Visual power distribution network modeling method, system, equipment and medium

Abstract

The invention provides a visual power distribution network modeling method, system and device and a medium, and the method comprises the steps: building a three-dimensional model corresponding to a power distribution network based on the geographic position data of facilities in the power distribution network; performing object detection and identification on the video stream of the area where the power distribution network is located to obtain position information and state information of facilities in the power distribution network; based on the position information, mapping the state information to the three-dimensional model to obtain a real scene layer corresponding to the power distribution network; and taking the three-dimensional model as a scene layer corresponding to the power distribution network, and fusing the scene layer with the real scene layer to obtain a three-dimensional scene model of the power distribution network. According to the method, the actual operation condition of the facilities in the power distribution network can be comprehensively and accurately reflected on the basis of the omnibearing visual three-dimensional scene model.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network operation analysis, and particularly to a modeling method, system, device and medium for a visual distribution network. Background Art

[0002] As an important part of the urban power system, the distribution network undertakes the key task of distributing the electric energy sent by the high-voltage transmission line to each end user. With the growth of power demand and the acceleration of new energy access, the traditional distribution network monitoring and management methods often rely on manual inspections and manual records, resulting in problems such as untimely information acquisition and inaccurate data processing. Moreover, the traditional distribution network simulation methods are usually based on static models and it is difficult to obtain the system dynamic changes and complex distribution scenarios. Summary of the Invention

[0003] In order to solve the problems of the prior art, the present invention proposes a modeling method, system, device and medium for a visual distribution network, aiming to comprehensively and accurately reflect the actual operation status of the facilities in the distribution network based on an all-round visual three-dimensional scene model.

[0004] The object of the present invention is achieved by the following technical solutions:

[0005] On the one hand, the present invention provides a modeling method for a visual distribution network, the method comprising:

[0006] Based on the geographical location data of the facilities in the distribution network, building a three-dimensional model corresponding to the distribution network;

[0007] Performing object detection and recognition on the video stream of the area where the distribution network is located to obtain the position information and status information of the facilities in the distribution network;

[0008] Based on the position information, mapping the status information into the three-dimensional model to obtain a real scene layer corresponding to the distribution network;

[0009] Taking the three-dimensional model as a scene layer corresponding to the distribution network and fusing it with the real scene layer to obtain a three-dimensional scene model of the distribution network.

[0010] Optionally, the geographical location data includes: the elevation information of the facilities in the distribution network and the initial coordinates in the geocentric coordinate system. Building the three-dimensional model corresponding to the distribution network based on the geographical location data of the facilities in the distribution network includes:

[0011] Converting the initial coordinates in the geocentric coordinate system into target coordinates in the plane rectangular coordinate system;

[0012] Input the elevation information and the target coordinates into 3D modeling software, and combine them using an interpolation algorithm to obtain the intermediate model corresponding to the distribution network;

[0013] Perform scene rendering on the intermediate model to obtain the 3D model.

[0014] Optionally, the object detection and recognition of the video stream to obtain the position information and status information of the facilities in the distribution network includes:

[0015] Perform video decoding and video frame preprocessing on the video stream in sequence to obtain a video frame sequence;

[0016] Use a trained object recognition network to perform object detection and recognition on the video frame sequence to obtain the position information and the status information.

[0017] Optionally, the position information includes: the pixel coordinates of the facilities in the distribution network in the video frames of the video stream. Based on the position information, map the status information to the 3D model to obtain the real scene layer corresponding to the distribution network, including:

[0018] Use the first conversion relationship between the pixel coordinate system and the camera coordinate system, and the second conversion relationship between the world coordinate system and the camera coordinate system to convert the pixel coordinates into 3D space coordinates;

[0019] Based on the 3D space coordinates, map the status information to the 3D model to obtain the real scene layer corresponding to the distribution network.

[0020] Optionally, the mapping of the status information to the 3D model based on the 3D space coordinates to obtain the real scene layer corresponding to the distribution network includes:

[0021] Based on the 3D space coordinates, map the status information to the 3D model to obtain an initial dynamic layer;

[0022] Cover the texture information extracted from the video frames of the video stream onto the initial dynamic layer to obtain the real scene layer corresponding to the distribution network.

[0023] Optionally, after using the 3D model as the scene layer corresponding to the distribution network and fusing it with the real scene layer to obtain the 3D scene model of the distribution network, the method further includes:

[0024] Perform object detection and recognition on a new video stream in the area where the distribution network is located to obtain the to-be-updated position information and to-be-updated status information of the facilities in the distribution network;

[0025] Using the to-be-updated location information and the to-be-updated status information, update the three-dimensional scene model to obtain the updated three-dimensional scene model.

[0026] Correspondingly, the present invention further provides a modeling system for a visualized distribution network, and the system includes:

[0027] A building module, configured to build a three-dimensional model corresponding to the distribution network based on the geographical location data of the facilities in the distribution network;

[0028] An identification module, configured to perform object detection and identification on the video stream of the area where the distribution network is located to obtain the location information and status information of the facilities in the distribution network;

[0029] A mapping module, configured to map the status information to the three-dimensional model based on the location information to obtain a real-scene layer corresponding to the distribution network;

[0030] A fusion module, configured to use the three-dimensional model as a scene layer corresponding to the distribution network and fuse it with the real-scene layer to obtain a three-dimensional scene model of the distribution network.

[0031] Optionally, the geographical location data includes: the elevation information of the facilities in the distribution network and the initial coordinates in the geocentric coordinate system,

[0032] The building module is specifically configured to convert the initial coordinates in the geocentric coordinate system into target coordinates in the plane rectangular coordinate system;

[0033] Input the elevation information and the target coordinates into three-dimensional modeling software, and use an interpolation algorithm for combination to obtain an intermediate model corresponding to the distribution network;

[0034] Perform scene rendering on the intermediate model to obtain the three-dimensional model.

[0035] Optionally, the identification module is specifically configured to sequentially perform video decoding and video frame preprocessing on the video stream to obtain a video frame sequence;

[0036] Use a trained object recognition network to perform object detection and identification on the video frame sequence to obtain the location information and the status information.

[0037] Optionally, the location information includes: the pixel coordinates of the facilities in the distribution network in the video frames of the video stream,

[0038] The mapping module is specifically configured to use a first conversion relationship between the pixel coordinate system and the camera coordinate system and a second conversion relationship between the world coordinate system and the camera coordinate system to convert the pixel coordinates into three-dimensional space coordinates;

[0039] Based on the three-dimensional spatial coordinates, map the state information into the three-dimensional model to obtain the real-scene layer corresponding to the distribution network.

[0040] Optionally, the mapping module is specifically configured to map the state information into the three-dimensional model based on the three-dimensional spatial coordinates to obtain an initial dynamic layer;

[0041] Overlay the texture information extracted from the video frames of the video stream onto the initial dynamic layer to obtain the real-scene layer corresponding to the distribution network.

[0042] Optionally, the system further includes:

[0043] An update module, configured to perform object detection and recognition on a new video stream in the area where the distribution network is located, to obtain the to-be-updated position information and to-be-updated state information of the facilities in the distribution network;

[0044] Use the to-be-updated position information and the to-be-updated state information to update the three-dimensional scene model to obtain the updated three-dimensional scene model.

[0045] On the other hand, the present invention further provides an electronic device, including: at least one processor and a memory; the memory and the processor are connected by a bus;

[0046] The memory is used to store one or more programs;

[0047] When the one or more programs are executed by the at least one processor, the modeling method of the visual distribution network as described in any one of the above is implemented.

[0048] On yet another aspect, the present invention further provides a readable storage medium, on which an execution program is stored, and when the execution program is executed, the modeling method of the visual distribution network as described in any one of the above is implemented.

[0049] Compared with the prior art, the beneficial effects of the present invention are:

[0050] The present invention provides a modeling method, system, device and medium for a visual distribution network. First, based on the geographical location data of the facilities in the distribution network, a three-dimensional model corresponding to the distribution network is built. Then, object detection and recognition are performed on the video stream of the area where the distribution network is located to obtain the position information and status information of the facilities in the distribution network, and based on this position information, the status information is mapped to the three-dimensional model to obtain a real scene layer corresponding to the distribution network. Finally, the three-dimensional model is used as the scene layer corresponding to the distribution network and fused with the real scene layer to obtain a three-dimensional scene model of the distribution network. In this way, based on the fusion of the scene layer and the real scene layer corresponding to the distribution network, a three-dimensional scene model of the distribution network with multi-level visualization is constructed, which can comprehensively and accurately reflect the actual operation status of the facilities in the distribution network based on the omni-directional visualization three-dimensional scene model, thereby improving the efficiency and accuracy of distribution network management and reducing the maintenance cost of the facilities in the distribution network.

[0051] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the technical solutions provided by the embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings, where:

[0053] Figure 1 It is a schematic flowchart of a modeling method for a visual distribution network provided by an embodiment of the present invention;

[0054] Figure 2 It is a schematic flowchart of modeling using the modeling method for a visual distribution network provided by the present invention;

[0055] Figure 3 It is a schematic diagram of the composition of a modeling system for a visual distribution network provided by an embodiment of the present invention;

[0056] Figure 4 It is a schematic diagram of the composition of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for explaining the present invention, rather than limiting the protection scope of the present invention.

[0058] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0059] In the following description, the terms "first / second / third" are only used to distinguish similar objects, and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged with a specific order or sequence when permitted, so that the embodiments of the present invention described here can be implemented in an order other than that illustrated or described here.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the embodiments of the present invention belong. The terms used herein are only for the purpose of describing the embodiments of the present invention, and are not intended to limit the embodiments of the present invention.

[0061] As an important part of the urban power system, the distribution network undertakes the key task of distributing the electric energy sent by the high-voltage transmission line to each end user. With the growth of power demand and the acceleration of new energy access, the traditional distribution network monitoring and management methods often rely on manual inspections and manual records, resulting in problems such as untimely information acquisition and inaccurate data processing. Moreover, the traditional distribution network simulation methods are usually based on static models, and it is difficult to obtain the system's dynamic changes and complex distribution scenarios.

[0062] Meanwhile, with the increase in renewable energy, the popularization of electric vehicles, and the development of smart grid technologies, the requirements for real-time scheduling, fault tolerance, and security of distribution network systems are becoming increasingly high. In related technologies, considering visual dynamic modeling, a distribution network model with higher fineness needs to be established, which covers various types of equipment, topological structures, and their corresponding operating states. In addition, the non-linear characteristics and dynamic responses of the system need to be involved, including: load changes, fault occurrence and recovery processes, etc. In this way, it is necessary to rely on a real-time data acquisition system, such as sensors, monitoring devices, and data collected by a Supervisory Control and Data Acquisition (SCADA) system, to be input into the simulation model in real time. These data can provide accurate system state information for dynamic modeling to support real-time updates and dynamic adjustments of the modeling. However, the existing distribution network simulation systems still have the following three deficiencies:

[0063] (1) It cannot accurately reflect the complex functions and control strategies in the distribution network, especially showing certain limitations in multi-level control and distributed energy management. For example, there are obvious differences between the corresponding simulation results in the existing distribution network simulation system and the actual operation details captured by visual dynamics, such as load transfer, distributed generation, etc.

[0064] (2) Most of the existing distribution network simulation systems rely on offline data modeling and are difficult to perform accurate simulations in a real-time dynamic environment. For example, when the actual load changes or emergencies in the distribution network are captured by visual dynamics, the existing distribution network simulation systems have a response lag and thus cannot synchronize with the rapid adjustment of the real power grid.

[0065] (3) Although the existing distribution network simulation systems can prevent and handle some common grid faults, their fault identification and handling speeds are far from the actual performance of the real power grid. That is, through real-time monitoring, it can be clearly seen that there are differences in the responses when faults occur. The existing distribution network simulation systems have a certain lag in fast response and recovery capabilities.

[0066] In view of the above deficiencies, the present invention provides a modeling method, system, device, and medium for a visual distribution network. Based on the fusion of the corresponding scenario layer and the real scene layer of the distribution network, a three-dimensional scene model of the distribution network with multi-level visualization is constructed, which can comprehensively and accurately reflect the actual operating conditions of the facilities in the distribution network based on the three-dimensional scene model with all-round visualization, thereby improving the efficiency and accuracy of distribution network management and reducing the maintenance costs of the facilities in the distribution network.

[0067] Example 1:

[0068] The embodiment of the present invention provides a modeling method for a visual distribution network. Refer to Figure 1As shown, it is a schematic flowchart of a modeling method for a visual distribution network provided by an embodiment of the present invention. In combination with Figure 1 The following is an explanation of the modeling method for the visual distribution network:

[0069] Step 101: Based on the geographical location data of the facilities in the distribution network, build a three-dimensional model corresponding to the distribution network.

[0070] In some embodiments of the present invention, the distribution network refers to a medium- and low-voltage power grid system that transmits high-voltage electricity to each power consumption point and is an important part of the power system. Correspondingly, the facilities in the distribution network include but are not limited to: substations, distribution transformers, cables, switchgear, etc.

[0071] In some embodiments of the present invention, taking the geographical location data of the facilities in the distribution network as an example of the geographical location data of the substations in the distribution network, it can be expressed as: the coordinates of the substations in the distribution network in the geocentric coordinate system. In the present invention, the representation form of the geographical location data is not limited.

[0072] In some embodiments of the present invention, the geographical location data of the facilities in the distribution network can be the geographical location data provided by the Geographic Information System (GIS) corresponding to the facilities in the distribution network. Further, through the combination of the GIS technology corresponding to the facilities in the distribution network and the three-dimensional modeling technology (which can be used to provide the polygon representation of the facilities in the distribution network), a three-dimensional model corresponding to the distribution network can be constructed to intuitively display the geographical location and layout of the facilities in the distribution network.

[0073] It should be noted that the GIS technology corresponding to the facilities in the distribution network is mainly used to store, analyze, and manage the geographical spatial data of the facilities in the distribution network. The GIS technology can provide the geographical location data of the facilities in the distribution network, such as: the location information of substations, lines, distributed energy, etc. And these geographical location data are usually stored in the form of coordinates (for example: longitude, latitude, elevation) to ensure the accuracy of the data.

[0074] In some embodiments of the present invention, the geographical location data in Step 101 includes: the elevation information of the facilities in the distribution network and the initial coordinates in the geocentric coordinate system. Correspondingly, the above Step 101 can be implemented in the following ways of Step 1011 to Step 1013 (not shown in the figure):

[0075] Step 1011: Convert the initial coordinates in the geocentric coordinate system into target coordinates in the plane rectangular coordinate system.

[0076] In some embodiments of the present invention, the geocentric coordinate system may be the World Geodetic System-1984 Coordinate System (WGS-84); wherein, the WGS-84 coordinate system is a space rectangular coordinate system established with the geocenter of the earth as the origin. Correspondingly, the plane rectangular coordinate system may be the Universal Transverse Mercator Grid System (UTM), that is, the UTM coordinate system.

[0077] It should be noted that in practical applications, the position coordinates in the geographical location data of the facilities in the distribution network are usually represented by the coordinate data in the WGS-84 coordinate system, while in 3D modeling, it is usually necessary to convert to a coordinate system more suitable for regional measurement, such as: the coordinate data in the UTM coordinate system.

[0078] In some embodiments of the present invention, it is necessary to first convert the initial coordinates (λ, φ) of the facilities in the distribution network in the geocentric coordinate system, that is, the WGS-84 coordinate system, into a plane rectangular coordinate system, such as: the target coordinates (X, Y) in the UTM coordinate system (i.e., the projected plane coordinates). The corresponding geographic coordinate projection conversion can be referred to the following formula (1):

[0079]

[0080] where λ is the longitude and φ is the latitude; λ 0 is the reference longitude (usually the central meridian). Here, through the coordinate conversion of formula (1), the geographical information of the facilities in the distribution network, that is, the geographical location data, can accurately represent the actual position information of the facilities in the distribution network in the 3D modeling software subsequently.

[0081] In some embodiments of the present invention, tools such as remote sensing technology, Global Positioning System (GPS) surveying equipment, and laser scanners can be used to collect the geographical data and elevation information of the facilities in the distribution network, and obtain the initial coordinates of the facilities in the distribution network in the geocentric coordinate system and the elevation information of the facilities in the distribution network. Here, these geographical location data and elevation information can be further converted into vector maps (such as: Shapefile) or raster maps.

[0082] Step 1012: Input the elevation information and the target coordinates into 3D modeling software, and combine them using an interpolation algorithm to obtain the intermediate model corresponding to the distribution network.

[0083] In some embodiments of the present invention, the elevation information (i.e., the height information of the facilities) of the facilities in the distribution network can be obtained from the Digital Elevation Model (DEM) data of the facilities in the distribution network; then, the target coordinates and the elevation information are simultaneously input into 3D modeling software, such as CityEngine, SketchUp, ArcGIS Pro, so as to use these 3D modeling software to convert the target coordinates and the elevation information into an intermediate model corresponding to the distribution network. Specifically, the 3D modeling software can adopt an interpolation algorithm (such as bilinear interpolation algorithm, Kriging interpolation algorithm, etc.) to combine the height information with the target coordinates (the target coordinates are coordinates in the plane rectangular coordinate system, that is, a two-dimensional coordinate), so as to obtain the grid data of the facilities in the distribution network, and thus an intermediate model of the distribution network can be constructed based on the grid data; wherein, the height value of each grid point in the grid data of the facilities in the distribution network can be calculated by the following formula (2):

[0084] Z = f(x, y) Formula (2);

[0085] wherein, Z is the elevation value, that is, the height (elevation) information, (x, y) are the horizontal and vertical coordinates of the grid data; f(x, y) is the interpolation function. In this way, by using the 3D modeling technology, on the basis of obtaining the target coordinates of the facilities in the distribution network in the plane rectangular coordinate system, the elevation data of the facilities in the distribution network is interpolated and meshed accordingly, so as to obtain an intermediate model of the distribution network, the geographical location included therein not only involves the plane coordinates of the facilities in the distribution network, but also includes the elevation information of the facilities in the distribution network, thus an intermediate model that can initially represent the 3D scene of the distribution network can be obtained.

[0086] In some embodiments of the present invention, through the 3D modeling technology, the elevation information and the target coordinates of the facilities in the distribution network are converted into the data required for building a 3D scene of the distribution network, so as to generate a realistic distribution network model, that is, the intermediate model described in the text.

[0087] Step 1013, perform scene rendering on the intermediate model to obtain the 3D model.

[0088] In some embodiments of the present invention, the constructed intermediate model can be further graphically rendered by using graphic rendering technology (such as OpenGL, WebGL or Unreal Engine, etc.) to generate a high-precision visual model of the distribution network, that is, the 3D model. Here, in the process corresponding to the graphic rendering technology, technologies such as texture mapping, lighting effects, and ambient lighting can all be used, so as to enhance the authenticity and visualization effect of the scene corresponding to the 3D model of the distribution network.

[0089] Correspondingly, during the process of constructing the 3D model of the distribution network, texture information is usually required to be pasted on the surface of the 3D model to enhance the realism of the 3D model. Among them, texture mapping can use UV mapping technology to map a 2D texture (which can be provided based on the image information corresponding to the facilities in the distribution network here) to the surface of the intermediate model to obtain the 3D model of the distribution network. The corresponding mapping formula can refer to the following formula (3):

[0090] (U, V) = (x' / W, y' / H) Formula (3);

[0091] Among them, (U, V) are the 2D texture coordinates, (x', y') are the coordinates of the surface points in the intermediate model, and W and H are the width and height of the image corresponding to the facilities in the distribution network for providing the 2D texture.

[0092] In some embodiments of the present invention, a real-time rendering engine (such as: Unity 3D or Unreal Engine, etc.) can also be used for rendering to generate a dynamic visualization effect on the basis of the intermediate model to obtain the final 3D model corresponding to the distribution network.

[0093] It should be noted that the subsequent 3D model can be used as a scene layer in the 3D scene model for constructing the simulation system corresponding to the distribution network; among them, the scene layer can be used to provide the visualization background of the distribution network, that is, a static layer. Here, that is, the scene layer forms an association between the GIS data (including elevation information and position coordinates) of all facilities in the distribution network through the use of 3D modeling software, so as to ensure the accurate geographical positioning of the facilities in the distribution network corresponding to the generated 3D model.

[0094] In this way, through the combination of GIS technology and 3D modeling, the 3D model corresponding to the distribution network (the visualization background of the distribution network) is obtained, which can realize the accurate geographical positioning and dynamic simulation of the facilities in the distribution network. In addition, during the process of building the 3D model, it also involves: geographic coordinate projection, elevation data interpolation, 3D modeling and texture mapping, etc. It can not only ensure the high consistency between the subsequent 3D model as the scene layer and the layout of the facilities in the actual power grid, thereby improving the accuracy and reliability of the simulation and management of the distribution network. And it can make the facilities, line layout, terrain features and surrounding environment, etc. in the distribution network be intuitively presented on the visualization interface, and can provide parameter support for subsequent real-time update and interaction, so as to provide accurate and comprehensive support for the management and dispatching of the facilities in the distribution network.

[0095] Step 102, perform object detection and recognition on the video stream in the area where the distribution network is located to obtain the position information and status information of the facilities in the distribution network.

[0096] In some embodiments of the present invention, devices such as cameras and drones deployed or installed within the distribution network can be used to capture in real time the power grid facilities, equipment operations, line status, and environmental conditions, etc. within the corresponding site of the distribution network. Specifically, relevant data acquisition devices can be used to capture dynamic information such as changes in the status and load of facilities within the distribution network, and changes in the environment where the distribution network is located, so as to obtain a video stream of the area where the distribution network is located. And this video stream is usually transmitted in high-definition format to ensure the clarity of the image, thereby providing parameter support for subsequent accurate analysis of relevant data.

[0097] In some embodiments of the present invention, the video stream of the area where the distribution network is located refers to the real-time video stream within the area where the distribution network is located.

[0098] In some embodiments of the present invention, the status information of the facilities within the distribution network includes but is not limited to: the status of the facilities within the distribution network, load changes, etc.; correspondingly, the location information of the facilities within the distribution network includes: the pixel coordinates of the facilities within the distribution network in the video stream.

[0099] It should be noted that through deep learning algorithms, such as single-stage object detection networks (You Only Look Once, YOLO), faster region convolutional neural networks (Faster Region-Convolutional Neural Networks, Faster R-CNN), etc., facilities, equipment, and related environmental elements within the distribution network can be detected and recognized in the video frames of the video stream to obtain relevant location information and status information.

[0100] It should be noted that a video stream is a layer that transmits and processes video content (images and audio) in a continuous streaming media manner. It is captured by cameras, drones, or other monitoring devices and transmitted through a network to a central server or client for analysis and display. It can be transmitted in real time or played after recording.

[0101] In some embodiments of the present invention, object detection and recognition are performed on the video stream of the area where the distribution network is located. Here, the object can refer to various facilities or equipment within the distribution network, etc., so as to obtain the location information and status information of the facilities within the distribution network corresponding to the video stream.

[0102] In some embodiments of the present invention, the above step 102 can be implemented in the following manner of step 1021 and step 1022 (not shown in the figure):

[0103] Step 1021: Sequentially perform video decoding and video frame preprocessing on the video stream to obtain a video frame sequence.

[0104] In some embodiments of the present invention, after the video stream is accessed, the video stream can be first decoded (the video stream usually uses encoding formats such as H.264 or H.265), and each frame of the image is extracted in sequence, that is, an image frame sequence is obtained. Here, after the image frame sequence is obtained, image preprocessing is further performed on each image frame in the image frame sequence, including but not limited to: operations such as denoising, brightness adjustment, and color balance, to obtain a video frame sequence. In this way, through image preprocessing, it can be ensured that the quality of the obtained video frame sequence meets the requirements of subsequent relevant analysis.

[0105] Step 1022: Use the trained object recognition network to perform object detection and recognition on the video frame sequence to obtain the position information and the status information.

[0106] In some embodiments of the present invention, the trained object recognition network (i.e., deep learning algorithm) includes but is not limited to: trained YOLO, trained Faster R-CNN, etc.; correspondingly, use the trained object recognition network to perform object detection and recognition on each frame of the video frame sequence extracted to obtain the position information and the status information of facilities in the distribution network, such as: substations, transformers, lines, and equipment, etc. In addition, relevant environmental elements in the video frame sequence can also be recognized.

[0107] In this way, by performing object detection and recognition on the video stream in the area where the distribution network is located, the position information and the status information of objects such as facilities in the distribution network, such as: substations, transformers, lines, and equipment, etc., can be obtained, so as to provide parameter support for building the scene layer of the distribution network subsequently.

[0108] Step 103: Based on the position information, map the status information to the 3D model to obtain the real scene layer corresponding to the distribution network.

[0109] In some embodiments of the present invention, based on determining the position information of facility 1 in the distribution network, the recognized status information of facility 1 can be correspondingly mapped to the corresponding area of facility 1 in the 3D model to obtain the real scene layer 1 of facility 1, and so on, that is, the real scene layer composed of all facilities of the distribution network can be obtained. Here, the real scene layer can be a dynamic layer.

[0110] It should be noted that after the object detection in the video stream is completed, that is, after the position information and status information of the facilities in the distribution network are obtained, these information (position information and status information) can be transmitted to the corresponding 3D model of the distribution network in real time. Here, the modeling system corresponding to the 3D model can map the status information of the facilities in the video stream to the 3D model according to the identified static information, that is, the position information of the facilities in the distribution network in the video stream, that is, map it to the corresponding 3D scene of the distribution network, so as to realize the dynamic update of the facilities in the distribution network. For example: when the camera deployed in the area where the distribution network is located captures a substation or a transmission line in the distribution network, the corresponding acquisition data forms a video stream, and then the information in the video stream is presented in the corresponding 3D model of the distribution network in real time, that is, the dynamic fusion of the video stream and the 3D model is realized to dynamically reflect the operation status and changes of the facilities in the distribution network.

[0111] In some embodiments of the present invention, the position information includes: the pixel coordinates of the facilities in the distribution network in the video frames of the video stream, and the above step 103 can be implemented in the following ways of step 1031 and step 1032 (not shown in the figure):

[0112] Step 1031: Use the first conversion relationship between the pixel coordinate system and the camera coordinate system, and the second conversion relationship between the world coordinate system and the camera coordinate system to convert the pixel coordinates into three-dimensional space coordinates.

[0113] In some embodiments of the present invention, first, based on the first conversion relationship between the pixel coordinate system and the camera coordinate system, the pixel coordinates of the facilities in the distribution network in the video frames of the video stream can be converted into the camera coordinate system to obtain the first coordinate, and then based on the second conversion relationship between the world coordinate system and the camera coordinate system, the first coordinate is converted into the world coordinate system to obtain the actual physical coordinates of the facilities in the distribution network.

[0114] In some embodiments of the present invention, in order to map the information extracted from the obtained video stream (video frame sequence), such as: the status information, to the corresponding 3D model of the distribution network, it is necessary to convert the object coordinates of the facilities in the distribution network in the video frames of the video stream, that is, the pixel coordinates, into three-dimensional space coordinates. This conversion process involves: camera calibration and perspective projection conversion, etc., that is, it can be implemented by the following formula (4):

[0115]

[0116] Wherein: (X, Y, Z) are the coordinates of an object in three-dimensional space; (x', y') are the pixel coordinates of the facilities in the power distribution network in the video frame of the video stream; K is the acquisition device corresponding to the acquired video stream, such as: the camera internal parameter matrix, which is used to project the three-dimensional coordinates of the facilities in the power distribution network onto a two-dimensional plane; R and T are the rotation matrix and the translation matrix respectively, which describe the pose of the camera relative to the three-dimensional space. Here, the camera can be calibrated through formula (4), and the corresponding transformation matrix can be obtained, so as to accurately map the pixel coordinates of the facilities in the power distribution network in the video frame of the video stream to the three-dimensional scene, so as to obtain relatively accurate three-dimensional space coordinates.

[0117] Step 1032: Based on the three-dimensional space coordinates, map the status information to the three-dimensional model to obtain the real scene layer corresponding to the power distribution network.

[0118] In some embodiments of the present invention, for the three-dimensional model corresponding to the power distribution network, the coordinate parameters involved therein are all three-dimensional coordinates. Here, the pixel coordinates of the facilities in the power distribution network in the video frame of the video stream are converted into specific three-dimensional space coordinates, so as to realize the accurate mapping of the status information of the facilities in the power distribution network in the video frame of the video stream to the three-dimensional model according to the corresponding three-dimensional space coordinates, thereby obtaining the real scene layer corresponding to the power distribution network.

[0119] In some embodiments of the present invention, the above step 1032 can be implemented through the following process:

[0120] The first step: Based on the three-dimensional space coordinates, map the status information to the three-dimensional model to obtain the initial dynamic layer of the three-dimensional model.

[0121] The second step: Cover the texture information extracted from the video frame of the video stream onto the initial dynamic layer to obtain the real scene layer corresponding to the power distribution network.

[0122] In some embodiments of the present invention, it is also possible to first accurately map the status information of the facilities in the power distribution network in the video frame of the video stream to the three-dimensional model based on the three-dimensional space coordinates to obtain the initial dynamic layer corresponding to the power distribution network, and the initial dynamic layer only involves: the status information of the facilities in the power distribution network. Then, the corresponding texture information can be further extracted from the video frame of the video stream and the texture information can be covered onto the initial dynamic layer to obtain the final real scene layer corresponding to the power distribution network. In this way, the real scene layer can include not only: the status information of the facilities in the power distribution network, but also relevant texture data.

[0123] It should be noted that the video frames of the video stream are used as the source of texture data in the real scene image to obtain the final real scene layer through mapping and updating. For example, the video frames of the video stream or the scene texture information in the video frames can be covered on the initial dynamic layer in real time, so as to synchronize the obtained scene layer with the actual situation of the distribution network, that is, it can ensure that the information presented by the subsequent three-dimensional scene model of the distribution network (based on the fusion of the scene layer and the three-dimensional model of the distribution network) is synchronized with the actual situation information of the distribution network. Here, the mapping or covering technology corresponding to the relevant texture information can also adopt the UV mapping technology, and its specific implementation can refer to the above description of step 1013, and the present invention will not elaborate on this.

[0124] In this way, first based on the three-dimensional space coordinates, the state information of the facilities in the distribution network in the video frames of the video stream is accurately mapped to the three-dimensional model to obtain the initial dynamic layer, and then the corresponding texture information is extracted from the video frames of the video stream and covered on the initial dynamic layer to obtain the real scene layer corresponding to the distribution network. In this way, it can be realized that the obtained real scene layer not only includes the state information of the facilities in the distribution network, but also can include relevant texture data, so as to further realize the synchronization of the information included in the obtained scene layer with the actual situation of the distribution network.

[0125] In this way, with the help of coordinate transformation, it can be realized that the video stream in the area where the distribution network is located is accessed into the three-dimensional model corresponding to the distribution network, that is, the corresponding real scene layer is obtained. It can provide parameter support for the subsequent construction of the three-dimensional scene model of the distribution network, so that the three-dimensional scene model can realize the visualization and real-time simulation of the distribution network, so as to realize the real-time and dynamic reflection of the facilities and environment in the distribution network and the actual situation.

[0126] Step 104: Use the three-dimensional model as the scene layer corresponding to the distribution network, and fuse it with the real scene layer to obtain the three-dimensional scene model of the distribution network.

[0127] In some embodiments of the present invention, further, the obtained three-dimensional model can be used as the scene layer corresponding to the distribution network, and fused with the obtained real scene layer corresponding to the distribution network to construct the three-dimensional scene model of the distribution network. That is, the three-dimensional scene model is a multi-level visualization scene model.

[0128] Based on the above description, after performing step 104, the following steps A1 and A2 can also be performed:

[0129] Step A1: Perform object detection and recognition on the new video stream in the area where the distribution network is located to obtain the to-be-updated position information and to-be-updated state information of the facilities in the distribution network.

[0130] In some embodiments of the present invention, object detection and recognition can be performed on a new video stream in the area where the distribution network is located to obtain the position information and status to be updated of the distribution network facilities. Here, the specific execution logic is similar to that of step 102 above, and its implementation can refer to the above description of step 102. The present invention will not elaborate on this.

[0131] It should be noted that the position information to be updated and the status information to be updated can be the same as or different from the position information and status information involved above. The present invention does not make any limitation on this.

[0132] Step A2: Update the three-dimensional scene model by using the position information to be updated and the status information to be updated, so as to obtain the updated three-dimensional scene model.

[0133] In some embodiments of the present invention, first, based on the position information to be updated, the current position information in the three-dimensional scene model can be updated to obtain an intermediate three-dimensional scene model with updated position information; then, the status information to be updated is mapped to the intermediate three-dimensional scene model with updated position information correspondingly based on the position information in the intermediate three-dimensional scene model with updated position information, so as to obtain the updated three-dimensional scene model. In this way, the status information and position information in the real scene layer in the three-dimensional scene model can be updated synchronously.

[0134] In this way, the three-dimensional scene model is updated in real time through the real-time updated real-time stream, that is, the new video stream in the area where the distribution network is located, so as to view the real-time dynamic information of the facilities in the distribution network in real time, thereby providing parameter support for the subsequent management of the distribution network.

[0135] It should be noted that the real scene layer is obtained based on the video stream in the area where the distribution network is located. In this solution, it is a real-time video stream, that is, the real scene layer integrates the real-time monitoring data corresponding to the facilities and the environment in the distribution network, so as to reflect the current operation status of the facilities in the distribution network, so that the relevant operation users of the distribution network can obtain important information in time and make effective decisions. Further, it is combined with the three-dimensional model, that is, the scene layer, to obtain the three-dimensional scene model of the distribution network, which can not only realize the visualization of the layout of the distribution network, but also enable the relevant operators to obtain the operation conditions of the facilities in the distribution network, so as to further promote the rapid decision-making on the relevant facilities in the distribution network.

[0136] In some embodiments of the present invention, the three-dimensional scene model of the distribution network can also evaluate the environmental changes in the distribution network in real time (such as: light, weather, activity patterns) to automatically adjust the deployment configuration of the acquisition units (camera units) deployed in the area where the distribution network is located. For example, when an emergency occurs in the area where the distribution network is located (such as: a large gathering or a traffic accident) with the help of this three-dimensional scene model, the number of cameras in the area where the emergency occurs can be immediately increased or their angles can be adjusted to capture more detailed scene data, so as to combine the real-time collected video data and multi-source sensor data subsequently to generate an interactive virtual reality (VR) / augmented reality (AR) live scene layer. Here, the relevant operation users corresponding to the distribution network can view enhanced information (such as: navigation, facility status) in the real environment by wearing devices.

[0137] It should be noted that the three-dimensional scene model of the distribution network involved in the embodiments of the present invention is essentially a three-dimensional (3D) model of the real scene information of the distribution network generated according to the data collected by the camera units deployed in the area where the distribution network is located, so as to specifically present the real-time environmental changes of the distribution network. Subsequently, due to its ability to have real-time rendering layers and automatic modeling, this three-dimensional model can also be used in fields such as urban planning and environmental monitoring.

[0138] The modeling method of the visual distribution network provided by the present invention is as follows: First, based on the geographical location data of the facilities in the distribution network, a three-dimensional model corresponding to the distribution network is built; then, object detection and recognition are performed on the video stream in the area where the distribution network is located to obtain the location information and status information of the facilities in the distribution network, and based on this location information, the status information is mapped to the three-dimensional model to obtain the live scene layer corresponding to the distribution network; finally, the three-dimensional model is used as the scene layer corresponding to the distribution network and fused with the live scene layer to obtain the three-dimensional scene model of the distribution network. In this way, based on the fusion of the scene layer and the live scene layer corresponding to the distribution network, a three-dimensional scene model of the distribution network with multi-level visualization is constructed, which can comprehensively and accurately reflect the actual operation status of the facilities in the distribution network based on the all-round visual three-dimensional scene model, thereby improving the efficiency and accuracy of distribution network management and reducing the maintenance cost of the facilities in the distribution network.

[0139] That is to say, the object of the present invention is to provide a dynamic visualization power distribution network modeling method based on video stream access to solve the deficiencies in aspects such as complex function simulation, real-time dynamic response, and fault handling in the existing power distribution network. Compared with the traditional offline data modeling method, the present invention builds a three-dimensional scene model of the power distribution network to form a real-time simulation system of the power distribution network. On the one hand, through the integration of real-time dynamic data and multi-level (such as: scene layer, real scene layer) control strategies, the present invention accurately simulates complex functions such as load transfer and distributed energy management in the power distribution network, and can overcome the limitation that the simulation system of the power distribution network in the prior art is difficult to reflect actual operation details. On the one hand, through the access of the video stream, the present invention can more comprehensively and accurately reflect the actual operation status of the facilities in the power distribution network, and can achieve a high degree of consistency with the operation details in the actual power distribution network, thus making up for the deficiencies in multi-level control and distributed energy management of the simulation system built in the prior art. In addition, the three-dimensional scene model built by the present invention also combines real-time monitoring technology to dynamically capture the load changes and emergencies in the power distribution network to ensure that the response speed of the facilities in the simulated power distribution network is synchronized with the data in the real power distribution network, so as to make up for the lag problem of the existing offline modeling in a dynamic environment. And the present invention can quickly identify and respond when a fault occurs to improve the timeliness and accuracy of fault handling, thereby improving the operation efficiency of the power distribution network.

[0140] The present invention can realize a dynamic visualization power distribution network modeling method and system based on video stream access through drone oblique aerial photography, high-precision three-dimensional modeling, and real-time data integration in the area where the power distribution network is located, so as to realize the full-range visualization and intelligent monitoring of the operation state of the power distribution network, and further significantly improve the efficiency and accuracy of power distribution network management. And with the help of the high-resolution images obtained by the drone, a high-precision three-dimensional scene model of the power distribution network can be generated to truly reflect the geometric shape and operation state of the facilities in the power distribution network. In addition, combined with real-time monitoring data, the system can dynamically update the model and display the load, operation parameters, and fault conditions of the facilities in the power distribution network in real time to facilitate the quick identification and location of relevant problems in the power distribution network.

[0141] In addition, the three-dimensional scene model built based on the integration of the scene layer and the real scene layer, that is, the visualization simulation system of the power distribution network, enables relevant operators of the power distribution network to view the three-dimensional model and operation state of the power distribution network at any time and place in a relevant browser, so as to perform equipment monitoring and fault analysis through an intuitive interface, greatly improving the convenience of operation and the efficiency of decision-making. For example: when a fault occurs in the power distribution network equipment, the system can automatically update the three-dimensional model and mark the fault location in the interface to help the operation and maintenance personnel quickly locate and respond, thus significantly shortening the fault repair time and further improving the safety and reliability of the power distribution network.

[0142] Referring to the above description, as Figure 2 shown, it is a schematic flowchart of the modeling process for modeling using the visualization distribution network modeling method provided by the present invention; among them, after the start of 201, first, the GIS technology is used to obtain the geographical location data of the distribution network facilities in 202, and the obtained geographical location data is input into the 3D modeling software to perform the 3D modeling of the distribution network, that is, 203 is executed to obtain the 3D model in 204, that is, the 3D model corresponding to the distribution network, so as to use the 3D model in 204 as the scene layer in 205 for subsequent construction of a 3D scene model with a multi-level visualization effect. Secondly, data collection is performed on the area where the distribution network is located to perform the video stream collection in 206, and the video stream obtained in 206 is decoded, that is, the decoded video stream in 207 is executed to obtain a video frame sequence, that is, 208. Then, for the obtained video frame sequence in 208, first, video frame recognition is performed, that is, 209, to recognize the position and status of the distribution network facilities in the video frame, that is, 210, and at the same time, texture extraction is performed on the video frame, that is, 211, to obtain a texture information set 212, and then the obtained texture information 212, position and status 210 are mapped to the 3D model in 204 based on relevant technical means to obtain the real scene layer of the distribution network, that is, 213. Finally, the real scene layer in 213 and the scene layer in 205 are fused to obtain a 3D scene model 214 with a multi-level visualization effect of the distribution network, and the end 215 is executed.

[0143] It should be noted that the data of the video stream can provide a data basis for real-time monitoring and interaction of the data, status and environmental information of the relevant facilities in the distribution network in the visualization simulation system corresponding to the 3D scene model of the distribution network. In this 3D scene model, the operating status of the facilities in the distribution network can be viewed in real time according to the information provided by the video stream, and the response in different scenarios can be adjusted or tested through interactive operations. For example: Equipment monitoring: The status of the equipment is monitored in real time through the video stream, such as: the temperature of the transformer, the load of the line, etc. Load transfer simulation: According to the real-time video stream data, the effect of load transfer can be simulated in the 3D scene model, and the comparison between the actual simulation result and the scene change in the video stream can be viewed.

[0144] In addition, the combination of video stream access and 3D modeling technology, that is, mapping the data (texture information, location information, and status information) extracted from the collected video stream to the 3D model of the distribution network, can enable the visualization simulation system of the distribution network, that is, this 3D scene model, to have real-time and dynamic characteristics. Further, through technologies such as video decoding, object recognition, 3D coordinate conversion, and texture mapping, the simulation system where this 3D scene model is located can map the 2D information in the video stream to the 3D scene in real time, so as to further achieve more accurate and real-time dynamic simulation and monitoring of the distribution network, as well as precise visualization of the facilities within the distribution network. And based on the intelligent object detection and recognition algorithm of deep learning, combined with the dynamic coordinate conversion technology, accurately mapping the 2D information in the video stream to the 3D space can also realize real-time update and high-precision simulation of the data in the 3D scene model, thereby being able to improve the response speed and accuracy to changes in the distribution network environment. That is to say, the modeling method of the visualized distribution network provided by the present invention can not only improve the reliability of the simulation system where the 3D scene model is located, but also provide a more efficient visualization tool and data support for the management and dispatching of the distribution network.

[0145] Generally speaking, the 3D scene model of the distribution network built in the embodiments of the present invention can significantly improve the intelligent management level of the distribution network through technology integration and visualization display, thereby being able to optimize the operation efficiency of the distribution network and reduce the maintenance cost of the facilities within the distribution network, that is, it has broad application prospects.

[0146] Embodiment 2:

[0147] Based on the same inventive concept, the present invention also provides a modeling system for a visualized distribution network. Refer to Figure 3 As shown, it is a schematic diagram of the composition of a modeling system for a visualized distribution network provided by an embodiment of the present invention. This system 300 includes:

[0148] A building module 301, configured to build the 3D model corresponding to the distribution network based on the geographical location data of the facilities within the distribution network;

[0149] An identification module 302, configured to perform object detection and recognition on the video stream in the area where the distribution network is located to obtain the location information and status information of the facilities within the distribution network;

[0150] A mapping module 303, configured to map the status information to the 3D model based on the location information to obtain the real scene layer corresponding to the distribution network;

[0151] A fusion module 304, configured to use the 3D model as the scene layer corresponding to the distribution network and fuse it with the real scene layer to obtain the 3D scene model of the distribution network.

[0152] Optionally, the geographical location data includes: the elevation information of the facilities in the distribution network and the initial coordinates in the geocentric coordinate system. The building module 301 is specifically configured to convert the initial coordinates in the geocentric coordinate system into target coordinates in the plane rectangular coordinate system;

[0153] Input the elevation information and the target coordinates into 3D modeling software, and combine them using an interpolation algorithm to obtain an intermediate model corresponding to the distribution network;

[0154] Perform scene rendering on the intermediate model to obtain the 3D model.

[0155] Optionally, the recognition module 302 is specifically configured to perform video decoding and video frame preprocessing on the video stream in sequence to obtain a video frame sequence;

[0156] Use a trained object recognition network to perform object detection and recognition on the video frame sequence to obtain the position information and the status information.

[0157] Optionally, the position information includes: the pixel coordinates of the facilities in the distribution network in the video frames of the video stream,

[0158] The mapping module 303 is specifically configured to use the first conversion relationship between the pixel coordinate system and the camera coordinate system, and the second conversion relationship between the world coordinate system and the camera coordinate system to convert the pixel coordinates into three-dimensional space coordinates;

[0159] Based on the three-dimensional space coordinates, map the status information to the 3D model to obtain a real scene layer corresponding to the distribution network.

[0160] Optionally, the mapping module 303 is specifically configured to map the status information to the 3D model based on the three-dimensional space coordinates to obtain an initial dynamic layer;

[0161] Cover the texture information extracted from the video frames of the video stream onto the initial dynamic layer to obtain a real scene layer corresponding to the distribution network.

[0162] Optionally, the system 300 further includes:

[0163] An update module, configured to perform object detection and recognition on a new video stream in the area where the distribution network is located to obtain the to-be-updated position information and to-be-updated status information of the facilities in the distribution network;

[0164] Use the to-be-updated position information and the to-be-updated status information to update the 3D scene model to obtain the updated 3D scene model.

[0165] It should be noted that the description of the modeling system of the visual distribution network is similar to the description of the above-described embodiment of the modeling method of the visual distribution network, and has beneficial effects similar to those of the method embodiment. For the technical details not disclosed in the system embodiment of the present invention, please refer to the description of the method embodiment of the present invention for understanding.

[0166] Embodiment 3:

[0167] Based on the same inventive concept, as Figure 4 shown, the present invention also provides an electronic device, which may be a computer device, a single-chip microcomputer device, a smart mobile device, etc. The electronic device in this embodiment may include a processor 410, a memory 420, a transceiver component 430, etc. The processor 410, the memory 8420, and the transceiver component 430 are connected through a bus 440; the memory 420 can be used to store an execution program, and an exemplary execution program may include instructions; the processor 410 is used to execute the instructions stored in the memory. The memory 420 can also be used to store data, and this data can be called and / or modified when the instructions are executed.

[0168] The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the storage medium to implement the corresponding method flow or corresponding function, so as to implement a modeling method of a visual distribution network in the above embodiment.

[0169] Embodiment 4:

[0170] Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device-readable storage medium (Memory). The electronic device-readable storage medium is a memory device in the electronic device and is used to store programs and data. It can be understood that the storage medium here can include both the built-in storage medium in the electronic device and, of course, the extended storage medium supported by the electronic device. The storage medium provides a storage space, and this storage space stores the operating system of the terminal. And, in this storage space, there are also stored one or more instructions suitable for being loaded and executed by the processor. These instructions can be one or more executable programs (including program codes). It should be noted that the storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor loads and executes one or more instructions stored in the storage medium to implement a method for modeling a visualized distribution network in the above-mentioned embodiments.

[0171] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0172] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0173] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0174] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable apparatus provide steps for realizing the functions specified in one process or multiple processes and / or one block or multiple blocks. Figure 1 one process or multiple processes and / or Figure 1 steps for realizing the functions specified in one block or multiple blocks.

[0175] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A modeling method for a visual distribution network, characterized in that: The method comprises: Based on the geographic location data of the facilities in the distribution network, a three-dimensional model corresponding to the distribution network is constructed; Performing object detection and recognition on the video stream of the area where the distribution network is located to obtain location information and status information of facilities in the distribution network; Based on the location information, mapping the state information to the three-dimensional model to obtain a real scene layer corresponding to the distribution network; The three-dimensional model is used as a scene layer corresponding to the distribution network and is fused with the real scene layer to obtain a three-dimensional scene model of the distribution network.

2. The method according to claim 1, characterized in that The geographic location data includes: elevation information of the facilities in the distribution network and initial coordinates in the geocentric coordinate system. The three-dimensional model corresponding to the distribution network is constructed based on the geographic location data of the facilities in the distribution network, including: Converting the initial coordinates in the geocentric coordinate system into target coordinates in a plane rectangular coordinate system; Inputting the elevation information and the target coordinates into a three-dimensional modeling software, and combining them using an interpolation algorithm to obtain an intermediate model corresponding to the distribution network; The intermediate model is subjected to scene rendering to obtain the three-dimensional model.

3. The method according to claim 1 or 2, characterized in that: The performing of object detection and recognition on the video stream to obtain location information and status information of facilities in the distribution network includes: Performing video decoding and video frame preprocessing on the video stream in sequence to obtain a video frame sequence; The trained object recognition network is used to perform object detection and recognition on the video frame sequence to obtain the position information and the state information.

4. The method according to claim 1 or 2, characterized in that: The location information includes: pixel coordinates of the facilities in the distribution network in the video frame of the video stream, and mapping the state information to the three-dimensional model based on the location information to obtain a real scene layer corresponding to the distribution network includes: The pixel coordinates are converted into three-dimensional space coordinates by using a first conversion relationship between a pixel coordinate system and a camera coordinate system and a second conversion relationship between a world coordinate system and the camera coordinate system; Based on the three-dimensional space coordinates, the state information is mapped to the three-dimensional model to obtain a real scene layer corresponding to the power distribution network.

5. The method according to claim 4, characterized in that The step of mapping the state information to the three-dimensional model based on the three-dimensional space coordinates to obtain a real scene layer corresponding to the power distribution network includes: Based on the three-dimensional space coordinates, mapping the state information to the three-dimensional model to obtain an initial dynamic layer; The texture information extracted from the video frame of the video stream is overlaid on the initial dynamic layer to obtain a real scene layer corresponding to the power distribution network.

6. The method according to claim 1, characterized in that After the three-dimensional model is used as the scene layer corresponding to the distribution network and is merged with the real scene layer to obtain the three-dimensional scene model of the distribution network, the method further includes: Performing object detection and recognition on a new video stream in the area where the distribution network is located, and obtaining the to-be-updated location information and to-be-updated status information of the facilities in the distribution network; The three-dimensional scene model is updated using the position information to be updated and the state information to be updated to obtain the updated three-dimensional scene model.

7. A modeling system for visual distribution network, characterized in that: The system comprises: A building module, used to build a three-dimensional model corresponding to the distribution network based on the geographical location data of the facilities in the distribution network; An identification module, used to perform object detection and identification on the video stream of the area where the distribution network is located, and obtain location information and status information of facilities in the distribution network; A mapping module, used to map the state information to the three-dimensional model based on the location information to obtain a real scene layer corresponding to the distribution network; A fusion module is used to use the three-dimensional model as the scene layer corresponding to the distribution network and fuse it with the real scene layer to obtain a three-dimensional scene model of the distribution network.

8. The system according to claim 7, characterized in that The geographic location data includes: the elevation information of the facilities in the distribution network and the initial coordinates in the geocentric coordinate system, The building module is specifically used to convert the initial coordinates in the geocentric coordinate system into the target coordinates in the plane rectangular coordinate system; Inputting the elevation information and the target coordinates into a three-dimensional modeling software, and combining them using an interpolation algorithm to obtain an intermediate model corresponding to the distribution network; The intermediate model is subjected to scene rendering to obtain the three-dimensional model.

9. The system according to claim 7 or 8, characterized in that: The recognition module is specifically used to perform video decoding and video frame preprocessing on the video stream in sequence to obtain a video frame sequence; The trained object recognition network is used to perform object detection and recognition on the video frame sequence to obtain the position information and the state information.

10. The system according to claim 7 or 8, characterized in that: The location information includes: pixel coordinates of the facilities in the distribution network in the video frame of the video stream, The mapping module is specifically used to convert the pixel coordinates into three-dimensional space coordinates by using a first conversion relationship between a pixel coordinate system and a camera coordinate system, and a second conversion relationship between a world coordinate system and the camera coordinate system; Based on the three-dimensional space coordinates, the state information is mapped to the three-dimensional model to obtain a real scene layer corresponding to the power distribution network.

11. The system according to claim 10, characterized in that The mapping module is specifically used to map the state information to the three-dimensional model based on the three-dimensional space coordinates to obtain an initial dynamic layer; The texture information extracted from the video frame of the video stream is overlaid on the initial dynamic layer to obtain a real scene layer corresponding to the power distribution network.

12. The system according to claim 7, characterized in that The system further comprises: An updating module, used for performing object detection and recognition on a new video stream in the area where the distribution network is located, and obtaining location information and status information to be updated of facilities in the distribution network; The three-dimensional scene model is updated using the position information to be updated and the state information to be updated to obtain the updated three-dimensional scene model.

13. An electronic device, characterized in that: include: at least one processor and memory; The memory and the processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, the modeling method of a visualized power distribution network according to any one of claims 1 to 6 is implemented.

14. A readable storage medium, characterized in that: An execution program is stored thereon, and when the execution program is executed, the modeling method of a visualized distribution network as described in any one of claims 1 to 6 is implemented.

Images