A method for tracking the trajectory of moving objects in a substation based on a three-dimensional digital model

Abstract

The present application provides a method for tracking the trajectory of moving objects in a substation based on a three-dimensional digital model, which relates to the technical field of safety control. The method is applied to the server of the substation control system. The substation control system includes a server, multiple controllers, and multiple laser point cloud sensors. The server is connected to the multiple controllers simultaneously, and each controller is connected to a laser point cloud sensor. The method includes: obtaining first position data transmitted by the first controller; calculating the probability that the moving target moves to the scanning area of each sensor according to the preset spatial structure of the substation; if it is determined that the probability that the moving target moves to the second scanning area is greater than or equal to a preset threshold, sending a collection instruction to the second controller; receiving the change data transmitted by the second controller; and generating a continuous motion state of the three-dimensional moving target according to the change data. The present application can effectively reduce the amount of data transmitted when tracking the trajectory of moving objects in a substation based on a three-dimensional digital model.

Description

Technical Field

[0001] This application relates to the technical field of security control, and specifically relates to a method for tracking the trajectory of moving objects in a substation based on a three-dimensional digital model. Background Art

[0002] In the power system, as the core node of power transmission and conversion, the safety and stability of the substation directly affect the normal operation of the entire power grid. Traditional substation monitoring and warning methods mostly rely on manual inspections and a small number of fixed monitoring devices. This method not only limits the monitoring efficiency and coverage, but also brings higher operating costs. In addition, in the face of emergencies, the response speed of traditional methods is slow, making it difficult to meet the requirements of modern power systems for real-time monitoring and efficient warning of substations. Therefore, an efficient and intelligent monitoring system is needed to improve the safety and response ability of substations, thereby ensuring the stable operation of the power grid.

[0003] With the development of three-dimensional laser scanning and computer vision technologies, the application of three-dimensional reconstruction technology in the power system has attracted increasing attention. By using three-dimensional point cloud data to monitor and warn substation equipment, the spatial information of the equipment can be obtained more comprehensively and accurately. Under conditions where the line of sight is blocked, such as in haze or smoke, the laser point cloud has higher tracking stability compared to video monitoring. The laser point cloud is not affected by changes in illumination and can work continuously in environments with complex or dim light, such as at night, in shadows, or under strong light, which is particularly important for all-weather monitoring of substations. Laser point cloud modeling can also accurately measure the physical parameters of equipment (such as size, distance, position), facilitating spatial modeling and subsequent analysis. However, due to the large amount of data generated by the laser point cloud, there may be delays during transmission, which affects real-time performance and poses higher requirements for trajectory tracking. Summary of the Invention

[0004] This application provides a method for tracking the trajectory of moving objects in a substation based on a three-dimensional digital model, which can effectively reduce the amount of data transmitted when tracking the trajectory of moving objects in a substation based on a three-dimensional digital model.

[0005] In a first aspect of this application, a method for tracking the trajectory of moving objects in a substation based on a three-dimensional digital model is provided. The method is applied to a server of a substation control system. The substation control system includes the server, multiple controllers, and multiple laser point cloud sensors. The server is connected to multiple controllers simultaneously, and each controller is connected to one laser point cloud sensor. The method includes:

[0006] Obtain the first position data transmitted by the first controller, where the first controller, based on the first point cloud data collected by the acquired first sensor, if it determines that there is a moving target in the first scanning area of the first sensor, sends the first position data of the first scanning area to the server. The first controller is any one of the multiple controllers, and the first sensor is the laser point cloud sensor connected to the first controller among the multiple laser point cloud sensors;

[0007] Calculate the probability that the moving target moves to the scanning areas of each of the sensors according to the preset substation space structure;

[0008] If it is determined that the probability that the moving target moves to the second scanning area is greater than or equal to the preset threshold, send an acquisition instruction to the second controller, where the second controller is any one of the multiple controllers other than the first controller, the scanning area of the second sensor is the second scanning area, and the second sensor is the laser point cloud sensor connected to the second controller among the multiple laser point cloud sensors;

[0009] Receive the change data transmitted by the second controller, where after the second sensor receives the acquisition instruction, it controls the second sensor to perform continuous scanning, and based on the second point cloud data obtained from multiple scans, compares two consecutive second point cloud data point by point to find the changed data part, and obtains the change data;

[0010] Generate the continuous motion state of the three-dimensional moving target according to the change data.

[0011] Optionally, the calculating the probability that the moving target moves to the scanning areas of each of the sensors according to the preset substation space structure specifically includes:

[0012] Obtain the preset substation space structure, where the substation space structure includes the connection structure of the laser point cloud sensors based on the internal routes of the substation and the connection distances between two interconnected laser point cloud sensors. The connection structure takes the installation positions of the laser point cloud sensors as nodes and the internal routes of the substation as links, and the nodes are connected through the internal routes of the substation;

[0013] Determine the continuous position change of the moving target in the substation according to the first point cloud data obtained from multiple scans transmitted by the received first controller;

[0014] Determine the moving direction of the moving target according to the continuous position change;

[0015] Obtain the historical probabilities of different moving objects moving from the first scanning area to each of the scanning areas in the historical record;

[0016] Perform weighted product fusion on the substation spatial structure, the moving direction, and the historical probability to calculate the probability that the moving target moves to the scanning area of each sensor.

[0017] Optionally, before determining that the probability that the moving target moves to the second scanning area is greater than or equal to a preset threshold, the method further includes:

[0018] Perform weighted product fusion on the substation spatial structure, the moving direction, and the historical probability to calculate the probability that the moving target moves to the second scanning area, specifically calculated by the following formula:

[0019]

[0020] Where P is the probability that the moving target moves to the second scanning area, σ is the Sigmoid function, f 1 = f(θ), f 2 = f(d), f 3 = f(h), w i is the weight coefficient. When i = 1, w 1 is the direction weight coefficient. When i = 2, w 2 is the distance weight coefficient. When i = 3, w 3 is the historical weight coefficient, α is the direction sensitivity, θ is the angle between the moving direction and the moving direction, the moving direction is the direction from the center of the first scanning area to the center of the second scanning area, θ 0 is the expected angle based on the first scanning area, d 12 is the distance between the first scanning area and the second scanning area, τ is a constant, τ is used to prevent the denominator from being zero, γ is the distance sensitivity coefficient, λ is the time decay factor, T is the total number of historical records, P t (1→2) is the transition probability from the first scanning area to the second scanning area recorded at the t-th time.

[0021] Optionally, before obtaining the changed data by comparing two consecutive second point cloud data point by point according to the second point cloud data obtained by multiple scans, the method further includes:

[0022] Send the background point cloud data to the second controller, so that the second controller compares the background point cloud data with the real-time point cloud data, and uses the background difference algorithm to extract the point cloud data corresponding to the moving target in the real-time point cloud data, thereby obtaining the second point cloud data.

[0023] Optionally, for the second point cloud data obtained through multiple scans, the changed data part is found by comparing two consecutive second point cloud data point by point to obtain the changed data, specifically including:

[0024] The second controller performs initial registration on the first sub-data and the second sub-data, where the first sub-data and the second sub-data are any two adjacent second point cloud data among the multiple second point cloud data;

[0025] Based on the initial registration result, the second controller queries multiple groups of first data points and second data points in the first sub-data and the second sub-data, where the first data point is any point in the first sub-data, and the second data point is the point in the second sub-data that is closest to the first data point;

[0026] The second controller calculates the rigid body transformation between the first data point and the second data point to make the first sub-data coincide with the second sub-data;

[0027] The second controller continuously iterates and updates the calculation until the rigid body transformation error converges below the threshold to complete the accurate point cloud registration;

[0028] After the second controller completes the accurate point cloud registration, by comparing the spatial position changes of each data point in the first sub-data and the second sub-data, the moved or newly added data points can be found to obtain the changed data.

[0029] Optionally, the second controller calculates the rigid body transformation between the first data point and the second data point to make the first sub-data coincide with the second sub-data, specifically including:

[0030] The second controller calculates the first centroid of the first sub-data {p 1 , p 2, …, p n}, and calculates the second centroid of the second sub-data {q 1 , q 2 , …, q n}, specifically calculated by the following formula:

[0031]

[0032] where c p is the first centroid, c q is the second centroid, {p 1 , p 2, …, p n} is the first sub-data, {q 1 , q 2 , …, q n} is the second sub-data;

[0033] The second controller calculates the covariance matrix, specifically calculated by the following formula:

[0034]

[0035] where H is the covariance matrix, c p is the first centroid, c q is the second centroid, {p 1 , p 2, …, p n} is the first sub-data, {q 1 , q 2 , …, q n} is the second sub-data;

[0036] The second controller constructs a rigid body transformation matrix based on the covariance matrix, specifically as follows:

[0037]

[0038] where T is the rigid body transformation matrix, H is the covariance matrix, E is a diagonal matrix, c p is the first centroid, c q is the second centroid;

[0039] The second controller applies the rigid body transformation matrix to the first sub-data to update the first data point, and the updated first data point is obtained, specifically as follows:

[0040]

[0041] where p i ' is the updated first data point, H is the covariance matrix, E is the diagonal matrix, p i is the first data point.

[0042] Optionally, generating the continuous motion state of the three-dimensional moving target according to the change data specifically includes:

[0043] By extracting the centroid position of each change data, the preliminary trajectory of the moving target is obtained;

[0044] Accumulate the change data obtained from multiple scans into a global coordinate system to form a cumulative point cloud;

[0045] Based on the cumulative point cloud, perform surface reconstruction to obtain a target three-dimensional model;

[0046] According to the time series, form a dynamic three-dimensional dynamic model.

[0047] In the second aspect of the present application, a device for tracking the trajectory of moving objects in a substation based on a three-dimensional digital model is provided. The device is a server, and the device includes an acquisition module, a processing module, and a sending module, where:

[0048] The acquisition module is configured to acquire first position data transmitted by a first controller. Among them, the first controller, according to the first point cloud data collected by the acquired first sensor, if it determines that there is a moving target in the first scanning area of the first sensor, then sends the first position data of the first scanning area to the server. The first controller is any one of multiple controllers, and the first sensor is the laser point cloud sensor connected to the first controller among multiple laser point cloud sensors;

[0049] The processing module is configured to calculate the probability that the moving target moves to the scanning areas of each of the sensors according to a preset substation space structure;

[0050] The sending module is configured to, if it determines that the probability that the moving target moves to a second scanning area is greater than or equal to a preset threshold, then send an acquisition instruction to a second controller. Among them, the second controller is any one of the multiple controllers other than the first controller, the scanning area of the second sensor is the second scanning area, and the second sensor is the laser point cloud sensor connected to the second controller among multiple laser point cloud sensors;

[0051] The acquisition module is configured to receive change data transmitted by the second controller. Among them, after the second sensor receives the acquisition instruction, it controls the second sensor to perform continuous scanning, and according to the second point cloud data obtained from multiple scans, compares two consecutive second point cloud data point by point to find the changed data part, and obtains the change data;

[0052] The processing module is configured to generate a continuous motion state of the three-dimensional moving target according to the change data.

[0053] Optionally, the acquisition module is configured to acquire a preset substation space structure. Among them, the substation space structure includes the connection structure of laser point cloud sensors based on the internal routes of the substation and the connection distances between two mutually connected laser point cloud sensors. The connection structure uses the installation positions of the laser point cloud sensors as nodes and the internal routes of the substation as links, and the nodes are connected through the internal routes of the substation;

[0054] The processing module is configured to determine the continuous position change of the moving target in the substation according to the first point cloud data obtained from multiple scans transmitted by the received first controller;

[0055] The processing module is configured to determine the moving direction of the moving target according to the continuous position change;

[0056] The obtaining module is configured to obtain the historical probabilities of different moving objects moving from the first scanning area to each of the scanning areas in the historical record;

[0057] The processing module is configured to perform weighted product fusion on the substation spatial structure, the moving direction, and the historical probability, and calculate the probability that the moving target moves to the scanning area of each of the sensors.

[0058] Optionally, the processing module is configured to perform weighted product fusion on the substation spatial structure, the moving direction, and the historical probability, and calculate the probability that the moving target moves to the second scanning area, specifically calculated by the following formula:

[0059]

[0060] where P is the probability that the moving target moves to the second scanning area, σ is the Sigmoid function, f 1 = f(θ), f 2 = f(d), f 3 = f(h), w i is the weight coefficient. When i = 1, w 1 is the direction weight coefficient. When i = 2, w 2 is the distance weight coefficient. When i = 3, w 3 is the historical weight coefficient, α is the direction sensitivity, θ is the angle between the moving direction and the moving direction, the moving direction is the direction from the center of the first scanning area to the center of the second scanning area, θ 0 is the expected angle based on the first scanning area, d 12 is the distance between the first scanning area and the second scanning area, τ is a constant, τ is used to prevent the denominator from being zero, γ is the distance sensitivity coefficient, λ is the time decay factor, T is the total number of historical records, P t (1→2) is the transition probability from the first scanning area to the second scanning area recorded at the t-th time.

[0061] Optionally, the sending module is configured to send the background point cloud data to the second controller, so that the second controller compares the background point cloud data with the real-time point cloud data, and uses the background difference algorithm to extract the point cloud data corresponding to the moving target in the real-time point cloud data, thereby obtaining the second point cloud data.

[0062] Optionally, the processing module is configured to obtain a preliminary trajectory of the moving target by extracting the centroid position of the data changed each time.

[0063] The processing module is configured to accumulate the changed data obtained by multiple scans into a global coordinate system to form an accumulated point cloud.

[0064] The processing module is configured to perform surface reconstruction on the basis of the accumulated point cloud to obtain a target three-dimensional model.

[0065] The processing module is configured to form a dynamic three-dimensional dynamic model according to the time series.

[0066] In a third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions. Both the user interface and the network interface are used to communicate with other devices. The processor is configured to execute the instructions stored in the memory so that the electronic device executes the method described in any one of the above.

[0067] In a fourth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions, and when the instructions are executed, the method described in any one of the above is executed.

[0068] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0069] 1. The present application reduces the data transmission volume through distributed control and local computing, mainly relying on the local processing of the controller and the efficient scheduling of the server. Specifically, the controller analyzes the point cloud data locally and only reports to the server when a moving target is detected and the probability that it may enter the area of other sensors is relatively high, avoiding continuous transmission of a large amount of unchanged point cloud data. In addition, by probability prediction, the acquisition instructions of adjacent controllers are triggered only when necessary, further reducing redundant data transmission and ensuring that only key data such as changed data and trajectory updates are uploaded to the server, thereby greatly reducing the data volume and network load.

[0070] 2. The present application gradually calculates the centroid, covariance matrix, and rigid body transformation matrix of the point cloud data, realizing accurate registration and difference detection of the point cloud data, thereby effectively identifying the changed data of the moving target. Through multiple iterative calculations, two consecutive point cloud frames are made to coincide, ensuring the accuracy of data alignment. This method greatly improves the registration accuracy and stability, can accurately identify the moving or newly added data points, and generate clear motion trajectories and states. Especially through the precise registration of point-by-point comparison and rigid body transformation, while reducing errors, it realizes efficient and continuous target tracking, meeting the high-precision monitoring requirements in the complex environment of the substation. Brief Description of the Drawings

[0071] Figure 1 is a schematic flowchart of a method for tracking the trajectory of moving objects in a substation based on a three-dimensional digital model disclosed in an embodiment of the present application;

[0072] Figure 2 is a schematic structural diagram of a substation management and control system disclosed in an embodiment of the present application;

[0073] Figure 3 is a schematic block diagram of a device for tracking the trajectory of moving objects in a substation based on a three-dimensional digital model disclosed in an embodiment of the present application;

[0074] Figure 4 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.

[0075] Description of the reference numerals: 301, acquisition module; 302, processing module; 303, sending module; 401, processor; 402, communication bus; 403, user interface; 404, network interface; 405, memory. Detailed Embodiments

[0076] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0077] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "for example" or "for illustration" is intended to present relevant concepts in a specific manner.

[0078] In the description of the embodiments of the present application, the term "a plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0079] A substation is a core node of the power system, and its safety and stability are crucial for the normal operation of the power grid. Traditional monitoring methods rely on manual inspections and fixed equipment, which have problems such as low monitoring efficiency and slow response speed, and it is difficult to meet the real-time monitoring requirements. With the development of 3D laser scanning and computer vision technologies, using 3D point cloud data for substation monitoring and early warning has gradually become a trend. Laser point clouds have the advantages of being unaffected by light and adapting to complex environments, and can efficiently track and accurately measure equipment information under various light conditions, which helps with all-weather monitoring and equipment analysis. However, the transmission of a large amount of point cloud data may cause delays, increasing the real-time challenges of trajectory tracking.

[0080] This embodiment discloses a method for tracking the trajectory of moving objects in a substation based on a 3D digital model. Referring to Figure 1 , it includes the following steps S110 - S150:

[0081] S110, obtain the first position data transmitted by the first controller.

[0082] A method for tracking the trajectory of moving objects in a substation based on a 3D digital model disclosed in an embodiment of this application is applied to the server of a substation management and control system. Referring to Figure 2 , the substation management and control system includes a server, multiple controllers, and multiple laser point cloud sensors. The server is connected to multiple controllers simultaneously, and each controller is connected to a laser point cloud sensor. The laser point cloud sensors and controllers are arranged in different areas of the substation according to actual monitoring requirements.

[0083] The server includes, but is not limited to, electronic devices such as mobile phones, tablets, wearable devices, PCs (Personal Computers), etc., and can also be a background server running a method for tracking the trajectory of moving objects in a substation based on a 3D digital model. The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0084] The controller is one of the key components in the substation management and control system, and is used to connect the laser point cloud sensor and perform local data processing. It receives the data collected by the sensor, conducts preliminary analysis and processing, such as detecting change points and judging object movement, reduces unnecessary data volume, and preferentially filters and compresses important information before transmitting it to the server. The controller can also coordinate with other controllers to jointly complete tasks such as area monitoring and data verification, and achieve efficient distributed data management.

[0085] The laser point cloud sensor is a device used for high-precision three-dimensional scanning in a substation. By emitting lasers and receiving reflected signals, it generates three-dimensional point cloud data of the equipment and environment in the substation. This sensor can operate under various light conditions, is not affected by factors such as illumination and weather, and is suitable for all-weather monitoring at night or in complex environments. By precisely measuring the shape, position, and changes of the equipment, the laser point cloud sensor provides accurate and reliable data support for equipment monitoring, anomaly detection, and three-dimensional modeling.

[0086] The first controller controls the connected first laser point cloud sensor to scan its monitoring area regularly or continuously, and obtains three-dimensional point cloud data within the area. Each scan generates a frame of three-dimensional point cloud data, which contains the shape and position of the objects in the monitoring area of the substation. Among them, the first controller is any one of multiple controllers, and the first sensor is the laser point cloud sensor connected to the first controller among multiple laser point cloud sensors;

[0087] The first controller performs difference detection between the current frame (the point cloud data of the latest scan) and the point cloud data of the previous frame to determine whether there are moving targets. By comparing the positions of each point in the two consecutive frames of point clouds, if the displacement of some points exceeds the set threshold, it is considered that these points may belong to moving targets. The controller determines whether the changed area is a valid moving target according to the set threshold (such as displacement distance, change speed).

[0088] If the first controller determines that there is a moving target that meets the conditions in the scanning area, it encapsulates the position information of the target as "first position data". The position data is compressed or formatted to meet the transmission requirements, ensuring the efficiency and accuracy of transmission. The data may include the centroid position, boundary size, movement direction, and speed of the target, etc. The controller sends the position data to the server through the network. After receiving the data, the server performs global monitoring and analysis to decide whether to further dispatch other controllers or execute an early warning.

[0089] S120, according to the preset spatial structure of the substation, calculate the probability of the moving target moving to the scanning areas of each sensor.

[0090] In a possible implementation manner, according to a preset substation spatial structure, calculate the probability that a moving target moves to the scanning areas of each sensor, specifically including: obtaining the preset substation spatial structure, where the substation spatial structure includes the connection structure of the laser point cloud sensors based on the internal routes of the substation and the connection distances between two interconnected laser point cloud sensors. The connection structure uses the installation positions of the laser point cloud sensors as nodes and the internal routes of the substation as links, and the nodes are connected through the internal routes of the substation; determine the continuous position change of the moving target in the substation according to the first point cloud data obtained from multiple scans transmitted by the first controller; determine the moving direction of the moving target according to the continuous position change; obtain the historical probabilities of different moving objects moving from the first scanning area to each scanning area in the historical records; perform weighted product fusion on the substation spatial structure, the moving direction, and the historical probabilities to calculate the probability that the moving target moves to the scanning areas of each sensor.

[0091] Specifically, the spatial structure information of the substation includes the installation positions of the laser point cloud sensors, the connection relationships and distances between any two adjacent sensors, etc. These structure data can be obtained through 3D modeling or on-site measurement. In the substation spatial structure, the installation position of each laser point cloud sensor is regarded as a node, and each node is connected through the internal routes of the substation to form a network graph structure. Obtain the distances between adjacent sensors. For example, define the distance by the straight-line distance or the path length. This distance information will be used to estimate the migration probability of the moving target. The adjacent relationships between sensors can be constructed into a topological structure graph using the graph representation method, which is convenient for subsequent path and probability calculations.

[0092] Track the continuous position change of the moving target in the substation through the scan data transmitted by the first controller multiple times, and calculate its moving direction. In multiple scans, the centroid position of the moving target is obtained each time, and these positions are recorded to form a trajectory sequence, and then the moving direction is calculated through adjacent position points.

[0093] Based on historical data, count the frequencies of different moving objects moving from one scanning area to other areas, and obtain the historical transition probabilities from the first scanning area to each target scanning area. For different target areas, calculate the historical transition probability Ph(A→B) of moving from the current area to the adjacent area. For example, assume that among 100 movements starting from area A of the target, 40 times move to area B, then the historical probability is 0.4.

[0094] On the basis of knowing the substation spatial structure, the moving direction, and the historical probabilities, calculate the probabilities that the moving target reaches the scanning areas of each sensor. To calculate the probability that the moving target moves from the first scanning area to the second scanning area, the specific calculation process is as follows:

[0095] First, calculate the direction consistency mapping function, which is used to calculate the degree of coincidence between the current direction of the target and the expected moving direction. This function is represented by the Gaussian distribution formula and can smoothly reflect the impact of direction deviation on probability:

[0096]

[0097] Among them, α is the direction sensitivity, which is used to control the degree of influence of direction consistency on probability. The larger the value, the more sensitive the system is to direction deviation, and small deviations will also lead to a significant decrease in probability. θ is the angle between the moving direction and the moving pointing direction. The moving pointing direction is the direction from the center of the first scanning area to the center of the second scanning area, and θ 0 is the expected angle based on the first scanning area.

[0098] The characteristics of the Gaussian distribution make this formula reach the maximum value when θ = θ 0 When, and as the direction deviation ∣θ - θ 0 ∣ increases, the value decreases exponentially. In this way, the movement closer to the expected direction has a higher probability, and the more deviated the direction, the lower the probability. This method can smoothly control the impact of the target direction consistency on the final probability.

[0099] Next, calculate the distance mapping function, which is used to calculate the distance impact of the target moving from the first scanning area to the second scanning area. The closer the distance, the greater the probability; the farther the distance, the smaller the probability:

[0100]

[0101] Among them, d 12 is the distance between the first scanning area and the second scanning area. The greater the distance, the less likely it is to migrate from the current area to the target area. τ is a small constant used to prevent the denominator from being zero. γ is the distance sensitivity coefficient. The larger the value, the more obvious the attenuation of the distance.

[0102] The characteristics of the power exponential decay make the probability of short-distance migration greater, while the probability of long-distance migration will decrease significantly as the distance increases. This can effectively limit unreasonable long-distance predictions and make the model more in line with the actual situation.

[0103] Then, calculate the historical transition probability mapping function. The historical transition probability mapping function uses a weighted average method with time decay to reflect the probability of the target migrating from the first scanning area to the second scanning area in the historical record:

[0104]

[0105] Among them, λ is the time decay factor, whose function is to make the weight of the most recent record larger and the weight of the earlier record smaller. T is the total number of historical records, and P t (1→2) is the transition probability from the first scanning area to the second scanning area recorded at the t-th time.

[0106] The weighted time average combines the idea of time decay, allowing the system to pay more attention to the recent behavior patterns while retaining the long-term trend. With the effect of the time decay factor, the formula is more sensitive to recent data, which can adapt to short-term changes in the environment and improve the accuracy of prediction.

[0107] Take the above three mapping functions as f 1 = f(θ), f 2 = f(d), f 3 = f(h), and perform weighted product fusion according to the weight coefficients:

[0108]

[0109] Among them, P is the probability that the moving target moves to the second scanning area, σ is the Sigmoid function, f 1 = f(θ), f 2 = f(d), f 3 = f(h), w i is the weight coefficient. When i = 1, w 1 is the direction weight coefficient. When i = 2, w 2 is the distance weight coefficient. When i = 3, w 3 is the historical weight coefficient.

[0110] The product part represents the calculation result of the weighted product of the three factors. The Sigmoid function is used to map the result to the range of 0 to 1:

[0111]

[0112] Therefore, the final formula is:

[0113]

[0114] The product model ensures a higher probability when multiple factors are satisfied. Therefore, each factor must be relatively high to maintain a high overall probability. The weight of each factor adjusts the relative importance of each factor, allowing for flexible control of the influence of different factors in the fusion. After the fusion result, the Sigmoid function is used to smoothly map it to the range of 0 to 1. This mapping makes the fusion result more in line with the probability distribution requirements, and the smoothing process can avoid the excessive influence of extreme values on the final probability.

[0115] S130, if it is determined that the probability of the moving target moving to the second scanning area is greater than or equal to the preset threshold, send a collection instruction to the second controller.

[0116] As described above, the probability of the moving target entering the second scanning area is calculated by the method of weighted product fusion, and a preset probability threshold is set to determine whether the target may enter the second scanning area. This threshold can be adjusted according to the error requirements and monitoring needs of the actual environment. For example, it can be set according to the success rate and error range of the target entering the adjacent area. Adjust the threshold according to historical data or statistical analysis to adapt to different environmental requirements. For example, in an area where the target moves frequently or the path is complex, the threshold can be appropriately reduced to perform more sensitive detection.

[0117] Once the probability P is calculated, compare it with the threshold P threshold as follows:

[0118] If P≥P threshold , it means that the target is likely to enter the second scanning area, triggering subsequent control instructions.

[0119] If P<P threshold , maintain the current monitoring state and do not send a collection instruction to the second controller.

[0120] If it is determined that the condition is met, send a collection instruction to the second controller to enable it to activate the laser point cloud sensor in the second scanning area to monitor the entry of the target.

[0121] S140, receive the changed data transmitted by the second controller.

[0122] In a possible implementation, before obtaining the changed data by comparing two consecutive second point cloud data point by point based on the second point cloud data obtained from multiple scans, the method further includes: sending background point cloud data to the second controller so that the second controller compares the background point cloud data with the real-time point cloud data and uses the background difference algorithm to extract the point cloud data corresponding to the moving target in the real-time point cloud data, thereby obtaining the second point cloud data.

[0123] Specifically, in the normal static state of the substation, one or more frames of point cloud data are collected by the laser point cloud sensors of each controller, and after denoising processing, a stable background point cloud data is generated. To improve stability, the background data can be obtained by averaging multiple frames or long-term sampling. Send the collected background point cloud data to the second controller. The background point cloud data can include the spatial coordinate information of static objects in the target scanning area, providing a benchmark for subsequent comparison.

[0124] When the system is running normally, the second controller continuously collects real-time point cloud data for detecting whether there are moving targets. The second controller controls the laser point cloud sensor connected to it to collect the point cloud data of the current area at a fixed frequency, generating real-time point cloud data frames. The real-time point cloud data is preprocessed, such as noise removal and coordinate alignment, to ensure that the quality of the real-time point cloud data is consistent with the background point cloud data for subsequent comparison.

[0125] The second controller aligns the real-time point cloud data to the coordinate system of the background point cloud data. Usually, the ICP (Iterative Closest Point) or NDT (Normal Distributions Transform) algorithm is used for registration to ensure that the two sets of point cloud data are under the same reference framework. Each point in the background point cloud and the real-time point cloud is compared point by point, and the Euclidean distance between each pair of corresponding points is calculated. At the same time, a distance threshold is defined. If the distance of a certain point exceeds the threshold, then this point is regarded as a changed point. All points exceeding the threshold are retained to form changed point cloud data. After background difference and screening processing, the point cloud data of the moving target is obtained, and this data is defined as "the second point cloud data".

[0126] After receiving the acquisition instruction, the second sensor controls the second sensor to perform continuous scanning. According to the second point cloud data obtained from multiple scans, the changed data part is found by comparing two consecutive second point cloud data point by point, and the changed data is obtained.

[0127] In a possible implementation manner, according to the second point cloud data obtained from multiple scans, the changed data part is found by comparing two consecutive second point cloud data point by point, and the changed data is obtained, specifically including: the second controller performs initial registration on the first sub-data and the second sub-data, where the first sub-data and the second sub-data are any two adjacent second point cloud data among multiple second point cloud data; the second controller queries multiple groups of first data points and second data points in the first sub-data and the second sub-data according to the initial registration result, where the first data point is any point in the first sub-data, and the second data point is the point in the second sub-data closest to the first data point; the second controller calculates the rigid body transformation between the first data point and the second data point to make the first sub-data coincide with the second sub-data; the second controller continuously iterates and updates the calculation until the rigid body transformation error converges below the threshold to complete the accurate point cloud registration; after the second controller completes the accurate point cloud registration, by comparing the spatial position changes of each data point in the first sub-data and the second sub-data, the moving or newly added data points can be found to obtain the changed data.

[0128] Specifically, first, it is necessary to calculate the centroids of the first sub-data and the second sub-data to calculate the rotation relationship of the point cloud while removing the translation influence. The second controller calculates the first sub-data {p 1 ,p2, …, p n}, the first centroid, calculate the second sub - data set {q 1 , q 2 , …, q n}, and its second centroid is specifically calculated by the following formula:

[0129]

[0130] where c p is the first centroid, c q is the second centroid, {p 1 , p 2, …, p n} is the first sub - data set, and {q 1 , q 2 , …, q n} is the second sub - data set.

[0131] The purpose of calculating the centroid is to decentralize two sets of point cloud data, thus facilitating the subsequent calculation of the rotation matrix to align the two sets of data. By subtracting each point from its corresponding centroid, the decentralized point cloud data is obtained. After decentralization, the translational offset can be eliminated, enabling the calculation to focus on rotational alignment. Based on the decentralized data, calculate the covariance matrix between the first sub - data set and the second sub - data set for constructing the rigid - body transformation matrix. It is specifically calculated by the following formula:

[0132]

[0133] where H is the covariance matrix, c p is the first centroid, c q is the second centroid, {p 1 , p 2, …, p n} is the first sub - data set, and {q 1 , q 2 , …, q n} is the second sub - data set.

[0134] The calculation of the covariance matrix H involves the "similarity" of two sets of decentralized point clouds. For each pair of corresponding points p i and q i , first subtract their respective centroids to obtain the decentralized points, then calculate the outer product of the two, and sum over all points. The covariance matrix reflects the alignment degree between the point cloud data.

[0135] Perform singular value decomposition (SVD) on the covariance matrix H, and decompose H into three matrices:

[0136] H = U·E·V T

[0137] Among them, U and V are orthogonal matrices, representing a rotation relationship. E is a diagonal matrix that contains singular values.

[0138] Singular Value Decomposition (SVD) is a matrix decomposition method that decomposes matrix H into the product of U, E, and V. U and V are orthogonal matrices, representing rotation information, and E is a diagonal matrix that contains the singular values (scale factors) of the covariance matrix, reflecting the scaling relationship between two point cloud sets in different directions. The diagonal matrix E is a diagonal matrix during the singular value decomposition process, and its expression is:

[0139]

[0140] During the singular value decomposition process, the diagonal matrix E contains the singular values of matrix H, σ 1 、σ 2 、and σ 3 , and these values reflect the scaling relationship between two point cloud sets in different directions.

[0141] Combine the rotation matrix and the translation vector to construct a 4x4 rigid body transformation matrix T:

[0142]

[0143] The rigid body transformation matrix T is used to rotate and translate the first sub-data into the coordinate system of the second sub-data. The rotation matrix R is located in the upper left corner of the matrix, and the translation vector T is located in the upper right corner of the matrix. The rigid body transformation matrix can act on points in homogeneous coordinate form to achieve rotation and translation operations.

[0144] Use the rigid body transformation matrix T to transform each point of the first sub-data to obtain the updated first sub-data points, as follows:

[0145]

[0146] Among them, p i ' is the updated first data point, H is the covariance matrix, E is the diagonal matrix, and p i is the first data point. For each point of the first sub-data, apply rotation and translation transformations to convert the point from the coordinate system of the first sub-data to the coordinate system of the second sub-data. This can make the first sub-data coincide with the second sub-data and achieve precise registration.

[0147] After applying the rigid body transformation, check the registration error. If the registration error does not converge below the preset threshold, then use the updated first sub-data as the input again and repeat the above steps for further iteration until the registration error reaches the convergence condition.

[0148] After completing the precise registration of two frames of point cloud data, identify the moving or newly added points by comparing the spatial position differences of each point in the first sub-data and the second sub-data. Compare the distances of each paired point. If the distance exceeds the set threshold, it is determined as a changed data point. Finally, collect all the points that exceed the distance threshold to form a changed data set, representing the moving or newly added part in two consecutive frames of point cloud data.

[0149] S150. Generate the continuous motion state of the three-dimensional moving target according to the changed data.

[0150] In a possible implementation manner, generating the continuous motion state of the three-dimensional moving target according to the changed data specifically includes: obtaining the preliminary trajectory of the moving target by extracting the centroid position of each changed data; accumulating the changed data obtained from multiple scans into a global coordinate system to form an accumulated point cloud; performing surface reconstruction on the basis of the accumulated point cloud to obtain the three-dimensional model of the target; and forming a dynamic three-dimensional dynamic model according to the time series.

[0151] Specifically, from the changed data obtained by multiple scans, the centroid position of the moving target can be obtained, and the preliminary motion trajectory of the target can be generated using the centroid position. For each frame of changed data, calculate the centroid position of the point cloud. The centroid position reflects the center of the point cloud data of this frame and is the spatial position of the target at this moment.

[0152] Connect the centroids of each frame in chronological order to form the preliminary trajectory of the target. These centroids constitute a trajectory line representing the path of the moving target and record the movement process of the target in space. To generate the complete three-dimensional model of the moving target, it is necessary to accumulate the changed data at different time points into a global coordinate system. The point cloud data obtained from each scan needs to be aligned in the global coordinate system to ensure that the changed data between different frames can be accumulated into the same coordinate system. Accumulate the aligned changed data of each frame together to form the accumulated point cloud of the target. The accumulated point cloud contains the position and shape information of the target at each moment and provides a complete three-dimensional data basis.

[0153] On the basis of the accumulated point cloud, generate the complete three-dimensional model of the moving target through a surface reconstruction algorithm. Surface reconstruction is used to convert the dense point cloud data into a continuous three-dimensional surface, facilitating the display of the geometric shape of the target. For areas with sparse point clouds, interpolation methods can be used to fill in the missing parts to ensure the integrity of the model. The interpolation completion method can eliminate discontinuous edges or holes.

[0154] By accumulating point cloud and time series information, a dynamic 3D model of the moving object is formed to display its continuous motion state. Based on the time series, the data of the accumulated point cloud is updated frame by frame to form a continuous dynamic 3D model. For each frame of point cloud data, its coordinates and time information are combined to update the 3D model of the object. After obtaining the changed data from each new scan, it is registered in the global coordinate system and the 3D model is updated frame by frame. The dynamic model not only includes the morphological changes of the object, but also combines its motion trajectory. By recording the motion states such as displacement and rotation of the object through the time series, the 3D model can reflect the real motion process of the object. After the dynamic model is generated, it can be further used to generate a visual 3D animation or continuous motion state output for display or monitoring. The accumulated 3D model and the time series trajectory are combined to display the continuous motion process of the object in the form of an animation. The animation display can clearly show the moving path and morphological changes of the object. The key parameters of the 3D dynamic model, including information such as position, speed, and direction, are extracted and output in the form of a time series for monitoring and analysis.

[0155] This embodiment also discloses a device for tracking the trajectory of a moving object in a substation based on a 3D digital model. The device is a server, and the device includes an acquisition module 301, a processing module 302, and a sending module 303, where:

[0156] The acquisition module 301 is configured to acquire first position data transmitted by a first controller. Among them, the first controller, according to the first point cloud data collected by the acquired first sensor, if it determines that there is a moving object in the first scanning area of the first sensor, then sends the first position data of the first scanning area to the server. The first controller is any one of multiple controllers, and the first sensor is a laser point cloud sensor connected to the first controller among multiple laser point cloud sensors.

[0157] The processing module 302 is configured to calculate the probability that the moving object moves to the scanning areas of each sensor according to the preset spatial structure of the substation.

[0158] The sending module 303 is configured to, if it determines that the probability that the moving object moves to the second scanning area is greater than or equal to a preset threshold, then send an acquisition instruction to a second controller, where the second controller is any one of multiple controllers other than the first controller, the scanning area of the second sensor is the second scanning area, and the second sensor is a laser point cloud sensor connected to the second controller among multiple laser point cloud sensors.

[0159] The acquisition module 301 is configured to receive changed data transmitted by the second controller. Among them, after the second sensor receives the acquisition instruction, it controls the second sensor to perform continuous scanning. According to the second point cloud data obtained from multiple scans, the changed data part is found by comparing two consecutive second point cloud data point by point to obtain the changed data.

[0160] The processing module 302 is configured to generate a continuous motion state of a three-dimensional moving target according to the changed data.

[0161] In a possible implementation manner, the obtaining module 301 is configured to obtain a preset substation space structure, where the substation space structure includes a connection structure of a laser point cloud sensor based on the internal route of the substation and a connection distance between two interconnected laser point cloud sensors. The connection structure uses the installation positions of the laser point cloud sensors as nodes and the internal route of the substation as links, and the nodes are connected through the internal route of the substation.

[0162] The processing module 302 is configured to determine the continuous position change of the moving target in the substation according to the first point cloud data obtained by multiple scans transmitted by the first controller.

[0163] The processing module 302 is configured to determine the moving direction of the moving target according to the continuous position change.

[0164] The obtaining module 301 is configured to obtain the historical probabilities of different moving objects moving from the first scanning area to each scanning area in the historical record.

[0165] The processing module 302 is configured to perform weighted product fusion on the substation space structure, the moving direction, and the historical probability, and calculate the probability that the moving target moves to the scanning area of each sensor.

[0166] In a possible implementation manner, the processing module 302 is configured to perform weighted product fusion on the substation space structure, the moving direction, and the historical probability, and calculate the probability that the moving target moves to the second scanning area, specifically calculated by the following formula:

[0167]

[0168] where P is the probability that the moving target moves to the second scanning area, σ is the Sigmoid function, f 1 = f(θ), f 2 = f(d), f 3 = f(h), w i is the weight coefficient. When i = 1, w 1 is the direction weight coefficient. When i = 2, w 2 is the distance weight coefficient. When i = 3, w 3 is the historical weight coefficient, α is the direction sensitivity, θ is the angle between the moving direction and the moving pointing, the moving pointing is the direction from the center of the first scanning area to the center of the second scanning area, θ 0 is the expected angle based on the first scanning area, d 12is the distance between the first scanning area and the second scanning area, τ is a constant used to prevent the denominator from being zero, γ is the distance sensitivity coefficient, λ is the time decay factor, T is the total number of historical records, and P t (1→2) is the transition probability from the first scanning area to the second scanning area recorded at the t-th time.

[0169] In a possible implementation, the sending module 303 is configured to send background point cloud data to the second controller, so that the second controller compares the background point cloud data with the real-time point cloud data, and uses the background difference algorithm to extract the point cloud data corresponding to the moving target in the real-time point cloud data, thereby obtaining the second point cloud data.

[0170] In a possible implementation, the processing module 302 is configured to obtain the preliminary trajectory of the moving target by extracting the centroid position of each change data.

[0171] The processing module 302 is configured to accumulate the change data obtained from multiple scans into a global coordinate system to form an accumulated point cloud.

[0172] The processing module 302 is configured to perform surface reconstruction on the basis of the accumulated point cloud to obtain a target three-dimensional model.

[0173] The processing module 302 is configured to form a dynamic three-dimensional dynamic model according to the time series.

[0174] It should be noted that: when the device provided in the above embodiment realizes its functions, only the above-mentioned division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiment, which will not be elaborated here.

[0175] This embodiment also discloses an electronic device. Referring to Figure 4 , the electronic device may include: at least one processor 401, at least one communication bus 402, a user interface 403, a network interface 404, and at least one memory 405.

[0176] Among them, the communication bus 402 is used to realize the connection and communication between these components.

[0177] Among them, the user interface 403 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 403 may further include a standard wired interface and a wireless interface.

[0178] Among them, the network interface 404 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface).

[0179] Among them, the processor 401 may include one or more processing cores. The processor 401 connects various parts within the entire server through various interfaces and lines, and executes various functions of the server and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 405, and by calling the data stored in the memory 405. Optionally, the processor 401 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 401 may integrate one or a combination of several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 401 and may be implemented separately by a single chip.

[0180] Among them, the memory 405 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory includes a non-transitory computer-readable storage medium. The memory 405 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 405 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. Optionally, the memory 405 may further be at least one storage device located far from the aforementioned processor 401. As a computer storage medium, the memory 405 may include an operating system, a network communication module, a user interface 403 module, and an application program for a method of tracking the trajectory of a moving object in a substation based on a three-dimensional digital model.

[0181] InFigure 4 In the electronic device shown, the user interface 403 is mainly used to provide an interface for the user to input and obtain the data input by the user; and the processor 401 can be used to call an application program stored in the memory 405, which is a method for tracking the trajectory of moving objects in a substation based on a three-dimensional digital model. When executed by one or more processors 401, the electronic device is caused to execute the method of one or more of the above embodiments.

[0182] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0183] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0184] In several embodiments provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0185] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0186] In addition, the functional units in each embodiment of this application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0187] When the integrated unit 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 memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 405 and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. And the aforementioned memory 405 includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0188] The present application also discloses a computer-readable storage medium storing instructions. When executed by one or more processors 401, it causes the electronic device to execute one or more of the methods as described in the above embodiments.

[0189] The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. After considering the specification and the disclosure of the practical truth, those skilled in the art will easily think of other implementation schemes of the present disclosure. The present application aims to cover any variations, uses, or adaptive changes of the present disclosure, and these variations, uses, or adaptive changes follow the general principles of the present disclosure and include the common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for tracking the trajectory of a moving object in a substation based on a three-dimensional digital model, characterized in that: The method is applied to a server of a substation management and control system, wherein the substation management and control system comprises the server, multiple controllers and multiple laser point cloud sensors, wherein the server is connected to multiple controllers at the same time, and each of the controllers is connected to one laser point cloud sensor, and the method comprises: Acquire first position data transmitted by a first controller, wherein the first controller sends the first position data of the first scanning area to the server if it is determined that there is a moving target in the first scanning area of ​​the first sensor based on the acquired first point cloud data collected by the first sensor, the first controller is any one of the plurality of controllers, and the first sensor is a laser point cloud sensor connected to the first controller among the plurality of laser point cloud sensors; According to the preset substation spatial structure, the probability of the mobile target moving to the scanning area of ​​each sensor is calculated; If it is determined that the probability that the mobile target moves to the second scanning area is greater than or equal to a preset threshold, a collection instruction is sent to a second controller, wherein the second controller is any one of the multiple controllers except the first controller, the scanning area of ​​the second sensor is the second scanning area, and the second sensor is a laser point cloud sensor connected to the second controller among the multiple laser point cloud sensors; receiving the change data transmitted by the second controller, wherein after receiving the acquisition instruction, the second sensor controls the second sensor to perform continuous scanning, and compares two consecutive second point cloud data point by point to find the changed data part according to the second point cloud data obtained by multiple scans, so as to obtain the change data; A three-dimensional continuous motion state of the moving object is generated according to the change data.

2. A method for tracking the trajectory of a moving object in a substation based on a three-dimensional digital model according to claim 1, characterized in that: The calculating, according to the preset substation spatial structure, the probability that the mobile target moves to the scanning area of ​​each sensor specifically includes: Acquire a preset substation spatial structure, wherein the substation spatial structure includes a connection structure of laser point cloud sensors based on an internal route of the substation and a connection distance between two mutually connected laser point cloud sensors, the connection structure uses the installation positions of the laser point cloud sensors as nodes, uses the internal route of the substation as links, and nodes are connected through the internal route of the substation; Determining continuous position changes of the mobile target in the substation according to the received first point cloud data obtained by multiple scans transmitted by the first controller; Determining a moving direction of the moving target according to the continuous position change; Acquire historical probabilities of different moving objects moving from the first scanning area to each of the scanning areas in historical records; The substation spatial structure, the moving direction and the historical probability are weightedly fused to calculate the probability of the moving target moving to the scanning area of ​​each sensor.

3. A method for tracking the trajectory of a moving object in a substation based on a three-dimensional digital model according to claim 2, characterized in that: Before determining that the probability that the moving target moves to the second scanning area is greater than or equal to a preset threshold, the method further includes: The substation spatial structure, the moving direction and the historical probability are weighted and fused to calculate the probability of the moving target moving to the second scanning area, which is specifically calculated by the following formula: Wherein, P is the probability that the mobile target moves to the second scanning area, σ is the Sigmoid function, f1=f(θ), f2=f(d), f3=f(h), w i is the weight coefficient, when i=1, w1 is the direction weight coefficient, when i=2, w2 is the distance weight coefficient, when i=3, w3 is the history weight coefficient, α is the direction sensitivity, θ is the angle between the moving direction and the moving direction, the moving direction is the direction from the center of the first scanning area to the center of the second scanning area, θ0 is the expected angle based on the first scanning area, d 12 is the distance between the first scanning area and the second scanning area, τ is a constant, τ is used to prevent the denominator from being zero, γ is the distance sensitivity coefficient, λ is the time attenuation factor, T is the total number of historical records, P t (1→2) is the transition probability from the first scanning area to the second scanning area recorded at the tth time.

4. The method for tracking the trajectory of a moving object in a substation based on a three-dimensional digital model according to claim 1, characterized in that: Before comparing two consecutive second point cloud data point by point to find a changed data portion based on the second point cloud data obtained by multiple scans and obtaining the changed data, the method further includes: The background point cloud data is sent to the second controller so that the second controller compares the background point cloud data with the real-time point cloud data, and uses a background difference algorithm to extract the point cloud data corresponding to the mobile target in the real-time point cloud data, thereby obtaining the second point cloud data.

5. The method for tracking the trajectory of a moving object in a substation based on a three-dimensional digital model according to claim 1, characterized in that: The step of comparing two consecutive second point cloud data point by point to find a changed data portion based on the second point cloud data obtained by multiple scans to obtain the changed data specifically includes: The second controller initially aligns the first sub-data with the second sub-data, where the first sub-data and the second sub-data are any two adjacent second point cloud data among the plurality of second point cloud data; The second controller queries multiple groups of first data points and second data points in the first sub-data and the second sub-data according to the initial registration result, wherein the first data point is any point in the first sub-data, and the second data point is a point in the second sub-data that is closest to the first data point; The second controller calculates a rigid body transformation between the first data point and the second data point so that the first sub-data and the second sub-data coincide with each other; The second controller continuously iterates and updates the calculation until the rigid body transformation error converges below the threshold, completing the precise point cloud registration; After the second controller completes the precise point cloud registration, the moved or newly added data points can be found by comparing the spatial position changes of each data point in the first sub-data and the second sub-data to obtain the change data.

6. A method for tracking the trajectory of a moving object in a substation based on a three-dimensional digital model according to claim 5, characterized in that: The second controller calculates the rigid body transformation between the first data point and the second data point so that the first sub-data and the second sub-data overlap, specifically including: The second controller calculates the first sub-data {p1, p 2, …,p n }, calculate the first centroid of the second sub-data {q1,q2,…,q n The second centroid of} is calculated by the following formula: Among them, c p is the first centroid, c q is the second centroid, {p1,p 2, …,p n } is the first sub-data, {q1,q2,…,q n } is the second sub-data; The second controller calculates the covariance matrix, specifically by the following formula: Where H is the covariance matrix, c p is the first centroid, c q is the second centroid, {p1,p 2, …,p n } is the first sub-data, {q1,q2,…,q n } is the second sub-data; The second controller constructs a rigid body transformation matrix based on the covariance matrix, as follows: Wherein, T is the rigid body transformation matrix, H is the covariance matrix, E is the diagonal matrix, c p is the first centroid, c q is the second centroid; The second controller applies the rigid body transformation matrix to the first sub-data, updates the first data point, and obtains an updated first data point, as follows: Among them, p i ' is the first data point after update, H is the covariance matrix, E is the diagonal matrix, p i is the first data point.

7. The method for tracking the trajectory of a moving object in a substation based on a three-dimensional digital model according to claim 1, characterized in that: Generating the three-dimensional continuous motion state of the moving target according to the change data specifically includes: By extracting the centroid position of each change data, a preliminary trajectory of the moving target is obtained; Accumulate the change data obtained from multiple scans into a global coordinate system to form a cumulative point cloud; Based on the accumulated point cloud, surface reconstruction is performed to obtain the target three-dimensional model; According to the time series, a dynamic three-dimensional dynamic model is formed.

8. A moving object trajectory tracking device in a substation based on a three-dimensional digital model, characterized in that: The device is a server, and comprises an acquisition module (301), a processing module (302), and a sending module (303), wherein: The acquisition module (301) is used to acquire first position data transmitted by a first controller, wherein the first controller sends the first position data of the first scanning area to the server if it is determined that there is a moving target in the first scanning area of ​​the first sensor based on the acquired first point cloud data collected by the first sensor, the first controller is any one of a plurality of controllers, and the first sensor is a laser point cloud sensor connected to the first controller among a plurality of laser point cloud sensors; The processing module (302) is used to calculate the probability of the mobile target moving to the scanning area of ​​each sensor according to the preset substation spatial structure; The sending module (303) is used to send a collection instruction to a second controller if it is determined that the probability of the mobile target moving to the second scanning area is greater than or equal to a preset threshold, wherein the second controller is any one of the plurality of controllers except the first controller, the scanning area of ​​the second sensor is the second scanning area, and the second sensor is a laser point cloud sensor connected to the second controller among the plurality of laser point cloud sensors; The acquisition module (301) is used to receive the change data transmitted by the second controller, wherein after the second sensor receives the acquisition instruction, the second sensor is controlled to perform continuous scanning, and based on the second point cloud data obtained by multiple scans, two consecutive second point cloud data are compared point by point to find the changed data part, so as to obtain the change data; The processing module (302) is used to generate a three-dimensional continuous motion state of the moving target according to the change data.

9. An electronic device, characterized in that: The electronic device comprises a processor (401), a communication bus (402), a user interface (403), a network interface (404) and a memory (405), wherein the memory (405) is used to store instructions, the user interface (403) and the network interface (404) are both used to communicate with other devices, and the processor (401) is used to execute the instructions stored in the memory (405) so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images