Low-altitude airspace electric wire detection method, device, equipment, medium and product

Abstract

The invention discloses a low-altitude airspace wire detection method, device and equipment, a medium and a product, and relates to the field of aircraft navigability, and the method comprises the steps: carrying out the training of a region rebalance convolutional neural network based on the self-adaption of a slender target according to a low-altitude airspace wire data set, and obtaining a wire detection model; the self-adaptive regional rebalance convolutional neural network based on the slender target comprises a backbone network and a segmentation head which are connected in sequence; the backbone network is an HRNet network in which a 3 * 3 standard convolution is a dynamic snakelike convolution in a Bottleneck module; the segmentation head comprises a segmentation head network and a region rebalance branch module; the first input end of the area rebalance branch module and the input end of the segmentation head network are both connected with the output end of the backbone network, the second input end of the area rebalance branch module is used for inputting mask labels, the accuracy of low-altitude airspace electric wire detection can be improved, and the line collision risk during low-altitude operation of an aircraft is reduced.

Description

Technical Field

[0001] The present application relates to the field of aircraft airworthiness, and in particular to a method, device, equipment, medium and product for detecting electric wires in low-altitude airspace. Background Art

[0002] The problem of avoiding collision with high-voltage wires of low-altitude aircraft has become a key issue involving low-altitude safety and airworthiness. The "sense and avoid (S&A)" capability is a necessary ability for pilots to sense the terrain of the space and avoid obstacles that may threaten flight safety in a timely manner during the process of flying the aircraft. For low-altitude aircraft, improving the S&A capability that does not rely on the pilot can effectively improve its safety and airworthiness. In S&A, perception (S) is the premise and basis of avoidance (A). However, due to the huge number of low-altitude aircraft and the characteristics of low cost and small load, they do not have safe and reliable S&A capabilities. For large low-altitude aircraft, they mainly rely on the primary and secondary radars of air traffic control to sense and avoid terrain obstacles, mainly including special equipment such as Automatic Dependent Surveillance (ADS) and Traffic Alert and Collision Avoidance System (TACAS). However, these devices are not suitable for light low-altitude aircraft. Therefore, it is of great significance to improve the autonomous perception ability of low-altitude aircraft to detect low-altitude high-voltage wires and enhance their safety and airworthiness. Therefore, it is of great significance to study a low-altitude airspace wire detection method to improve the accuracy of low-altitude airspace wire detection to reduce the risk of collision with wires when low-altitude aircraft are operating at low altitude. Summary of the invention

[0003] The purpose of this application is to provide a low-altitude airspace wire detection method, device, equipment, medium and product, which can improve the accuracy of low-altitude airspace wire detection and reduce the risk of collision with the wire during low-altitude operations of aircraft.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a method for detecting electric wires in low-altitude airspace, comprising:

[0006] Acquire a low-altitude airspace wire data set; the low-altitude airspace wire data set includes a plurality of samples, each sample is an external view image of a sample low-altitude aircraft and a corresponding mask label; the external view image includes wires; the mask label is a mask image with a wire boundary;

[0007] According to the low-altitude airspace wire data set, a regional rebalancing convolutional neural network based on slender target adaptation is trained to obtain a wire detection model, and the wire detection model is used to perform wire detection in the low-altitude airspace; the regional rebalancing convolutional neural network based on slender target adaptation includes a backbone network and a segmentation head connected in sequence; the backbone network is an HRNet network in which the 3x3 standard convolution in the Bottleneck module is a dynamic snake convolution; the segmentation head includes a segmentation head network and a regional rebalancing branch module; the first input end of the regional rebalancing branch module and the input end of the segmentation head network are both connected to the output end of the backbone network, and the second input end of the regional rebalancing branch module is used to input a mask label.

[0008] Optionally, the wire detection model is used to perform wire detection in low-altitude airspace, specifically including:

[0009] Acquire external visual images of the low-altitude aircraft to be detected;

[0010] The external visual image of the low-altitude aircraft to be detected is input into the wire detection model without the regional rebalancing branch module to obtain a mask image with wire boundaries corresponding to the external visual image of the low-altitude aircraft to be detected.

[0011] Optionally, the segmentation head network is a depth-wise separable convolution.

[0012] Optionally, training a regional rebalancing convolutional neural network based on slender target adaptation according to the low-altitude airspace wire dataset to obtain a wire detection model specifically includes:

[0013] Using a data enhancement algorithm to perform data enhancement processing on the low-altitude airspace power line dataset to obtain an enhanced dataset;

[0014] With the goal of minimizing the loss function value, the enhanced dataset is used to train the regional rebalancing convolutional neural network based on slender target adaptation to obtain the wire detection model.

[0015] Optionally, the HRNet network is HRNet-w48.

[0016] Optionally, the loss function is:

[0017] in represents the loss function, represents the area loss, represents pixel cross entropy loss, λ represents The coefficient of It is calculated based on the output of the regional rebalancing branch module and the mask label. Calculated based on the output of the segmentation head network and the mask labels.

[0018] In a second aspect, the present application provides a low-altitude airspace wire detection device, comprising:

[0019] An acquisition module is used to acquire a low-altitude airspace wire data set; the low-altitude airspace wire data set includes a plurality of samples, each sample is an external view image of a sample low-altitude aircraft and a corresponding mask label; the external view image includes wires; the mask label is a mask image with a wire boundary;

[0020] A training module is used to train a regional rebalancing convolutional neural network based on slender targets according to the low-altitude airspace wire data set to obtain a wire detection model, and the wire detection model is used to detect wires in low-altitude airspace; the regional rebalancing convolutional neural network based on slender targets includes a backbone network and a segmentation head connected in sequence; the backbone network is an HRNet network in which the 3x3 standard convolution in the Bottleneck module is a dynamic snake convolution; the segmentation head includes a segmentation head network and a regional rebalancing branch module; the first input end of the regional rebalancing branch module and the input end of the segmentation head network are both connected to the output end of the backbone network, and the second input end of the regional rebalancing branch module is used to input a mask label.

[0021] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described low-altitude airspace wire detection methods.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described low-altitude airspace wire detection methods.

[0023] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned low-altitude airspace wire detection methods.

[0024] According to the specific embodiments provided in this application, this application has the following technical effects:

[0025] The present application provides a method, device, equipment, medium and product for low-altitude airspace wire detection. The present application uses HRNet integrated with DSConv in the regional rebalancing convolutional neural network based on slender target adaptation, which ensures high resolution of the image while paying more attention to the characteristics of slender targets, thereby improving the accuracy of wire detection. The regional rebalancing branch module is used to solve the imbalance problem of positive and negative samples, improve accuracy, reduce missed detection rate, improve the accuracy of low-altitude airspace wire detection, and reduce the risk of collision with the wire during low-altitude operations of aircraft. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 A flow chart of a low-altitude airspace wire detection method provided in one embodiment of the present application;

[0028] Figure 2 A flow chart of using a wire detection model to perform low-altitude airspace wire detection according to an embodiment of the present application;

[0029] Figure 3 This is a schematic diagram of the specific principle of the low-altitude airspace wire detection process;

[0030] Figure 4 It is the first data schematic diagram of the low-altitude airspace power line data set;

[0031] Figure 5 It is a second data schematic diagram of the low-altitude airspace power line data set;

[0032] Figure 6 It is the third data schematic diagram of the low-altitude airspace power line data set;

[0033] Figure 7 Schematic diagram of the regional rebalancing convolutional neural network structure based on slender target adaptation;

[0034] Figure 8 It is a schematic diagram of the structure of the backbone network in the wire detection model;

[0035] Fig. 9 It is a schematic diagram of the structure of the segmentation head in the wire detection model;

[0036] Fig.10 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0038] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0039] In an exemplary embodiment, Figure 1 and Figure 3 As shown, a method for detecting electric wires in low-altitude airspace is provided, comprising the following steps, wherein:

[0040] Step 201: Obtain a low-altitude airspace wire dataset; the low-altitude airspace wire dataset includes multiple samples, each sample is an external view image of a sample low-altitude aircraft and a corresponding mask label (real mask); the external view image includes wires; the mask label is a mask image with wire boundaries. Specifically, a low-altitude airspace wire dataset is obtained using drones and general aviation helicopters. Part of the data in the low-altitude airspace wire dataset is as follows Figures 4 to 6 As shown. When it comes to deep learning models, datasets play a vital role, and high-quality datasets that reflect real-world scenarios will greatly improve the accuracy of deep learning models. Therefore, the low-altitude airspace wire dataset to be used should accurately reflect the real scenario of low-altitude aircraft operations.

[0041] Step 202: According to the low-altitude airspace wire data set, the regional rebalancing convolutional neural network based on slender target adaptation is trained to obtain a wire detection model, and the wire detection model is used for low-altitude airspace wire detection; the regional rebalancing convolutional neural network based on slender target adaptation includes a backbone network and a segmentation head connected in sequence; the backbone network is an HRNet network in which the 3x3 standard convolution in the Bottleneck module is a dynamic snake convolution (Depthwise Separable Convolution, DSConv); the segmentation head includes a segmentation head network and a regional rebalancing branch module; the first input end of the regional rebalancing branch module and the input end of the segmentation head network are both connected to the output end of the backbone network, and the second input end of the regional rebalancing branch module is used to input a mask label. Specifically, the regional rebalancing branch module includes: a cross multiplication operation and a classifier; the cross multiplication operation is used to perform a cross multiplication operation on the output of the backbone network and the mask label, and then the result of the cross multiplication operation is input into the classifier.

[0042] In the above steps 201 to 202, HRNet is used to extract hierarchical features while ensuring high resolution of the image to obtain a feature map. DSConv is used for the slender features of the adaptive wires. The class imbalance problem is alleviated by the regional rebalancing branch module. The regional rebalancing branch module encourages the feature map to be located in a more balanced regional classification space and rebalances at the regional level rather than the pixel level. In the regional rebalancing branch module, the pixel features are cross-multiplied ( Figure 7 and Fig. 9 In the ) are averaged to group pixels belonging to the same category into regional features. The extracted regional features are then input into the regional classifier (i.e., the classifier mentioned above), and the long-tail image classification technology is borrowed to enhance rebalancing to solve the regional imbalance problem. At the same time, there is no additional testing cost because the regional rebalancing branch module is deleted after training is completed.

[0043] The feature encoding process uses HRNet integrated with DSConv to ensure high image resolution while paying more attention to the features of slender targets and improving the accuracy of wire detection. The feature decoding process uses the regional rebalancing branch module to solve the imbalance problem of positive and negative samples, improve accuracy and reduce missed detection rate.

[0044] In an exemplary embodiment, Figure 2 As shown, the wire detection model is used to detect wires in low-altitude airspace, specifically including:

[0045] Acquire external visual images of the low-altitude aircraft to be detected.

[0046] The external visual image of the low-altitude aircraft to be detected is input into the wire detection model without the regional rebalancing branch module to obtain a mask image with wire boundaries corresponding to the external visual image of the low-altitude aircraft to be detected.

[0047] In an exemplary embodiment, the segmentation head network is a lightweight network segmentation head module, specifically a lightweight FCN, i.e., a depth-separable convolution. The use of a lightweight network segmentation head module can ensure a faster detection speed. FCN can accept input images of any size, use bilinear interpolation to initialize the parameters of the deconvolution layer, upsample the feature map output by the backbone network, and restore it to the same size as the input image, so that a prediction can be generated for each pixel, while retaining the spatial information in the original input image, and finally perform pixel-by-pixel classification on the upsampled feature map.

[0048] In an exemplary embodiment, a wire detection model is obtained by training a regional rebalancing convolutional neural network based on slender target adaptation according to the low-altitude airspace wire dataset, specifically including:

[0049] The data enhancement algorithm is used to perform data enhancement processing on the low-altitude airspace wire dataset to obtain an enhanced dataset. Specifically, the data enhancement library Albumentations is used to process the low-altitude airspace wire dataset to obtain an enhanced dataset. The data enhancement methods are divided into pixel-level transformation and space-level transformation. The pixel-level transformation will only change the input image, such as: blur, color jitter, image compression, Gaussian noise, inversion, normalization, random rain, random brightness contrast, sharpening, hue saturation value, etc.; the space-level transformation acts on the image and mask at the same time, such as: horizontal rotation, vertical rotation, rotation of 90 degrees, center flip, row and column transposition, scale scaling, etc.

[0050] With the goal of minimizing the loss function value, the enhanced dataset is used to train the regional rebalancing convolutional neural network based on slender target adaptation to obtain the wire detection model.

[0051] In an exemplary embodiment, the loss function is:

[0052] in represents the loss function, represents the area loss, represents pixel cross entropy loss, λ represents The coefficient can be taken as 0.5. It is calculated based on the output of the regional rebalancing branch module (the external view map in the enhanced dataset is input into the regional rebalancing convolutional neural network based on slender target adaptation) and the mask label. It is calculated based on the output of the segmentation head network (the external view map in the enhanced dataset is input into the regional rebalancing convolutional neural network based on slender target adaptation) and the mask label.

[0053] Specifically, The purpose of this formula is to use ground-truth (X gt ) The region map averages the pixels belonging to the same class, groups the pixels belonging to the same class into regional features, and then inputs the extracted regional features into the region classifier, where D is the enhanced data set, represents the frequency of regions in the i-th category, R represents all extracted regions obtained by the regional rebalancing branch module in the cross product process, and r y is the label mask of region r in the enhanced dataset, r y It represents the area value corresponding to the yth category (the result output by the regional rebalancing branch module), where Y is the label set including background, wires and towers.

[0054] Among them, P(i) is the true probability of the i-th class, which is obtained according to the label mask; Q(i) is the probability of the i-th class predicted by the model, which is the result of the segmentation head network output, and n represents the total number of categories.

[0055] In an exemplary embodiment, the HRNet network is HRNet-w48. Specifically, the present application uses the improved HRNet-w48 as the backbone network to maintain the high resolution of the image while downsampling and minimize the loss of wire features. Figure 7 and Figure 8 As shown in the figure, HRNet has four basic layers, Layer1 to Layer4, with the number of branches increasing in each layer. Each branch first passes through 4 repeatedly stacked convolutional blocks, Bottleneck modules or BasicBlock modules, each module uses 48 channels, and then fuses information at different scales. The output of each branch in the next layer is obtained by fusion of the output of the branch in the previous layer. For example, for the output of the Layer3 downsampled 4x branch, the output of the downsampled 4x branch, the output of the downsampled 8x branch upsampled 2x, and the output of the downsampled 16x branch upsampled 4x are added together and finally obtained through ReLU. The other branches are similar.

[0056] In order to make the model adaptive to thin and long targets such as wires, this application replaces the Bottleneck module in HRNetLayer1 and uses DSConv to replace the original 3x3 standard convolution. Considering that the characteristics of tubular target segmentation are thin and complex, standard convolution and hole convolution cannot adjust the focus area according to the target characteristics, and deformable convolution can learn the region of interest more adaptively. However, for tubular targets, deformable convolution cannot limit the connectivity of the focus area, while DSConv limits the connectivity of the focus area, making it more suitable for wire segmentation scenarios.

[0057] In order to give the convolution kernel more flexibility so that it can focus on the slender geometric features of the target, a deformation offset Δ is introduced, inspired by deformable convolution. However, if the model is completely free to learn the deformation offset, the receptive field tends to deviate from the target, especially when dealing with slender tubular structures. Therefore, DSConv adopts an iterative strategy to select the next position of each target to be processed for observation in turn, thereby ensuring the continuity of attention and not spreading the receptive range too far due to large deformation offsets.

[0058] In dynamic snake convolution, the standard convolution kernel is linearized in both the x-axis and y-axis directions. Consider a convolution kernel of size 9:

[0059] N={(x-1, y-1), (x-1, y),…, (x+1, y+1)}

[0060] Taking the x-axis direction as an example, the specific position of each grid in K is expressed as:

[0061]

[0062] Where c represents the horizontal distance from the center grid. The selection of each grid position Ki±c in the convolution kernel K is an accumulation process. i Initially, the position of the grid away from the center depends on the position of the previous grid: Ki+1 increases the offset Δ={δ|δ∈[-1,1]} relative to Ki. Therefore, the offset needs to be accumulated ∑ to ensure that the convolution kernel conforms to the linear morphology structure.

[0063] This application utilizes a regional rebalancing network that is adaptive to slender targets to improve the accuracy of mask convolutional neural networks in detecting wires in low-altitude airspace, while reducing the missed detection rate of wires while achieving the best balance between detection speed and detection accuracy, significantly improving model performance and reducing the risk of collisions with wires when aircraft are operating at low altitudes.

[0064] The HRNet network architecture in this application continuously performs multi-scale fusion during the downsampling process to ensure high resolution of the image when extracting features and avoid the loss of the slender features of the wires, thereby providing a solid foundation for the precise semantic segmentation task in the regional rebalancing convolutional neural network structure based on slender object adaptation.

[0065] This application uses a Bottleneck module of dynamic snake convolution so that during the downsampling process, the convolution kernel in the residual structure can adaptively deform to fit the slender topological structure, making it easier to capture the slender features of the wires for further classification and positioning.

[0066] After the backbone network extracts the feature map of the image, this application uses the fully connected layer of the lightweight network segmentation head module, uses deep separable convolution to reduce the computational complexity, and then performs pixel-by-pixel classification after upsampling the feature map to the original image size.

[0067] The regional rebalancing branch module of this application belongs to the auxiliary segmentation head, which aggregates pixels within the same mask label into one region, solves the imbalance problem of positive and negative samples from a regional perspective, and improves the accuracy of wire detection. This module only participates in supervision during the model training process and does not introduce additional inference costs.

[0068] Based on the same inventive concept, the embodiment of the present application also provides a low-altitude airspace wire detection device for implementing the low-altitude airspace wire detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more low-altitude airspace wire detection device embodiments provided below can refer to the limitations of the low-altitude airspace wire detection method above, and will not be repeated here.

[0069] In an exemplary embodiment, a low-altitude airspace wire detection device is provided, comprising:

[0070] An acquisition module is used to acquire a low-altitude airspace wire data set; the low-altitude airspace wire data set includes multiple samples, each sample is an external view image of a sample low-altitude aircraft and a corresponding mask label; the external view image includes wires; the mask label is a mask image with wire boundaries.

[0071] A training module is used to train a regional rebalancing convolutional neural network based on slender targets according to the low-altitude airspace wire data set to obtain a wire detection model, and the wire detection model is used to detect wires in low-altitude airspace; the regional rebalancing convolutional neural network based on slender targets includes a backbone network and a segmentation head connected in sequence; the backbone network is an HRNet network in which the 3x3 standard convolution in the Bottleneck module is a dynamic snake convolution; the segmentation head includes a segmentation head network and a regional rebalancing branch module; the first input end of the regional rebalancing branch module and the input end of the segmentation head network are both connected to the output end of the backbone network, and the second input end of the regional rebalancing branch module is used to input a mask label.

[0072] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig.10As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store low-altitude airspace wire detection data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a low-altitude airspace wire detection method is implemented.

[0073] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above-mentioned method embodiments when executing the computer program.

[0074] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0075] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0076] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0077] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0078] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0079] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0080] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for detecting electric wires in low altitude airspace, characterized in that: The low-altitude airspace wire detection method comprises: Acquire a low-altitude airspace wire data set; the low-altitude airspace wire data set includes a plurality of samples, each sample is an external view image of a sample low-altitude aircraft and a corresponding mask label; the external view image includes wires; the mask label is a mask image with a wire boundary; According to the low-altitude airspace wire data set, a regional rebalancing convolutional neural network based on slender target adaptation is trained to obtain a wire detection model, and the wire detection model is used to perform wire detection in the low-altitude airspace; the regional rebalancing convolutional neural network based on slender target adaptation includes a backbone network and a segmentation head connected in sequence; the backbone network is an HRNet network in which the 3x3 standard convolution in the Bottleneck module is a dynamic snake convolution; the segmentation head includes a segmentation head network and a regional rebalancing branch module; the first input end of the regional rebalancing branch module and the input end of the segmentation head network are both connected to the output end of the backbone network, and the second input end of the regional rebalancing branch module is used to input a mask label.

2. The low-altitude airspace wire detection method according to claim 1 is characterized in that: The wire detection model is used to detect wires in low-altitude airspace, specifically including: Acquire external visual images of the low-altitude aircraft to be detected; The external visual image of the low-altitude aircraft to be detected is input into the wire detection model without the regional rebalancing branch module to obtain a mask image with wire boundaries corresponding to the external visual image of the low-altitude aircraft to be detected.

3. The low-altitude airspace wire detection method according to claim 1 is characterized in that: The segmentation head network is a depth-wise separable convolution.

4. The low-altitude airspace wire detection method according to claim 1 is characterized in that: According to the low-altitude airspace wire data set, a regional rebalancing convolutional neural network based on slender target adaptation is trained to obtain a wire detection model, which specifically includes: Using a data enhancement algorithm to perform data enhancement processing on the low-altitude airspace power line dataset to obtain an enhanced dataset; With the goal of minimizing the loss function value, the enhanced dataset is used to train the regional rebalancing convolutional neural network based on slender target adaptation to obtain the wire detection model.

5. The low-altitude airspace wire detection method according to claim 1 is characterized in that: The HRNet network is HRNet-w48.

6. The low-altitude airspace wire detection method according to claim 4 is characterized in that: The loss function is: in represents the loss function, represents the area loss, represents pixel cross entropy loss, λ represents The coefficient of It is calculated based on the output of the regional rebalancing branch module and the mask label. Calculated based on the output of the segmentation head network and the mask labels.

7. A low-altitude airspace wire detection device, characterized in that: The low-altitude airspace wire detection device comprises: An acquisition module is used to acquire a low-altitude airspace wire data set; the low-altitude airspace wire data set includes a plurality of samples, each sample is an external view image of a sample low-altitude aircraft and a corresponding mask label; the external view image includes wires; the mask label is a mask image with a wire boundary; A training module is used to train a regional rebalancing convolutional neural network based on slender targets according to the low-altitude airspace wire data set to obtain a wire detection model, and the wire detection model is used to detect wires in low-altitude airspace; the regional rebalancing convolutional neural network based on slender targets includes a backbone network and a segmentation head connected in sequence; the backbone network is an HRNet network in which the 3x3 standard convolution in the Bottleneck module is a dynamic snake convolution; the segmentation head includes a segmentation head network and a regional rebalancing branch module; the first input end of the regional rebalancing branch module and the input end of the segmentation head network are both connected to the output end of the backbone network, and the second input end of the regional rebalancing branch module is used to input a mask label.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the low-altitude airspace wire detection method described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the low-altitude airspace wire detection method described in any one of claims 1-6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the low-altitude airspace wire detection method described in any one of claims 1-6 is implemented.

Images