Method and system for interacting with rendering entity on three-dimensional streetscape map

Abstract

The invention provides a method and system for interacting with a rendering entity on a three-dimensional streetscape map, and the method comprises the steps: determining the three-dimensional boundary of each building in the three-dimensional streetscape map, and recognizing each complete building; acquiring information of the building in real time, and endowing the information to the identified corresponding building; and according to the required target result, obtaining a target building and / or corresponding building information in the three-dimensional streetscape map, and completing interaction with the rendering entity on the three-dimensional streetscape map. According to the invention, the information is endowed to the NeRF model, so that the user can interact with the entity building on the three-dimensional streetscape map to obtain real-time information, the problem that the three-dimensional streetscape map does not have a function of interacting with the rendering entity is solved, the user can know the building information in the map anytime and anywhere, and the user experience is enhanced; the problem that information is not fed back in time is solved, real-time information feedback and processing have high timeliness, and the functions of the map are greatly enriched.

Description

Technical Field

[0001] The present invention relates to the field of real-scene three-dimensional technology, and in particular to a method and system for interacting with a rendering entity on a three-dimensional street view map, as well as a corresponding computer terminal and a computer-readable storage medium. Background Art

[0002] 3D real scene is one of the important development directions in recent years. It is a digital space that reacts and expresses human production, life and ecological space in a real, three-dimensional and time-sequential manner within a certain range, so as to build an immersive user experience. It is also an important core technology for realizing concepts such as metaverse and digital twin. 3D street view map is one of the important applications of real scene 3D. Compared with traditional 2D maps, it is more accurate and greatly enhances the user experience and immersion. However, the current 3D street view maps such as Google Street View Map and Baidu Street View Map do not have map interaction functions, and the interaction methods of 3D maps and 2D maps are quite different. Therefore, it is necessary to study and develop a method for interacting with rendering entities on 3D maps, so that users can understand the situation and information of each building on the map in real time.

[0003] After searching, we found:

[0004] The Chinese invention patent application "Interactive map and progress bar graphical user interface for computers" with application number CN202030776159.9 discloses a map user interface for display and interaction, including: displaying the value of the content displayed on the map interface at the corresponding time point; displaying the map display range of the selected area; selecting the items displayed on the map interface. Its focus is on the processing and interaction of two-dimensional maps. The current three-dimensional street view map does not have this function. Since three-dimensional maps need to be rendered and the borders of each building are displayed, this technology cannot be applied to three-dimensional maps.

[0005] At present, no description or report of similar technology to the present invention has been found, and similar information at home and abroad has not been collected yet. Summary of the invention

[0006] In view of the above-mentioned deficiencies in the prior art, the present invention provides a method and system for interacting with a rendering entity on a three-dimensional street view map, and also provides a corresponding computer terminal and a computer-readable storage medium.

[0007] According to one aspect of the present invention, a method for interacting with a rendered entity on a three-dimensional street view map is provided, comprising:

[0008] Determine the 3D boundaries of each building in the 3D street view map, and then identify each complete building;

[0009] Acquire building information in real time and assign it to the corresponding identified buildings;

[0010] According to the desired target result, the target building and / or the corresponding building information in the three-dimensional street view map is obtained, and the interaction with the rendering entity on the three-dimensional street view map is completed.

[0011] Preferably, determining the three-dimensional boundary of each building in the three-dimensional street view map, and then identifying each complete building, includes:

[0012] Perform semantic segmentation on 3D street view maps;

[0013] Based on the result of the semantic segmentation, distinguish the building from the surrounding environment;

[0014] Based on the results of the differentiation, the building boundaries are selected and each complete building is identified.

[0015] Preferably, the three-dimensional street view map is semantically segmented, including:

[0016] NeRF rendering of 3D street view maps using Instant-NGP software;

[0017] Label each part of the rendered image;

[0018] Based on the labels, entities of the three-dimensional street view map are determined through semantic segmentation.

[0019] Preferably, the distinguishing the building from the surrounding environment based on the result of the semantic segmentation includes:

[0020] Determine the rendered entity through the results of semantic segmentation;

[0021] For buildings with regular shapes, the coordinates of the building boundaries are input to distinguish between the building and the surrounding environment. For buildings with irregular shapes, the difference in color between the ground and the building is used to compare the RGB values ​​of the part of the building close to the ground with the ground to determine the boundary between the ground and the building, thereby completing the distinction between the building and the surrounding environment.

[0022] Preferably, the step of selecting building boundaries and identifying each complete building according to the result of the differentiation includes:

[0023] Based on the results of the distinction, the boundaries are identified and highlighted. Each independent building has a connected boundary. For institutions or facilities consisting of several buildings, the range is delineated by two-dimensional coordinates, and all independent buildings within this range are treated as a whole, thereby identifying each complete building.

[0024] Preferably, the boundary is displayed as a boundary box in a top-down perspective.

[0025] Preferably, the real-time acquisition of building information and assigning it to the identified corresponding building includes:

[0026] Obtain real-time information of buildings and perform data processing and conversion;

[0027] The converted data is input into the 3D street view map and corresponds to the corresponding buildings identified in the 3D street view map.

[0028] Preferably, the acquisition of real-time information of the building and data processing and conversion include:

[0029] Acquire real-time information of buildings, aggregate the same or similar information types of different buildings through classification processing algorithms, and output the aggregated information as text and / or numbers using data stream conversion methods.

[0030] Preferably, the real-time information includes: the number of people in the building and the number of vacant parking spaces.

[0031] Preferably, the step of inputting the converted data into the three-dimensional street view map and corresponding the converted data to the corresponding buildings identified in the three-dimensional street view map comprises:

[0032] The source of the converted data is recorded, and then the converted data is input into the three-dimensional street view map through a point-to-point coordinate method, and corresponds to the corresponding buildings to form an overall target area that includes both buildings and real-time information.

[0033] Preferably, the step of acquiring the target building and / or the corresponding building information in the three-dimensional street view map according to the desired target result, and completing the interaction with the rendering entity on the three-dimensional street view map, comprises:

[0034] According to the selected target building, obtain the real-time building information of the building; and / or, according to the target building information, obtain related buildings within a set range;

[0035] The acquired target building and its building information are displayed.

[0036] Preferably, the displayed target building includes a boundary box in a bird's-eye view, and the displayed building information is located on one side of the boundary box; through classification processing, the building information boxes of other buildings with the same or similar information types are close to each other.

[0037] According to a second aspect of the present invention, there is provided a system for interacting with a rendered entity on a three-dimensional street view map, comprising:

[0038] A building recognition module, which is used to determine the three-dimensional boundaries of each building in the three-dimensional street view map, and then identify each complete building;

[0039] An information assignment module, which is used to obtain building information in real time and assign it to the corresponding identified building;

[0040] The interaction and pop-up module is used to obtain the target building and / or corresponding building information in the three-dimensional street view map according to the required target result, and complete the interaction with the rendering entity on the three-dimensional street view map.

[0041] According to a third aspect of the present invention, there is provided a computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, can be used to execute any one of the methods described above in the present invention, or to run the system described above in the present invention.

[0042] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can be used to execute any of the methods described above in the present invention, or to run the system described above in the present invention.

[0043] Due to the adoption of the above technical solution, the present invention has at least one of the following beneficial effects compared with the prior art:

[0044] The method and system for interacting with rendering entities on a three-dimensional street view map provided by the present invention redesigns the graphical interface and uses existing algorithms to make each building part on the map interactive, so that users can quickly understand information and explore in depth, thereby solving the problem that there is no interaction function with rendering entities in the three-dimensional street view map, allowing users to understand the building information in the map anytime and anywhere, thereby enhancing the user experience.

[0045] The method and system for interacting with rendering entities on a three-dimensional street view map provided by the present invention can acquire building information in real time and detect information changes by establishing a building information collection and communication platform, thereby solving the problem of untimely feedback of information, making real-time information feedback and processing highly timely and greatly enriching the functions of the map. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0047] Figure 1 The flowchart is a method for interacting with a rendering entity on a three-dimensional street view map according to an embodiment of the present invention.

[0048] Figure 2 FIG. 4 is a schematic diagram of component modules of a system for interacting with a rendering entity on a three-dimensional street view map according to an embodiment of the present invention.

[0049] Figure 3 This is a flowchart of a system for interacting with a rendering entity on a three-dimensional street view map in a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following is a detailed description of the embodiments of the present invention: This embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation method and a specific operation process are given. 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.

[0051] In view of the lack of technology for interacting with rendered entities on three-dimensional maps in the prior art, an embodiment of the present invention provides a method for interacting with rendered entities on a three-dimensional street view map. The method imparts information to a NeRF (neural radiant field) model, allowing users to interact with physical buildings on the three-dimensional street view map and obtain real-time information.

[0052] Specifically, Figure 1 As shown, the method for interacting with a rendering entity on a three-dimensional street view map provided in this embodiment may include the following operations:

[0053] S1, determine the three-dimensional boundary of each building in the three-dimensional street view map, and then identify each complete building;

[0054] S2, obtains building information in real time and assigns it to the corresponding identified building;

[0055] S3, according to the required target result, obtaining the target building and / or corresponding building information in the three-dimensional street view map, and completing the interaction with the rendering entity on the three-dimensional street view map.

[0056] In some preferred implementations, the above S1, determining the three-dimensional boundary of each building in the three-dimensional street view map, and then identifying each complete building, may further include the following operations:

[0057] S11, semantic segmentation of 3D street view map;

[0058] S12, based on the results of semantic segmentation, distinguishes the building from the surrounding environment;

[0059] S13, based on the differentiation result, the building boundary is selected to identify each complete building.

[0060] In some preferred implementations, the above S11, semantic segmentation of the three-dimensional street view map, may further include the following operations:

[0061] S111, NeRF rendering of 3D street view map using Instant-NGP software;

[0062] S112, labeling each part of the rendered image;

[0063] S113, buildings are usually of high height and have walls of consistent color style, while roads have traffic signs and vehicles travel on them. Therefore, based on labels, semantic segmentation is used to determine entities such as buildings, roads, vehicles, and pedestrians in the three-dimensional street view map to facilitate subsequent boundary identification.

[0064] In some preferred implementations, the above S12, based on the result of semantic segmentation, distinguishing the building from the surrounding environment, may further include the following operations:

[0065] S121, determining most of the rendered entities through the result of semantic segmentation;

[0066] S122, since there may be areas without common features and semantics between buildings and the surrounding environment, this problem can be solved by inputting the coordinates of the building boundary. At the same time, for buildings with irregular shapes, the difference in color between the ground and the building can be used to compare the RGB value of the part of the building close to the ground with the ground to determine the boundary between the ground and the building, thereby completing the distinction between the building and the surrounding environment.

[0067] In some preferred implementations, the above S13, based on the differentiation result, selects the building boundary and identifies each complete building, and may further include the following operations:

[0068] Based on the results of the distinction, the boundaries are identified and highlighted (for example, in other colors (such as red)). Each independent building has a connected boundary. For an institution or facility that includes several buildings, the scope can be delineated by two-dimensional coordinates, and all independent buildings in this scope can be regarded as a whole, thereby identifying each complete building.

[0069] in:

[0070] Bounds are shown as a bounding box from a top-down perspective.

[0071] In some preferred implementations, the above S2, real-time acquisition of building information and assigning it to the identified corresponding building, may further include the following operations:

[0072] S21, obtain real-time information of the building and perform data processing and conversion;

[0073] S22, inputting the converted data into the three-dimensional street view map, and corresponding to the corresponding buildings identified in the three-dimensional street view map.

[0074] In some preferred implementations, the above S21, obtaining real-time information of the building and performing data processing and conversion, may further include the following operations:

[0075] Acquire real-time information of buildings, aggregate the real-time information of the same or similar information types of different buildings through classification processing algorithms, and then use data stream conversion methods to output the aggregated information into generalized text and / or numbers;

[0076] Among them, real-time information includes: the number of people in the building, the number of empty parking spaces, etc.

[0077] In some preferred implementations, the above S22, inputting the converted data into the three-dimensional street view map and corresponding to the corresponding buildings identified in the three-dimensional street view map, may further include the following operations:

[0078] The source of the converted data is recorded, and then the converted data is input into the three-dimensional street view map through a point-to-point coordinate method, and corresponds to the corresponding buildings to form an overall target area that includes both buildings and real-time information.

[0079] In some preferred implementations, the above S3, according to the desired target result, obtains the target building and / or the corresponding building information in the three-dimensional street view map, completes the interaction with the rendering entity on the three-dimensional street view map, and may further include the following operations:

[0080] According to the selected target building, obtain the real-time building information of the building; and / or, according to the target building information, obtain related buildings within a set range;

[0081] Display the acquired target building and its building information;

[0082] in:

[0083] The displayed target building includes a bounding box in a bird's-eye view, and the displayed building information is located on one side of the bounding box; through the aforementioned classification processing algorithm, the building information boxes of other buildings with the same or similar information types are close to each other.

[0084] An embodiment of the present invention provides a system for interacting with a rendering entity on a three-dimensional street view map.

[0085] Specifically, Figure 2As shown, the system for interacting with a rendering entity on a three-dimensional street view map provided in this embodiment may include the following modules:

[0086] A building recognition module, which is used to determine the three-dimensional boundaries of each building in the three-dimensional street view map, and then identify each complete building;

[0087] An information assignment module, which is used to obtain building information in real time and assign it to the corresponding identified building;

[0088] The interaction and pop-up module is used to obtain the target building and / or corresponding building information in the three-dimensional street view map according to the required target result, and complete the interaction with the rendering entity on the three-dimensional street view map.

[0089] It should be noted that the steps in the method provided by the present invention can be implemented by using corresponding modules, devices, units, etc. in the system. Those skilled in the art can refer to the technical solution of the method to realize the composition of the system, that is, the embodiments in the method can be understood as preferred examples for constructing the system, which will not be elaborated here.

[0090] The following further describes the working contents of each component module of the system for interacting with a rendering entity on a three-dimensional street view map provided by the embodiment. Figure 3 shown.

[0091] Building recognition module: This module is used to distinguish buildings in the 3D street view map, determine the 3D boundaries of each building, and thus identify each complete building. It includes an environment scanning module, a boundary identification module, and a frame construction module. The input data of this module is a street view photo or video, which contains information about the building and the surrounding environment.

[0092] Information assignment module: This module is used to assign the real-time building information, such as the number of people in the building, the number of empty parking spaces, etc., to the corresponding buildings that have been identified. It includes a real-time transmission and conversion module and a data docking module. The input data of this module is the real-time building information obtained.

[0093] Interaction and pop-up module: This module is used to pop up real-time building information when the user clicks on a building in the map, so that the user can understand the situation of the building anytime and anywhere; or, according to the building information searched by the user, determine the relevant buildings within the set range. It includes an interaction module and an information pop-up module.

[0094] The building identification module further includes:

[0095] Environment scanning module: This module is used to scan street scenes and assign different semantics. Through the provided photos or videos, nerf rendering is first performed through instant-ngp, and then each part is labeled. Buildings are usually of high height, with consistent wall color style, and roads have traffic signs and vehicles running. In this way, entities such as buildings, roads, vehicles, and pedestrians can be determined through semantic segmentation, which is convenient for subsequent boundary identification.

[0096] Boundary identification module: This module is used to distinguish between buildings and the surrounding environment and minimize the fuzzy area between the two. Through semantic segmentation, most of the entities after rendering can be determined, but there will be areas between the building and the surrounding environment that have no common characteristics and are not given semantics. Therefore, this problem can be solved by inputting the coordinates of the building boundary. At the same time, for buildings with irregular shapes, the angle between the area and the ground can be calculated by the RGB values ​​of nearby points. The place where the angle changes beyond a certain range is regarded as the boundary of the building.

[0097] Border construction module: This module is used to display the border of the selected building. After successful border identification, the border is displayed in other colors (such as red). Each independent building has a connected border. For institutions or facilities that include several buildings, the scope can still be delineated by two-dimensional coordinates, and all independent buildings in this scope are regarded as a whole.

[0098] Among them, the information assignment module includes:

[0099] Real-time transmission and conversion module: This module is used to obtain real-time information of the building and perform data processing and conversion. It can establish a connection between each information source and the main server. When the data is input into the server, it will be classified and converted into generalized text and numbers.

[0100] Data docking module: This module is used to input the converted data into the street view map. After obtaining the converted data, it is necessary to record which building the data comes from and correspond to the building in the three-dimensional map through point-to-point coordinates, so that this area becomes a whole that contains both the building and the corresponding information.

[0101] Among them, the interactive and pop-up modules include:

[0102] Interaction module: This module is used to identify the user's operation and understand what information the user wants (i.e., understand the desired target result). When the user clicks on a building in the 3D map or sets a location as a navigation point, the building labels and corresponding information in the area are confirmed through the search technology near the location. In addition, if the user searches for certain information, the system will automatically select buildings related to the information in a certain area nearby, such as an area with a radius of 5 kilometers (which can be set by yourself).

[0103] Information pop-up module: This module is used to design the pop-up building information and pop-up interface. After selecting a building in the interactive module, all selected buildings will display their bounding boxes from a bird's-eye view, which is exactly the result obtained by the border construction module, and the building information will be displayed next to it. When multiple buildings are selected, the information boxes of buildings with the same or similar information types will be closer, which is convenient for customers to compare and contrast.

[0104] The technical solution provided by the above embodiment of the present invention is further described below in conjunction with a specific application implementation. This specific application example will help those skilled in the art to further understand the present invention, but does not limit the present invention in any form. It should be pointed out that for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0105] The method and system for interacting with a rendering entity on a three-dimensional street view map adopted in this specific application example specifically include the following technical contents:

[0106] First, the work content of the building recognition module is executed, and the obtained street view photos or street view videos are input.

[0107] The street scene is then scanned and assigned different semantics through the environment scanning module, nerfed and rendered through instant-ngp, and each part is labeled. Buildings are usually taller and have consistent wall colors, while roads have traffic signs and vehicles running on them. In this way, entities such as buildings, roads, vehicles, and pedestrians can be determined through semantic segmentation.

[0108] The boundary identification module is then used to distinguish the building from the surrounding environment and minimize the fuzzy area between the two. Through semantic segmentation, most of the entities after rendering can be determined, but there will be areas between the building and the surrounding environment that have no common characteristics and are not given semantics. Therefore, this problem can be solved by inputting the coordinates of the building boundary. At the same time, for irregularly shaped buildings, the angle between the area and the ground can be calculated by the RGB values ​​of nearby points. The place where the angle changes beyond a certain range is regarded as the boundary of the building.

[0109] The selected building border is then displayed through the border construction module. After successful border identification, the border is displayed in other colors (such as red). Each independent building has a connected border. For institutions or facilities that include several buildings, the scope can still be delineated by two-dimensional coordinates, and all independent buildings in this scope are considered as a whole.

[0110] Then, the work content of the information assignment module is executed and the real-time building information obtained is input.

[0111] After that, the real-time information of the building is obtained through the real-time transmission and conversion module, and data processing and conversion are performed. The connection between each information source and the main server is established. When the data is input into the server, it will be classified and converted into generalized text and numbers.

[0112] After that, the converted data is input into the street view map through the data docking module. After obtaining the converted data, it is necessary to record which building the data comes from and correspond to the building in the three-dimensional map through the point-to-point coordinate method, so that this area becomes a whole that contains both the building and the corresponding information.

[0113] Then, the work content of the interaction and pop-up module is executed, and the user's click position and navigation position information are input (that is, the required target result is understood).

[0114] After that, the interactive module recognizes the user's operation and understands what information the user wants. When the user clicks on a building in the 3D map or sets a location as a navigation point, the building labels and corresponding information in the area are confirmed through the search technology near the location. In addition, if the user searches for certain information, the system will automatically select buildings related to the information in a certain area nearby, such as an area with a radius of 5 kilometers (which can be set by yourself).

[0115] The building information is then popped up through the information pop-up module. After the building is selected in the interactive module, all selected buildings will display their bounding boxes from a bird's-eye view, which is exactly the result obtained by the border construction module, and the building information will be displayed next to it. When multiple buildings are selected, the information boxes of buildings with similar information types will be closer, making it easier for customers to compare and contrast. Ultimately, the effect of users being able to interact with the 3D street view map is achieved.

[0116] An embodiment of the present invention further provides a computer terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the processor can be used to execute any method of the above-mentioned embodiments of the present invention, or to run any system of the above-mentioned embodiments of the present invention.

[0117] Optionally, the memory is used to store programs; the memory may include volatile memory (English: volatile memory), such as random-access memory (English: random-access memory, abbreviated: RAM), such as static random-access memory (English: static random-access memory, abbreviated: SRAM), double data rate synchronous dynamic random access memory (English: Double Data Rate Synchronous Dynamic Random Access Memory, abbreviated: DDR SDRAM), etc.; the memory may also include non-volatile memory (English: non-volatile memory), such as flash memory (English: flash memory). The memory is used to store computer programs (such as applications, functional modules, etc. that implement the above method), computer instructions, etc., and the above computer programs, computer instructions, etc. can be partitioned and stored in one or more memories. And the above computer programs, computer instructions, data, etc. can be called by the processor.

[0118] The above-mentioned computer programs, computer instructions, etc. may be stored in one or more memories in partitions, and the above-mentioned computer programs, computer instructions, data, etc. may be called by a processor.

[0119] The processor is used to execute the computer program stored in the memory to implement the various steps of the method or various modules of the system involved in the above embodiments. For details, please refer to the relevant descriptions in the above method and system embodiments.

[0120] The processor and the memory may be independent structures or integrated structures. When the processor and the memory are independent structures, the memory and the processor may be coupled and connected via a bus.

[0121] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it can be used to execute any method of the above embodiments of the present invention, or to run any system of the above embodiments of the present invention.

[0122] The method and system for interacting with rendering entities on a three-dimensional street view map provided by the present invention solve the problem that there is no interaction function with rendering entities in the three-dimensional street view map, so that users can understand the building information in the map anytime and anywhere, thereby enhancing the user experience; it solves the problem of untimely feedback information, so that real-time information feedback and processing have strong timeliness, greatly enriching the function of the map.

[0123] All matters not covered in the above embodiments of the present invention are well known in the art.

[0124] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art may make various modifications or variations within the scope of the claims, which do not affect the essence of the present invention.

Claims

1. A method for interacting with a rendered entity on a three-dimensional street view map, characterized in that: include: Determine the 3D boundaries of each building in the 3D street view map, and then identify each complete building; Acquire building information in real time and assign it to the corresponding identified buildings; According to the desired target result, the target building and / or the corresponding building information in the three-dimensional street view map is obtained, and the interaction with the rendering entity on the three-dimensional street view map is completed.

2. The method for interacting with a rendered entity on a three-dimensional street view map according to claim 1, characterized in that: Determining the three-dimensional boundary of each building in the three-dimensional street view map, and then identifying each complete building, includes: Perform semantic segmentation on 3D street view maps; Based on the result of the semantic segmentation, distinguish the building from the surrounding environment; Based on the results of the differentiation, the building boundaries are selected and each complete building is identified.

3. The method for interacting with a rendered entity on a three-dimensional street view map according to claim 2, characterized in that: The three-dimensional street view map is semantically segmented, including: NeRF rendering of 3D street view maps using Instant-NGP software; Label each part of the rendered image; Based on the labels, determining entities of the three-dimensional street view map by semantic segmentation; The distinguishing the building from the surrounding environment based on the result of the semantic segmentation includes: Determine the rendered entity through the results of semantic segmentation; For buildings with regular shapes, the coordinates of the building boundary are input to distinguish between the building and the surrounding environment. For buildings with irregular shapes, the difference in color between the ground and the building is used to compare the RGB values ​​of the part of the building close to the ground with the ground to determine the boundary between the ground and the building, thus completing the distinction between the building and the surrounding environment. According to the result of the differentiation, the building boundary is selected to identify each complete building, including: Based on the results of the distinction, the boundaries are identified and highlighted. Each independent building has a connected boundary. For an institution or facility that includes several buildings, the scope is delineated by two-dimensional coordinates, and all independent buildings in the scope are considered as a whole, thereby identifying each complete building. in: The boundaries are shown as bounding boxes from a top-down perspective.

4. The method for interacting with a rendered entity on a three-dimensional street view map according to claim 1, characterized in that: The real-time acquisition of building information and assigning it to the identified corresponding building includes: Obtain real-time information of buildings and perform data processing and conversion; The converted data is input into the 3D street view map and corresponds to the corresponding buildings identified in the 3D street view map.

5. The method for interacting with a rendering entity on a three-dimensional street view map according to claim 4, characterized in that: The obtaining of real-time information of the building and performing data processing and conversion include: Obtain real-time information of buildings, aggregate the same or similar information types of different buildings through classification processing algorithms, and output the aggregated information into text and / or numbers using data stream conversion methods; The real-time information includes: the number of people in the building and the number of empty parking spaces; The step of inputting the converted data into the three-dimensional street view map and corresponding the converted data to the corresponding buildings identified in the three-dimensional street view map includes: The source of the converted data is recorded, and then the converted data is input into the three-dimensional street view map through a point-to-point coordinate method, and corresponds to the corresponding buildings to form an overall target area that includes both buildings and real-time information.

6. The method for interacting with a rendered entity on a three-dimensional street view map according to claim 1, characterized in that: The step of obtaining the target building and / or corresponding building information in the three-dimensional street view map according to the desired target result and completing the interaction with the rendering entity on the three-dimensional street view map includes: According to the selected target building, obtain the real-time building information of the building; and / or, according to the target building information, obtain related buildings within a set range; The acquired target building and its building information are displayed.

7. The method for interacting with a rendering entity on a three-dimensional street view map according to claim 6, characterized in that: The displayed target building includes a bounding box in a bird's-eye view, and the displayed building information is located on one side of the bounding box; through classification processing, the building information boxes of other buildings with the same or similar information types are close to each other.

8. A system for interacting with a rendered entity on a three-dimensional street view map, characterized in that: include: A building recognition module, which is used to determine the three-dimensional boundaries of each building in the three-dimensional street view map, and then identify each complete building; An information assignment module, which is used to obtain building information in real time and assign it to the corresponding identified building; The interaction and pop-up module is used to obtain the target building and / or corresponding building information in the three-dimensional street view map according to the required target result, and complete the interaction with the rendering entity on the three-dimensional street view map.

9. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it can be used to perform the method described in any one of claims 1 to 7, or to run the system described in claim 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it can be used to perform the method described in any one of claims 1 to 7, or to run the system described in claim 8.

Images