A power transmission line hidden danger bird nest detection method, system, device and storage medium

Abstract

The present application provides a power transmission line hidden nest detection method, system, device and storage medium, to solve the problem that the existing nest detection cannot accurately determine whether the insulator and the nest are located at the same depth, and it is difficult to define ordinary nests and hidden nests, and relates to the technical field of deep learning. Including: acquiring the power transmission line image to be detected shot by the unmanned aerial vehicle inspection; inputting the power transmission line image to be detected into the pre-trained nest detection model for identification; the nest detection model adopts the yolov8 model framework, and the original bounding box regression loss function of the yolov8 model framework is replaced by the EIOU loss function; output the identification result. The method can combine the advantages of target detection and depth estimation model, and realize high-precision discrimination of hidden nests. Through the coordinate relationship, the nests located above the insulator are screened out as hidden nest candidates, and then whether the insulator and the nest are in the same depth range is judged according to the depth map, realizing the discrimination of hidden nests.

Description

Technical Field

[0001] This application relates to the field of deep learning technology, and in particular to a method, system, device and storage medium for detecting bird nests as a hidden danger on power transmission lines. Background Technology

[0002] High-voltage transmission lines are a crucial infrastructure component of modern industry and society, and their safe operation is vital for the economy, society, and the safety of people's lives and property. However, numerous safety hazards exist in the operation and maintenance of transmission lines, with bird nests posing a significant challenge. Birds can nest anywhere on transmission towers, and artificial nests are often placed in safe locations on the towers, so most bird nests do not pose a threat to the transmission lines. Generally, only bird nests located at the same depth as the suspension insulator string and directly above it should be considered potential hazards. This is because bird droppings around the nest can contaminate the insulators below, creating a risk of flashover discharge, which can severely impact the normal operation of high-voltage transmission lines. Traditional bird nest detection methods typically only identify the nest's location through target detection, failing to accurately determine whether the insulator and the nest are at the same depth, making it difficult to distinguish between ordinary and potentially hazardous nests, requiring significant manpower for secondary screening later.

[0003] In conclusion, how to provide a reliable and efficient method for detecting bird nests as a hidden danger in power transmission lines, and reduce the high cost of manual screening, is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] This application provides a method, system, equipment, and storage medium for detecting hidden bird nests in power transmission lines. It addresses the technical problems of existing bird nest detection methods, which cannot accurately determine whether insulators and bird nests are located at the same depth, make it difficult to distinguish between ordinary bird nests and hidden bird nests, and require a large amount of manpower for secondary screening.

[0005] On one hand, this application provides a method for detecting bird nests that may pose a hazard to power transmission lines. The method includes: acquiring images of the power transmission line to be detected taken by a drone during inspection; inputting the images of the power transmission line to be detected into a pre-trained bird nest detection model for identification; wherein the bird nest detection model adopts the YOLOv8 model framework, and the original bounding box regression loss function of the YOLOv8 model framework is replaced with the EIOU loss function; and outputting the bird nest identification result.

[0006] In one implementation of this application, the EIOU loss function includes: IOU loss, distance loss, and width / height loss, and the EIOU loss function is defined as:

[0007]

[0008] Where IOU represents the intersection-union ratio between the predicted bounding box and the ground truth bounding box, ρ 2 (b,b gt ) represents the Euclidean distance between the center points of the predicted bounding box and the ground truth bounding box, c represents the diagonal distance of the smallest closure region that can simultaneously contain both the predicted and ground truth bounding boxes, and ρ represents the distance between the center points of the predicted bounding box and the ground truth bounding box. 2 (w,w gt ρ represents the square of the difference between the width of the predicted bounding box and the width of the ground truth bounding box. 2 (h,h gt ) represents the square of the height difference between the predicted bounding box and the actual bounding box.

[0009] In one implementation of this application, after acquiring the image of the transmission line to be inspected taken by the UAV inspection, the method further includes: labeling the bird nests and insulators in the transmission line image; constructing a target detection dataset for bird nests and insulators, and labeling the depth information; and constructing a monocular depth estimation dataset based on the Lite-Mono monocular depth estimation algorithm.

[0010] In one implementation of this application, the process of inputting the image of the transmission line to be detected into a pre-trained bird nest detection model for identification specifically includes: performing monocular depth estimation on the transmission line image to generate a detection box; determining whether the target bird nest is located in the area directly above the target insulator by using the coordinates of the detection box, and generating a detection result image.

[0011] In one implementation of this application, the step of performing monocular depth estimation on the transmission line image to generate detection boxes specifically involves: filtering by the horizontal coordinates of the target insulator and the target bird's nest, retaining bird's nest detection boxes that intersect with the horizontal coordinates of the target insulator; and filtering by the vertical coordinates of the target insulator and the target bird's nest, retaining bird's nest detection boxes that are smaller than the vertical coordinates of the target insulator.

[0012] In one implementation of this application, the method further includes: calculating the coordinates of the center point of the detection frame of the target bird's nest and the target insulator in the detection result image; reading the depth of the coordinates of the center point of the target bird's nest and the target insulator; calculating the difference between the depth of the target bird's nest and the target insulator and comparing it with a preset threshold; if it is less than the preset threshold, the target bird's nest is determined to be a potential hazard bird's nest.

[0013] This application embodiment also provides a power transmission line hidden danger bird nest detection system. The system includes: an image acquisition unit for acquiring images of the power transmission line to be detected taken by a drone during inspection; a bird nest detection unit for inputting the images of the power transmission line to be detected into a pre-trained bird nest detection model for identification; wherein the bird nest detection model adopts the YOLOv8 model framework, and the original bounding box regression loss function of the YOLOv8 model framework is replaced with the EIOU loss function; and an alarm unit for outputting the hidden danger bird nest identification results and issuing an alarm.

[0014] This application embodiment also provides a device for detecting bird nests that may pose a hazard to power transmission lines. The device includes: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which, when executed, enable the at least one processor to: acquire images of the power transmission line to be detected captured by a drone inspection; input the images of the power transmission line to be detected into a pre-trained bird nest detection model for identification; wherein the bird nest detection model uses the YOLOv8 model framework, and replaces the original bounding box regression loss function of the YOLOv8 model framework with an EIOU loss function; and outputs the bird nest identification result.

[0015] This application embodiment also provides a non-volatile computer storage medium for detecting bird nests that pose a hidden danger to power transmission lines, storing computer-executable instructions. The computer-executable instructions are configured to: acquire images of the power transmission line to be detected taken by a drone during inspection; input the images of the power transmission line to be detected into a pre-trained bird nest detection model for identification; wherein the bird nest detection model adopts the YOLOv8 model framework, and the original bounding box regression loss function of the YOLOv8 model framework is replaced with the EIOU loss function; and output the bird nest identification result.

[0016] The method, system, equipment, and storage medium for detecting bird nests as a hidden danger in power transmission lines provided in this application have the following beneficial effects:

[0017] (1) Using the improved YOLOv8 target detection algorithm and Lite-Mono monocular depth estimation algorithm with EIOU loss function, as well as the candidate bird nest screening algorithm based on location information, this method can combine the advantages of target detection and depth estimation models to achieve high-precision identification of potential bird nests.

[0018] (2) A post-processing method combining detection results and depth estimation results is proposed. First, the bird nests located above the insulator are selected as potential bird nests by using coordinate relationships. Then, the insulator and the bird nest are judged to be in the same depth range based on the depth map, thus realizing the identification of potential bird nests. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 A flowchart illustrating a method for detecting hidden bird nests on power transmission lines, as provided in this application embodiment;

[0021] Figure 2 This is a flowchart illustrating the process of identifying potential bird nests in this application.

[0022] Figure 3 This is an application scenario diagram of a detection method provided in an embodiment of this application;

[0023] Figure 4 A diagram illustrating the components of a power transmission line bird nest detection system provided in this application embodiment;

[0024] Figure 5 This is a schematic diagram of a bird nest detection device for power transmission lines, provided as an embodiment of this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] This application provides a method, system, device, and storage medium for detecting hidden bird nests on power transmission lines. It addresses the technical problems of existing bird nest detection methods, which cannot accurately determine whether insulators and bird nests are located at the same depth, making it difficult to distinguish between ordinary bird nests and hidden bird nests, and requiring significant manpower for secondary screening. The technical solution proposed in this application is described in detail below with reference to the accompanying drawings.

[0027] Figure 1 This is a flowchart illustrating a method for detecting bird nests as a hidden danger in power transmission lines, provided as an embodiment of this application. Figure 1 As shown, the method mainly includes the following steps:

[0028] Step 101: Obtain images of the power transmission lines to be inspected taken by the drone during inspection.

[0029] In this embodiment of the application, the drone will focus on taking pictures of the transmission towers during the inspection process. Transmission towers are generally installed in the wild and are easily nested by birds. Bird droppings can corrode the insulators on the transmission towers, so it is necessary to clean up the bird nests that pose a hazard regularly.

[0030] Step 102: Input the image of the transmission line to be detected into the pre-trained bird's nest detection model for recognition.

[0031] In this embodiment of the application, targets such as bird nests and insulators appearing in the captured images of transmission lines are labeled to construct a target detection dataset for bird nests and insulators. In addition, a monocular depth estimation dataset is constructed based on the Lite-Mono monocular depth estimation algorithm to label the depth information and construct a monocular estimated depth dataset.

[0032] In this embodiment, the bird's nest detection model uses the YOLOv8 model framework. This application improves upon this framework by replacing its original bounding box regression loss function with the EIOU loss function, which is defined as:

[0033]

[0034] Where IOU represents the intersection-union ratio between the predicted bounding box and the ground truth bounding box, ρ 2 (b,b gt ) represents the Euclidean distance between the center points of the predicted bounding box and the ground truth bounding box, c represents the diagonal distance of the smallest closure region that can simultaneously contain both the predicted and ground truth bounding boxes, and ρ represents the distance between the center points of the predicted bounding box and the ground truth bounding box. 2 (w,w gt ρ represents the square of the difference between the width of the predicted bounding box and the width of the ground truth bounding box. 2 (h,h gt ) represents the square of the height difference between the predicted bounding box and the actual bounding box.

[0035] In this embodiment of the application, the process of inputting the image of the transmission line to be detected into a pre-trained bird nest detection model for identification is as follows: First, a monocular depth estimation dataset is constructed based on the Lite-Mono monocular depth estimation algorithm for the transmission line image, monocular depth estimation is performed, and detection boxes are generated; then, the coordinates of the detection boxes are used to determine whether the target bird nest is located in the area directly above the target insulator, and a detection result image is generated.

[0036] Specifically, the detection frames are filtered by the horizontal coordinates of the target insulator and the target bird's nest, retaining those bird's nest detection frames that intersect with the horizontal coordinates of the target insulator; and by the vertical coordinates of the target insulator and the target bird's nest, retaining those bird's nest detection frames that are smaller than the vertical coordinates of the target insulator.

[0037] More specifically, the coordinates of the center point of the detection frame of the target bird's nest and the target insulator in the detection result image are calculated; the depth of the center point of the target bird's nest and the target insulator is read; the difference between the depth of the target bird's nest and the target insulator is calculated and compared with a preset threshold. If it is less than the preset threshold, the target bird's nest is determined to be a potential hazard bird's nest.

[0038] Step 103: Output the results of identifying potential bird nest hazards.

[0039] The flowchart for identifying potential bird nests in this embodiment is as follows: Figure 2 As shown, the general process is as follows: acquire images taken by drones, detect and identify the insulators of the target bird nests, obtain depth maps based on monocular depth estimation, then filter candidate bird nests as potential bird nests by the coordinates of the detected and identified insulators, and finally determine the potential bird nests by the depth information.

[0040] In the embodiments of this application, specific application scenarios are as follows: Figure 3 As shown, if a bird's nest is detected directly above a target insulator, the presence of the bird's nest will pose a potential hazard to the insulator and needs to be addressed. In this case, the system will issue an alarm and send the detection information to the terminal equipment of the power maintenance personnel.

[0041] The above is a method for detecting bird nests that may be hidden in power transmission lines, provided by an embodiment of this application. Based on the same inventive concept, this application also provides a system for detecting bird nests that may be hidden in power transmission lines. Figure 4 A diagram illustrating the components of a power transmission line bird nest detection system provided in this application embodiment is shown below. Figure 4 As shown, the system mainly includes:

[0042] Image acquisition unit 401 is used to acquire images of the power transmission line to be inspected taken by the UAV during inspection; bird nest detection unit 402 is used to input the images of the power transmission line to be inspected into a pre-trained bird nest detection model for identification; wherein, the bird nest detection model adopts the YOLOv8 model framework, and the original bounding box regression loss function of the YOLOv8 model framework is replaced with the EIOU loss function; alarm unit 403 is used to output the identification results of the hidden bird nests and issue an alarm.

[0043] This application provides a method for detecting potential bird nests on power transmission lines. It employs a YOLOv8 target detection algorithm improved with an EIOU loss function, a Lite-Mono monocular depth estimation algorithm, and a candidate bird nest selection algorithm based on location information. This method combines the advantages of target detection and depth estimation models to achieve high-precision identification of potential bird nests. A post-processing method combining detection and depth estimation results is also proposed. First, bird nests located above insulators are selected as candidate potential bird nests based on coordinate relationships. Then, the depth map is used to determine whether the insulator and the bird nest are within the same depth range, thus identifying potential bird nests.

[0044] The above is an embodiment of a power transmission line bird nest detection system provided in this application. Based on the same inventive concept, this application also provides a power transmission line bird nest detection device. Figure 5 This application provides a schematic diagram of a power transmission line bird nest detection device, as shown in the embodiment of the present application. Figure 5 As shown, the device mainly includes: at least one processor 501; and a memory 502 communicatively connected to the at least one processor; wherein the memory 502 stores instructions that can be executed by the at least one processor 501, and the instructions are executed by the at least one processor 501 to enable the at least one processor 501 to: acquire images of the transmission line to be inspected taken by the UAV inspection; input the images of the transmission line to be inspected into a pre-trained bird nest detection model for identification; wherein the bird nest detection model adopts the YOLOv8 model framework, and the original bounding box regression loss function of the YOLOv8 model framework is replaced with the EIOU loss function; and output the identification result of the hidden bird nest.

[0045] In addition, this application embodiment also provides a non-volatile computer storage medium for detecting bird nests that pose a hidden danger to power transmission lines, storing computer-executable instructions. The computer-executable instructions are set to: acquire images of the power transmission line to be detected taken by a drone during inspection; input the images of the power transmission line to be detected into a pre-trained bird nest detection model for identification; wherein the bird nest detection model adopts the YOLOv8 model framework, and the original bounding box regression loss function of the YOLOv8 model framework is replaced with the EIOU loss function; and output the bird nest identification result.

[0046] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0047] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0048] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0049] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0050] 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 device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0051] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0052] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for detecting bird nests as a hidden danger on power transmission lines, characterized in that, The method includes: Acquire images of the power transmission lines to be inspected taken by drones during inspections; label bird nests and insulators in the images; construct a target detection dataset for bird nests and insulators, and label the depth information; construct a monocular depth estimation dataset based on the Lite-Mono monocular depth estimation algorithm. The image of the transmission line to be detected is input into a pre-trained bird nest detection model for identification. The bird nest detection model uses the YOLOv8 model framework, but the original bounding box regression loss function of the YOLOv8 model framework is replaced with an EIOU loss function. The process of inputting the image of the transmission line to be detected into the pre-trained bird nest detection model for identification specifically involves: performing monocular depth estimation on the transmission line image to generate detection boxes; determining whether the target bird nest is located directly above the target insulator using the coordinates of the detection boxes, and generating a detection result image; the process of inputting the image of the transmission line to be detected into the pre-trained bird nest detection model for identification specifically involves: performing monocular depth estimation on the transmission line image to generate detection boxes; determining whether the target bird nest is located directly above the target insulator using the coordinates of the detection boxes, and generating a detection result image; the process of inputting the image of the transmission line to be detected into the pre-trained bird nest detection model for identification... Monocular depth estimation is performed to generate detection boxes. Specifically, the process involves: filtering by the x-coordinate of the target insulator and the target bird's nest, retaining bird's nest detection boxes that intersect with the x-coordinate of the target insulator; filtering by the y-coordinate of the target insulator and the target bird's nest, retaining bird's nest detection boxes whose y-coordinate is smaller than that of the target insulator; further including: calculating the coordinates of the center point of the detection box of the target bird's nest and the target insulator in the detection result image; reading the depth of the center point of the target bird's nest and the target insulator; calculating the difference between the depth of the target bird's nest and the target insulator and comparing it with a preset threshold. If the difference is less than the preset threshold, the target bird's nest is determined to be a potential hazard bird's nest. Output the results of identifying potentially hazardous bird nests.

2. The method for detecting hidden bird nests on power transmission lines according to claim 1, characterized in that, The EIOU loss function includes: IOU loss, distance loss, and width / height loss. The EIOU loss function is defined as follows: ； Where IOU represents the intersection-union ratio between the predicted bounding box and the ground truth bounding box. represents the Euclidean distance between the center points of the predicted bounding box and the ground truth bounding box, and c represents the diagonal distance of the smallest closure region that can simultaneously contain both the predicted and ground truth bounding boxes. This represents the square of the difference between the width of the predicted bounding box and the width of the actual bounding box. This represents the square of the height difference between the predicted bounding box and the actual bounding box.

3. A system for detecting bird nests as a hidden danger on power transmission lines, characterized in that, The system includes: The image acquisition unit is used to acquire images of the transmission lines to be inspected taken by drones during inspections; to annotate bird nests and insulators in the transmission line images; to construct a target detection dataset for bird nests and insulators, and to annotate the depth information; and to construct a monocular depth estimation dataset based on the Lite-Mono monocular depth estimation algorithm. A bird's nest detection unit is used to input the image of the transmission line to be detected into a pre-trained bird's nest detection model for recognition. The bird's nest detection model uses the YOLOv8 model framework, and the original bounding box regression loss function of the YOLOv8 model framework is replaced with an EIOU loss function. The process of inputting the image of the transmission line to be detected into the pre-trained bird's nest detection model for recognition specifically includes: performing monocular depth estimation on the transmission line image to generate a detection box; determining whether the target bird's nest is located directly above the target insulator using the coordinates of the detection box, and generating a detection result image; the ... includes: performing monocular depth estimation on the transmission line image to generate a detection box; determining whether the target bird's nest is located directly above the target insulator using the coordinates of the detection box, and generating a detection result image; the process of inputting the image of the transmission line to be detected into the pre-trained bird's nest detection model to generate a detection result image. The process involves monocular depth estimation of the power line image to generate detection boxes. Specifically, this includes: filtering by the horizontal coordinates of the target insulator and the target bird's nest, retaining bird's nest detection boxes that intersect with the horizontal coordinates of the target insulator; filtering by the vertical coordinates of the target insulator and the target bird's nest, retaining bird's nest detection boxes whose vertical coordinates are smaller than those of the target insulator; furthermore, it includes: calculating the coordinates of the center point of the detection box between the target bird's nest and the target insulator in the detection result image; reading the depth of the center point coordinates of the target bird's nest and the target insulator; calculating the difference between the depth of the target bird's nest and the target insulator and comparing it with a preset threshold. If the difference is less than the preset threshold, the target bird's nest is determined to be a potential hazard bird's nest. The alarm unit is used to output the identification results of potential bird nests and issue an alarm.

4. A device for detecting bird nests as hidden dangers on power transmission lines, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Acquire images of the power transmission lines to be inspected taken by drones during inspections; label bird nests and insulators in the images; construct a target detection dataset for bird nests and insulators, and label the depth information; construct a monocular depth estimation dataset based on the Lite-Mono monocular depth estimation algorithm. The image of the transmission line to be detected is input into a pre-trained bird nest detection model for identification. The bird nest detection model uses the YOLOv8 model framework, but the original bounding box regression loss function of the YOLOv8 model framework is replaced with an EIOU loss function. The process of inputting the image of the transmission line to be detected into the pre-trained bird nest detection model for identification specifically involves: performing monocular depth estimation on the transmission line image to generate detection boxes; determining whether the target bird nest is located directly above the target insulator using the coordinates of the detection boxes, and generating a detection result image; the process of inputting the image of the transmission line to be detected into the pre-trained bird nest detection model for identification specifically involves: performing monocular depth estimation on the transmission line image to generate detection boxes; determining whether the target bird nest is located directly above the target insulator using the coordinates of the detection boxes, and generating a detection result image; the process of inputting the image of the transmission line to be detected into the pre-trained bird nest detection model for identification... Monocular depth estimation is performed to generate detection boxes. Specifically, the process involves: filtering by the x-coordinate of the target insulator and the target bird's nest, retaining bird's nest detection boxes that intersect with the x-coordinate of the target insulator; filtering by the y-coordinate of the target insulator and the target bird's nest, retaining bird's nest detection boxes whose y-coordinate is smaller than that of the target insulator; further including: calculating the coordinates of the center point of the detection box of the target bird's nest and the target insulator in the detection result image; reading the depth of the center point of the target bird's nest and the target insulator; calculating the difference between the depth of the target bird's nest and the target insulator and comparing it with a preset threshold. If the difference is less than the preset threshold, the target bird's nest is determined to be a potential hazard bird's nest. Output the results of identifying potentially hazardous bird nests.

5. A non-volatile computer storage medium for detecting bird nests as a hidden danger on power transmission lines, storing computer-executable instructions, characterized in that, The computer-executable instructions are set as follows: Acquire images of the power transmission lines to be inspected taken by drones during inspections; label bird nests and insulators in the images; construct a target detection dataset for bird nests and insulators, and label the depth information; construct a monocular depth estimation dataset based on the Lite-Mono monocular depth estimation algorithm. The image of the transmission line to be detected is input into a pre-trained bird nest detection model for identification. The bird nest detection model uses the YOLOv8 model framework, but the original bounding box regression loss function of the YOLOv8 model framework is replaced with an EIOU loss function. The process of inputting the image of the transmission line to be detected into the pre-trained bird nest detection model for identification specifically involves: performing monocular depth estimation on the transmission line image to generate detection boxes; determining whether the target bird nest is located directly above the target insulator using the coordinates of the detection boxes, and generating a detection result image; the process of inputting the image of the transmission line to be detected into the pre-trained bird nest detection model for identification specifically involves: performing monocular depth estimation on the transmission line image to generate detection boxes; determining whether the target bird nest is located directly above the target insulator using the coordinates of the detection boxes, and generating a detection result image; the process of inputting the image of the transmission line to be detected into the pre-trained bird nest detection model for identification... Monocular depth estimation is performed to generate detection boxes. Specifically, the process involves: filtering by the x-coordinate of the target insulator and the target bird's nest, retaining bird's nest detection boxes that intersect with the x-coordinate of the target insulator; filtering by the y-coordinate of the target insulator and the target bird's nest, retaining bird's nest detection boxes whose y-coordinate is smaller than that of the target insulator; further including: calculating the coordinates of the center point of the detection box of the target bird's nest and the target insulator in the detection result image; reading the depth of the center point of the target bird's nest and the target insulator; calculating the difference between the depth of the target bird's nest and the target insulator and comparing it with a preset threshold. If the difference is less than the preset threshold, the target bird's nest is determined to be a potential hazard bird's nest. Output the results of identifying potentially hazardous bird nests.

Images