Three-dimensional point location automatic creation method and device relating to Internet of Things
By acquiring the two-dimensional position information of the target object and using a convolutional neural network to verify and generate three-dimensional point information, the problems of easy errors in manual point marking and large limitations of automatic point marking are solved, and efficient and accurate automatic creation of three-dimensional points is achieved.
Patent Information
- Application Number
- CN202511538320.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-24
- Publication Date
- 2026-01-27
AI Technical Summary
In existing technologies, manual marking is prone to errors, involves a large workload, and is difficult to verify. Automated marking requires the collection of equipment information and relies on external positioning equipment, which has significant limitations.
By acquiring the two-dimensional location information of the target object, the accuracy of the marked points is verified using a convolutional neural network, point information is generated and three-dimensional coordinate information is obtained. Reference points are determined by combining type features and clustering, a three-dimensional point creation scheme is generated, and the information is bound to the Internet of Things platform.
It improves the efficiency and accuracy of point marking, realizes automated 3D point creation, reduces human error, and reduces dependence on external equipment.
Smart Images
Figure CN121414973A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to a method and apparatus for automatically creating three-dimensional points related to IoT. Background Technology
[0002] With the development of technology, smart parks need to build digital platforms. This requires a 3D visualization platform, a digital twin platform, to monitor and control a large number of devices (over 100,000) in real time. Existing technologies mainly rely on manual modeling and point marking or automatic point marking under limited conditions. Generally, manual point marking and modeling are based on CAD drawings, or automatic point marking and coding are performed using the latitude and longitude information of the devices. However, manual point marking is extremely labor-intensive due to the tens of thousands of points, and is prone to errors and difficult to verify. Automatic point marking using latitude and longitude requires the prior collection of the latitude and longitude information of the devices, which requires positioning devices or external positioning equipment for data collection and input, resulting in significant limitations. Summary of the Invention
[0003] In view of the aforementioned problems, this application is proposed to provide a method and apparatus for automatically creating three-dimensional points related to the Internet of Things (IoT) to overcome or at least partially solve the aforementioned problems, comprising: A method for automatically creating 3D point locations related to the Internet of Things (IoT), the method being used to generate 3D point locations for monitoring and querying via the IoT by using the 2D location information of a target object in a target area and a 3D model, including the following steps: Obtain the two-dimensional position information of the target object and determine the two-dimensional marker position of the target object in the target area based on the two-dimensional position information; Point information is generated based on the two-dimensional marked points, and at least two reference points are generated based on the point information; wherein, the point information includes point type information, point quantity information, point location information, and point code information; Obtain the three-dimensional coordinate information corresponding to the reference point and determine the coordinate ratio based on the three-dimensional coordinate information; A three-dimensional point creation scheme is generated based on the point information and the coordinate ratio.
[0004] Further, the step of acquiring the two-dimensional position information of the target object and determining the two-dimensional marker position of the target object in the target area based on the two-dimensional position information includes: A two-dimensional image containing the two-dimensional location information of the target object is acquired, and a relevant primitive code of the target object is generated based on the two-dimensional image; Two-dimensional marker points are generated based on the relevant primitive codes and the two-dimensional location information; The accuracy of the two-dimensional marker points is determined by verifying them.
[0005] Furthermore, the step of verifying the two-dimensional marker points and determining their accuracy includes: A convolutional neural network is constructed and trained using a CAD primitive library, enabling the convolutional neural network to recognize two-dimensional marked points. The two-dimensional marker points are identified and verified using the convolutional neural network.
[0006] Further, the step of generating point information based on the two-dimensional marked points and generating at least two reference points based on the point information includes: Based on the location information, the corresponding type characteristics are determined; wherein, the type characteristics include location functional attributes, spatial distribution characteristics, and associated equipment parameters; The locations are clustered and grouped according to the aforementioned type characteristics; Reference points are determined based on the clustering grouping.
[0007] Further, the step of obtaining the three-dimensional coordinate information corresponding to the reference point and determining the coordinate scale based on the three-dimensional coordinate information includes: Obtain the three-dimensional coordinate information of the reference point; The initial coordinate ratio is determined based on the three-dimensional coordinate information and the two-dimensional coordinates of the reference point; The initial coordinate ratio is obtained by verifying the ratio of the two-dimensional coordinates of the non-reference point and the transformed three-dimensional coordinates.
[0008] Further, the step of generating a three-dimensional point creation scheme based on the point information and the coordinate ratio includes: The model points are obtained by marking them in a 3D view based on the point information and the coordinate ratio. The model points are encoded and bound to a monitoring and query scheme to obtain the points bound to the IoT platform; The IoT platform is assigned values based on the location information to generate spatial information and a three-dimensional location creation scheme.
[0009] Furthermore, the step of assigning values to the IoT platform based on the location information, generating spatial information, and generating a 3D location creation scheme includes: The location information is mapped to attribute fields that can be recognized by the Internet of Things platform. The attribute fields include spatial coordinate fields, device type fields, and unique identifier fields. The attribute fields are written into the database of the IoT platform through the API interface to establish an association mapping between the attribute fields and the monitoring data in the platform. A spatial information model is generated based on the aforementioned association mapping.
[0010] A device for automatically creating and binding 3D points related to the Internet of Things includes: The acquisition module is used to acquire the two-dimensional position information of the target object and determine the two-dimensional marker position of the target object in the target area based on the two-dimensional position information; The point information module is used to generate point information based on the two-dimensional marked points, and to generate at least two reference points based on the point information; wherein, the point information includes point type information, point quantity information, point location information, and point code information; The coordinate scaling module is used to obtain the three-dimensional coordinate information corresponding to the reference point and determine the coordinate scaling based on the three-dimensional coordinate information. A creation module is used to generate a three-dimensional point creation scheme based on the point information and the coordinate ratio.
[0011] A device for automatically creating and binding 3D points related to the Internet of Things (IoT) includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the method for automatically creating and binding 3D points related to the IoT as described above.
[0012] A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the above-described method for automatically creating and binding three-dimensional points related to the Internet of Things.
[0013] This application has the following advantages: In the embodiments of this application, compared with the shortcomings of manual point marking in the prior art, which is prone to errors and difficult to verify, and automatic point marking, which requires the collection of device information and relies on external devices and has great limitations, this application provides a method for automatically creating three-dimensional point locations related to the Internet of Things (IoT). The method is used to generate three-dimensional point locations for monitoring and querying by the IoT using the two-dimensional position information of a target object in a target area and a three-dimensional model. The method includes the following steps: obtaining the two-dimensional position information of the target object and determining the two-dimensional marker point location of the target object in the target area based on the two-dimensional position information; generating point location information based on the two-dimensional marker point location and generating at least two reference points based on the point location information; wherein, the point location information includes point location type information, point location number information, point location information, and point location code information; obtaining the three-dimensional coordinate information corresponding to the reference points and determining the coordinate ratio based on the three-dimensional coordinate information; and generating a three-dimensional point location creation scheme based on the point location information and the coordinate ratio. By converting the two-dimensional position information of the target object in the target area into three-dimensional point locations, the efficiency of point marking is improved, automatic point marking is achieved, and the accuracy of point marking is enhanced. Attached Figure Description
[0014] To more clearly illustrate the technical solution of this application, the drawings used in the description of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 This is a flowchart illustrating the steps of an embodiment of the present application for an automatic three-dimensional point creation method involving the Internet of Things; Figure 2 This is a diagram of the main network structure of a deep learning convolutional neural network algorithm for verifying two-dimensional marker points provided in an embodiment of this application; Figure 3 This is a structural block diagram of a three-dimensional point automatic creation device related to the Internet of Things provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation
[0015] To make the objectives, features, and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.
[0016] The inventors discovered through analysis of existing technologies that they mainly rely on manual modeling and point marking or automatic point marking under limited conditions. Generally, manual point marking and modeling are based on CAD drawings, or automatic point marking and coding are performed using the latitude and longitude information of the equipment. However, manual point marking is extremely labor-intensive due to the number of points being in the tens of thousands, and is prone to errors and difficult to verify. Automatic point marking using latitude and longitude requires the prior collection of the latitude and longitude information of the equipment, and requires a positioning device or external positioning equipment for data collection and input, which has great limitations.
[0017] Reference Figure 1 This application illustrates an embodiment of a method for automatically creating three-dimensional points related to the Internet of Things (IoT). The method generates three-dimensional points for monitoring and querying via the IoT by using the two-dimensional location information of a target object in a target area and a three-dimensional model. The method includes the following steps: S110. Obtain the two-dimensional position information of the target object and determine the two-dimensional marker position of the target object in the target area based on the two-dimensional position information; S120. Generate point information based on the two-dimensional marked points, and generate at least two reference points based on the point information; wherein, the point information includes point type information, point quantity information, point location information, and point code information; S130. Obtain the three-dimensional coordinate information corresponding to the reference point and determine the coordinate ratio based on the three-dimensional coordinate information; S140. Generate a three-dimensional point creation scheme based on the point information and the coordinate ratio.
[0018] In the embodiments of this application, compared with the shortcomings of manual point marking in the prior art, which is prone to errors and difficult to verify, and automatic point marking, which requires the collection of device information and has great limitations due to external equipment, this application provides a method for automatically creating three-dimensional point locations related to the Internet of Things (IoT). The method is used to generate three-dimensional point locations for monitoring and querying via the IoT by using the two-dimensional position information of a target object in a target area and a three-dimensional model. The method includes the following steps: obtaining the two-dimensional position information of the target object and determining the two-dimensional marker point location of the target object in the target area based on the two-dimensional position information; generating point location information based on the two-dimensional marker point location and generating at least two reference points based on the point location information; wherein, the point location information includes point location type information, point location number information, point location information, and point location code information; obtaining the three-dimensional coordinate information corresponding to the reference points and determining the coordinate ratio based on the three-dimensional coordinate information; and generating a three-dimensional point location creation scheme based on the point location information and the coordinate ratio. By converting the two-dimensional position information of the target object in the target area into three-dimensional point locations, the efficiency of point marking is improved, automatic point marking is achieved, and the accuracy of point marking is enhanced.
[0019] The following will further describe an exemplary embodiment of a method for automatically creating three-dimensional points related to the Internet of Things.
[0020] As described in step S110, the two-dimensional position information of the target object is obtained, and the two-dimensional marker position of the target object in the target area is determined based on the two-dimensional position information.
[0021] It should be noted that the original location information is usually recorded in two-dimensional carriers, such as CAD drawings, floor plans, and BIM 2D views. The specific location of the target object is obtained from these two-dimensional carriers, a unique identifier is generated for each target object, and the accurate location of the target object is marked on the 2D drawing to form 2D marker points; and the accuracy of the markings is verified to ensure the reliability of the basic data for subsequent 3D conversion.
[0022] In one embodiment of the present invention, the specific process of "obtaining the two-dimensional position information of the target object and determining the two-dimensional marker position of the target object in the target area based on the two-dimensional position information" in step S110 can be further described in conjunction with the following description.
[0023] As described in the following steps, a two-dimensional image containing the two-dimensional location information of the target object is obtained, and a relevant primitive code of the target object is generated based on the two-dimensional image; the location data and attribute information of the target object are extracted from the two-dimensional carrier, and a unique primitive code is generated to avoid confusion of the positions of different target objects.
[0024] As described in the following steps, a two-dimensional marker point is generated based on the relevant primitive code and the two-dimensional location information; the primitive code is bound to the two-dimensional location to generate a visualized and structured two-dimensional marker point, the location to be marked is determined, and the number of the marked location is obtained.
[0025] The following steps verify the accuracy of the two-dimensional marker points. Relying on drawing analysis and OCR recognition technologies to identify the drawings may result in errors in the obtained two-dimensional marker points. Directly using these markers for subsequent 3D conversion could lead to mislabeling or omission of 3D points. Therefore, AI verification of the marker points is essential.
[0026] In one embodiment of the present invention, the specific process of step “verifying the two-dimensional marker points and determining the accuracy of the two-dimensional marker points” can be further explained in conjunction with the following description.
[0027] As described in the following steps, a convolutional neural network is constructed and trained using a CAD primitive library to enable the convolutional neural network to recognize two-dimensional marked points. The two-dimensional marker points are identified and verified using the convolutional neural network as described in the following steps.
[0028] In one specific implementation, the YOLOv8 deep learning convolutional neural network algorithm is adopted. YOLOv8 is a cutting-edge object detection technology. It builds on the success of previous versions of YOLO in object detection tasks and further improves performance and flexibility, including a new backbone network, a new Ancher-Free detection head and a new loss function, which can run on various hardware platforms from CPU to GPU. Reference Figure 2 This is the main network structure of the YOLOv8 deep learning convolutional neural network algorithm. During the training phase, the algorithm is first built using Python or C++ based on the above network model structure. Then, a CAD primitive library is collected for classification and annotation for training and testing. After training, the algorithm model with an accuracy that meets the application standard is deployed to a specified GPU or NPU device for inference operations. During the inference phase, inputting a specified CAD image (using the AsposeCAD tool to convert DWG format to JPEG image format) will output the detected multiple targets and their locations. The CAD points identified by the AI algorithm are then subjected to auxiliary verification or benchmark input, and manual verification, efficiently and accurately exporting a CAD point table containing information such as the specified point type and location.
[0029] As described in step S120, point information is generated based on the two-dimensional marker points, and at least two reference points are generated based on the point information; wherein, the point information includes point type information, point quantity information, point location information, and point code information.
[0030] It should be noted that the scattered two-dimensional marker points are integrated into a structured and categorizable point information database, clearly defining the type, quantity, location, and unique code of each point. All point information must originate from the two-dimensional marker points and correspond one-to-one with them to avoid information gaps. Select at least two representative points from the available points. The core requirements are strong representativeness and wide coverage. Therefore, this requires the steps of type feature extraction, clustering and grouping, and selection of representative points to ensure that at least two reference points can cover the conversion needs of most points.
[0031] In one embodiment of the present invention, the specific process of step S120, "generating point information based on the two-dimensional marker points and generating at least two reference points based on the point information; wherein the point information includes point type information, point quantity information, point location information and point code information," can be further explained in conjunction with the following description.
[0032] As described in the following steps, the corresponding type characteristics are determined based on the location information; wherein, the type characteristics include location functional attributes, spatial distribution characteristics, and associated equipment parameters; As described in the following steps, the locations are clustered and grouped according to the type characteristics; The reference point is determined based on the clustering grouping as described in the following steps.
[0033] It should be noted that three key features need to be extracted from the location information (location functional attributes, spatial distribution characteristics, and associated equipment parameters). Each feature serves the goal of grouping locations with similar conversion needs together; grouping locations with similar type characteristics together ensures that the 2D to 3D conversion rules for locations within the same group are basically consistent. This step solves the problem that the conversion rules for different types / regions vary greatly, and a single reference point cannot cover them all. One most representative location needs to be selected from each group to ensure that it reflects the 2D to 3D conversion characteristics of all locations in that group. The final number of reference points equals the number of clusters, and must be at least two.
[0034] By extracting type features and clustering, it is ensured that reference points can cover points of different functions, regions, and equipment types, avoiding uneven conversion accuracy caused by traditional "random point selection". The conversion rules of points in the same group are similar, so the proportions calculated using reference points can be directly applied to other points in the same group, significantly reducing the workload of 3D coordinate acquisition. As described in step S130, the three-dimensional coordinate information corresponding to the reference point is obtained, and the coordinate ratio is determined based on the three-dimensional coordinate information.
[0035] By establishing the correspondence between the two-dimensional and three-dimensional coordinates of a reference point, a reusable transformation ratio is calculated. The general steps include obtaining the precise coordinates of the reference point in the three-dimensional model; establishing the mathematical mapping relationship between the two-dimensional and three-dimensional coordinates of the reference point and calculating the transformation ratio for each axis; and verifying and correcting the ratio to ensure its applicability to the transformation of all points.
[0036] In one embodiment of the present invention, the specific process of "obtaining the three-dimensional coordinate information corresponding to the reference point and determining the coordinate ratio based on the three-dimensional coordinate information" in step S130 can be further described in conjunction with the following description.
[0037] The three-dimensional coordinate information of the reference point is obtained as described in the following steps; As described in the following steps, the initial coordinate ratio is determined based on the three-dimensional coordinate information and the two-dimensional coordinates of the reference point; As described in the following steps, the initial coordinate ratio is verified by comparing the two-dimensional coordinates of the non-reference point with the transformed three-dimensional coordinates to obtain the coordinate ratio.
[0038] It should be noted that the initial coordinate ratio is a formula for converting two-dimensional coordinates to three-dimensional coordinates. The core is to calculate the ratio along the three axes of x, y, and z. The x-axis and y-axis are based on the direct ratio between two-dimensional and three-dimensional coordinates, while the z-axis requires special handling because there is no coordinate in two dimensions.
[0039] The initial scales of the x-axis and y-axis, for each reference point, are the x-axis scale (kx) and the y-axis scale (k). y The formula for calculating ) is: x-axis scale: kx = 3D x-coordinate of reference point (x3) / 2D x-coordinate of reference point (x2) y-axis scale: k y = Reference point 3D y coordinate (y3) / Reference point 2D y coordinate (y2).
[0040] Two-dimensional drawings only contain x-axis and y-axis coordinates, but not z-axis coordinates. Therefore, the z-axis scale needs to be determined by rules based on the spatial properties of the reference points. Z3 = Floor baseline elevation + Equipment installation height Extract floor and equipment types from the location information of the reference points; determine the floor benchmark elevation and equipment installation height; and verify the calculation results by back-calculation using z3 of the reference points.
[0041] In one specific implementation, given the horizontal positions of two points in the CAD drawing and the 3D scene, and knowing the coordinates of any third point in the CAD drawing, it is necessary to determine the horizontal position of that third point in the 3D scene.
[0042] Given that the coordinates of two points A and B are in two different Cartesian coordinate systems O1 and O2, respectively (AX1, AY1), (BX1, BY1) and (AX2, AY2), (BX2, BY2), where coordinate system O2 has different units of measurement and there are scaling factors (SX, SY) in the X and Y directions compared to coordinate system O1. Also, given that the coordinates of point C in coordinate system O1 are (CX1, CY1), we need to find the coordinates of point C in coordinate system O2 (CX2, CY2).
[0043] This allows us to determine the lengths (AX1-BX1) and (AX2-BX2) of the two points in these two different coordinate systems. Since the ratio of these lengths (i.e., the scaling factor SX) remains constant, we can deduce... SX=(AX1-BX1) / (AX2-BX2)=(AX1-CX1) / (AX2-CX2) Similarly, we can obtain SY=(AY1-BY1) / (AY2-BY2)=(AY1-CY1) / (AY2-CY2) Simplified as follows: (AX1-BX1) / (AX2-BX2)=(AX1-CX1) / (AX2-CX2) (AY1-BY1) / (AY2-BY2)=(AY1-CY1) / (AY2-CY2) The unknowns are CX2 and CY2, and the others are known quantities. The position (CX2, CY2) of point C in the O2 coordinate system can be obtained from the above system of equations: CX2=AX2-(AX1-CX1)(AX2-BX2) / (AX1-BX1) CY2=AY2-(AY1-CY1)(AY2-BY2) / (AY1-BY1).
[0044] As described in step S140, a three-dimensional point creation scheme is generated based on the point information and the coordinate ratio.
[0045] It should be noted that integrating structured point information with precise coordinate ratios to generate a 3D point solution requires more than just outputting 3D coordinates; it also necessitates integration with an IoT platform to meet the core needs of real-time monitoring and spatial querying. This process includes four steps: 3D model point generation, encoding and binding with the monitoring scheme, IoT platform assignment, and output of the spatial information model and scheme.
[0046] In one embodiment of the present invention, the specific process of "generating a three-dimensional point creation scheme based on the point information and the coordinate ratio" in step S140 can be further described in conjunction with the following description.
[0047] As described in the following steps, the model points are marked in the 3D view according to the point information and the coordinate ratio; the 2D points are accurately converted into 3D coordinates according to the coordinate ratio and marked in the 3D view to ensure that the spatial position of each point matches the device type, laying the foundation for subsequent function binding.
[0048] As described in the following steps, the model points are encoded and bound to a monitoring and query scheme to obtain the bound points with the IoT platform; the model points need to be assigned unique identifiers and functional attributes in order to become monitoring nodes that can be identified by the IoT platform.
[0049] As described in the following steps, the IoT platform is assigned values based on the location information to generate spatial information and a 3D location creation scheme. Through attribute mapping, data writing, and model integration, the linkage between 3D locations, monitoring data, and spatial information is realized, and an executable complete scheme is output.
[0050] It should be noted that through steps such as 3D marking, function binding, platform integration, and solution output, a complete transformation from 2D points to IoT 3D monitoring nodes is achieved. The core is not only to place points in a 3D view, but also to enable each point to have spatial positioning, data monitoring, and rapid retrieval capabilities, ultimately providing a visualized, manageable, and interactive spatial monitoring solution for scenarios such as smart parks and industrial IoT.
[0051] In one embodiment of the present invention, the specific process of the step "assigning values to the Internet of Things platform based on the location information, generating spatial information and generating a three-dimensional location creation scheme" can be further explained in conjunction with the following description.
[0052] As described in the following steps, the location information is mapped to attribute fields that can be recognized by the Internet of Things platform. The attribute fields include spatial coordinate fields, device type fields, and unique identifier fields. As described in the following steps, the attribute fields are written into the database of the IoT platform through the API interface to establish an association mapping between the attribute fields and the monitoring data in the platform; As described in the following steps, a spatial information model is generated based on the association mapping.
[0053] It should be noted that the location information is in a custom format and needs to be converted into pre-defined, parsable attribute fields by the platform to ensure that the platform can recognize and store this information. The mapped fields are written to the platform database via API, and a link is established between the attribute fields and the platform's monitoring data to ensure that location queries can display data and data queries can pinpoint location. By integrating the discrete attribute fields with the monitoring data into a spatially hierarchical, viewable and controllable model, the problems of data dispersion and unintuitive spatial location are solved, supporting spatialized operation and maintenance in scenarios such as smart parks and industrial plants.
[0054] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.
[0055] Reference Figure 2 This application illustrates an embodiment of a device for automatically creating and binding three-dimensional points related to the Internet of Things. Specifically, it includes: The acquisition module 310 is used to acquire the two-dimensional position information of the target object and determine the two-dimensional marker position of the target object in the target area based on the two-dimensional position information. The point information module 320 is used to generate point information based on the two-dimensional marked points, and to generate at least two reference points based on the point information; wherein, the point information includes point type information, point quantity information, point location information and point code information; The coordinate scaling module 330 is used to acquire the three-dimensional coordinate information corresponding to the reference point and determine the coordinate scaling based on the three-dimensional coordinate information. The creation module 340 is used to generate a three-dimensional point creation scheme based on the point information and the coordinate ratio.
[0056] In one embodiment of the present invention, the acquisition module 310 includes: The primitive encoding submodule is used to acquire a two-dimensional image containing the two-dimensional location information of the target object, and generate relevant primitive codes for the target object based on the two-dimensional image; The two-dimensional marker point submodule is used to generate two-dimensional marker points based on the relevant primitive codes and the two-dimensional location information; The point verification submodule is used to verify the two-dimensional marker points and determine their accuracy.
[0057] In one embodiment of the present invention, the location verification submodule includes: A network construction unit is used to construct a convolutional neural network and train the convolutional neural network using a CAD primitive library, so that the convolutional neural network has the ability to recognize two-dimensional marked points. The verification unit is used to identify and verify the two-dimensional marked points through the convolutional neural network.
[0058] In one embodiment of the present invention, the location information module 320 further includes: The type feature submodule is used to determine the corresponding type feature based on the location information; wherein, the type feature includes location functional attributes, spatial distribution characteristics, and associated equipment parameters; The clustering and grouping submodule is used to cluster and group the points according to the type characteristics; The reference point submodule is used to determine reference points based on the clustering grouping.
[0059] In one embodiment of the present invention, the coordinate scaling module 330 includes: The three-dimensional coordinate submodule is used to obtain the three-dimensional coordinate information and two-dimensional coordinates of the reference point; The initial coordinate scaling submodule is used to obtain the initial coordinate scaling based on the ratio of the three-dimensional coordinate information to the two-dimensional coordinates along the corresponding axis. The coordinate scaling submodule is used to verify the initial coordinate scaling based on the two-dimensional coordinates of the non-reference point and the transformed three-dimensional coordinates to obtain the coordinate scaling.
[0060] In one embodiment of the present invention, the creation module 340 includes: The model point location submodule is used to mark the model points in the three-dimensional view based on the point location information and the coordinate ratio; The binding point submodule is used to encode the model points and bind them to the monitoring and query scheme to obtain the binding points with the Internet of Things platform; A scheme creation submodule is used to assign values to the IoT platform based on the location information, generate spatial information, and generate a three-dimensional location creation scheme.
[0061] In one embodiment of the present invention, the scheme creation submodule includes: The attribute field unit is used to map the location information into attribute fields that can be recognized by the Internet of Things platform. The attribute fields include spatial coordinate fields, device type fields, and unique identifier fields. The association unit is used to write the attribute fields into the database of the IoT platform through the API interface, and establish an association mapping between the attribute fields and the monitoring data in the platform; The spatial information model unit is used to generate a spatial information model based on the association mapping.
[0062] Reference Figure 4 The computer device illustrating the present invention relates to an automatic three-dimensional point creation method for the Internet of Things, and may specifically include the following: The computer device 12 described above is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).
[0063] Bus 18 refers to one or more of several types of bus 18 architectures, including memory bus 18 or memory controller, peripheral bus 18, graphics acceleration port, processor, or local bus 18 using any of the various bus 18 architectures. For example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus 18, Micro Channel Architecture (MAC) bus 18, Enhanced ISA bus 18, Audio / Video Electronics Standards Association (VESA) local bus 18, and Peripheral Component Interconnect (PCI) bus 18.
[0064] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.
[0065] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (commonly referred to as a "hard disk drive"). Although Figure 4 Not shown, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42 configured to perform the functions of the embodiments of the present invention.
[0066] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory. Such program modules 42 include—but are not limited to—an operating system, one or more application programs, other program modules 42, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.
[0067] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, camera, etc.), and with one or more devices that enable a user to interact with the computer device 12, and / or with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN)), wide area network (WAN), and / or public networks (e.g., the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although... Figure 4 Not shown, it can be combined with computer device 12 to use other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processing unit 16, external disk drive array, RAID system, tape drive and data backup storage system 34, etc.
[0068] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing an automatic three-dimensional point creation method related to the Internet of Things provided in the embodiments of the present invention.
[0069] That is, when the processing unit 16 executes the above program, it achieves the following: acquiring the two-dimensional position information of the target object and determining the two-dimensional marker position of the target object in the target area based on the two-dimensional position information; Point information is generated based on the two-dimensional marked points, and at least two reference points are generated based on the point information; wherein, the point information includes point type information, point quantity information, point location information, and point code information; Obtain the three-dimensional coordinate information corresponding to the reference point and determine the coordinate ratio based on the three-dimensional coordinate information; A three-dimensional point creation scheme is generated based on the point information and the coordinate ratio.
[0070] In this embodiment of the invention, the invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements a method for automatically creating three-dimensional points related to the Internet of Things, as provided in all embodiments of this application. That is, when the program is executed by the processor, it performs the following: acquiring the two-dimensional position information of the target object and determining the two-dimensional marker position of the target object in the target area based on the two-dimensional position information; Point information is generated based on the two-dimensional marked points, and at least two reference points are generated based on the point information; wherein, the point information includes point type information, point quantity information, point location information, and point code information; Obtain the three-dimensional coordinate information corresponding to the reference point and determine the coordinate ratio based on the three-dimensional coordinate information; A three-dimensional point creation scheme is generated based on the point information and the coordinate ratio.
[0071] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-to-signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in connection with an instruction execution system, apparatus, or device.
[0072] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.
[0073] Computer program code for performing the operations of this invention can be written in one or more programming languages or a combination thereof. These programming languages include object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider). The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably.
[0074] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.
[0075] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.
[0076] The above provides a detailed description of the method and apparatus for automatically creating three-dimensional points related to the Internet of Things. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A method for automatically creating three-dimensional points involving the Internet of Things, characterized in that, The method is used to generate three-dimensional point locations for monitoring and querying via the Internet of Things (IoT) by combining the two-dimensional location information of the target object in the target area with a three-dimensional model, including the following steps: Acquire the two-dimensional position information of the target object and determine the two-dimensional marker position of the target object in the target area based on the two-dimensional position information; Point information is generated based on the two-dimensional marked points, and at least two reference points are generated based on the point information; wherein, the point information includes point type information, point quantity information, point location information, and point code information; Obtain the three-dimensional coordinate information corresponding to the reference point and determine the coordinate ratio based on the three-dimensional coordinate information; A three-dimensional point creation scheme is generated based on the point information and the coordinate ratio.
2. The method for automatically creating three-dimensional points according to claim 1, characterized in that, The step of acquiring the two-dimensional location information of the target object and determining the two-dimensional marker position of the target object in the target area based on the two-dimensional location information includes: A two-dimensional image containing the two-dimensional location information of the target object is acquired, and a relevant primitive code of the target object is generated based on the two-dimensional image; Two-dimensional marker points are generated based on the relevant primitive codes and the two-dimensional location information; The accuracy of the two-dimensional marker points is determined by verifying them.
3. The method for automatically creating three-dimensional points according to claim 2, characterized in that, The step of verifying the two-dimensional marker points and determining their accuracy includes: A convolutional neural network is constructed and trained using a CAD primitive library, enabling the convolutional neural network to recognize two-dimensional marked points. The two-dimensional marker points are identified and verified using the convolutional neural network.
4. The method for automatically creating three-dimensional points according to claim 1, characterized in that, The step of generating point information based on the two-dimensional marked points and generating at least two reference points based on the point information includes: Based on the location information, the corresponding type characteristics are determined; wherein, the type characteristics include location functional attributes, spatial distribution characteristics, and associated equipment parameters; The locations are clustered and grouped according to the aforementioned type characteristics; Reference points are determined based on the clustering grouping.
5. The method for automatically creating three-dimensional points according to claim 1, characterized in that, The step of obtaining the three-dimensional coordinate information corresponding to the reference point and determining the coordinate scale based on the three-dimensional coordinate information includes: Obtain the three-dimensional coordinate information of the reference point; The initial coordinate ratio is determined based on the three-dimensional coordinate information and the two-dimensional coordinates of the reference point; The initial coordinate ratio is obtained by verifying the ratio of the two-dimensional coordinates of the non-reference point and the transformed three-dimensional coordinates.
6. The method for automatically creating three-dimensional points according to claim 1, characterized in that, The step of generating a 3D point creation scheme based on the point information and the coordinate ratio includes: The model points are obtained by marking them in a 3D view based on the point information and the coordinate ratio. The model points are encoded and bound to a monitoring and query scheme to obtain the points bound to the IoT platform; The IoT platform is assigned values based on the location information to generate spatial information and a three-dimensional location creation scheme.
7. The method for automatically creating three-dimensional points according to claim 6, characterized in that, The steps of assigning values to the IoT platform based on the location information, generating spatial information, and generating a 3D location creation scheme include: The location information is mapped to attribute fields that can be recognized by the Internet of Things platform. The attribute fields include spatial coordinate fields, device type fields, and unique identifier fields. The attribute fields are written into the database of the IoT platform through the API interface to establish an association mapping between the attribute fields and the monitoring data in the platform. A spatial information model is generated based on the aforementioned association mapping.
8. A three-dimensional point automatic creation and binding device involving the Internet of Things, characterized in that, include: The acquisition module is used to acquire the two-dimensional position information of the target object and determine the two-dimensional marker position of the target object in the target area based on the two-dimensional position information; The point information module is used to generate point information based on the two-dimensional marked points, and to generate at least two reference points based on the point information; wherein, the point information includes point type information, point quantity information, point location information, and point code information; The coordinate scaling module is used to obtain the three-dimensional coordinate information corresponding to the reference point and determine the coordinate scaling based on the three-dimensional coordinate information. A creation module is used to generate a three-dimensional point creation scheme based on the point information and the coordinate ratio.
9. A device for automatically creating and binding three-dimensional points in the context of the Internet of Things, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method for automatically creating and binding three-dimensional points related to the Internet of Things as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the method for automatically creating and binding three-dimensional points related to the Internet of Things as described in any one of claims 1 to 7.