unnecessary system resources.

[0040] The building point cloud is segmented a second time to obtain point clouds of multiple parts of the target building's outer surface. These parts include planes, curved surfaces, straight lines, and curves, thus revealing the specific structure of the target building's surface. The point clouds of each part are then clustered to obtain multiple part models of the target building's outer surface. Based on the 3D point clouds of each part, the geometric surfaces of each part are determined. The relative positional relationships between the multiple parts are determined based on their 3D coordinates. Finally, a 3D building model of the target building is constructed based on these part models and their relative positional relationships. This effectively creates a 3D building model of the target building, preserving the building's geometric structure while simplifying specific details, making the 3D building model more easily recognizable by users.

[0041] Optionally, before clustering the point clouds of multiple parts of the building to obtain multiple part models of the outer surface of the target building, the method further includes: determining whether there are adjacent buildings to the target building using two-dimensional map data; if there are adjacent buildings to the target building, collecting adjacent three-dimensional data of the adjacent buildings and generating adjacent three-dimensional point clouds; determining the intersection line between the adjacent buildings and the target building based on the adjacent three-dimensional point clouds and the target building's three-dimensional point cloud, wherein the intersection line and the ground form an adjacent interface; generating an adjacent interface model based on the point cloud of the intersection line and determining the relative positional relationship between the adjacent interface and the target building; and establishing a three-dimensional building model of the target building based on multiple part models and the relative positional relationship of multiple parts, including: establishing a three-dimensional building model of the target building based on multiple part models, the relative positional relationship of multiple parts, the adjacent interface model, and the relative positional relationship between the adjacent interface and the target building.

[0042] In one scenario, the target building has adjacent buildings that share a common building surface. In this case, it's necessary to determine the geometric features of these adjacent buildings. Specifically, adjacent 3D data of the adjacent buildings is collected, and adjacent 3D point clouds are generated. Based on the adjacent 3D point clouds and the target building's 3D point cloud, the intersection line between the two buildings is determined, where the intersection line and the ground form the adjacent interface. Based on the point cloud of the intersection line, an adjacent interface model is generated. The adjacent interface model is then created using the same method as for the target building's 3D building model.

[0043] Then, based on the multiple component models, the relative positions of these components, and the adjacent interface models and their relative positions to the target building, a 3D building model of the target building is established. This avoids situations where the target building has adjacent buildings, leading to the inability to collect some 3D data and resulting in an incomplete or missing 3D building model.

[0044] Optionally, the acquisition device is an image acquisition device. The aircraft is controlled to traverse the acquisition route at the acquisition altitude. The acquisition device acquires three-dimensional data of the target building, including: while the aircraft traverses the acquisition route at the acquisition altitude, the image acquisition device is controlled to acquire depth images of the target building from multiple angles at a preset acquisition frequency; the three-dimensional data of the building is generated from the multiple depth images; and the three-dimensional data of the building is acquired by the image acquisition device for subsequent creation of a three-dimensional point cloud.

[0045] Alternatively, the data acquisition device can be a ranging device. The aircraft is controlled to traverse the acquisition route at the acquisition altitude. The acquisition of 3D data of the target building through this device includes: while the aircraft traverses the acquisition route at the acquisition altitude, the ranging device continuously monitors the distance between the building and the aircraft; based on the aircraft's position on the acquisition route, the acquisition altitude, and the real-time distance between the building and the aircraft, 3D data of the building is generated. This allows for the subsequent creation of a 3D point cloud.

[0046] Optionally, when the acquisition device is an image acquisition device, after establishing a three-dimensional building model of the target building based on multiple part models and their relative positional relationships, the method further includes: identifying the contour of the target building in the depth image acquired by the image acquisition device by recognizing the model, wherein the contour includes the outer contour and the boundary line; determining the construction line at the angle corresponding to the three-dimensional building model and the depth image; verifying the generated three-dimensional building model by comparing the contour and the construction line; determining that the three-dimensional building model is unqualified if the similarity between the contour and the construction line does not reach a preset threshold; correcting the construction line based on the contour; and repeatedly verifying and correcting the three-dimensional building model using multiple depth images.

[0047] After the image acquisition device acquires a depth image, this depth image can also be used to inspect the constructed 3D building model and determine whether the 3D building model is qualified. Specifically, the outline of the target building in the depth image acquired by the image acquisition device is identified by the model recognition device. The outline includes the outer contour and the boundary line. The construction lines of the 3D building model at the angle corresponding to the depth image are determined, which are the construction lines of the 3D building model at the acquisition viewpoint of the image acquisition device. This acquisition viewpoint is the viewpoint of the image acquisition device relative to the actual target building when acquiring the depth image.

[0048] The generated 3D building model is verified by comparing its contours with construction lines. If the similarity between the contours and construction lines reaches a preset threshold, the 3D building model is deemed acceptable; otherwise, it is deemed unacceptable. This method of verifying the 3D building model based on depth images improves its accuracy.

[0049] If the similarity between the contour and the construction lines does not reach a preset threshold, the 3D building model is determined to be unqualified; the construction lines are corrected based on the contour; the 3D building model is repeatedly checked and corrected through multiple depth images, thereby improving the accuracy of the 3D building model.

[0050] Figure 2 This is a schematic diagram of a building model generation system for photovoltaic system installation according to an embodiment of the present invention, such as... Figure 2 As shown, according to another aspect of the present invention, a building model generation system for photovoltaic system installation is provided, comprising: a determination module 21, a control module 22, a generation module 23, and a creation module 24. The system will now be described in detail.

[0051] The determination module 21 is used to determine the two-dimensional map data of the map area where the target building is located, wherein the two-dimensional map data includes the location of the target building; the control module 22, connected to the determination module 21, is used to control the aircraft to collect three-dimensional data of the target building, wherein the aircraft is equipped with a data acquisition device for collecting three-dimensional data, and the three-dimensional data is the geometric data of the outer surface of the target building; the generation module 23, connected to the control module 22, is used to generate a three-dimensional point cloud of the target building based on the three-dimensional data, wherein the three-dimensional point cloud is the three-dimensional point cloud of the outer surface of the target building; the establishment module 24, connected to the generation module 23, is used to establish a three-dimensional building model of the building based on the three-dimensional point cloud of the building and the two-dimensional map data of the target building.

[0052] The system employs two-dimensional map data of a map region to determine the location of a target building, including the building's position. It controls an aircraft equipped with a data acquisition device to collect three-dimensional data of the target building, specifically the geometric data of the building's outer surface. A three-dimensional point cloud of the target building is generated based on this data, again representing the building's outer surface. A three-dimensional building model is then constructed based on this point cloud and the two-dimensional map data. This method, using the aircraft to collect the target building's three-dimensional data and then building the model from the two-dimensional map data, achieves the goal of automatically and effectively acquiring the target building's three-dimensional data. This improves the efficiency and accuracy of building the three-dimensional model, solving the problems of low efficiency and accuracy inherent in existing methods that rely solely on two-dimensional map information and building parameters. Furthermore, the completed three-dimensional building model allows for convenient research into building height, sunlight exposure time, and shading between buildings, facilitating the integration of photovoltaic arrays with buildings.

[0053] According to another aspect of the present invention, a computer storage medium is provided, the computer storage medium storing program instructions, wherein, when the program instructions are executed, the device where the computer storage medium is located controls the execution of any one of the methods described above.

[0054] According to another aspect of the present invention, a processor is provided for running a program, wherein the program, when running, performs the method described in any of the above embodiments.

[0055] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0056] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0057] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0058] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0059] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0060] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0061] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for generating a building model for photovoltaic system installation, characterized in that, include: Two-dimensional map data of a map area that determines the location of a target building, wherein the two-dimensional map data includes the location of the target building; Based on the two-dimensional map data, the acquisition route of the aircraft to collect data on the target building is determined, and the aircraft is controlled to collect three-dimensional data of the target building. The aircraft is equipped with an acquisition device for collecting the three-dimensional data, which is the geometric data of the outer surface of the target building. A three-dimensional point cloud of the target building is generated based on the three-dimensional data, wherein the three-dimensional point cloud is the three-dimensional point cloud of the outer surface of the target building; Based on the 3D point cloud of the building and the 2D map data of the target building, establishing a 3D building model of the building includes: The three-dimensional point cloud is segmented once, and the three-dimensional point cloud of the two-dimensional ground is deleted, while the three-dimensional point cloud of the target building is retained. Principal component analysis is performed on the three-dimensional point cloud of the target building to obtain the building point cloud of the target building; The building point cloud is segmented in a secondary manner to obtain building point clouds of multiple parts of the outer surface of the target building, wherein the multiple parts of the outer surface include planes, curved surfaces, straight lines and curves; The two-dimensional map data is used to determine whether the target building has adjacent buildings. If the target building has adjacent buildings, collect the adjacent three-dimensional data of the adjacent buildings and generate adjacent three-dimensional point clouds; Based on the adjacent 3D point cloud and the target building's 3D point cloud, the intersection line between the adjacent building and the target building is determined, wherein the intersection line and the ground form an adjacent interface; Based on the point cloud of the intersection line, generate an adjacent interface model and determine the relative positional relationship between the adjacent interface and the target building; Clustering is performed on the point clouds of multiple parts of the building to obtain multiple part models of the outer surface of the target building; The relative positional relationships between multiple parts are determined based on the three-dimensional coordinates of the building point cloud of multiple parts. Based on the multiple component models and their relative positional relationships, the three-dimensional building model of the target building is established as follows: Based on the multiple part models, the relative positional relationships of the multiple parts, and the adjacent interface models, the relative positional relationships between the adjacent interfaces and the target building, a three-dimensional building model of the target building is established.

2. The method of claim 1, wherein, The control of the aircraft to acquire three-dimensional data of the target building includes: The target building includes one or more individual buildings, and the acquisition route is a route for fully acquiring the side views of the target building based on a two-dimensional plane; The sampling altitude of the aircraft is determined based on the sampling range of the sampling device on the aircraft; The aircraft is controlled to traverse the acquisition route at the acquisition altitude, and the acquisition device is used to acquire three-dimensional data of the target building. After the aircraft has completed collecting data according to the collection route, determine whether the three-dimensional data of the target building in terms of height has been completely collected; If the three-dimensional data of the target building at its height has not been collected, the aircraft's collection altitude is adjusted, and the collection continues along the collection route until the three-dimensional data of the target building is collected.

3. The method of claim 2, wherein, Generating a 3D point cloud of the target building based on the 3D data includes: A three-dimensional coordinate system is established based on the aforementioned two-dimensional map data; In the three-dimensional coordinate system, based on the collected three-dimensional data, three-dimensional point cloud data of the target building is established; The three-dimensional point cloud data is filtered to remove outliers, resulting in the processed three-dimensional point cloud.

4. The method according to claim 3, characterized in that, The acquisition device is an image acquisition device. Controlling the aircraft to traverse the acquisition route at the acquisition altitude, the acquisition device acquires three-dimensional data of the target building, including: When the aircraft traverses the acquisition route at the acquisition altitude, the image acquisition device is controlled to acquire depth images of the target building from multiple angles at a preset acquisition frequency. Three-dimensional data of the building is generated using multiple depth images; Alternatively, the acquisition device is a ranging device, controlling the aircraft to traverse the acquisition route at the acquisition altitude, and acquiring the three-dimensional data of the target building through the acquisition device includes: When the aircraft traverses the data collection route at the data collection altitude, the ranging device is controlled to detect the distance between the building and the aircraft in real time. Based on the location of the aircraft in the data collection route, the data collection altitude of the aircraft, and the real-time distance between the building and the aircraft, three-dimensional data of the building is generated.

5. The method according to claim 4, characterized in that, When the acquisition device is an image acquisition device, after establishing a three-dimensional building model of the target building based on multiple part models and the relative positional relationships of the multiple parts, the method further includes: The outline of the target building in the depth image acquired by the image acquisition device is identified by the recognition model, wherein the outline includes an outer outline and a boundary line; Determine the construction lines at the angles corresponding to the 3D building model and the depth image; The generated three-dimensional building model is verified by comparing the outline with the construction lines. If the similarity between the outline and the construction line does not reach a preset threshold, the three-dimensional building model is determined to be unqualified. The construction lines are modified according to the outline; The three-dimensional building model is repeatedly checked and corrected using multiple depth images.

6. A building model generation system for photovoltaic system installation, characterized in that, The method for generating a building model for photovoltaic system installation according to any one of claims 1-5 includes: A determination module is used to determine the two-dimensional map data of the map area where the target building is located, wherein the two-dimensional map data includes the location of the target building; A control module is used to control the aircraft to collect three-dimensional data of the target building. The aircraft is equipped with a data acquisition device, which is used to collect the three-dimensional data, which is the geometric data of the outer surface of the target building. A generation module is used to generate a three-dimensional point cloud of the target building based on the three-dimensional data, wherein the three-dimensional point cloud is a three-dimensional point cloud of the outer surface of the target building; A module is used to build a three-dimensional building model of the target building based on the three-dimensional point cloud of the building and the two-dimensional map data of the target building.

7. A computer storage medium, characterized in that, The computer storage medium stores program instructions, wherein when the program instructions are executed, they control the device where the computer storage medium is located to perform the method described in any one of claims 1 to 5.

Images