Obstacle risk level determination method and device and electronic equipment

Abstract

The invention discloses an obstacle risk level determination method and device and electronic equipment. The method comprises the following steps: acquiring a plurality of area images of a target area; determining an initial region parameter of the target region according to the plurality of region images; according to the initial region parameter and predetermined point cloud data corresponding to the predetermined region, determining a refinement parameter; according to the refining parameter, refining the initial region parameter to obtain a target region parameter; according to the target area parameters, determining spatial relation parameters, corresponding to the power transmission line, of the multiple obstacles; and according to the spatial relationship parameters corresponding to the plurality of obstacles and the power transmission line, determining the risk levels of the plurality of obstacles affecting the power transmission line. According to the method and the device, the technical problems that the accuracy of the determined obstacle risk is low and the monitoring accuracy requirement is difficult to meet when the obstacle risk of a large-area region is determined in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular, to a method, apparatus, and electronic device for determining the risk level of obstacles. Background Art

[0002] Determining the risk level of obstacles is of great significance for the management and safety maintenance of equipment in the target area. At present, lidar technology and satellite remote sensing technology are mainly used to collect data and model the target area for roadblock analysis. However, when determining obstacle risks in a large area, this method has the technical problems of low accuracy of the determined obstacle risks and difficulty in meeting the monitoring accuracy requirements.

[0003] In view of the above problems, no effective solution has been proposed yet. Summary of the Invention

[0004] Embodiments of the present invention provide a method, apparatus, and electronic device for determining the risk level of obstacles, so as to at least solve the technical problems in the related art that when determining obstacle risks in a large area, the accuracy of the determined obstacle risks is low and it is difficult to meet the monitoring accuracy requirements.

[0005] According to one aspect of the embodiments of the present invention, a method for determining the risk level of obstacles is provided, including: obtaining a plurality of regional images of a target area, where the plurality of regional images include a power transmission line and a plurality of obstacles, and the plurality of obstacles are objects whose risk impact probability on the power transmission line is greater than a predetermined threshold; determining initial regional parameters of the target area according to the plurality of regional images; determining refinement parameters according to the initial regional parameters and predetermined point cloud data corresponding to a predetermined area, where the predetermined area is an area in the target area where corresponding predetermined point cloud data exists; refining the initial regional parameters according to the refinement parameters to obtain target area parameters; determining spatial relationship parameters corresponding to the plurality of obstacles and the power transmission line according to the target area parameters; and determining the risk levels of the plurality of obstacles on the power transmission line respectively according to the spatial relationship parameters corresponding to the plurality of obstacles and the power transmission line respectively.

[0006] Optionally, determining refinement parameters according to the initial regional parameters and predetermined point cloud data corresponding to a predetermined area includes: determining regional parameters corresponding to the predetermined area in the initial regional parameters to obtain first regional parameters; determining predetermined area parameters corresponding to the predetermined area according to the predetermined point cloud data; determining a first parameter difference between the predetermined area parameters and the first regional parameters; and determining the refinement parameters according to the first parameter difference, the first regional parameters, and the initial regional parameters.

[0007] Optionally, determining the refinement parameter according to the first parameter difference, the first region parameter, and the initial region parameter includes: determining an initial region feature according to the initial region parameter; determining a predetermined region feature corresponding to the predetermined region according to the first region parameter; and determining the refinement parameter according to the first parameter difference, the predetermined region feature, and the initial region feature.

[0008] Optionally, determining the refinement parameter according to the first parameter difference, the predetermined region feature, and the initial region feature includes: when both the initial region feature and the predetermined region feature include multiple features, determining an influence index between each of the multiple predetermined region features and the first parameter difference; determining a first target feature from the multiple predetermined region features according to the multiple influence indexes, where the target influence index corresponding to the first target feature is greater than a target threshold; determining a target region feature corresponding to the first target feature from the multiple initial region features; and determining the refinement parameter according to the target region feature, the first parameter difference, and the first target feature.

[0009] Optionally, after determining the refinement parameter according to the first parameter difference, the first region parameter, and the initial region parameter, further includes: determining test point cloud data corresponding to a test region, where the test region is a region in the target region except the predetermined region and having corresponding test point cloud data; determining a region parameter corresponding to the test region in the initial region parameter to obtain a second region parameter; determining a test region parameter according to the second region parameter and the refinement parameter; determining a second parameter difference according to the test region parameter and the test point cloud data corresponding to the test region; and when the second parameter difference is greater than an error threshold, updating the refinement parameter to obtain an updated refinement parameter, so as to refine the initial region parameter according to the updated refinement parameter.

[0010] Optionally, determining the spatial relationship parameter between each of the multiple obstacles and the transmission line according to the target region parameter includes: when the obstacle is a tree and the target region parameter includes the tree height, determining the spectral feature corresponding to the tree according to the multiple region images; determining the tree type corresponding to the tree according to the spectral feature and the tree height; and determining the spatial relationship parameter between each of the multiple trees and the transmission line according to the tree type and the tree height.

[0011] Optionally, based on the multiple regional images, initial regional parameters are determined, including: based on the multiple regional images, multiple target regional images respectively corresponding to multiple target objects are determined, where the multiple target objects include the transmission line and the multiple obstacles, and the angular difference between the shooting angles corresponding to the multiple target regional images is greater than an angular threshold; based on the multiple target regional images and the shooting angles respectively corresponding to the multiple target regional images, coordinate parameters respectively corresponding to the multiple target objects are determined; based on the multiple coordinate parameters, the initial regional parameters corresponding to the target region are determined.

[0012] According to one aspect of an embodiment of the present invention, a device for determining the risk level of obstacles is provided, including: an acquisition module, configured to acquire multiple regional images of a target region, where the multiple regional images include a transmission line and multiple obstacles, and the multiple obstacles are objects with a risk impact probability on the transmission line greater than a predetermined threshold; a first determination module, configured to determine initial regional parameters of the target region based on the multiple regional images; a second determination module, configured to determine refinement parameters based on the initial regional parameters and predetermined point cloud data corresponding to a predetermined region, where the predetermined region is a region in the target region where corresponding predetermined point cloud data exists; a refinement module, configured to refine the initial regional parameters based on the refinement parameters to obtain target region parameters; a third determination module, configured to determine spatial relationship parameters respectively corresponding to the multiple obstacles and the transmission line based on the target region parameters; a fourth determination module, configured to determine the risk levels of the multiple obstacles respectively affecting the transmission line based on the spatial relationship parameters respectively corresponding to the multiple obstacles and the transmission line.

[0013] According to one aspect of an embodiment of the present invention, an electronic device is provided, including: a processor; a memory for storing instructions executable by the processor; wherein, the processor is configured to execute the instructions to implement the method for determining the risk level of obstacles in any one of the above.

[0014] According to one aspect of an embodiment of the present invention, a computer-readable storage medium is provided, when the instructions in the computer-readable storage medium are executed by the processor of the electronic device, enabling the electronic device to execute the method for determining the risk level of obstacles in any one of the above.

[0015] In an embodiment of the present invention, multiple regional images of a target area are acquired, where the multiple regional images include a transmission line and multiple obstacles, and the multiple obstacles are objects with a risk impact probability on the transmission line greater than a predetermined threshold; based on the multiple regional images, initial regional parameters of the target area are determined; based on the initial regional parameters and predetermined point cloud data corresponding to a predetermined area, refinement parameters are determined, where the predetermined area is an area in the target area where corresponding predetermined point cloud data exists; based on the refinement parameters, the initial regional parameters are refined to obtain target area parameters; based on the target area parameters, spatial relationship parameters corresponding to the multiple obstacles and the transmission line are determined respectively; based on the spatial relationship parameters corresponding to the multiple obstacles and the transmission line respectively, a method for determining the risk level of the impact of the multiple obstacles on the transmission line respectively is adopted. By determining the refinement parameters based on the initial regional parameters and the predetermined point cloud data corresponding to the predetermined area, the purpose of refining the initial regional parameters based on the refinement parameters to obtain the target area parameters is achieved. Since the point cloud data has high precision, using the refinement parameters determined by the high-precision point cloud data to refine the initial regional parameters can obtain target area parameters with high accuracy. Using these target area parameters to determine the spatial relationship parameters between the obstacles and the transmission line can improve the accuracy of the determined obstacle risk level, thereby solving the technical problem in the related art that when determining the obstacle risk for a large-area region, the determined obstacle risk accuracy is low and it is difficult to meet the monitoring accuracy requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0017] Figure 1 is a flowchart of a method for determining the obstacle risk level in an embodiment of the present invention;

[0018] Figure 2 is a flowchart of a method for determining the tree obstacle risk of an overhead transmission line provided by an alternative embodiment of the present invention;

[0019] Figure 3 is a structural block diagram of a device for determining the obstacle risk level in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0021] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0022] Embodiment 1

[0023] According to an embodiment of the present invention, an embodiment of a method for determining the obstacle risk level is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from that here.

[0024] Figure 1 is a flowchart of the method for determining the obstacle risk level according to an embodiment of the present invention. As Figure 1 shown, the method includes the following steps:

[0025] Step S102, obtain multiple regional images of the target area, where the multiple regional images include a power transmission line and multiple obstacles, and the multiple obstacles are objects with a risk impact probability on the power transmission line greater than a predetermined threshold.

[0026] In step S102 provided in the present application, multiple regional images of the target area are obtained.

[0027] Among them, the target area is involved. The target area refers to the geographical area that needs to be monitored and analyzed, such as the area including the power transmission line and its surrounding environment.

[0028] Among them, regional images are involved. Regional images refer to multiple images covering the target area obtained through satellites, drones, or other remote sensing platforms.

[0029] Among them, obstacles are involved. Obstacles refer to natural or man-made objects that pose risks to transmission lines, such as trees, buildings, bridges, mountains, etc. These obstacles may approach or contact the transmission lines due to growth, movement, or collapse, thus threatening the safe and stable operation of the power system.

[0030] Among them, a predetermined threshold is involved. The predetermined threshold refers to a set standard or boundary used to judge the risk impact probability of obstacles. If the risk impact probability of a certain obstacle exceeds the predetermined threshold, it is necessary to determine its risk level.

[0031] In this step, at the beginning of determining the risk level of obstacles in the target area, it is necessary to first obtain multiple regional images of the target area, and these regional images include transmission lines and those obstacles that are judged to have a high risk possibility to the transmission lines.

[0032] Step S104: Determine the initial regional parameters of the target area based on multiple regional images.

[0033] In step S104 provided in this application, the initial regional parameters of the target area are determined.

[0034] Among them, initial regional parameters are involved. Initial regional parameters refer to preliminary measurement parameters used to describe the surface characteristics of the target area. For example, digital surface model data (DSM) and digital elevation model data (DEM).

[0035] In this step, first, use multiple regional images (such as satellite stereo pairs) to preliminarily determine the surface characteristic parameters of the target area (around the transmission line), such as DSM data and DEM data. These parameters are the basis for subsequent precise analysis, such as calculating the tree height, identifying tree species, and evaluating the risk of tree obstacles. Through this step, an initial analysis of the large-area target area is carried out to determine the preliminary terrain characteristics of the target area, effectively reducing the overall cost and providing a solid data basis for subsequent risk level assessment.

[0036] Step S106: Determine the refinement parameters based on the initial regional parameters and the predetermined point cloud data corresponding to the predetermined area, where the predetermined area is the area in the target area where there is corresponding predetermined point cloud data.

[0037] In step S106 provided in this application, the refinement parameters are determined.

[0038] Among them, a predetermined area is involved. The predetermined area refers to an area within the target area where detailed point cloud data has been previously obtained by other means (such as drone point cloud data collection).

[0039] Among them, predetermined point cloud data is involved. The predetermined point cloud data refers to high-precision three-dimensional point cloud data obtained by means such as drones in the predetermined area. The point cloud data is a dataset composed of a series of three-dimensional points, which can represent the three-dimensional structure of the ground surface in detail, including information such as the height, shape, and position of trees.

[0040] Among them, refinement parameters are involved. The refinement parameters refer to the parameters for optimizing or adjusting the initial area parameters, aiming to improve the accuracy and efficiency of data processing. For example, the parameters used to correct the DSM and DEM data obtained by satellites.

[0041] Through this step, in the target area, for the predetermined area where high-precision point cloud data has been obtained, the predetermined point cloud data corresponding to the predetermined area is used to determine the parameters for optimizing the initial area parameters. By determining these refinement parameters, the low-precision initial area parameters can be corrected more accurately, and the terrain data accuracy of the entire monitoring area can be improved.

[0042] Step S108: Refine the initial area parameters according to the refinement parameters to obtain the target area parameters.

[0043] In step S108 provided by the present application, the target area parameters are obtained.

[0044] Among them, target area parameters are involved. The target area parameters refer to the final set of area parameters after being adjusted and optimized by the refinement parameters, which are used to guide subsequent precise analysis or monitoring activities.

[0045] Through this step, the target area parameters are determined, providing more detailed information, fusing remote sensing data from different sources and with different precisions, realizing the complementary advantages of multi-source data, ensuring both the wide-area coverage of the data and improving the accuracy of local areas, enhancing the overall performance of the monitoring system, and at the same time reducing the overall monitoring and management costs.

[0046] Step S110: Determine the spatial relationship parameters between multiple obstacles and the transmission line respectively according to the target area parameters.

[0047] In step S110 provided by the present application, the spatial relationship parameters between multiple obstacles and the transmission line are determined respectively.

[0048] Among them, spatial relationship parameters are involved. The spatial relationship parameters refer to the measurement parameters of the mutual position and direction relationship between each obstacle and the transmission line in the target area.

[0049] Through this step, based on the target area parameters, the spatial relationship between the obstacles and the transmission line can be clarified, and the tree obstacle risk can be evaluated more precisely. It can be predicted which obstacles may pose a threat to the transmission line in the future, so as to take measures in advance to ensure the safe operation of the power system.

[0050] Step S112: Determine the risk levels of the multiple obstacles' impacts on the transmission line respectively according to the spatial relationship parameters corresponding to the multiple obstacles and the transmission line.

[0051] In step S112 provided in this application, determine the risk levels of the multiple obstacles' impacts on the transmission line respectively.

[0052] Among them, the risk level is involved. The risk level refers to the risk degree that the obstacle may pose to the transmission line, which is calculated through a certain evaluation model based on the spatial relationship parameters between the obstacle and the transmission line, combined with the physical characteristics of the obstacle (such as size, stability, growth rate, etc.) and environmental conditions (such as wind speed, humidity, etc.).

[0053] In this step, by analyzing the spatial relationship parameters of the obstacles, such as parameters like position, distance, height, tilt angle, etc., the potential risk degree of each obstacle to the transmission line is evaluated and classified into different risk levels. The determination of the risk level helps to optimize the warning system, ensure that an alarm is issued in time when a high-risk obstacle approaches the transmission line, and reduce the risk of power system failures.

[0054] Through the above steps S102 - S112, multiple regional images of the target area can be obtained. Among them, the multiple regional images include a transmission line and multiple obstacles, and the multiple obstacles are objects with a risk impact probability on the transmission line greater than a predetermined threshold. According to the multiple regional images, the initial regional parameters of the target area are determined. According to the initial regional parameters and the predetermined point cloud data corresponding to the predetermined area, refinement parameters are determined, where the predetermined area is the area in the target area with corresponding predetermined point cloud data. According to the refinement parameters, the initial regional parameters are refined to obtain the target area parameters. According to the target area parameters, the spatial relationship parameters corresponding to the multiple obstacles and the transmission line are determined respectively. According to the spatial relationship parameters corresponding to the multiple obstacles and the transmission line respectively, the risk levels of the multiple obstacles affecting the transmission line are determined. By determining the refinement parameters according to the initial regional parameters and the predetermined point cloud data corresponding to the predetermined area, the purpose of refining the initial regional parameters according to the refinement parameters to obtain the target area parameters is achieved. Since the point cloud data has high precision, using the high-precision point cloud data to determine the refinement parameters to refine the initial regional parameters can obtain target area parameters with high accuracy. Using the target area parameters to determine the spatial relationship parameters between the obstacles and the transmission line can improve the accuracy of the determined obstacle risk levels, thereby solving the technical problem in the related art that when determining the obstacle risk for a large-area area, the determined obstacle risk accuracy is low and it is difficult to meet the monitoring accuracy requirements.

[0055] As an optional embodiment, determining the refinement parameters according to the initial regional parameters and the predetermined point cloud data corresponding to the predetermined area includes: determining the regional parameters corresponding to the predetermined area in the initial regional parameters to obtain the first regional parameters; determining the predetermined regional parameters corresponding to the predetermined area according to the predetermined point cloud data; determining the first parameter difference between the predetermined regional parameters and the first regional parameters; and determining the refinement parameters according to the first parameter difference, the first regional parameters, and the initial regional parameters.

[0056] In this embodiment, the specific steps of determining the refinement parameters according to the initial regional parameters and the predetermined point cloud data corresponding to the predetermined area are described.

[0057] Among them, the first regional parameters are involved. The first regional parameters refer to the partial regional parameters selected from the initial regional parameters and corresponding to the predetermined area. It includes the terrain features of the predetermined area, but the data accuracy is low.

[0058] Among them, the predetermined regional parameters are involved. The predetermined regional parameters refer to the data extracted from the predetermined point cloud data and describing the terrain features in the predetermined area. They provide high-precision terrain information and can be used to correct the inaccuracies in the first regional parameters.

[0059] Among them, the first parameter difference is involved. The first parameter difference refers to the difference value between the predetermined area parameter and the first area parameter, which reflects the deviation degree between the low-precision satellite data and the high-precision UAV point cloud data when describing the same area.

[0060] In this step, first, determine the partial area parameter corresponding to the predetermined area in the initial area parameter, that is, the first area parameter, and this part of the data is used for the next correction. Then, extract the detailed terrain parameters of the predetermined area from the predetermined point cloud data, that is, the predetermined area parameter, and these parameters provide high-precision terrain information. Next, determine the difference between the predetermined area parameter and the first area parameter, that is, the first parameter difference, and this step helps to quantify the error of the satellite data. Finally, determine the refinement parameter according to the first parameter difference, the first area parameter and the initial area parameter, and these refinement parameters are used to improve the terrain data accuracy of the entire target area, that is, correct the initial area parameter. Through this step, by using the high-precision data of the limited predetermined area to determine the refinement parameter, the initial area parameter of the entire target area is corrected, while improving the accuracy of the initial area parameter, the overall cost of data collection and processing is greatly reduced.

[0061] As an optional embodiment, determine the refinement parameter according to the first parameter difference, the first area parameter and the initial area parameter, including: determine the initial area feature according to the initial area parameter; determine the predetermined area feature corresponding to the predetermined area according to the first area parameter; determine the refinement parameter according to the first parameter difference, the predetermined area feature and the initial area feature.

[0062] In this embodiment, the specific steps of determining the refinement parameter according to the first parameter difference, the first area parameter and the initial area parameter are described.

[0063] Among them, the initial area feature is involved. The initial area feature refers to the preliminary data extracted from the initial area parameter and used to describe the surface feature of the predetermined area, such as elevation, slope, aspect, terrain undulation degree, etc., and the accuracy is relatively low.

[0064] Among them, the predetermined area feature is involved. The predetermined area feature refers to the feature determined based on the first area parameter (i.e., UAV point cloud data).

[0065] In this step, first, initial region features are determined based on initial region parameters (low-precision satellite remote sensing data), and these features are preliminary descriptions of the surface features of the entire monitoring area. Next, predetermined region features are determined based on first region parameters (high-precision UAV point cloud data), that is, more precise feature analysis is performed on specific regions with detailed point cloud data. Finally, by comparing the first parameter difference (elevation error between point cloud data and satellite data) and the two region features, refinement parameters can be determined, and these parameters are used to optimize the processing of satellite remote sensing data, especially the correction of DSM and DEM data, to improve its accuracy and applicability.

[0066] As an optional embodiment, refinement parameters are determined based on the first parameter difference, predetermined region features, and initial region features, including: when both the initial region features and the predetermined region features include multiple ones, determining the influence indices between the multiple predetermined region features and the first parameter difference respectively; based on the multiple influence indices, determining a first target feature from the multiple predetermined region features, where the target influence index corresponding to the first target feature is greater than the target threshold; determining a target region feature corresponding to the first target feature among the multiple initial region features; and determining refinement parameters based on the target region feature, the first parameter difference, and the first target feature.

[0067] In this embodiment, the specific steps for determining refinement parameters based on the first parameter difference, predetermined region features, and initial region features are described.

[0068] Among them, the influence index is involved. The influence index refers to an index that quantifies the influence degree of the predetermined region feature on the first parameter difference. The higher the influence index, the greater the contribution of this feature to the error, which means that this feature needs to be considered more when correcting the error.

[0069] Among them, the first target feature is involved. The first target feature refers to the key feature selected from multiple predetermined region features, and its influence index exceeds the set target threshold, which is the key point for error correction and accuracy improvement.

[0070] Among them, the target influence index is involved. The target influence index refers to the influence index corresponding to the first target feature.

[0071] Among them, the target threshold is involved. The target threshold refers to the threshold set for determining the first target feature. When the influence index of a predetermined region feature is higher than the target threshold, it proves that the influence of this predetermined region feature on the first parameter difference is relatively high and can be determined as the first target feature.

[0072] Among them, the target region feature is involved. The target region feature refers to the feature corresponding to the first target feature among the multiple initial region features.

[0073] In this step, first, quantify the influence degree of the predetermined region features on the first parameter difference. By setting a target threshold, screen out the features that significantly contribute to the error as the first target features. Then, find the features corresponding to the first target features among the features of the entire target region, that is, the target region features. Since the first target features have been identified as features that significantly affect the error within the predetermined region, finding similar features in the entire target region and analyzing and correcting them key points can significantly improve the overall accuracy of DSM and DEM. Finally, based on the target region features, the first parameter difference, and the first target features, determine the optimal refinement parameters.

[0074] Through this step, by analyzing multiple region features, it is possible to more comprehensively consider the influence of factors such as terrain, vegetation, and meteorology on the accuracy of DSM and DEM, identify the features that significantly affect the error, and perform targeted error correction to improve the accuracy and reliability of risk assessment. At the same time, only focusing on the features with a greater impact on the error can effectively reduce the computational amount, improve the data processing efficiency, and reduce the cost of remote sensing analysis.

[0075] As an alternative embodiment, after determining the refinement parameters based on the first parameter difference, the first region parameters, and the initial region parameters, it further includes: determining the test point cloud data corresponding to the test region, where the test region is the region in the target region except for the predetermined region and there is corresponding test point cloud data; determining the region parameters corresponding to the test region in the initial region parameters to obtain the second region parameters; determining the test region parameters based on the second region parameters and the refinement parameters; determining the second parameter difference based on the test region parameters and the test point cloud data corresponding to the test region; in the case where the second parameter difference is greater than the error threshold, updating the refinement parameters to obtain the updated refinement parameters, so as to refine the initial region parameters based on the updated refinement parameters.

[0076] In this embodiment, the specific steps for updating the refinement parameters are described.

[0077] Among them, the test point cloud data is involved. The test point cloud data refers to the point cloud data of the region (i.e., the test region) in the target region except for the predetermined region where there is corresponding test point cloud data.

[0078] Among them, the second region parameters are involved. The second region parameters refer to the unoptimized region parameters determined by the initial region parameters in the test region.

[0079] Among them, the test region parameters are involved. The test region parameters refer to the region data obtained by optimizing the second region parameters of the test region based on the refinement parameters.

[0080] Among them, the second parameter difference is involved. The second parameter difference refers to the deviation between the test area parameter and the test point cloud data, which is used to evaluate the effectiveness of the refinement parameter in improving the accuracy of the initial area parameter.

[0081] Among them, the error threshold is involved. The error threshold refers to a set allowable error range, which is used to determine whether the optimized area parameter meets the expected accuracy standard.

[0082] Among them, the updated refinement parameter is involved. The updated refinement parameter refers to the optimized refinement parameter. The area parameter corrected according to the updated refinement parameter can meet the standard of risk level assessment.

[0083] In this step, first, by comparing the predetermined point cloud data and the first area parameter (preliminary processed satellite data), the first parameter difference and the preliminary refinement parameter are determined. Then, a test area that is not used by the predetermined point cloud data is selected within the target area, and the test point cloud data is compared with the test area parameter generated based on the second area parameter (satellite data of the test area) and the preliminary refinement parameter to obtain the second parameter difference. If the second parameter difference exceeds the predetermined error threshold, the refinement parameter needs to be corrected and optimized again until the updated refinement parameter that meets the accuracy requirements is obtained.

[0084] Through this step, by cyclically optimizing the refinement parameter, the accuracy of the parameters of the entire monitoring area can be continuously improved. For example, the accuracy of DSM and DEM data can be ensured to keep the optimized area data at a high precision, ensure the accurate expression of terrain features, be beneficial to subsequent risk assessment, and enhance the generalization ability of the model.

[0085] As an optional embodiment, according to the target area parameter, the spatial relationship parameters of multiple obstacles corresponding to the transmission line are determined, including: when the obstacle is a tree and the target area parameter includes the tree height, according to multiple area images, the spectral characteristics corresponding to the tree are determined; according to the spectral characteristics and the tree height, the tree type corresponding to the tree is determined; according to the tree type and the tree height, the spatial relationship parameters of multiple trees corresponding to the transmission line are determined.

[0086] In this embodiment, the specific steps of determining the spatial relationship parameters of multiple obstacles corresponding to the transmission line according to the target area parameter are described.

[0087] Among them, the spectral characteristics are involved. The spectral characteristics refer to the reflectivity or absorptivity performance of an object in different wavelength ranges. In remote sensing and image processing, by analyzing multi-spectral images, the spectral response characteristics of different types of vegetation or surface materials can be identified and distinguished.

[0088] In this step, first, by analyzing the multi-spectral image, the spectral characteristics of each tree in the target area are determined; then, combined with the tree height information, the tree types are identified because different tree species have different growth rates and toppling tendencies; finally, based on the tree type and height, the vertical distance, horizontal distance between each tree and the transmission line, and the toppling range of the tree are calculated to clarify the degree of safety impact of the tree on the transmission line.

[0089] As an optional embodiment, based on multiple regional images, initial regional parameters are determined, including: based on multiple regional images, multiple target regional images corresponding to multiple target objects are determined, where the multiple target objects include a transmission line and multiple obstacles, and the angular difference between the shooting angles corresponding to the multiple target regional images is greater than an angular threshold; based on the multiple target regional images and the shooting angles corresponding to the multiple target regional images respectively, coordinate parameters corresponding to the multiple target objects are determined; based on the multiple coordinate parameters, the initial regional parameters corresponding to the target area are determined.

[0090] In this embodiment, the specific steps of determining the initial regional parameters based on multiple regional images are described.

[0091] Among them, target regional images are involved. The target regional images refer to a set of images selected from multiple regional images and specifically for each target object (transmission line and obstacle). These images provide information on observing the target object from different perspectives, which helps to accurately identify and locate the object.

[0092] Among them, the angular difference is involved. The angular difference refers to the difference between the shooting angles corresponding to the multiple target regional images when shooting the same target object (transmission line and obstacle).

[0093] Among them, the angular threshold is involved. The angular threshold refers to a set angular value used to determine the target regional images, ensuring that the target object can be observed from sufficiently different angles to improve the three-dimensionality and information content of the data.

[0094] Among them, the shooting angle is involved. The shooting angle refers to the shooting angles corresponding to the multiple target regional images when shooting the same target object (transmission line and obstacle) respectively.

[0095] Among them, the coordinate parameters are involved. The coordinate parameters refer to the position information of the target object in the geographical space, such as longitude and latitude coordinates, elevation coordinates, three-dimensional coordinates, etc.

[0096] In this step, from multiple regional images captured from multiple angles and time points, the target regional images related to the transmission line and obstacles are determined to ensure that the target objects can be observed from multiple dimensions, improving the diversity and information content of the data. Next, by analyzing the target regional images and their corresponding shooting angles, the coordinate parameters (three-dimensional position information) of each target object are calculated. Finally, based on these coordinate parameters, the initial regional parameters of the target area are determined, that is, a preliminary description of the terrain features of the entire monitoring area. Through this step, based on the coordinate parameters, the three-dimensional positions of the target objects can be accurately calculated, providing a basis for subsequent data processing and analysis, which is crucial for evaluating the spatial relationship between the obstacles and the transmission line and helps to quantify the risk assessment parameters.

[0097] Based on the above embodiments and alternative embodiments, an alternative implementation manner is provided, which is specifically described below.

[0098] In the related art, a three-dimensional modeling and tree obstacle analysis of transmission lines are carried out by using the lidar (LiDAR) technology carried by an unmanned aerial vehicle. This method can realize echo ranging and orientation through lasers, obtain information such as the position and radial velocity of the target object, and realize the monitoring of tree obstacle risks. However, the cost of the lidar (LiDAR) technology carried by an unmanned aerial vehicle is relatively high, and it is difficult to be applied to the tree obstacle monitoring of large-area transmission channels. Although satellite remote sensing technology can achieve large-scale coverage in extracting DSM and DEM, limited by its resolution and sensor characteristics, the accuracy of the obtained data is relatively low, with large errors, and it cannot meet the tree obstacle monitoring accuracy.

[0099] In view of this, an alternative implementation manner of the present invention provides a dynamic monitoring and early warning method for tree obstacle risks of overhead transmission lines based on multi-source remote sensing data fusion. Figure 2 It is a flowchart of a method for determining tree obstacle risks of an overhead transmission line provided by an alternative implementation manner of the present invention. As Figure 2 shown, high-resolution optical satellite remote sensing stereo pair data and unmanned aerial vehicle point cloud data are acquired and data preprocessing is performed; based on the preprocessed point cloud data, locally high-precision DSM and DEM data of the monitoring area are obtained, and based on the preprocessed stereo pair, relatively low-precision DSM and DEM data of the entire monitoring area are obtained. The random forest algorithm is used to perform adjustment and correction of the latter by the former to obtain high-precision and large-scale DSM and DEM data of the entire monitoring area; by performing differential calculation on the corrected DSM and DEM data, the height of the trees is calculated. Combining multi-spectral images can effectively identify the tree species and their distribution ranges, and at the same time obtain the horizontal and vertical distances between the tree tops and the overhead transmission lines and the disturbance range after the trees fall; finally, based on the time-series satellite data, the dynamic monitoring and early warning of the tree obstacle risks of the overhead transmission lines can be realized.

[0100] The steps of the dynamic monitoring and early warning method for tree obstacle risks of overhead transmission lines based on multi-source remote sensing data fusion provided by the optional implementation manner of the present invention are specifically introduced below.

[0101] S1. Obtain multiple regional images of the target area.

[0102] Obtain high-resolution optical satellite remote sensing stereo pair data (same as the above regional images) and UAV point cloud data (same as the above predetermined point cloud data), and perform data preprocessing.

[0103] The preprocessing of satellite stereo pair data includes steps such as geometric correction, radiometric correction, atmospheric correction, image mosaicking and cropping, and the preprocessing of UAV point cloud data includes steps such as data screening, filtering, coordinate transformation, accuracy inspection, denoising, color assignment and feature extraction.

[0104] S2. Determine the initial regional parameters of the target area according to the multiple regional images.

[0105] Based on the preprocessed stereo pair, obtain lower-precision DSM and DEM data of the entire monitoring area (same as the above initial regional parameters). Use the stereo matching algorithm to automatically or semi-automatically match corresponding points on the stereo pair, obtain the three-dimensional coordinates of ground points (same as the above coordinate parameters), screen and optimize these coordinates, remove outliers and points with large errors, generate DSM according to the three-dimensional coordinates, and then separate the ground points from the DSM through the ground point extraction algorithm to generate DEM.

[0106] S3. Determine the refinement parameters according to the initial regional parameters and the predetermined point cloud data corresponding to the predetermined area.

[0107] First, extract high-precision DSM and DEM from the UAV point cloud data (same as the above predetermined regional parameters), and obtain local high-precision DSM and DEM data of the monitoring area (same as the above predetermined area) based on the preprocessed point cloud data. The multi-angle images taken by the camera carried by the UAV can be used to generate point cloud data. Through the preprocessed UAV point cloud data, through the multi-view stereo matching technology, the three-dimensional coordinates of each pixel point can be extracted from these images, and then high-precision DSM and DEM can be constructed. These data have the characteristics of high density and high resolution.

[0108] Then, using these high-precision DSMs and DEMs as control data, compare and analyze them with the DSMs and DEMs obtained from satellite stereo image pairs. Through the random forest algorithm, establish a relationship model between the elevation errors of satellite data and influencing factors such as terrain factors. Using this model, the elevation errors in satellite data can be predicted and corrected (same as the above refinement parameters), thereby improving its accuracy. Due to its good applicability and robustness, the random forest algorithm can effectively handle this complex regression problem and provide relatively accurate correction results. Finally, the satellite DSM and DEM data after adjustment and correction will have higher accuracy and reliability and be suitable for large-scale topographic mapping and monitoring.

[0109] Specifically, the random forest model construction method is as follows:

[0110] Calculate the slope, aspect, terrain undulation degree, slope change rate, and aspect change rate (same as the above regional characteristics) within the monitoring area.

[0111] Among them, the slope formula is:

[0112]

[0113] The aspect formula is:

[0114]

[0115] The slope rate formula is:

[0116]

[0117] The aspect rate formula is:

[0118]

[0119] Among them, Z is the elevation, X and Y are the spatial coordinates in the east-west and north-south directions respectively, and represents the elevation change rate along the grid; Z i is the elevation value of adjacent pixels in the city, is the average value of the elevation; n is the number of pixels; θ i is the slope value of the surrounding pixels, is the average slope value.

[0120] For the DEM data obtained from the stereo image pair data within a certain area, if the average value of the elevation difference between it and the reference DEM to be processed, that is, the DEM data extracted from the UAV point cloud, is μ and the standard deviation is σ, then according to the 3σ criterion, the elevation error (d) distribution probability (P) should satisfy the following formula:

[0121] P(μ - 3σ ≤ d ≤ μ + 3σ) ≈ 0.9973

[0122] Therefore, elevation points in the stereo image pair data with elevation errors outside the range of [μ - 3σ, μ + 3σ] are removed as gross errors.

[0123] Extract the longitude and latitude coordinates, slope, aspect, slope rate, aspect rate, DSM, and DEM data corresponding to the filtered stereo image pair data and read them into a table as the geospatial features of the dataset. Then, extract the DSM and DEM values of the UAV point cloud data at the corresponding positions. Next, use the DSM and DEM values of the UAV point cloud data as control points, calculate the elevation error values between the DSM and DEM values obtained from the stereo image pair data and the DSM and DEM values corresponding to the control points as the target variables, and construct a table dataset indexed by the longitude and latitude coordinates of the control points, where each row in the table represents a sample point.

[0124] S4. Refine the initial area parameters according to the refinement parameters to obtain the target area parameters.

[0125] Based on the preprocessed point cloud data, obtain the local high-precision DSM and DEM data of the monitoring area. Based on the preprocessed stereo image pair, obtain the lower-precision DSM and DEM data of the entire monitoring area. Use the random forest algorithm to perform adjustment and correction of the latter with the former to obtain the high-precision and large-scale DSM and DEM data of the entire monitoring area.

[0126] Taking the regression random forest classification algorithm as the framework, perform parameter optimization. Combining longitude and latitude coordinates, slope, aspect, slope rate, and aspect rate, select the optimal parameters, calculate the importance of the optimal parameters, select 70% of the features as the training set and 30% as the test set. After training the model, perform adjustment of the DSM and DEM in the monitoring area to obtain the high-precision and large-scale DSM and DEM data.

[0127] S5. Determine the spatial relationship parameters between multiple obstacles and the corresponding transmission lines according to the target area parameters.

[0128] By performing differential calculation on the corrected DSM and DEM data, calculate the height of the trees. Combining with the multispectral image, the tree species and range distribution can be effectively identified, and at the same time, the horizontal and vertical distances between the tree tops and the overhead transmission lines and the disturbance range after the trees fall can be obtained.

[0129] By analyzing multi-spectral images, the reflectance characteristics of trees in different spectral bands are extracted. The tree height information in the DSM data is combined with the spectral characteristics of the multi-spectral images. Machine learning algorithms such as support vector machines (SVM) or random forests are used to learn the spectral and height characteristics of different tree species and identify them accordingly. Finally, by comparing the actual height of the trees with the spectral characteristics in the multi-spectral images, different tree species and their range distributions can be accurately identified and classified.

[0130] S6. According to the spatial relationship parameters corresponding to the transmission line for each of the multiple obstacles, determine the risk levels of the impacts of the multiple obstacles on the transmission line respectively.

[0131] Finally, based on the time-series satellite data, dynamic monitoring and early warning of the tree obstacle risks for overhead transmission lines are realized.

[0132] Based on the aforementioned extracted tree height information, if the tree height is greater than the vertical safety distance, it is considered that there is a potential safety hazard in this area; if the tree height is less than the vertical safety distance, it is considered that this area is safe. Based on the aforementioned extracted tree range distribution, the nearest horizontal distance between the overhead transmission line and the tree is calculated using neighborhood analysis. Based on the minimum horizontal safety distance specification for overhead transmission line tree obstacles, it is determined whether the tree is outside the minimum horizontal safety distance range. Based on the aforementioned extracted tree height information, the influence range of vegetation toppling is calculated. The influence range of tree toppling is a circular area with the intersection of the tree trunk and the ground as the center and the tree height as the radius. Similarly, neighborhood analysis is used to calculate the nearest distance between the overhead transmission line and the circle, and it is determined whether the tree is outside the minimum horizontal safety distance range after toppling.

[0133] Through the above optional implementation manners, at least the following beneficial effects can be achieved:

[0134] (1) It can combine satellite remote sensing and UAV point cloud technology, correct the DSM and DEM obtained from satellite data through a machine learning model, calculate the tree height and the range of toppling disturbance, and combine multi-spectral images to identify the crown range, realizing dynamic early warning of tree obstacles;

[0135] (2) This method improves the accuracy and efficiency of tree obstacle monitoring, reduces costs, and has important value for the safe operation of the power system.

[0136] 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 the present invention is not limited by the described action sequence, because according to the present invention, 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 the present invention.

[0137] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0138] Embodiment 2

[0139] According to an embodiment of the present invention, there is also provided a device for implementing the method for determining the obstacle risk level described above. Figure 3 It is a structural block diagram of the device for determining the obstacle risk level according to an embodiment of the present invention, as Figure 3 shown. The device includes: an acquisition module 302, a first determination module 304, a second determination module 306, a refinement module 308, a third determination module 310, and a fourth determination module 312. The device will be described in detail below.

[0140] The acquisition module 302 is configured to acquire multiple regional images of a target area. Among them, the multiple regional images include a power transmission line and multiple obstacles, and the multiple obstacles are objects whose risk impact probability on the power transmission line is greater than a predetermined threshold. The first determination module 304 is connected to the above acquisition module 302 and is configured to determine an initial regional parameter of the target area based on the multiple regional images. The second determination module 306 is connected to the above first determination module 304 and is configured to determine a refinement parameter based on the initial regional parameter and predetermined point cloud data corresponding to a predetermined area, where the predetermined area is an area in the target area where there is corresponding predetermined point cloud data. The refinement module 308 is connected to the above second determination module 306 and is configured to refine the initial regional parameter based on the refinement parameter to obtain a target area parameter. The third determination module 310 is connected to the above refinement module 308 and is configured to determine spatial relationship parameters corresponding to the power transmission line for each of the multiple obstacles based on the target area parameter. The fourth determination module 312 is connected to the above third determination module 310 and is configured to determine the risk level of the impact on the power transmission line for each of the multiple obstacles based on the spatial relationship parameters corresponding to the power transmission line for each of the multiple obstacles.

[0141] It should be noted here that the above-mentioned acquisition module 302, the first determination module 304, the second determination module 306, the refinement module 308, the third determination module 310, and the fourth determination module 312 correspond to steps S102 to S112 in the method for determining the obstacle risk level. The instances and application scenarios implemented by the multiple modules and the corresponding steps are the same, but are not limited to the content disclosed in the above-mentioned Embodiment 1.

[0142] Embodiment 3

[0143] According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including: a processor; a memory for storing processor-executable instructions, wherein the processor is configured to execute the instructions to implement the method for determining the obstacle risk level according to any one of the above.

[0144] Embodiment 4

[0145] According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device can execute the method for determining the obstacle risk level according to any one of the above.

[0146] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.

[0147] In the above embodiments of the present invention, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0148] In the several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units can be 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 couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the units or modules can be in an electrical or other form.

[0149] 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 distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0150] In addition, in each embodiment of the present invention, the functional units may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0151] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0152] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for determining the risk level of an obstacle, characterized in that, Including: Obtaining a plurality of regional images of a target area, where the plurality of regional images include a transmission line and a plurality of obstacles, and the plurality of obstacles are objects with a risk impact probability on the transmission line greater than a predetermined threshold; Determining initial regional parameters of the target area according to the plurality of regional images; Determining refinement parameters according to the initial regional parameters and predetermined point cloud data corresponding to a predetermined area, where the predetermined area is an area in the target area with corresponding predetermined point cloud data; Refining the initial regional parameters according to the refinement parameters to obtain target regional parameters; Determining spatial relationship parameters corresponding to the plurality of obstacles and the transmission line respectively according to the target regional parameters; Determining risk levels of the plurality of obstacles affecting the transmission line respectively according to the spatial relationship parameters corresponding to the plurality of obstacles and the transmission line respectively.

2. The method according to claim 1, characterized in that, The determining the refinement parameters according to the initial regional parameters and the predetermined point cloud data corresponding to the predetermined area includes: Determining regional parameters corresponding to the predetermined area in the initial regional parameters to obtain first regional parameters; Determining predetermined area parameters corresponding to the predetermined area according to the predetermined point cloud data; Determining a first parameter difference between the predetermined area parameters and the first regional parameters; Determining the refinement parameters according to the first parameter difference, the first regional parameters and the initial regional parameters.

3. The method according to claim 2, wherein The determining the refinement parameters according to the first parameter difference, the first regional parameters and the initial regional parameters includes: Determining initial regional features according to the initial regional parameters; Determining predetermined area features corresponding to the predetermined area according to the first regional parameters; Determining the refinement parameters according to the first parameter difference, the predetermined area features and the initial regional features.

4. The method according to claim 3, wherein The determining the refinement parameters according to the first parameter difference, the predetermined area features and the initial regional features includes: When both the initial regional features and the predetermined area features include a plurality, determining influence indices between the plurality of predetermined area features and the first parameter difference respectively; Determining a first target feature from the plurality of predetermined area features according to the plurality of influence indices, where the target influence index corresponding to the first target feature is greater than a target threshold; Determining a target regional feature corresponding to the first target feature from the plurality of initial regional features; Determining the refinement parameters according to the target regional feature, the first parameter difference and the first target feature.

5. The method according to claim 2, characterized in that, After the determining the refinement parameters according to the first parameter difference, the first regional parameters and the initial regional parameters, it further includes: Determining test point cloud data corresponding to a test area, where the test area is an area in the target area, except the predetermined area, with corresponding test point cloud data; Determining regional parameters corresponding to the test area in the initial regional parameters to obtain second regional parameters; Determining test area parameters according to the second regional parameters and the refinement parameters. Determine a second parameter difference based on the test area parameters and the test point cloud data corresponding to the test area; When the second parameter difference is greater than an error threshold, update the refinement parameter to obtain an updated refinement parameter, and refine the initial area parameter according to the updated refinement parameter.

6. The method according to claim 1, wherein The determining, according to the target area parameter, the spatial relationship parameters of the multiple obstacles corresponding to the transmission line respectively includes: When the obstacle is a tree and the target area parameter includes the tree height, determine the spectral characteristics corresponding to the tree according to the multiple area images; Determine the tree type corresponding to the tree according to the spectral characteristics and the tree height; Determine the spatial relationship parameters of the multiple trees corresponding to the transmission line respectively according to the tree type and the tree height.

7. The method according to claim 1, wherein The determining the initial area parameter according to the multiple area images includes: Determine multiple target area images respectively corresponding to multiple target objects according to the multiple area images, where the multiple target objects include the transmission line and the multiple obstacles, and the angle difference between the shooting angles corresponding to the multiple target area images is greater than an angle threshold; Determine the coordinate parameters corresponding to the multiple target objects respectively according to the multiple target area images and the shooting angles corresponding to the multiple target area images; Determine the initial area parameter corresponding to the target area according to the multiple coordinate parameters.

8. A device for determining the risk level of an obstacle, characterized in that, including: An acquisition module, configured to acquire multiple area images of a target area, where the multiple area images include a transmission line and multiple obstacles, and the multiple obstacles are objects with a risk impact probability on the transmission line greater than a predetermined threshold; A first determination module, configured to determine the initial area parameter of the target area according to the multiple area images; A second determination module, configured to determine a refinement parameter according to the initial area parameter and the predetermined point cloud data corresponding to a predetermined area, where the predetermined area is an area in the target area where there is corresponding predetermined point cloud data; A refinement module, configured to refine the initial area parameter according to the refinement parameter to obtain a target area parameter; A third determination module, configured to determine the spatial relationship parameters of the multiple obstacles corresponding to the transmission line respectively according to the target area parameter; A fourth determination module, configured to determine the risk levels of the multiple obstacles affecting the transmission line respectively according to the spatial relationship parameters of the multiple obstacles corresponding to the transmission line respectively.

9. An electronic device, characterized in that, including: A processor; A memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the method for determining the risk level of an obstacle according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device can execute the method for determining the risk level of an obstacle according to any one of claims 1 to 7.

Images