A UAV deicing method based on image recognition

Abstract

The present invention discloses a method for deicing a drone based on image recognition, and relates to the technical field of drone deicing. The method comprises: calling an image acquisition component of a target drone to acquire an image of a target deicing area, obtaining an image of the deicing area; using an image feature identifier to perform feature recognition on the deicing area image, obtaining an icing feature set; obtaining a sequence of regional environmental state parameter groups; determining multiple environmental state parameter feature groups; obtaining an environmental state parameter feature group sequence; determining iteratively associated environmental state parameter feature groups; obtaining a target drone deicing parameter set, and controlling the target drone to deicing the target deicing area. The present invention solves the technical problems in the prior art of drone deicing, such as the lack of correlation analysis of environmental states, inaccurate understanding of the actual icing conditions in the deicing area, and poor deicing quality, thereby achieving the technical effect of improving the reliability of drone deicing.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) deicing, and in particular to a UAV deicing method based on image recognition. Background Art

[0002] Currently, drone de-icing operations often rely on fixed paths and preset de-icing parameters, which can easily lead to a disconnect between de-icing strategies and actual conditions. Furthermore, they often lack accurate understanding of the icing conditions in the de-icing area. For example, when faced with uneven ice thickness, the de-icing device's mode and power are not adjusted accordingly, resulting in excessive energy waste in thin ice areas and incomplete de-icing in thick ice areas. Ultimately, this impacts de-icing quality, potentially leaving untreated frozen areas, and can even lead to serious consequences such as excessive energy consumption and low operational efficiency.

[0003] The existing technology has the technical problems of UAV deicing lacking correlation analysis of environmental conditions and inaccurate grasp of the actual icing conditions in the deicing area, resulting in poor deicing quality. Summary of the Invention

[0004] The present application provides a drone deicing method based on image recognition, which is used to solve the technical problems in the existing drone deicing technology that lacks correlation analysis of environmental conditions, has inaccurate understanding of the actual icing conditions in the deicing area, and leads to poor deicing quality.

[0005] In view of the above problems, the present application provides a method for deicing a drone based on image recognition, the method comprising:

[0006] Invoking an image acquisition component of the target UAV to acquire an image of the target deicing area to obtain an image of the deicing area, and using an image feature identifier to perform feature recognition on the deicing area image to obtain an icing feature set;

[0007] Invoking the environment acquisition component of the target UAV to continuously monitor the environmental status of the target deicing area within a preset monitoring window to obtain a sequence of regional environmental status parameter groups, wherein each regional environmental status parameter group includes a plurality of regional environmental status parameters;

[0008] Constructing multiple asynchronous recognition network layers to perform parameter feature analysis on the regional environmental state parameter group sequence to determine multiple environmental state parameter feature groups, wherein the multiple asynchronous recognition network layers include multiple asynchronous receptive fields;

[0009] Serializing the plurality of environmental state parameter feature groups based on the sizes of the plurality of asynchronous receptive fields to obtain an environmental state parameter feature group sequence;

[0010] Performing iterative correlation interaction analysis on the environmental state parameter feature group sequence in order from front to back to determine an iterative correlation environmental state parameter feature group;

[0011] Based on the icing feature set and the iteratively associated environmental state parameter feature group, UAV deicing parameter identification is performed, a target UAV deicing parameter set is obtained, and the target UAV is controlled to de-ice the target deicing area according to the target UAV deicing parameter set.

[0012] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0013] This application calls the target drone's image acquisition component to acquire an image of the target deicing area, obtaining an image of the deicing area. It then uses an image feature identifier to perform feature recognition on the deicing area image to obtain an icing feature set. It then calls the target drone's environment acquisition component to continuously monitor the target deicing area's environmental status within a preset monitoring window, obtaining a sequence of regional environmental state parameter groups, each of which includes multiple regional environmental state parameters. Furthermore, multiple asynchronous recognition network layers are constructed to perform parameter feature analysis on the sequence of regional environmental state parameter groups to determine multiple environmental state parameter feature groups. The multiple asynchronous recognition network layers include multiple asynchronous receptive fields. The multiple environmental state parameter feature groups are serialized based on the sizes of the multiple asynchronous receptive fields to obtain a sequence of environmental state parameter feature groups. It then performs iterative correlation interaction analysis on the sequence of environmental state parameter feature groups in a forward-to-back order to determine an iterative correlation environmental state parameter feature group. It then performs drone deicing parameter recognition based on the icing feature set and the iterative correlation environmental state parameter feature group to obtain a target drone deicing parameter set. The target drone is then controlled to de-ice the target deicing area based on the target drone deicing parameter set. This achieves the technical effect of improving drone deicing quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 A schematic diagram of a flow chart of a UAV de-icing method based on image recognition provided in an embodiment of the present application;

[0016] Figure 2 A schematic diagram of a process for determining an iteratively associated environmental state parameter feature group in an image recognition-based drone de-icing method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] This application provides a drone deicing method based on image recognition, which is used to solve the technical problems in the existing drone deicing technology that lacks correlation analysis of environmental conditions, has inaccurate understanding of the actual icing conditions in the deicing area, and leads to poor deicing quality.

[0018] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0019] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0020] Examples, such as Figure 1 As shown, the present application provides a method for deicing a drone based on image recognition, wherein the method includes:

[0021] S100: Calling an image acquisition component of a target UAV to acquire an image of a target deicing area to obtain an image of the deicing area, and performing feature recognition on the deicing area image using an image feature recognizer to obtain an icing feature set;

[0022] Furthermore, the image acquisition component of the target drone is called to acquire an image of the target deicing area to obtain an image of the deicing area, and an image feature identifier is used to perform feature recognition on the deicing area image to obtain an icing feature set. In this embodiment of the application, step S100 further includes:

[0023] Obtaining a preset flight path of the target UAV;

[0024] The target UAV collects images of the target deicing area according to the preset flight altitude and the preset flight speed and the preset flight path to obtain an initial deicing area image;

[0025] The initial deicing area image is subjected to histogram equalization processing, and the icing sub-areas of the processed initial deicing area image are identified using a segmentation algorithm to obtain the deicing area image.

[0026] Furthermore, step S100 in the embodiment of the present application further includes:

[0027] Counting the number of pixels of each grayscale value in the initial deicing area image to obtain a grayscale histogram;

[0028] Pixel values ​​of the initial deicing area image are redistributed based on the grayscale histogram to obtain the deicing area image.

[0029] In one possible embodiment, the target drone is any type of drone used for de-icing, employing methods such as hot air blasting, infrared heating, low-temperature liquid de-icing spray, or mechanical vibration de-icing. The target de-icing area is any area requiring de-icing after ice formation. The image acquisition component is a device installed on the target drone for stable image acquisition, including a high-definition camera, an RGB camera, an infrared camera, and a stabilization system (such as a three-axis gimbal).

[0030] The image acquisition component is used to capture images of the target deicing area, obtaining a deicing area image that reflects the icing conditions in the target deicing area. Furthermore, a trained image feature identifier is used to perform feature recognition on the deicing area image, extracting features reflecting the degree of icing, such as ice thickness, shape, texture, and area, to obtain the icing feature set. By acquiring the icing feature set, the technical effect of providing data support for subsequent reliable and accurate UAV deicing is achieved.

[0031] In one embodiment, information such as the geographic scope of the target deicing area, obstacle distribution (e.g., buildings, trees, etc.), and drone performance parameters (e.g., flight time, flight altitude) is obtained. Based on this information, a skilled person in the art determines the path along which the target drone will capture images of the target deicing area, thereby obtaining the preset flight path. Preferably, a grid-covered path planning method is employed, dividing the target area into several sub-areas, each corresponding to a flight path segment. Overlapping areas are also provided in the path design to avoid blind spots in image capture.

[0032] Preferably, those skilled in the art determine the flight altitude and speed of the target drone during image acquisition based on the above information. For example, the preset flight altitude is adjusted by those skilled in the art based on the camera's field of view and the size of the target area, such as 20 to 50 meters. The preset flight speed is set by those skilled in the art after balancing image clarity and acquisition efficiency, such as 1 to 2 m / s.

[0033] Optionally, the planned preset flight path is uploaded to the drone navigation system in the form of a GPS coordinate sequence. The target drone uses the image acquisition component to capture images of the target deicing area according to the navigation path to obtain the initial set of images of the deicing area to be spliced. Preferably, the three-axis gimbal is activated to ensure the stability of the camera and prevent flight jitter from affecting the image clarity. Each initial image of the deicing area to be spliced ​​is associated with corresponding geographic coordinates (GPS information), timestamp and flight altitude. The initial set of images of the deicing area to be spliced ​​is spliced ​​according to the geographic coordinates to obtain the initial deicing area image.

[0034] Furthermore, to improve the contrast of the image, the initial deicing area image is subjected to histogram equalization processing to stretch the contrast between low-brightness and high-brightness areas and enhance the visibility of the iced area. Optionally, the input format is an RGB image or a grayscale image, and the number of pixels for each grayscale value in the image is counted to generate a grayscale histogram. The grayscale histogram is used to analyze the image brightness distribution. For example, if the histogram values ​​are concentrated in the low grayscale range, it means that the image is dark overall; if the histogram values ​​are concentrated in the high grayscale range, it means that the image is bright overall; if the histogram distribution is uneven, the image contrast is low.

[0035] Based on the grayscale histogram, the number of pixels at each grayscale value is gradually accumulated to calculate the cumulative distribution function (CDF). The CDF represents the cumulative number of pixels from the lowest grayscale value to the current grayscale value. Furthermore, the CDF is normalized to a range of 0 to 1 to facilitate subsequent calculations. Based on the CDF, pixel values ​​are redistributed to achieve a more uniform distribution of grayscale values. Thus, the corresponding cumulative distribution value for each grayscale value is linearly mapped to a range of 0 to 255, resulting in a new grayscale value. This mapping relationship is recorded and a pixel value mapping table is generated. Each pixel in the image is traversed, its original grayscale value is read, and then, according to the pixel value mapping table, the original grayscale value is replaced with the new grayscale value. As a result, the processed image has a wider grayscale value distribution and enhanced contrast. The redistributed pixel values ​​are saved as a new image to obtain the deicing area image. This significantly enhances ice features in the initial deicing area image that may have been obscured by insufficient lighting or contrast, providing reliable data support for subsequent ice area identification.

[0036] In one embodiment, based on a segmentation algorithm, such as a threshold segmentation method, the optimal global grayscale threshold of the initial deicing area image is automatically calculated, and the initial deicing area image is divided into an icing sub-area and a non-icing sub-area, so that the obtained image of the position of the icing sub-area in the initial deicing area image is used as the deicing area image.

[0037] Optionally, multiple sample deicing area images and multiple sample icing feature sets are obtained as training data. This training data is used to conduct supervised training on a framework built based on a feedforward neural network, learning the mapping relationship between the deicing area images and the icing feature sets to obtain the icing feature set. The icing feature set includes multidimensional feature data characterizing the icing area, including location features, area features, thickness features, shape features, and so on. By obtaining this icing feature set, the technical effect of laying the foundation for reliable deicing of subsequent drones is achieved.

[0038] S200: Invoking the environment acquisition component of the target UAV to continuously monitor the environmental status of the target deicing area within a preset monitoring window to obtain a sequence of regional environmental status parameter groups, wherein each regional environmental status parameter group includes a plurality of regional environmental status parameters;

[0039] In one possible embodiment, first, ensure that the environmental collection components (such as temperature sensors, humidity sensors, anemometers, and infrared cameras) on the drone are functioning properly. Then, call the initialization program for the environmental collection components to set the sampling frequency and range of each collection device. When communication between the environmental collection components and the drone's main control system and ground station meets the requirements, collect the data collected by each sensor within the preset monitoring window to obtain the regional environmental state parameter group sequence. The regional environmental state parameter group sequence reflects how the environmental state of the target deicing area changes over time within the preset monitoring window.

[0040] Optionally, each regional environmental state parameter group reflects the environmental conditions of the target deicing area at a specific point in time within a preset monitoring window, including parameters such as temperature, wind speed, and humidity. By obtaining a sequence of these regional environmental state parameter groups, the technical effect of providing data support for subsequent refined analysis of regional environmental characteristics is achieved.

[0041] S300: Constructing multiple asynchronous recognition network layers to perform parameter feature analysis on the regional environmental state parameter group sequence to determine multiple environmental state parameter feature groups, wherein the multiple asynchronous recognition network layers include multiple asynchronous receptive fields;

[0042] Furthermore, multiple asynchronous recognition network layers are constructed to perform parameter feature analysis on the regional environmental state parameter group sequence to determine multiple environmental state parameter feature groups, wherein the multiple asynchronous recognition network layers include multiple asynchronous receptive fields. In this embodiment of the application, step S300 further includes:

[0043] Retrieving historical environmental change information of the target deicing area using the data types of the multiple regional environmental state parameters as an index to determine multiple parameter change period sets;

[0044] Calculating the mean of each of the plurality of parameter change period sets to obtain a plurality of parameter change period means;

[0045] Calculating the sum of the mean values ​​of the multiple parameter change periods divided by the mean values ​​of the multiple parameter change periods to obtain multiple variation coefficients;

[0046] Multiplying the multiple variation coefficients by a preset receptive field to obtain multiple asynchronous receptive fields, wherein the asynchronous receptive field is a feature extraction bandwidth of the asynchronous recognition network layer for the regional environmental state parameter group sequence;

[0047] The multiple asynchronous recognition network layers are constructed based on the multiple asynchronous receptive fields.

[0048] Furthermore, step S300 in the embodiment of the present application further includes:

[0049] Setting convolution kernel parameters and time windows for the initial convolutional neural network layers according to the multiple asynchronous receptive fields to obtain multiple initial asynchronous recognition network layers with completed parameter configurations;

[0050] A plurality of sample data sets are respectively obtained to perform supervised training on the plurality of initial asynchronous recognition network layers until the training converges, thereby obtaining the plurality of asynchronous recognition network layers that have completed training.

[0051] In one possible embodiment, the regional environmental state parameter group sequence reflects the environmental state changes of the target deicing area within a preset monitoring window. By constructing multiple asynchronous recognition network layers, parameter analysis of different scales is performed on the regional environmental state parameter group sequence, and the environmental state changes are deeply analyzed to obtain the multiple environmental state parameter feature groups. The multiple asynchronous recognition network layers include multiple asynchronous receptive fields. The network layers constructed with different receptive fields have different data extraction ranges. The larger the receptive field, the greater the breadth of data that can be identified. The smaller the receptive field, the more sensitive the recognition of data changes over time. By obtaining the multiple environmental state parameter feature groups, the technical effect of providing reliable data for the subsequent interactive analysis of features obtained from different receptive fields is achieved.

[0052] Optionally, the historical environmental change information includes environmental changes in the target deicing area over a historical period, including the time periods of changes in various environmental state parameters. Exemplarily, a temperature change time set is obtained based on the time periods at which temperature changes in the historical environmental change information exceed a preset temperature threshold. The multiple parameter change period sets are obtained by searching the historical environmental change information for the target deicing area using the data types of the multiple regional environmental state parameters as indexes. The multiple parameter change period sets reflect the change periods of multiple environmental state parameters in the target deicing area over a historical period.

[0053] Then, the mean values ​​of the multiple parameter change period sets are calculated to obtain multiple parameter change period means, wherein the multiple parameter change period means reflect the average change period of the multiple environmental state parameters. The ratios of the multiple parameter change period means to the sum of the multiple parameter change period means are respectively used as the multiple variation coefficients. The multiple variation coefficients reflect the fluctuations of the multiple environmental state parameters over a historical period. The larger the variation coefficient, the greater the degree of fluctuation of the corresponding environmental state parameter.

[0054] Optionally, a preset receptive field pre-set by a person skilled in the art is obtained. The preset receptive field is a preset maximum feature extraction bandwidth. Then, a plurality of variation coefficients are multiplied by the preset receptive field to obtain a plurality of asynchronous receptive fields, each of which corresponds to an environmental state parameter. The greater the degree of parameter fluctuation, the larger the data extraction bandwidth is required to analyze the overall data situation, and the smaller the degree of parameter fluctuation, the smaller the data extraction bandwidth is required to capture the fine fluctuation of the data. The asynchronous receptive field is the feature extraction bandwidth of the asynchronous recognition network layer for the sequence of environmental state parameter groups in the region. In other words, the asynchronous receptive field refers to the data range or time window covered by the asynchronous recognition network layer when performing feature extraction on the sequence of environmental state parameter groups within a specific time period.

[0055] Therefore, by obtaining different asynchronous receptive fields, when extracting features from the sequence of regional environmental state parameter groups, the feature extraction conditions of different environmental state parameters can be considered separately, thereby ensuring the comprehensiveness of the features of the multiple environmental state parameter feature groups extracted. Each environmental state parameter feature group corresponds to an asynchronous recognition network layer constructed using an asynchronous receptive field.

[0056] In one embodiment, the asynchronous receptive field defines the time window and data range covered when the network layer processes a sequence of environmental state parameter groups. In convolutional neural networks (CNNs), these receptive fields directly affect the time window setting and the size of the convolution kernel. The time window refers to the range of input data processed by the network layer at one time (i.e., the length of the sequence). The time window size is consistent with the asynchronous receptive field, reflecting the range of attention of the network layer to changes in input parameters. The size (length or width) of the convolution kernel matches the receptive field size to ensure that key features are extracted within a specific time range.

[0057] A person skilled in the art sets the time window and the convolution kernel parameters of the initial convolutional neural network layer according to the sizes of the multiple asynchronous receptive fields. Preferably, different time windows are assigned to each network layer according to the sizes of the multiple asynchronous receptive fields, and the size of each time window is directly equal to the value of an asynchronous receptive field. Exemplarily, if the asynchronous receptive field is 16, the time window is 16 time points. If the asynchronous receptive field is 8, the time window is 8 time points. The length of the convolution kernel is equal to or slightly smaller than the receptive field to capture the feature pattern within the receptive field. According to the parameter complexity and model requirements, multiple convolution kernels are set to extract different features.

[0058] A plurality of sample data sets are extracted from the historical data for training the initial network layer. Each sample data set includes a plurality of sample area environment state parameter group sequences and a plurality of sample environment state parameter feature groups of corresponding types.

[0059] Furthermore, the multiple sample data sets were divided into training, validation, and test sets. This ensured that the data covered a variety of environmental variations and improved the model's generalization capabilities. Each initial asynchronous recognition network layer was trained using supervised learning methods.

[0060] Input multiple sample data sets into the corresponding multiple initial asynchronous recognition network layers respectively. Extract features based on the convolution operation and calculate the output value. Adjust the network layer parameters (such as convolution kernel weights) through the error back propagation algorithm (such as gradient descent). After repeated iterations, the feature extraction ability of the network layer is gradually optimized. The mean square error is selected as the loss function. When the loss function value drops to a preset threshold, or the training error remains stable in several consecutive iterations, the network layer training is considered to converge, and the multiple asynchronous recognition network layers that have completed training are obtained. Preferably, each asynchronous recognition network layer is trained separately without interfering with each other.

[0061] Optionally, parameter feature extraction is performed on the sequence of regional environmental state parameter groups using the multiple asynchronous recognition network layers that have been trained to obtain the multiple environmental state parameter feature groups. Each environmental state parameter feature group includes the variation characteristics of multiple environmental state parameters obtained by analyzing an asynchronous recognition network layer constructed with an asynchronous receptive field within a preset monitoring window corresponding to the sequence of regional environmental state parameter groups. By utilizing the multiple asynchronous recognition network layers to extract features from multiple environmental state parameters at different scales, high-quality feature data is provided for subsequent analysis.

[0062] S400: Serializing the plurality of environmental state parameter feature groups based on the sizes of the plurality of asynchronous receptive fields to obtain an environmental state parameter feature group sequence;

[0063] S500: performing iterative correlation interaction analysis on the sequence of environmental state parameter feature groups in order from front to back to determine an iterative correlation environmental state parameter feature group;

[0064] Further, such as Figure 2 As shown, the environmental state parameter feature group sequence is subjected to iterative correlation interaction analysis in order from front to back to determine the iterative correlation environmental state parameter feature group. In this embodiment of the application, step S500 further includes:

[0065] Extracting a first environmental state parameter feature group and a second environmental state feature group in sequence from the environmental state parameter feature group sequence;

[0066] Performing iterative correlation and interaction analysis on the first environmental state parameter feature group and the second environmental state parameter feature group to determine a first correlated environmental state parameter feature group;

[0067] Performing iterative correlation and interaction analysis on the first associated environmental state parameter feature group and the third environmental state parameter feature group of the environmental state parameter feature group sequence to determine a second associated environmental state parameter feature group;

[0068] An iterative correlation interaction analysis is performed on the n-1th associated environmental state parameter feature group and the nth environmental state parameter feature group of the environmental state parameter feature group sequence to determine the iteratively associated environmental state parameter feature group, wherein n is the number of environmental state parameter feature group sequences in the environmental state parameter feature group sequence, and n is an integer greater than or equal to 1.

[0069] In a possible embodiment, each environmental state parameter feature group corresponds to an asynchronous receptive field. According to the size of the corresponding asynchronous receptive field, the corresponding environmental state parameter feature groups are sorted in order from small to large of the asynchronous receptive field to obtain the environmental state parameter feature group sequence.

[0070] In one possible embodiment, to integrate environmental state parameter features extracted at different scales, the sequence of environmental state parameter feature groups is subjected to an iterative correlation interaction analysis in a forward-to-back order. The interaction relationship between adjacent environmental state parameter feature groups is analyzed to determine an iterative correlation environmental state parameter feature group. The iterative correlation environmental state parameter feature group integrates the environmental conditions reflected by the environmental state parameter feature groups at each scale, reflecting the environmental state of the target UAV during the de-icing operation within the preset monitoring window.

[0071] In one embodiment, a first environmental state parameter feature group and a second environmental state parameter feature group are sequentially extracted from the sequence of environmental state parameter feature groups. For example, the first environmental state parameter feature group may be (temperature: -5°, humidity: 80°, wind speed: 5°), and the second environmental state parameter feature group may be (temperature: -4.8°, humidity: 81°, wind speed: 4.8°). An iterative correlation interaction analysis is performed on the first environmental state parameter feature group and the second environmental state parameter feature group to analyze the similarity between the same environmental state parameters, thereby determining the first correlated environmental state parameter feature group that includes the development trends of different environmental state parameters and the characteristics of different environmental state parameters.

[0072] Based on the same acquisition principle as that for obtaining the first associated environmental state parameter feature group, an iterative association interaction analysis is performed on the first associated environmental state parameter feature group and the third environmental state parameter feature group in the environmental state parameter feature group sequence to determine a second associated environmental state parameter feature group. Based on the same acquisition principle as that for obtaining the first associated environmental state parameter feature group, an iterative association interaction analysis is performed on the (n-1)th associated environmental state parameter feature group and the nth environmental state parameter feature group in the environmental state parameter feature group sequence to determine the iteratively associated environmental state parameter feature group, where n is the number of environmental state parameter feature group sequences in the environmental state parameter feature group sequence, and n is an integer greater than or equal to 1.

[0073] Furthermore, step S500 in the embodiment of the present application further includes:

[0074] Calculating the similarity of features corresponding to the same environmental state parameters in the first environmental state parameter feature group and the second environmental state parameter feature group to obtain a first associated similarity group;

[0075] performing intra-group interaction matrix identification on the first association similarity group to determine a first association interaction matrix;

[0076] A convolution calculation is performed on the first association interaction matrix and the second environmental state feature group to determine a first association environmental state parameter feature group.

[0077] Furthermore, step S500 in the embodiment of the present application further includes:

[0078] Obtain an intra-group interaction normalization processing formula, wherein the intra-group interaction normalization processing formula is:

[0079]

[0080] Among them, S[f(x i ,y i )] is the normalized value of the i-th association similarity in the first association similarity group, f(x i,y i ) is the i-th association similarity in the first association similarity group, x i is the first environmental state parameter feature of the first environmental state parameter feature group, y i is the i-th second environmental state parameter feature of the same type as the i-th first environmental state parameter in the second environmental state parameter group, e is the base of the natural logarithm, m is the total number of association similarities in the first association similarity group, and m is an integer greater than or equal to 1;

[0081] The association similarities in the first association similarity group are respectively input into the intra-group interaction normalization processing formula for normalization processing, and the processing results are embedded in a matrix to obtain the first association interaction matrix.

[0082] In one embodiment, the cosine similarity calculation formula is used to calculate the similarity of the corresponding features of the same environmental state parameters in the first environmental state parameter feature group and the second environmental state parameter feature group to obtain a first association similarity group. The first association similarity group reflects the degree of similarity between the first environmental state parameter feature group and the second environmental state parameter feature group. Furthermore, the association similarities in the first association similarity group are normalized using the intra-group interaction normalization processing formula, and the processed normalized values ​​are embedded in a matrix to obtain the first association interaction matrix. The first association interaction matrix reflects the strength of association between the first environmental state parameter feature group and the second environmental state parameter feature group. Using the first association interaction matrix can avoid data redundancy when performing association interaction analysis on adjacent environmental state parameter feature groups, thereby improving data processing efficiency.

[0083] The first correlation interaction matrix and the second environmental state feature set are then fed into a graph convolutional network for convolutional computation, fusing information at different scales and outputting a first correlation environmental state parameter feature set. This interaction of information at different scales yields an enhanced environmental state parameter feature set containing more trend information, better capturing environmental state changes and providing a robust analytical data foundation for effectively mitigating environmental impacts on UAV de-icing.

[0084] S600: Identify UAV deicing parameters based on the icing feature set and the iteratively associated environmental state parameter feature group, obtain a target UAV deicing parameter set, and control the target UAV to de-ice the target deicing area according to the target UAV deicing parameter set.

[0085] In an embodiment of the present application, the icing feature set reflects the degree of icing in the target deicing area, and the iteratively correlated environmental state parameter feature group reflects the changing environmental trends for UAV deicing. By using a parameter identifier to identify the icing feature set and the iteratively correlated environmental state parameter feature group, the target UAV deicing parameter set is obtained. Furthermore, the target UAV deicing parameter set is transmitted to the control unit of the target UAV, controlling the target UAV to perform deicing operations on the target deicing area. This achieves the technical effect of improving the reliability of UAV deicing.

[0086] Optionally, multiple historical icing feature sets, multiple historical iteratively associated environmental state parameter feature groups, and multiple historical target UAV deicing parameter sets are obtained as training data sets. The training data is used to perform supervised training on a framework built based on a feedforward neural network. During training, the mapping relationship between the icing feature sets and the iteratively associated environmental state parameter feature groups and the target UAV deicing parameter sets is learned until the training converges, thereby obtaining the trained parameter identifier. The target UAV deicing parameter set includes parameters such as heating intensity, heating duration, mechanical vibration frequency, mechanical vibration amplitude, injection pressure, and injection flow rate.

[0087] In summary, the embodiments of the present application have at least the following technical effects:

[0088] 1. This application utilizes an image acquisition component to capture high-resolution images of the target deicing area. An image feature identifier accurately identifies the location, area, thickness, and other features of the icing area, generating an icing feature set. This achieves the technical effect of enabling drones to perform precise operations within actual icing areas.

[0089] 2. This application combines environmental status monitoring data with multiple asynchronous recognition network layers to perform multi-dimensional analysis of the data, grasp the trend of environmental changes, and achieve the technical effect of reducing the impact of environmental changes on the de-icing capability of drones, thereby ensuring the accuracy and reliability of the de-icing effect.

[0090] 3. By identifying UAV de-icing parameters based on the icing feature set and the iteratively associated environmental state parameter feature group, a target UAV de-icing parameter set is obtained, and the target UAV is controlled to de-ice the target de-icing area based on the target UAV de-icing parameter set, thereby achieving the technical effect of grasping the actual de-icing situation and then adjusting the UAV's working mode, thereby avoiding excessive de-icing or inefficient de-icing.

[0091] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0093] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A UAV deicing method based on image recognition, characterized in that: The method comprises: Invoking an image acquisition component of the target UAV to acquire an image of the target deicing area to obtain an image of the deicing area, and using an image feature identifier to perform feature recognition on the deicing area image to obtain an icing feature set; Invoking the environment acquisition component of the target UAV to continuously monitor the environmental status of the target deicing area within a preset monitoring window to obtain a sequence of regional environmental status parameter groups, wherein each regional environmental status parameter group includes a plurality of regional environmental status parameters; Constructing multiple asynchronous recognition network layers to perform parameter feature analysis on the regional environmental state parameter group sequence to determine multiple environmental state parameter feature groups, wherein the multiple asynchronous recognition network layers include multiple asynchronous receptive fields; Serializing the plurality of environmental state parameter feature groups based on the sizes of the plurality of asynchronous receptive fields to obtain an environmental state parameter feature group sequence; Performing iterative correlation interaction analysis on the environmental state parameter feature group sequence in order from front to back to determine an iterative correlation environmental state parameter feature group; performing UAV deicing parameter identification based on the icing feature set and the iteratively associated environmental state parameter feature group, obtaining a target UAV deicing parameter set, and controlling the target UAV to de-ice the target deicing area according to the target UAV deicing parameter set; Wherein, multiple asynchronous recognition network layers are constructed to perform parameter feature analysis on the regional environmental state parameter group sequence to determine multiple environmental state parameter feature groups, wherein the multiple asynchronous recognition network layers include multiple asynchronous receptive fields, including: Retrieving historical environmental change information of the target deicing area using the data types of the multiple regional environmental state parameters as an index to determine multiple parameter change period sets; Calculating the mean of each of the plurality of parameter change period sets to obtain a plurality of parameter change period means; Calculating the sum of the mean values ​​of the multiple parameter change periods divided by the mean values ​​of the multiple parameter change periods to obtain multiple variation coefficients; Multiplying the multiple variation coefficients by a preset receptive field to obtain multiple asynchronous receptive fields, wherein the asynchronous receptive field is a feature extraction bandwidth of the asynchronous recognition network layer for the regional environmental state parameter group sequence; The multiple asynchronous recognition network layers are constructed based on the multiple asynchronous receptive fields.

2. The method for deicing a drone based on image recognition according to claim 1, characterized in that: Calling the image acquisition component of the target UAV to acquire an image of the target deicing area to obtain an image of the deicing area, and using an image feature identifier to perform feature recognition on the deicing area image to obtain an icing feature set, including: Obtaining a preset flight path of the target UAV; The target UAV collects images of the target deicing area according to the preset flight altitude and the preset flight speed and the preset flight path to obtain an initial deicing area image; The initial deicing area image is subjected to histogram equalization processing, and the icing sub-areas of the processed initial deicing area image are identified using a segmentation algorithm to obtain the deicing area image.

3. The method for deicing a drone based on image recognition according to claim 2, characterized in that: include: Counting the number of pixels of each grayscale value in the initial deicing area image to obtain a grayscale histogram; Pixel values ​​of the initial deicing area image are redistributed based on the grayscale histogram to obtain the deicing area image.

4. The method for deicing a drone based on image recognition according to claim 1, wherein: include: Setting convolution kernel parameters and time windows for the initial convolutional neural network layers according to the multiple asynchronous receptive fields to obtain multiple initial asynchronous recognition network layers with completed parameter configurations; A plurality of sample data sets are respectively obtained to perform supervised training on the plurality of initial asynchronous recognition network layers until the training converges, thereby obtaining the plurality of asynchronous recognition network layers that have completed training.

5. The method for deicing a drone based on image recognition according to claim 1, characterized in that: Performing iterative correlation interaction analysis on the sequence of environmental state parameter feature groups in order from front to back to determine an iterative correlation environmental state parameter feature group, including: Extracting a first environmental state parameter feature group and a second environmental state feature group in sequence from the environmental state parameter feature group sequence; Performing iterative correlation and interaction analysis on the first environmental state parameter feature group and the second environmental state parameter feature group to determine a first correlated environmental state parameter feature group; Performing iterative correlation and interaction analysis on the first associated environmental state parameter feature group and the third environmental state parameter feature group of the environmental state parameter feature group sequence to determine a second associated environmental state parameter feature group; An iterative correlation interaction analysis is performed on the n-1th associated environmental state parameter feature group and the nth environmental state parameter feature group of the environmental state parameter feature group sequence to determine the iteratively associated environmental state parameter feature group, wherein n is the number of environmental state parameter feature group sequences in the environmental state parameter feature group sequence, and n is an integer greater than or equal to 1.

6. The method for deicing a drone based on image recognition according to claim 5, characterized in that: include: Calculating the similarity of features corresponding to the same environmental state parameters in the first environmental state parameter feature group and the second environmental state parameter feature group to obtain a first associated similarity group; performing intra-group interaction matrix identification on the first association similarity group to determine a first association interaction matrix; A convolution calculation is performed on the first association interaction matrix and the second environmental state feature group to determine a first association environmental state parameter feature group.

7. The method for deicing a drone based on image recognition according to claim 6, characterized in that: include: Obtain an intra-group interaction normalization processing formula, wherein the intra-group interaction normalization processing formula is: Among them, S[f(x i ,y i )] is the normalized value of the i-th association similarity in the first association similarity group, f(x i ,y i ) is the i-th association similarity in the first association similarity group, x i is the first environmental state parameter feature of the first environmental state parameter feature group, y i is the i-th second environmental state parameter feature of the same type as the i-th first environmental state parameter in the second environmental state parameter group, e is the base of the natural logarithm, m is the total number of association similarities in the first association similarity group, and m is an integer greater than or equal to 1; The association similarities in the first association similarity group are respectively input into the intra-group interaction normalization processing formula for normalization processing, and the processing results are embedded in a matrix to obtain the first association interaction matrix.

Images