Semi-closed electric power scene three-dimensional space model construction method, monitoring method and system
Through multi-sensor fusion and deep learning technology, a three-dimensional model of semi-enclosed power scenes is built, which solves the problems of equipment identification and real-time monitoring in complex environments, realizes rapid data processing and intelligent early warning, and ensures grid safety and operation safety.
Patent Information
- Application Number
- CN202510613131.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-13
- Publication Date
- 2025-08-15
AI Technical Summary
The three-dimensional construction technology of semi-enclosed power scenarios faces the problems of complex environments, difficult equipment identification, large data processing, and unmet real-time monitoring requirements. It is difficult for traditional methods to achieve intelligent management and real-time early warning.
Multi-sensor fusion technology is adopted to collect scene point clouds, device point clouds and panoramic image data from multiple perspectives, combine deep learning and clustering algorithms to build a color point cloud model, and use IMU algorithm to monitor personnel's attitudes and divide alarm areas for real-time early warning.
It realizes rapid three-dimensional model construction and real-time monitoring of semi-enclosed power scenarios, improves data processing speed, and ensures safe operation of the power grid and safety of on-site operations.
Smart Images
Figure CN120495527A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of intelligent power systems, and specifically relates to a three-dimensional space model construction method, a monitoring method and a system for a semi-closed power scene. Background Art
[0002] With the development of intelligent and digital power systems, 3D construction technology for power grid equipment and scenarios is becoming increasingly important in ensuring grid security, improving operation and maintenance efficiency, and optimizing resource scheduling. In semi-enclosed power scenarios such as substations, cable tunnels, and pipe shafts, power equipment is densely distributed, complex, and operates in a volatile environment. Traditional on-site inspection and maintenance methods struggle to meet the demands of modern intelligent power grid management. Currently, 3D structure construction technology is widely used in fields such as construction engineering, urban planning, and manufacturing to achieve accurate scene reproduction and monitoring.
[0003] However, the 3D construction of semi-enclosed power scenarios still faces numerous challenges, including the complexity of semi-enclosed spaces, the precise identification and positioning of multiple types of power equipment, and large-scale data processing and real-time information transmission. Furthermore, power equipment and facilities typically operate in harsh environments, often impacted by natural disasters (such as typhoons and earthquakes) and equipment aging. Traditional secondary protection systems struggle to meet the demands of real-time monitoring and intelligent early warning. Summary of the Invention
[0004] The purpose of the present invention is to overcome the shortcomings of the existing technology and provide a method and system for constructing a three-dimensional spatial model of a semi-closed power scene, thereby improving the speed and efficiency of data processing, responding to on-site changes in time, ensuring the safe operation of the power grid, and at the same time conducting real-time monitoring of the work site to ensure civilized construction on site, and realizing intelligent prevention of dangerous behaviors in power transmission and transformation site operations.
[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A method for constructing a three-dimensional space model of a semi-enclosed power scene, characterized by comprising the following steps: Collect multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data within a semi-enclosed power scene; the scene point cloud data includes 3D coordinates, reflection intensity, and color information; the equipment point cloud information includes 3D coordinates, reflection intensity, and color information; and the personnel point cloud data includes 3D coordinates, motion, and posture information; The environmental point cloud data and the panoramic image data are fused according to the three-dimensional coordinates to obtain color point cloud data; Import the color point cloud data into the 3D modeling software to output the semi-enclosed power scene environment model; import the equipment point cloud data into the 3D modeling software to output the equipment model; import the personnel point cloud data into the 3D modeling software to output the personnel model; The personnel model and equipment model are mapped to the semi-enclosed power scene environment model to obtain a three-dimensional space model of the semi-enclosed power scene.
[0006] Preferably, the step of fusing the environmental point cloud data and the panoramic image data to obtain the color point cloud data includes downsampling, denoising, and registration of the color point cloud data, wherein: Downsampling: Use voxel grid division to divide the color point cloud data into cubic grids, and use the centroid of the cubic grid to represent all points in the cubic grid to form mass point cloud data; Denoising: Based on the cube grid established by downsampling, a random sampling consensus algorithm is used to perform plane fitting on the particle point cloud data to obtain the fitted plane. Based on the fitted plane, points far away from the plane are removed to obtain denoised multi-view clean point cloud data; Registration: The iterative closest point algorithm is used to stitch the clean point cloud data from multiple perspectives and merge them into complete color point cloud data.
[0007] Preferably, the step of collecting multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in a semi-enclosed power scene includes: Using a 3D laser scanning method, we planned the locations based on the terrain and topography of the semi-enclosed power scene, collected data from multiple stations, and converted the information of the semi-enclosed power scene into scene point cloud data. Use optical sensing equipment to obtain three-dimensional data of power equipment in a non-contact active measurement method; Set up a panoramic camera and use image stitching technology to obtain panoramic image data of semi-enclosed power scenes; Multiple cameras and IMU sensors are combined to collect point cloud data of workers in semi-enclosed power scenes.
[0008] Preferably, the steps of importing the color point cloud data into the 3D modeling software and outputting the semi-enclosed electric scene environment model; importing the equipment point cloud data into the 3D modeling software and outputting the equipment model; and importing the personnel point cloud data into the 3D modeling software and outputting the personnel model include: Determine a unified coordinate system in 3D software; According to the three-dimensional coordinates in the color point cloud data, the color point cloud data is converted into a unified coordinate system to obtain a semi-enclosed power scene environment model; Use a clustering algorithm to segment the device point cloud data to obtain multiple different types of device point cloud groups. Combined with a deep learning algorithm, the type of the device point cloud group is identified to obtain the device point cloud data recognition result. Based on the device point cloud data recognition result, use 3D modeling software to model the device to obtain a device model. The personnel point cloud data is converted into a unified coordinate system to obtain the personnel model.
[0009] In a second aspect, the present invention provides a method for monitoring a semi-enclosed power scene, wherein a three-dimensional space model of a semi-enclosed power scene is constructed using the method for constructing a three-dimensional space model of a semi-enclosed power scene, comprising: Based on the 3D coordinates, movements, and posture information in the personnel point cloud data, the IMU algorithm is used to predict the personnel's 3D coordinates, posture, and movements in the future, and the predicted 3D coordinates, posture, and movements are corrected by collecting RTK data. The alarm area is divided in the three-dimensional space model of the semi-enclosed power scene, and dangerous postures are preset. When the predicted three-dimensional coordinates are monitored to be close to the alarm area, or the predicted posture and movement are in a dangerous posture, an alarm command is issued and the alarm information is uploaded.
[0010] Preferably, the steps of predicting the three-dimensional coordinates, posture and motion of the person in a future period of time by an IMU algorithm based on the three-dimensional coordinates, motion and posture information in the person point cloud data, and correcting the predicted three-dimensional coordinates, posture and motion by collecting RTK data include: The output of the IMU algorithm is used to predict the personnel status, and the RTK observation data is used to correct the state estimation of the IMU algorithm. The IMU algorithm is:
[0011] in, X k|k-1 Indicates time-based k-1 The predicted state of the state includes three-dimensional coordinates, posture and action; g () is the state transition function; a k is the measurement value of the IMU sensor at time k, including the acceleration and angular velocity data of the person; h k is the process noise at time k; further, the state update formula is:
[0012] in, X k is the state estimate at time k; Z k is the location information at time k; h() is the measurement function; K k is the Kalman gain matrix.
[0013] In a third aspect, the present invention provides a system for constructing a three-dimensional spatial model of a semi-enclosed electric power scene. The system is applied to the method for constructing a three-dimensional spatial model of a semi-enclosed electric power scene, and the system includes: The model building platform is used to convert the three-dimensional coordinates in the pre-processed scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data into geographic coordinates in the cloud center database and build a three-dimensional spatial model; Point cloud data edge processing node, used to pre-process multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in semi-enclosed power scenes; Point cloud data acquisition equipment is used to collect multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in semi-enclosed power scenes, and upload them to the point cloud data edge processing node.
[0014] In a fourth aspect, the present invention provides a device for constructing a three-dimensional spatial model of a semi-enclosed electric power scene, comprising: The acquisition module is used to collect multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in semi-enclosed power scenes; A fusion module is used to fuse the environmental point cloud data and the panoramic image data according to the three-dimensional coordinates to obtain color point cloud data; Modeling module, used to import color point cloud data into 3D modeling software to output a semi-enclosed power scene environment model; import equipment point cloud data into 3D modeling software to output the equipment model; import personnel point cloud data into 3D modeling software to output the personnel model; The construction module is used to map the personnel model and the equipment model into the semi-enclosed power scene environment model to obtain a three-dimensional space model of the semi-enclosed power scene.
[0015] In a fifth aspect, the present invention provides an electronic device comprising a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the method for constructing a three-dimensional spatial model of a semi-enclosed power scene.
[0016] In a sixth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the method for constructing a three-dimensional spatial model of a semi-enclosed power scene is implemented.
[0017] After adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art: Through multi-sensor fusion and high-precision 3D modeling technology, semi-enclosed power space and equipment models can be quickly constructed with small calculation volume and fast construction speed; Real-time monitoring of personnel posture and early warnings prevent dangerous behaviors during on-site operations, improving the safety and intelligence of power grid operations and maintenance; By utilizing cloud-edge collaborative computing and edge computing technology, we can achieve rapid collection, preprocessing and construction of three-dimensional point cloud data for semi-closed power scenarios, improving the speed and efficiency of data processing, enabling timely response to on-site changes, and ensuring the safe operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings: Figure 1 This is a structural diagram of a method for constructing a three-dimensional space model of a semi-enclosed power scene according to embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the structure of a device for constructing a three-dimensional spatial model of a semi-enclosed power scene according to embodiment 2 of the present invention; Figure 3 This is a schematic structural diagram of an electronic device according to embodiment 3 of the present invention; Figure 4 This is a system for building a three-dimensional spatial model of a semi-closed power scene based on cloud-edge-end collaboration according to embodiment 4 of the present invention. DETAILED DESCRIPTION
[0019] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present application can be combined with each other.
[0020] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise indicated, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present invention.
[0021] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention.
[0022] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more. In the description of the present invention, it should be noted that, unless otherwise clearly specified and defined, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a communication between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0023] Figure 1 This is a technical roadmap for a method for constructing a three-dimensional spatial model of a semi-enclosed power scene in an embodiment of the present invention. The method includes the following steps: A method for constructing a three-dimensional space model of a semi-enclosed power scene, characterized by comprising the following steps: S1. Collect multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in a semi-enclosed power scene: Using ground-based laser radars and panoramic cameras and other optical sensing devices, the system directly acquires 3D data of power equipment such as substations and converter stations through non-contact active measurement. This data is then converted into processable point cloud data of equipment within semi-enclosed power scenarios. The point cloud data includes 3D coordinates, reflection intensity, and color information. Specifically, a three-dimensional laser station scanning method is adopted to plan the points according to the on-site terrain and topography of the semi-closed power scene. The collection of detailed point cloud data of the substation requires multiple station installations. When installing the station, the target ball is placed with reference to the site location, and the instrument is set up at the planned scanning site.
[0024] Set up a panoramic camera and use image stitching technology to obtain panoramic image data. Keep the panoramic camera and tripod level with the ground when installing them to reduce the impact of the power scene terrain on the panoramic image data.
[0025] S2. Fusing the environmental point cloud data and the panoramic image data according to the three-dimensional coordinates to obtain color point cloud data; Preprocessing the color point cloud data to obtain preprocessed color point cloud data; Perform downsampling, denoising, and registration on the color point cloud data, where: Downsampling: Use voxel grid division to divide the color point cloud data into cubic grids, and use the centroid of the cubic grid to represent all points in the cubic grid to form mass point cloud data; Denoising: Based on the cube grid established by downsampling, a random sampling consensus algorithm is used to perform plane fitting on the particle point cloud data to obtain the fitted plane. Based on the fitted plane, points far away from the plane are removed to obtain denoised multi-view clean point cloud data; Registration: The iterative closest point algorithm is used to stitch the clean point cloud data from multiple perspectives and merge them into complete color point cloud data.
[0026] Specifically, the random sampling consensus algorithm includes: Define the suitable model, minimum number of samples, initialize the maximum number of iterations, and the inlier error threshold. Randomly select a minimum number of samples from the mass point cloud dataset and use the selected samples to estimate the model parameters. Calculate the distance from all mass point cloud data to the estimated model, mark the points whose distance is within the error threshold as inliers, calculate the number of inliers, and compare it with the number of inliers in the currently known best model; If the number of inliers in the current model is greater than that of the previous best model, the best model is updated.
[0027] Specifically, the iterative closest point algorithm iteratively searches for the optimal rigid body transformation between clean point cloud data from multiple perspectives, minimizing the Euclidean distance between corresponding points of two clean point cloud data.
[0028] Among them, the rigid body transformation is calculated using the least squares method, assuming that there are source clean point cloud datasets and target clean point cloud datasets P and Q , each dataset contains I The rigid body transformation calculation formula is:
[0029] in, p i and q i are the corresponding points of the source clean point cloud dataset and the target clean point cloud dataset after initial alignment; t and R The translation vector and rotation matrix from the source clean point cloud data to the destination clean point cloud data are solved by the singular value decomposition method.
[0030] S3. Import the color point cloud data into the 3D modeling software to output a semi-enclosed power scene environment model; import the equipment point cloud data into the 3D modeling software to output the equipment model; import the personnel point cloud data into the 3D modeling software to output the personnel model; Specifically: Determine a unified coordinate system; Convert the pre-processed color point cloud data into a unified coordinate system, and convert the point cloud data of different point cloud data edge processing nodes into a unified coordinate system to obtain the point cloud data coordinates; Use a clustering algorithm to segment the device point cloud data to obtain multiple different types of device point cloud groups, such as transformers, circuit breakers, cables, etc. Combined with a deep learning algorithm to identify the type of device point cloud group, obtain the device point cloud data recognition results. Based on the device point cloud data recognition results, use 3D modeling software to model the device and obtain the device model; In a unified coordinate system, a 3D rendering engine is used to optimize scene lighting, shadows, materials, and textures to construct a semi-closed power scene environment model.
[0031] Specifically, the clustering algorithm includes: selecting an unvisited device point cloud data point, checking the number of device point cloud data points in its neighborhood, and if the number of device point cloud data points in the neighborhood is greater than or equal to a preset threshold, marking the device point cloud data point as a core point, otherwise, marking it as a noise point; secondly, for a new device point cloud data core point, checking all device point cloud data points in the neighborhood; if there are unvisited device point cloud data core points in the device point cloud data points, continuing to expand the new cluster; finally, repeating the marking and checking until all device point cloud data have been processed.
[0032] S4. Map the personnel model and the equipment model to the semi-enclosed power scene environment model to obtain a three-dimensional space model of the semi-enclosed power scene.
[0033] Specifically, the equipment model includes the geometric shape, size, and position of the power equipment, and the personnel model includes the position, action, and posture of the personnel.
[0034] Specifically, the rendering and visualization of the semi-closed power scene environment model adopts the OpenGL engine. Through the software graphics function library and graphics hardware interface, the semi-closed power scene environment model can be run on the mainstream operating system platform. For simple power equipment three-dimensional graphics, they are generated through OpenGL auxiliary functions. For complex power equipment models, entity modeling is performed through a series of OpenGL rules.
[0035] Example 2 A semi-enclosed power scene monitoring method, using the semi-enclosed power scene three-dimensional space model constructed by the semi-enclosed power scene three-dimensional space model construction method, comprises: Based on the 3D coordinates, movements, and posture information in the personnel point cloud data, the IMU algorithm is used to predict the personnel's 3D coordinates, posture, and movements in the future, and the predicted 3D coordinates, posture, and movements are corrected by collecting RTK data. The alarm area is divided in the three-dimensional space model of the semi-enclosed power scene, and dangerous postures are preset. When the predicted three-dimensional coordinates are monitored to be close to the alarm area, or the predicted posture and movement are in a dangerous posture, an alarm command is issued and the alarm information is uploaded.
[0036] Specifically, multiple cameras and IMU sensors are used to capture the posture of workers in semi-enclosed power scenes, and the posture data of workers in semi-enclosed power scenes are obtained. Open source deep learning models such as OpenPose and HRNet are used to identify the key points of the posture of workers in semi-enclosed power spaces. Based on the multi-view geometry method, the key point data from different perspectives are fused, and the triangulation method is used to map the 2D key data into 3D space. Specifically, the IMU algorithm is:
[0037] in, X k|k-1 Indicates time-based k-1 The predicted state of the state; g() is the state transition function; a k is the measurement value of the IMU sensor at time k, including the acceleration and angular velocity data of the person; h k is the process noise at time k; Furthermore, the state update formula is:
[0038] in, X k is the state estimate at time k; Z k is the location information at time k; h() is the measurement function; K k is the Kalman gain matrix.
[0039] Among them, the personnel contour extraction in the semi-enclosed power operation scene is achieved by calling the findContours function in OpenGL.
[0040] Example 3 like Figure 4 As shown, a system for constructing a three-dimensional space model of a semi-enclosed electric power scene is applied to the method for constructing a three-dimensional space model of a semi-enclosed electric power scene. The system includes: The model building platform is used to convert the three-dimensional coordinates in the pre-processed scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data into geographic coordinates in the cloud center database and build a three-dimensional spatial model; Point cloud data edge processing node, used to pre-process multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in semi-enclosed power scenes; Point cloud data acquisition equipment is used to collect multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in semi-enclosed power scenes, and upload them to the point cloud data edge processing node.
[0041] Specifically, the model reconstruction platform is a point cloud data comprehensive processing platform developed on the basis of the data center server cluster and operating system. It takes advantage of the massive storage, centralized computing, and flexible scalability of the data center server cluster to convert the three-dimensional visual position information data of scenes such as transmission cable maintenance, electrical installation in substations, and converter station maintenance into geographic coordinates in the cloud center database, and construct a three-dimensional spatial model of the site to achieve unified monitoring, early warning, and management of safety protection of power grid transmission and transformation site operations.
[0042] The point cloud data edge processing node leverages the computing and storage capabilities of edge devices by aggregating and pre-processing the data sent back by the equipment deployed at the work site, uploading it to the cloud video monitoring center for image optimization and sharpness and brightness adjustment, performing image analysis based on the processed images, and sending real-time safety zone identification warning instructions to the on-site warning device or the equipment carried by the workers when the workers approach the dangerous area, realizing sound and light alarms to remind the workers to pay attention to the work area.
[0043] The point cloud data acquisition equipment is equipped with multiple laser scanners, panoramic cameras, cameras and other sensors to obtain three-dimensional point cloud data and visible light image data of personnel, equipment, tools, environment, etc. at the infrastructure site and upload them to the edge node to provide data support for subsequent modeling and detection and monitoring.
[0044] The technical system for constructing rapid three-dimensional spatial models of semi-closed power scenarios based on cloud-edge-end collaboration collects, stores, processes and shares information through cloud, edge and end data, monitors the work site in real time to ensure civilized construction on site, and realizes intelligent prevention of dangerous behaviors in power transmission and transformation site operations.
[0045] Example 4 like Figure 2 As shown, based on the same inventive concept as Example 1, the present invention further provides a device for constructing a three-dimensional spatial model of a semi-enclosed power scene, comprising: The acquisition module is used to collect multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in semi-enclosed power scenes; A fusion module is used to fuse the environmental point cloud data and the panoramic image data according to the three-dimensional coordinates to obtain color point cloud data; Modeling module, used to import color point cloud data into 3D modeling software to output a semi-enclosed power scene environment model; import equipment point cloud data into 3D modeling software to output the equipment model; import personnel point cloud data into 3D modeling software to output the personnel model; The construction module is used to map the personnel model and the equipment model into the semi-enclosed power scene environment model to obtain a three-dimensional space model of the semi-enclosed power scene.
[0046] Example 5 Based on the same inventive concept as Example 2, the present invention further provides a semi-enclosed power scene monitoring device, comprising: The acquisition module is used to collect multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in semi-enclosed power scenes; A fusion module is used to fuse the environmental point cloud data and the panoramic image data according to the three-dimensional coordinates to obtain color point cloud data; Modeling module, used to import color point cloud data into 3D modeling software to output a semi-enclosed power scene environment model; import equipment point cloud data into 3D modeling software to output the equipment model; import personnel point cloud data into 3D modeling software to output the personnel model; The construction module is used to map the personnel model and the equipment model into the semi-enclosed power scene environment model to obtain a three-dimensional space model of the semi-enclosed power scene.
[0047] The alarm module is used to divide the alarm area in the three-dimensional space model of the semi-enclosed power scene and preset dangerous postures. When the predicted three-dimensional coordinates are monitored to be close to the alarm area, or the predicted posture and movement are in a dangerous posture, an alarm command is issued and the alarm information is uploaded.
[0048] Example 6 like Figure 3 As shown, the present invention also provides an electronic device 100 for implementing a method for constructing a three-dimensional space model of a semi-enclosed power scene; The electronic device 100 includes a memory 101 , at least one processor 102 , a computer program 103 stored in the memory 101 and executable on the at least one processor 102 , and at least one communication bus 104 .
[0049] The memory 101 can be used to store the computer program 103. The processor 102 implements the method for constructing a three-dimensional spatial model of a semi-enclosed power scene in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.
[0050] The memory 101 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data (such as audio data) created according to the use of the electronic device 100. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device.
[0051] The at least one processor 102 may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor. The processor 102 is the control center of the electronic device 100 and connects various parts of the entire electronic device 100 using various interfaces and lines.
[0052] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a method for constructing a three-dimensional spatial model of a semi-enclosed power scene. The processor 102 can execute the plurality of instructions to implement: Collect multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data within a semi-enclosed power scene; the scene point cloud data includes 3D coordinates, reflection intensity, and color information; the equipment point cloud information includes 3D coordinates, reflection intensity, and color information; and the personnel point cloud data includes 3D coordinates, motion, and posture information; The environmental point cloud data and the panoramic image data are fused according to the three-dimensional coordinates to obtain color point cloud data; Import the color point cloud data into the 3D modeling software to output the semi-enclosed power scene environment model; import the equipment point cloud data into the 3D modeling software to output the equipment model; import the personnel point cloud data into the 3D modeling software to output the personnel model; Mapping the personnel model and the equipment model to the semi-enclosed power scene environment model to obtain a three-dimensional space model of the semi-enclosed power scene; The alarm area is divided in the three-dimensional space model of the semi-enclosed power scene, and dangerous postures are preset. When the predicted three-dimensional coordinates are monitored to be close to the alarm area, or the predicted posture and movement are in a dangerous posture, an alarm command is issued and the alarm information is uploaded.
[0053] Example 7 If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. Computer-readable media may include: any entity or device that can carry computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).
[0054] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0055] The present invention is described with reference to 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 process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0056] These computer program instructions may 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 produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.
[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0058] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
[0059] 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 it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.
Claims
1. A method for constructing a three-dimensional space model of a semi-enclosed power scene, characterized in that: The following steps are involved: Collect multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data within a semi-enclosed power scene; the scene point cloud data includes 3D coordinates, reflection intensity, and color information; the equipment point cloud information includes 3D coordinates, reflection intensity, and color information; and the personnel point cloud data includes 3D coordinates, motion, and posture information; The environmental point cloud data and the panoramic image data are fused according to the three-dimensional coordinates to obtain color point cloud data; Import the color point cloud data into the 3D modeling software to output the semi-enclosed power scene environment model; import the equipment point cloud data into the 3D modeling software to output the equipment model; import the personnel point cloud data into the 3D modeling software to output the personnel model; The personnel model and equipment model are mapped to the semi-enclosed power scene environment model to obtain a three-dimensional space model of the semi-enclosed power scene.
2. The method for constructing a three-dimensional space model of a semi-enclosed power scene according to claim 1, characterized in that: The steps of fusing the environmental point cloud data and the panoramic image data to obtain the color point cloud data include downsampling, denoising, and registration of the color point cloud data, wherein: Downsampling: Use voxel grid division to divide the color point cloud data into cubic grids, and use the centroid of the cubic grid to represent all points in the cubic grid to form mass point cloud data; Denoising: Based on the cube grid established by downsampling, a random sampling consensus algorithm is used to perform plane fitting on the particle point cloud data to obtain the fitted plane. Based on the fitted plane, points far away from the plane are removed to obtain denoised multi-view clean point cloud data; Registration: The iterative closest point algorithm is used to stitch the clean point cloud data from multiple perspectives and merge them into complete color point cloud data.
3. The method for constructing a three-dimensional space model of a semi-enclosed power scene according to claim 1, characterized in that: The step of collecting multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in a semi-enclosed power scene includes: Using a 3D laser scanning method, we planned the locations based on the terrain and topography of the semi-enclosed power scene, collected data from multiple stations, and converted the information of the semi-enclosed power scene into scene point cloud data. Use optical sensing equipment to obtain point cloud data of power equipment in a non-contact active measurement manner; Set up a panoramic camera and use image stitching technology to obtain panoramic image data of semi-enclosed power scenes; Multiple cameras and IMU sensors are combined to collect point cloud data of workers in semi-enclosed power scenes.
4. The method for constructing a three-dimensional space model of a semi-enclosed power scene according to claim 3, characterized in that: Import the color point cloud data into the 3D modeling software and output the semi-enclosed power scene environment model; import the equipment point cloud data into the 3D modeling software and output the equipment model; Import the personnel point cloud data into the 3D modeling software and output the personnel model, including: Determine a unified coordinate system in 3D software; According to the three-dimensional coordinates in the color point cloud data, the color point cloud data is converted into a unified coordinate system to obtain a semi-enclosed power scene environment model; Use a clustering algorithm to segment the device point cloud data to obtain multiple different types of device point cloud groups. Combined with a deep learning algorithm, the type of the device point cloud group is identified to obtain the device point cloud data recognition result. Based on the device point cloud data recognition result, use 3D modeling software to model the device to obtain a device model. The personnel point cloud data is converted into a unified coordinate system to obtain the personnel model.
5. A semi-closed power scene monitoring method, characterized in that: A three-dimensional space model of a semi-enclosed electric power scene constructed by the method according to any one of claims 1 to 4 comprises: Based on the 3D coordinates, movements, and posture information in the personnel point cloud data, the IMU algorithm is used to predict the personnel's 3D coordinates, posture, and movements in the future, and the predicted 3D coordinates, posture, and movements are corrected by collecting RTK data. The alarm area is divided in the three-dimensional space model of the semi-enclosed power scene, and dangerous postures are preset. When the predicted three-dimensional coordinates are monitored to be close to the alarm area, or the predicted posture and movement are in a dangerous posture, an alarm command is issued and the alarm information is uploaded.
6. The semi-enclosed power scene monitoring method according to claim 5, characterized in that: Based on the 3D coordinates, motion, and posture information in the personnel point cloud data, the IMU algorithm is used to predict the personnel's 3D coordinates, posture, and motion in the future. The predicted 3D coordinates, posture, and motion are corrected by collecting RTK data, including the following steps: The output of the IMU algorithm is used to predict the personnel status, and the RTK observation data is used to correct the state estimation of the IMU algorithm. The IMU algorithm is: in, X k|k-1 Indicates time-based k-1 The predicted state of the state; g() is the state transition function; a k is the measurement value of the IMU sensor at time k, including the acceleration and angular velocity data of the person; h k is the process noise at time k; Furthermore, the state update formula is: in, X k is the state estimate at time k; Z k is the location information at time k; h() is the measurement function; K k is the Kalman gain matrix.
7. A semi-enclosed power scene three-dimensional space model construction system, characterized by: The system is applied to the method for constructing a three-dimensional space model of a semi-enclosed power scene according to any one of claims 1 to 4, and the system includes: The model building platform is used to convert the three-dimensional coordinates in the pre-processed scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data into geographic coordinates in the cloud center database and build a three-dimensional spatial model; Point cloud data edge processing node, used to pre-process multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in semi-enclosed power scenes; Point cloud data acquisition equipment is used to collect multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in semi-enclosed power scenes, and upload them to the point cloud data edge processing node.
8. A device for constructing a three-dimensional spatial model of a semi-enclosed power scene, characterized in that: include: The acquisition module is used to collect multi-perspective scene point cloud data, equipment point cloud data, panoramic image data, and personnel point cloud data in semi-enclosed power scenes; A fusion module is used to fuse the environmental point cloud data and the panoramic image data according to the three-dimensional coordinates to obtain color point cloud data; Modeling module, used to import color point cloud data into 3D modeling software to output a semi-enclosed power scene environment model; import equipment point cloud data into 3D modeling software to output the equipment model; import personnel point cloud data into 3D modeling software to output the personnel model; The construction module is used to map the personnel model and the equipment model into the semi-enclosed power scene environment model to obtain a three-dimensional space model of the semi-enclosed power scene.
9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the method for constructing a three-dimensional space model of a semi-enclosed power scene as described in any one of claims 1 to 4.
10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, the method for constructing a three-dimensional space model of a semi-enclosed power scene according to any one of claims 1 to 4 is implemented.