A method, equipment and medium for identifying hidden dangers in power transmission line protection zones

Abstract

This application discloses a method, device, and medium for identifying potential hazards in a transmission line protection zone. The method involves using a monitoring device mounted on a transmission line tower to capture images of the transmission line; inputting these images into a tower detection network model to obtain corresponding bounding boxes; performing edge detection on the transmission line images to identify multiple conductor trajectories; determining the coordinates of the conductor endpoints of the two outermost conductor trajectories based on their coordinates; determining the projections of the conductor endpoints based on their coordinates, the lower edge of the tower bounding boxes, and the lower edge of the transmission line image; and identifying the protection zone corresponding to the transmission line based on these projections; and issuing a hazard alarm when the area of ​​the hazard zone within the protection zone exceeds a preset area value.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, equipment and medium for identifying potential hazards in power transmission line protection zones. Background Technology

[0002] In power transmission scenarios, high-voltage lines are typically used. If construction machinery or other potentially hazardous materials enter the area and come into contact with the power lines, it could cause unpredictable disasters. Therefore, to ensure the stable operation of power transmission lines, it is necessary to identify and warn of potential hazards in advance.

[0003] In existing technologies, it is usually necessary to manually mark the protection zone corresponding to the transmission line and install sensing and detection devices within the protection zone. These devices are used to identify and issue warnings for potentially hazardous equipment such as construction machinery entering the protection zone. Therefore, existing technologies require the installation of a large amount of hardware on-site, resulting in high costs for identifying potential hazards in the transmission line protection zone. Summary of the Invention

[0004] This application provides a method, equipment, and medium for identifying potential hazards in transmission line protection zones, which addresses the following technical problem: existing technologies for identifying potential hazards in transmission line protection zones are costly.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] This application provides a method for identifying potential hazards in a transmission line protection zone. The method includes: capturing images of the transmission line using monitoring devices installed on transmission line towers; inputting the transmission line image into a tower detection network model to annotate the towers in the image with bounding boxes; performing edge detection on the transmission line image to identify multiple conductor trajectories; determining the coordinates of the endpoints of the two outermost conductor trajectories based on their coordinates; determining the projections of the conductor endpoints based on their coordinates, the lower edge of the tower bounding boxes, and the lower edge of the transmission line image, and identifying the corresponding protection zone based on these projections; and identifying potential hazard areas in the transmission line image, issuing a hazard alarm if the area of ​​the potential hazard within the protection zone exceeds a preset area value.

[0007] This embodiment of the application automatically identifies the towers corresponding to the transmission line by inputting images of the transmission line into the tower detection model. Based on the identified tower bounding boxes and the captured images of the transmission line, it automatically identifies the corresponding protection zone. This avoids the tedious process of manually marking the protection zone of the transmission line. Secondly, this embodiment identifies potential hazards near the protection zone and compares the area of ​​the identified hazard area with the area of ​​the protection zone to automatically determine whether the hazard area affects the transmission line, thereby improving the accuracy of hazard alarms and reducing false alarm rates. Furthermore, this embodiment eliminates the need to install hazard detection equipment near the transmission line, thus reducing both equipment costs and maintenance costs.

[0008] In one implementation of this application, the projection corresponding to the conductor endpoint is determined based on the conductor endpoint, the lower edge of the tower annotation frame, and the lower edge of the transmission line image, and the protection zone corresponding to the transmission line is determined based on the projection. Specifically, this includes: determining the coordinates of the first endpoint and the second endpoint corresponding to the two outermost conductor trajectories based on the pixel coordinates corresponding to the conductor trajectory in the transmission line image; wherein the first endpoint is the conductor endpoint closer to the tower, and the second endpoint is the conductor endpoint farther from the tower; determining the first projection based on the first endpoint coordinates corresponding to the two outermost trajectories on both sides and the lower edge of the tower annotation frame; determining the second projection based on the second endpoint coordinates corresponding to the two outermost trajectories on both sides and the lower edge of the transmission line image; and determining the protection zone corresponding to the transmission line based on the first projection and the second projection.

[0009] In one implementation of this application, the protection zone corresponding to the transmission line is determined based on the first projection and the second projection. Specifically, this includes: determining the coordinates of the third endpoints corresponding to the two outermost trajectories on both sides based on the lower edge of the first projection; determining the coordinates of the fourth endpoints corresponding to the two outermost trajectories on both sides based on the lower edge of the second projection; connecting any adjacent first endpoint, second endpoint, third endpoint, and fourth endpoint to determine the reference protection zone corresponding to the transmission line; and extending the reference protection zone to the left and right sides to obtain the protection zone corresponding to the transmission line. The extended area is related to the area of ​​the reference protection zone corresponding to the transmission line.

[0010] In one implementation of this application, edge detection is performed on a power transmission line image to determine the trajectories of multiple conductors in the image. Specifically, this includes: converting the power transmission line image to grayscale; performing histogram equalization on the grayscale-converted image; performing edge detection on the histogram-equalized image to obtain a first reference conductor region; filtering the first reference edge region based on dilation and erosion algorithms to obtain a second reference edge region corresponding to the power transmission line image; determining the sine curves corresponding to the pixels in the second reference edge region using the Hough transform algorithm; determining the set of pixels corresponding to the power transmission line by the number of sine curves intersecting at the same point; and determining the trajectories of multiple conductors in the power transmission line image based on the set of pixels corresponding to the power transmission line.

[0011] In one implementation of this application, edge detection processing is performed on the transmission line image after histogram equalization to obtain a first reference conductor region. Specifically, this includes: denoising the transmission line image after histogram equalization according to a median filtering algorithm; calculating pixel value gradients in the denoised transmission line image and filtering out pixels based on a non-maximum suppression algorithm to obtain a third reference edge region of the transmission line image; and filtering the third reference edge based on a dual threshold algorithm to remove pixels with grayscale changes less than a preset low threshold to obtain the first reference conductor region.

[0012] In one implementation of this application, based on the coordinates of multiple conductor trajectories, the coordinates of the endpoints of the two outermost conductor trajectories on both sides are determined. Specifically, this includes: determining the set of pixel coordinates corresponding to each of the multiple conductor trajectories; comparing the horizontal coordinates of the multiple pixel coordinate sets to determine the first reference pixel coordinate set corresponding to the leftmost conductor trajectory and the second reference pixel coordinate set corresponding to the rightmost conductor trajectory; comparing the vertical coordinates of the pixels in the first reference pixel coordinate set to determine the endpoint coordinates of the leftmost conductor trajectory and comparing the vertical coordinates of the pixels in the second reference pixel coordinate set to determine the endpoint coordinates of the rightmost conductor trajectory.

[0013] In one implementation of this application, before inputting the transmission line image into a pre-set tower detection network model to annotate the towers in the transmission line image with bounding boxes, the method further includes: constructing a neural network model; wherein the neural network model consists of a feature extraction backbone network, a feature image pyramid network, and a transmission line tower classification and localization network; inputting the transmission line tower dataset with marked towers into the neural network model, and extracting feature images from the transmission line tower dataset with marked towers through the feature extraction backbone network; performing top-down feature magnification processing on the feature images through the feature image pyramid network based on upsampling to obtain the tower feature image pyramid corresponding to the transmission line tower dataset with marked towers; distinguishing between tower regions and background regions in the tower image pyramid and locating bounding boxes for the tower regions in the tower feature image pyramid through the tower classification and localization network; calculating the foreground score and offset of the annotated tower regions through the tower classification and localization network; and completing the training of the tower detection network model when both the foreground score and offset meet the accuracy conditions of the pre-set model.

[0014] In one implementation of this application, a hazard area identification is performed on a transmission line image. If the area of ​​the hazard area within the protected zone exceeds a preset area value, a hazard alarm is issued. Specifically, this includes: identifying hazards in the transmission line image using a pre-set hazard identification network model and marking the identified hazard areas with hazard bounding boxes; determining the area of ​​the hazard area based on the pixel coordinates of the hazard bounding boxes; determining the area of ​​the overlapping area between the hazard area and the protected zone based on the pixel coordinates of the hazard bounding boxes and the pixel coordinates of the protected zone; calculating the ratio between the area of ​​the overlapping area and the area of ​​the hazard area; and issuing a hazard warning if the ratio exceeds a preset ratio threshold.

[0015] This application provides a power transmission line protection zone hazard identification device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to: capture images of the power transmission line using a monitoring device installed on the power transmission line towers to obtain images of the power transmission line; input the images of the power transmission line into a tower detection network model to annotate the towers in the images with bounding boxes; perform edge detection on the images of the power transmission line to determine multiple conductor trajectories in the images of the power transmission line; based on the coordinates of the multiple conductor trajectories, determine the coordinates of the conductor endpoints corresponding to the two outermost conductor trajectories on both sides; based on the conductor endpoint coordinates, the lower edge of the tower bounding box, and the lower edge of the images of the power transmission line, determine the projection corresponding to the conductor endpoints, and determine the protection zone corresponding to the power transmission line based on the projection; and identify hazard areas in the images of the power transmission line, issuing a hazard alarm when the area of ​​the hazard area within the protection zone is greater than a preset area value.

[0016] This application provides a non-volatile computer storage medium storing computer-executable instructions. These instructions are configured to: capture images of the power transmission line using a monitoring device mounted on a transmission line tower; input the transmission line image into a tower detection network model to annotate the towers in the image with bounding boxes; perform edge detection on the transmission line image to identify multiple conductor trajectories; based on the coordinates of the conductor trajectories, determine the coordinates of the conductor endpoints corresponding to the two outermost conductor trajectories on both sides; based on the conductor endpoint coordinates, the lower edge of the tower bounding box, and the lower edge of the transmission line image, determine the projection corresponding to the conductor endpoints, and determine the corresponding protection zone of the transmission line based on the projection; identify potential hazard areas in the transmission line image, and issue a hazard alarm if the area of ​​the potential hazard within the protection zone is greater than a preset area value.

[0017] The above-mentioned technical solutions adopted in this application embodiment can achieve the following beneficial effects: This application embodiment, by inputting transmission line images into the tower detection model, can automatically identify the towers corresponding to the transmission line, and thus automatically identify the protection zone corresponding to the transmission line based on the identified tower marking frames and the captured transmission line images. This avoids the tedious process of manually marking the transmission line protection zone. Secondly, this application embodiment identifies potential hazards near the protection zone and compares the area of ​​the identified hazard area with the area of ​​the protection zone, thereby automatically identifying whether the hazard area affects the transmission line, thus improving the accuracy of hazard alarms and reducing false alarm rates. Simultaneously, this application embodiment eliminates the need to install hazard detection equipment near the transmission line, thereby reducing both equipment costs and equipment maintenance costs. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0019] Figure 1 A flowchart illustrating a method for identifying potential hazards in a power transmission line protection zone, as provided in this application embodiment;

[0020] Figure 2 This application provides a schematic diagram of a power transmission line image as an embodiment of the present application.

[0021] Figure 3 This is a schematic diagram of the structure of a hazard identification device for a power transmission line protection zone provided in an embodiment of this application. Detailed Implementation

[0022] This application provides a method, equipment, and medium for identifying potential hazards in power transmission line protection zones.

[0023] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0024] In power transmission scenarios, high-voltage lines are typically used. If construction machinery or other potentially hazardous materials enter the area and come into contact with the power lines, it could cause unpredictable disasters. Therefore, to ensure the stable operation of power transmission lines, it is necessary to identify and warn of potential hazards in advance.

[0025] In existing technologies, it is usually necessary to manually mark the protection zone corresponding to the transmission line and install sensing and detection devices within the protection zone. These devices are used to identify and issue warnings for potentially hazardous equipment such as construction machinery entering the protection zone. Therefore, existing technologies require the installation of a large amount of hardware on-site, resulting in high costs for identifying potential hazards in transmission line protection zones.

[0026] To address the aforementioned issues, this application provides a method, device, and medium for identifying potential hazards in transmission line protection zones. By inputting images of the transmission line into a tower detection model, the corresponding towers can be automatically identified. Based on the identified tower bounding boxes and the captured images of the transmission line, the corresponding protection zone can be automatically identified, thus avoiding the tedious process of manually marking transmission line protection zones. Secondly, this application identifies potential hazards near the protection zone and compares the area of ​​the identified hazard area with the area of ​​the protection zone to automatically determine whether the hazard area affects the transmission line, thereby improving the accuracy of hazard alarms and reducing false alarm rates. Furthermore, this application eliminates the need to install hazard detection equipment near the transmission line, thus reducing both equipment costs and maintenance costs.

[0027] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0028] Figure 1 This is a flowchart illustrating a method for identifying potential hazards in a power transmission line protection zone, as provided in an embodiment of this application. Figure 1 As shown, the method for identifying potential hazards in transmission line protection zones includes the following steps:

[0029] S101. The transmission line is photographed by a monitoring device installed on the transmission line tower to obtain an image of the transmission line.

[0030] In one embodiment of this application, the monitoring device is mounted on a power pole with its lens facing the opposite pole. The power transmission line monitoring device can capture images of the power transmission line in real time or at regular intervals, obtaining images of the power transmission line, and then upload these images to a server.

[0031] Furthermore, the monitoring device captures a protected corridor zone within the transmission line scene. This protected corridor zone is defined as the area between two parallel lines extending outwards from the conductor's edge. Transmission lines are typically high-voltage lines; if construction machinery or other safety hazards enter this zone and collide with the transmission lines, it could cause unpredictable disasters.

[0032] Figure 2 This is a schematic diagram of a power transmission line provided as an embodiment of this application. Figure 2 As shown, the monitoring device installed on the tower will take pictures along the direction of the power transmission line, and the image will show multiple power transmission lines.

[0033] S102. Input the transmission line image into the tower detection network model to annotate the towers in the transmission line image with annotation boxes.

[0034] In one embodiment of this application, a neural network model is constructed, comprising a feature extraction backbone network, a feature image pyramid network, and a transmission line tower classification and localization network. The transmission line tower dataset with marked towers is input into the neural network model. The feature extraction backbone network extracts feature images from the dataset. The feature image pyramid network performs top-down feature amplification processing on the feature images using an upsampling method to obtain the tower feature image pyramid corresponding to the dataset of marked transmission line towers. The tower classification and localization network distinguishes between tower regions and background regions within the tower image pyramid and locates bounding boxes for the tower regions in the feature image pyramid. The tower classification and localization network calculates foreground scores and offsets for the labeled tower regions. The tower detection network model is trained when both the foreground score and offset meet the preset model accuracy conditions.

[0035] Specifically, the transmission line tower detection model involved in this application embodiment is a deep learning model of convolutional neural network, and the training of the model requires a certain amount of labeled data. Therefore, this application embodiment pre-constructs a dataset with labeled transmission line towers. For each tower, the minimum bounding rectangle of the tower is labeled for training the deep learning model.

[0036] Furthermore, the convolutional neural network model involved in this application embodiment has two branches: a classification branch and a bounding box regression branch. The input to the model is a color image. The classification branch is used to distinguish the foreground and background of the image, while the bounding box regression branch accurately locates the position of the tower. Since the towers are relatively obvious in this task, and the detection task is relatively simple, a lightweight detection model is selected in this paper to save inference time. During the model training phase, the tower detection model is trained using a pre-constructed dataset with tower markings under transmission lines.

[0037] Specifically, the model consists of three parts: a feature extraction backbone network based on residual modules, a feature image pyramid network that enhances feature information through path aggregation, and a transmission line tower classification and localization network.

[0038] Specifically, the feature extraction backbone network mainly consists of residual modules. These residual modules are composed of residual branches and identity branches. The residual branches primarily consist of convolutional layers, batch normalization layers, and activation layers. The convolutional layers extract feature maps through convolutional operations, the batch normalization layers normalize the convolutional outputs to stabilize model training, and the activation layers activate some features while suppressing less important ones. Furthermore, the residual module contains an identity branch, which directly passes the original input to the module's output. The output of the residual branch is then added to the result of the identity branch to obtain the residual module's output. This design significantly alleviates the gradient vanishing problem caused by excessively deep models. The feature extraction backbone network also uses pooling layers to reduce the size of feature maps and aggregate features, thus reducing computational cost and expanding the receptive field.

[0039] Specifically, the feature image pyramid network performs top-down feature amplification processing on the feature image based on upsampling. This top-down process amplifies the small feature maps at the top level to the features of the previous stage through upsampling. Figure 1 The size of the sample is important. This approach leverages both the strong semantic features of the top layer and the high-resolution information of the bottom layer. Upsampling can be implemented using nearest neighbor interpolation. To combine high-level semantic features with the precise localization capabilities of the bottom layer, lateral connections fuse features from the previous layer that have been upsampled and have the same resolution as the current layer through addition, similar to the lateral connection structure of a residual network. Considering the significant loss of feature information during the top-down process, the feature pyramid network used in this embodiment adds a bottom-up process and lateral connections to the traditional feature pyramid network. This significantly improves the network's performance.

[0040] In this neural network, a pole classification and localization network is used to distinguish and classify poles from the background, and to locate the pole detection boxes. The network outputs the scores of the obtained pole detection boxes and the offsets relative to pre-defined anchor boxes. The pole detection network model is trained when both the foreground score and the offset meet the preset model accuracy conditions.

[0041] S103. Perform edge detection on the transmission line image to determine the trajectories of multiple conductors in the transmission line image.

[0042] In one embodiment of this application, a transmission line image is converted to grayscale. The grayscale image is then subjected to histogram equalization. Edge detection is performed on the histogram-equalized image to obtain a first reference conductor region. Based on dilation and erosion algorithms, the first reference edge region is filtered to obtain a second reference edge region corresponding to the transmission line image. Using the Hough transform algorithm, the sine curves corresponding to the pixels in the second reference edge region are determined. The set of pixels corresponding to the transmission line is determined by the number of sine curves intersecting at the same point, and multiple conductor trajectories in the transmission line image are determined based on this set of pixels.

[0043] Specifically, the transmission line image after histogram equalization is denoised using a median filtering algorithm. Pixel gradients are then calculated on the denoised image, and pixels are filtered out using a non-maximum suppression algorithm to obtain the third reference edge region. A dual-threshold algorithm is then used to filter the third reference edge region, removing pixels with grayscale changes less than a preset low threshold to obtain the first reference conductor region.

[0044] Furthermore, in order to improve the detection speed when performing edge detection on transmission line images, this embodiment abandons the slow convolutional neural network-based conductor trajectory detection algorithm and selects a faster traditional method-based conductor detection algorithm. First, the transmission line images captured by the monitoring device are converted to grayscale. Then, an 8×8 grid is used to perform histogram equalization on the grayscale image. The working principle of histogram equalization is: first, the histogram of image pixel intensity is calculated, and the most frequently occurring pixel values ​​(i.e., the pixel values ​​with the largest counts in the histogram) are evenly distributed. Then, the linear trend of the cumulative distribution function is given, thereby improving the image contrast.

[0045] Further, edge detection is performed on the equalized transmission line image. The specific steps are as follows: (1) Denoising: Noise will affect the accuracy of edge detection, so noise must be filtered out first. In this embodiment, the transmission line image after histogram equalization can be denoised using the median filtering algorithm. (2) Calculate the magnitude and direction of the gradient. (3) Non-maximum suppression: Pixels are screened out, that is, the edges are appropriately "thinned" to obtain the third reference edge region of the transmission line image. (4) Determine the edge: The final edge information is determined using the double threshold algorithm. The third reference edge is screened out to remove pixels with grayscale change values ​​less than the preset low threshold to obtain the first reference conductor region. Then, the complete edge detection algorithm is performed on the image. Next, the obtained binary image is dilated and then eroded. Finally, the endpoints of the conductor can be detected by the statistical probability Hough linear transformation function.

[0046] S104. Based on the coordinates of multiple traverses, determine the coordinates of the endpoints of the two outermost traverses on both sides.

[0047] In one embodiment of this application, multiple sets of pixel coordinates corresponding to different conductor trajectories are determined. The horizontal coordinates of these multiple sets of pixel coordinates are compared to determine a first reference set of pixel coordinates corresponding to the leftmost conductor trajectory, and a second reference set of pixel coordinates corresponding to the rightmost conductor trajectory. The vertical coordinates of the pixels in the first reference set are compared to determine the coordinates of the conductor endpoint corresponding to the leftmost conductor trajectory, and the vertical coordinates of the pixels in the second reference set are compared to determine the coordinates of the conductor endpoint corresponding to the rightmost conductor trajectory.

[0048] Specifically, after performing edge detection on the captured images of the power transmission lines, the conductor trajectory can be obtained. Based on the obtained conductor trajectory, the set of pixel coordinates corresponding to the conductor trajectory can be obtained. The power transmission lines erected between the towers are erected in parallel, and the range corresponding to the power transmission line protection zone is related to the outermost power transmission lines on both the left and right sides. Therefore, the set of pixel coordinates can be compared. By comparing the horizontal coordinates, the set of coordinates corresponding to the outermost power transmission lines on the left and right sides can be determined.

[0049] Specifically, the set of pixel coordinates corresponding to the conductor trajectory is grouped according to different ordinates, resulting in multiple pixel coordinates for each row. The x-coordinates of these multiple pixel coordinates for each row are compared to determine the leftmost and rightmost coordinates for each row. A first reference pixel coordinate set is constructed based on the leftmost pixel in each row. A second reference pixel coordinate set is constructed based on the rightmost pixel in each row. The first reference pixel coordinate set is the set of pixels corresponding to the leftmost conductor, and the second reference pixel coordinate set is the set of pixels corresponding to the rightmost conductor.

[0050] Furthermore, the coordinates of the points in the first set of reference pixel coordinates are compared by their ordinates to determine the coordinates of the two endpoints corresponding to the leftmost conductor. Similarly, the coordinates of the points in the second set of reference pixel coordinates are compared by their ordinates to determine the coordinates of the two endpoints corresponding to the rightmost conductor. For example, a coordinate system is established with the straight line containing the left edge of the transmission line image as the Y-axis, the straight line containing the lower edge as the X-axis, and the intersection of the left and lower edges as the origin. In this case, the coordinates with the largest and smallest ordinate values ​​in the first set of reference pixel coordinates are the two endpoints corresponding to the leftmost conductor. Similarly, the coordinates with the largest and smallest ordinate values ​​in the second set of reference pixel coordinates are the two endpoints corresponding to the rightmost conductor.

[0051] S105. Based on the coordinates of the conductor endpoints, the lower edge of the tower annotation frame, and the lower edge of the transmission line image, determine the projection corresponding to the conductor endpoints, and determine the protection zone corresponding to the transmission line based on the projection.

[0052] In one embodiment of this application, based on the pixel coordinates corresponding to the conductor trajectories in the transmission line image, the coordinates of the first endpoint and the second endpoint corresponding to the two outermost conductor trajectories are determined, where the first endpoint is the conductor endpoint closer to the tower, and the second endpoint is the conductor endpoint farther from the tower. A first projection is determined based on the first endpoints corresponding to the two outermost trajectories and the lower edge of the tower's bounding box. A second projection is determined based on the coordinates of the second endpoints corresponding to the two outermost trajectories and the lower edge of the transmission line image. The protected area corresponding to the transmission line is determined based on the first and second projections.

[0053] Specifically, the transmission line monitoring device captures images of the transmission line, obtaining the image. This image is then input into a tower detection network. The network model outputs the tower with the highest score, which is the tower location for that transmission line scene. The bottom border of the tower represents its position on the ground. Next, conductor detection is performed on the original image to obtain the conductor trajectory. The outermost conductor trajectories on the left and right sides are obtained using coordinate information, and the endpoints corresponding to the two outermost conductor trajectories are determined. There are two conductor endpoints: a first endpoint closer to the tower and a second endpoint farther from the tower. The points at both ends of the conductor are projected downwards. The point closer to the tower is projected onto the horizontal line of the ground, obtaining the first projection. The point farther from the tower is projected onto the bottom boundary of the image, obtaining the second projection.

[0054] In one embodiment of this application, the coordinates of the third endpoints corresponding to the two outermost trajectories on both sides are determined based on the lower edge of the first projection. The coordinates of the fourth endpoints corresponding to the two outermost trajectories on both sides are determined based on the lower edge of the second projection. Any adjacent first, second, third, and fourth endpoints are connected to determine the reference protection zone corresponding to the transmission line. The reference protection zone is extended to the left and right sides to obtain the protection zone corresponding to the transmission line, wherein the extended area is related to the area of ​​the reference protection zone corresponding to the transmission line.

[0055] Specifically, the coordinates of the third endpoint are obtained based on the intersection of the first projection and the lower edge of the tower annotation frame. The coordinates of the fourth endpoint are obtained based on the intersection of the second projection and the lower edge of the transmission line image. Connecting the adjacent first, second, third, and fourth endpoints yields a cuboid-shaped reference protection zone. Next, the left and right sides of this reference protection zone are extended, for example, by 20% of its area. This formed area is the protection zone corresponding to the transmission line.

[0056] S106. Identify potential hazard areas in the image of the power transmission line. If the area of ​​the potential hazard area within the protected area is greater than a preset area value, issue a potential hazard alarm.

[0057] In one embodiment of this application, a pre-set hazard identification network model is used to identify hazards in transmission line images, and the identified hazard areas are marked with hazard bounding boxes. The area of ​​the hazard area is determined based on the pixel coordinates of the hazard bounding boxes. The area of ​​the overlapping area between the hazard area and the protected area is determined based on the pixel coordinates of the hazard bounding boxes and the pixel coordinates of the protected area. The ratio of the overlapping area to the hazard area is calculated, and a hazard warning is issued if the ratio is greater than a preset threshold.

[0058] Specifically, in this embodiment, image samples of transmission lines marked with potential hazard areas are pre-collected. These samples are then used to train a pre-set neural network model to obtain the pre-set hazard identification network model. The current transmission line image captured by the transmission line monitoring device is input into the pre-set hazard identification network model, which then marks the hazard areas in the image. The size of the hazard area is obtained from the marked hazard areas.

[0059] Furthermore, the set of pixel coordinates for the hazardous area and the set of pixel coordinates for the protected area are determined. Comparing these two sets of coordinates yields overlapping pixels. Based on these overlapping pixels, the area of ​​the hazardous area within the protected area is determined, i.e., the area within the protected area that the hazardous equipment enters. If the area of ​​this overlapping portion is greater than 50% of the hazardous area area, a warning is issued.

[0060] It should be noted that, in this embodiment, a warning is preferably issued when the area of ​​the overlapping portion is greater than 50% of the area of ​​the potential hazard zone. In practical applications, the size of the overlapping area can be adjusted according to the actual situation, and this embodiment does not impose any restrictions on this.

[0061] Figure 3 This is a structural schematic diagram of a hazard identification device for a power transmission line protection zone, provided as an embodiment of this application. Figure 3 As shown, the hazard identification equipment for transmission line protection zones includes:

[0062] At least one processor; and,

[0063] A memory communicatively connected to the at least one processor; wherein,

[0064] The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:

[0065] Images of the power transmission lines are obtained by taking pictures of the transmission lines using monitoring devices installed on the transmission line towers.

[0066] The transmission line image is input into the tower detection network model to annotate the towers in the transmission line image with bounding boxes;

[0067] Edge detection is performed on the transmission line image to determine the trajectories of multiple conductors in the transmission line image;

[0068] Based on the coordinates of the multiple conductor trajectories, the coordinates of the conductor endpoints corresponding to the two outermost conductor trajectories on both sides are determined.

[0069] Based on the coordinates of the conductor endpoint, the lower edge of the tower annotation frame, and the lower edge of the transmission line image, the projection corresponding to the conductor endpoint is determined, and the protection zone corresponding to the transmission line is determined based on the projection.

[0070] The image of the power transmission line is used to identify potential hazard areas. If the area of ​​the potential hazard within the protected area is greater than a preset area value, a hazard alarm is issued.

[0071] This application embodiment also provides a storage medium, characterized in that the storage medium is a non-volatile computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0072] Images of the power transmission lines are obtained by taking pictures of the transmission lines using monitoring devices installed on the transmission line towers.

[0073] The transmission line image is input into the tower detection network model to annotate the towers in the transmission line image with bounding boxes;

[0074] Edge detection is performed on the transmission line image to determine the trajectories of multiple conductors in the transmission line image;

[0075] Based on the coordinates of the multiple conductor trajectories, the coordinates of the conductor endpoints corresponding to the two outermost conductor trajectories on both sides are determined.

[0076] Based on the coordinates of the conductor endpoint, the lower edge of the tower annotation frame, and the lower edge of the transmission line image, the projection corresponding to the conductor endpoint is determined, and the protection zone corresponding to the transmission line is determined based on the projection.

[0077] The image of the power transmission line is used to identify potential hazard areas. If the area of ​​the potential hazard within the protected area is greater than a preset area value, a hazard alarm is issued.

[0078] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0079] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0080] The above description is merely an embodiment of this application and is not intended to limit this application. For those skilled in the art, various modifications and variations can be made to the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of this application should be included within the scope of the claims of this application.

Claims

1. A method for identifying hidden dangers in a power transmission line protection zone, characterized in that, The method comprises: photographing the power transmission line by a photographing device arranged on a power transmission line tower to obtain a power transmission line image; inputting the power transmission line image into a tower detection network model to perform bounding box labeling on the tower in the power transmission line image; performing edge detection on the power transmission line image to determine a plurality of conductor track in the power transmission line image; based on the coordinates of the plurality of conductor tracks, determining conductor endpoint coordinates corresponding to the two outermost conductor tracks on both sides in the plurality of conductor tracks; based on the conductor endpoint coordinates, the lower edge of the tower bounding box and the lower edge of the power transmission line image, determining a projection corresponding to the conductor endpoint, and based on the projection, determining a protection zone corresponding to the power transmission line, specifically comprising: based on the first endpoint coordinates corresponding to the two outermost tracks on both sides and the lower edge of the tower bounding box, determining a first projection; based on the second endpoint coordinates corresponding to the two outermost tracks on both sides and the lower edge of the power transmission line image, determining a second projection; based on the first projection and the second projection, determining the protection zone corresponding to the power transmission line; wherein the first endpoint is a conductor endpoint close to the tower, and the second endpoint is a conductor endpoint away from the tower; performing hidden danger area identification on the power transmission line image, and issuing a hidden danger warning if the area of the hidden danger area in the protection zone is greater than a preset area value.

2. The method of claim 1, wherein, Before determining the projection corresponding to the conductor endpoint based on the conductor endpoint, the lower edge of the tower bounding box and the lower edge of the power transmission line image, and determining the protection zone corresponding to the power transmission line based on the projection, the method further comprises: based on the pixel point coordinates corresponding to the conductor track in the power transmission line image, determining the first endpoint coordinates and the second endpoint coordinates corresponding to the two outermost conductor tracks.

3. The method of claim 1, wherein, The determination of the protection zone corresponding to the power transmission line based on the first projection and the second projection specifically comprises: based on the lower edge of the first projection, determining third endpoint coordinates corresponding to the two outermost tracks on both sides; based on the lower edge of the second projection, determining fourth endpoint coordinates corresponding to the two outermost tracks on both sides; connecting any adjacent first endpoint, second endpoint, third endpoint and fourth endpoint to determine a reference protection zone corresponding to the power transmission line; extending the reference protection zone to the left and right sides respectively to obtain a protection zone corresponding to the power transmission line; wherein the extension area is related to the area of the reference protection zone corresponding to the power transmission line.

4. The method of claim 1, wherein, The edge detection on the power transmission line image to determine the plurality of conductor tracks in the power transmission line image specifically comprises: performing grayscale processing on the power transmission line image; performing histogram equalization processing on the power transmission line image after grayscale processing; performing edge detection processing on the power transmission line image after histogram equalization processing to obtain a first reference edge region; The first reference edge region is filtered based on an expansion algorithm and an erosion algorithm to obtain a second reference edge region corresponding to the power transmission line image; According to a Hough transform algorithm, a sinusoidal curve corresponding to each pixel point of the second reference edge region is determined, a pixel point set corresponding to the power transmission line is determined according to the number of the sinusoidal curves intersecting at the same point, and a plurality of conductor track trajectories in the power transmission line image are determined based on the pixel point set corresponding to the power transmission line.

5. The method of claim 4, wherein, The power transmission line image subjected to the histogram equalization processing is subjected to edge detection processing to obtain a first reference edge region, and the first reference edge region is obtained by specifically including the following steps: The power transmission line image subjected to the histogram equalization processing is subjected to noise removal processing according to a median filter algorithm; The power transmission line image subjected to the noise removal processing is subjected to pixel value gradient calculation, and pixel points are filtered based on a non-maximum suppression algorithm to obtain a third reference edge region of the power transmission line image; The third reference edge region is filtered based on a double-threshold algorithm to filter out pixel points with a gray value less than a preset low threshold to obtain the first reference edge region.

6. The method of claim 1, wherein, Based on the coordinates of the plurality of conductor track trajectories, conductor end point coordinates corresponding to two conductor track trajectories on the outermost sides are determined in the plurality of conductor track trajectories, and the conductor end point coordinates are determined by specifically including the following steps: Pixel point coordinate sets corresponding to the plurality of conductor track trajectories are determined; A plurality of the pixel point coordinate sets are compared in terms of horizontal coordinates to determine a first reference pixel point coordinate set corresponding to a leftmost conductor track trajectory and a second reference pixel point coordinate set corresponding to a rightmost conductor track trajectory; Pixel points in the first reference pixel point coordinate set are compared in terms of vertical coordinates to determine conductor end point coordinates corresponding to the leftmost conductor track trajectory, and pixel points in the second reference pixel point coordinate set are compared in terms of vertical coordinates to determine conductor end point coordinates corresponding to the rightmost conductor track trajectory.

7. The method of claim 1, wherein, Before the power transmission line image is input into a preset tower detection network model to perform bounding box labeling on towers in the power transmission line image, the method further includes the following steps: A neural network model is constructed, wherein the neural network model is composed of a feature extraction backbone network, a feature image pyramid network, and a power transmission line tower classification and positioning network; A power transmission line tower data set with labeled towers is input into the neural network model, and the feature image extraction is performed on the power transmission line tower data set with labeled towers by using the feature extraction backbone network; The feature image is subjected to feature amplification processing from top to bottom based on an up-sampling manner by using the feature image pyramid network to obtain a tower feature image pyramid corresponding to the power transmission line tower data set with labeled towers; The tower region and the background region are distinguished from each other by using the tower classification and positioning network, and the tower region in the tower feature image pyramid is subjected to bounding box positioning; The foreground score calculation is performed on the labeled tower region by using the tower classification and positioning network, and the offset calculation is performed on the labeled tower region. In a case where the foreground score and the offset both meet preset model accuracy conditions, the tower detection network model training is completed.

8. The method of claim 1, wherein, The method further includes: identifying a hidden danger area in the power transmission line image, and issuing a hidden danger warning in a case where an area of the hidden danger area in the protection zone is greater than a preset area value. The hidden danger area is identified in the power transmission line image by using a preset hidden danger identification network model, and a hidden danger bounding box is labeled on the identified hidden danger area. An area of the hidden danger area is determined based on pixel point coordinates of the hidden danger bounding box. An area of an overlapping region between the hidden danger area and the protection zone is determined based on the pixel point coordinates of the hidden danger bounding box and pixel point coordinates of the protection zone. A ratio of the area of the overlapping region to the area of the hidden danger area is calculated, and a hidden danger warning is issued in a case where the obtained ratio is greater than a preset ratio threshold.

9. A hidden danger identification device for a protection zone of a power transmission line, comprising: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: capture the power transmission line by using a monitoring device arranged on a power transmission tower to obtain a power transmission line image; input the power transmission line image into a tower detection network model to label a tower bounding box on the tower in the power transmission line image; perform edge detection on the power transmission line image to determine a plurality of conductor track in the power transmission line image; determine conductor end point coordinates corresponding to two outermost conductor tracks on both sides in the plurality of conductor tracks based on coordinates of the plurality of conductor tracks; determine a projection corresponding to the conductor end points based on the conductor end point coordinates, a lower edge of the tower bounding box, and a lower edge of the power transmission line image, and determine the protection zone corresponding to the power transmission line based on the projection, specifically including: determining a first projection based on first end point coordinates corresponding to the two outermost tracks on both sides and the lower edge of the tower bounding box; determining a second projection based on second end point coordinates corresponding to the two outermost tracks on both sides and the lower edge of the power transmission line image; and determining the protection zone corresponding to the power transmission line based on the first projection and the second projection; wherein the first end point is a conductor end point close to the tower, and the second end point is a conductor end point away from the tower; identify a hidden danger area in the power transmission line image, and issue a hidden danger warning in a case where an area of the hidden danger area in the protection zone is greater than a preset area value.

10. A storage medium, characterized by The storage medium is a non-volatile computer readable storage medium, and stores computer executable instructions, which are configured to: capture the power transmission line by using a monitoring device arranged on a power transmission tower to obtain a power transmission line image; input the power transmission line image into a tower detection network model to label a tower bounding box on the tower in the power transmission line image; performing edge detection on the power transmission line image to determine a plurality of conductor track in the power transmission line image; determining, based on coordinates of the plurality of conductor track, conductor endpoint coordinates corresponding to two conductor tracks on the outermost sides of the plurality of conductor track; determining, based on the conductor endpoint coordinates, a lower edge of a tower bounding box, and a lower edge of the power transmission line image, a projection corresponding to the conductor endpoint, and determining, based on the projection, a protection zone corresponding to the power transmission line, specifically including: determining a first projection based on first endpoint coordinates corresponding to the two conductor tracks on the outermost sides and the lower edge of the tower bounding box; determining a second projection based on second endpoint coordinates corresponding to the two conductor tracks on the outermost sides and the lower edge of the power transmission line image; and determining the protection zone corresponding to the power transmission line based on the first projection and the second projection; wherein the first endpoint is a conductor endpoint close to the tower, and the second endpoint is a conductor endpoint away from the tower; performing hidden danger area identification on the power transmission line image, and issuing a hidden danger warning if an area of the hidden danger area is greater than a preset area value.

Images