Mangrove forest interspecific classification method and device based on unmanned aerial vehicle remote sensing

Abstract

The invention relates to the field of remote sensing monitoring, in particular to a mangrove forest inter-species classification method and device based on unmanned aerial vehicle remote sensing, and adopts a decision tree learning algorithm to update a feature threshold value in a feature corresponding relation of a plurality of mangrove plant categories in an initial multi-modal plant knowledge graph; and according to the extracted feature data set of the to-be-classified region, a plurality of types of feature data, feature values corresponding to the feature data and the updated multi-modal plant knowledge graph, inter-species classification reasoning is carried out to obtain an inter-species classification result of the mangrove forest, classification knowledge is fused, and the classification efficiency is improved. The method overcomes the defects of a method which purely depends on data, and improves the accuracy, efficiency and reliability of mangrove forest inter-species classification.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing monitoring, and in particular to a method, device, computer equipment and storage medium for mangrove interspecific classification based on unmanned aerial vehicle remote sensing. Background Art

[0002] Mangroves are the foundation of mangrove ecosystems. The species composition, community structure and diversity of mangrove plant communities have an important impact on the productivity and stability of the ecosystem, and determine the energy flow and material circulation process of the mangrove ecosystem. Therefore, efficient and accurate monitoring of the spatial distribution and dynamics of mangrove species is also an important challenge and key scientific issue in mangrove remote sensing research. However, the spatial distribution of mangroves is uneven and complex, resulting in great uncertainty in the current remote sensing interspecific classification of mangroves. Summary of the invention

[0003] Based on this, the purpose of the present invention is to provide a method, device, computer equipment and storage medium for interspecific classification of mangroves based on unmanned aerial vehicle remote sensing, adopt a decision tree learning algorithm to update the feature thresholds in the feature correspondence relationship of several mangrove plant categories in the initial multimodal plant knowledge graph, and obtain an updated multimodal plant knowledge graph. According to several types of feature data in the feature data set of the extracted area to be classified, the feature values ​​corresponding to the feature data and the updated multimodal plant knowledge graph, interspecific classification reasoning is performed to obtain the interspecific classification results of mangroves, which integrates classification knowledge, overcomes the shortcomings of methods that rely solely on data, and improves the accuracy, efficiency and reliability of interspecific classification of mangroves.

[0004] In a first aspect, an embodiment of the present application provides a method for mangrove species classification based on drone remote sensing, comprising the following steps:

[0005] Obtaining a multi-source remote sensing sample data set of several mangrove plant categories and an initial multimodal plant knowledge graph, wherein the initial multimodal plant knowledge graph includes feature correspondences of several mangrove plant categories, and the feature correspondences include several types of feature data and corresponding feature thresholds;

[0006] Extracting mangrove plant features based on the drone remote sensing data and elevation data in the multi-source remote sensing sample data set to obtain sample feature data sets of several mangrove plant categories, wherein the sample feature data sets include feature data of several types;

[0007] According to the sample feature data sets of several mangrove plant categories, a decision tree learning algorithm is used to update the feature thresholds corresponding to the feature data in the feature correspondence relationship of several mangrove plant categories in the initial multimodal plant knowledge graph to obtain an updated multimodal plant knowledge graph;

[0008] Obtain multi-source remote sensing data of the area to be classified, perform feature extraction based on the drone remote sensing data and elevation data in the multi-source remote sensing data, and obtain a feature data set of the area to be classified;

[0009] Interspecific classification reasoning is performed based on several types of feature data and feature values ​​corresponding to the feature data in the feature data set of the area to be classified, as well as several types of feature data and feature thresholds corresponding to the feature data in the feature correspondence relationship of several mangrove plant categories in the updated multimodal plant knowledge graph, to obtain the interspecific classification result of mangroves in the area to be classified.

[0010] In a second aspect, the embodiment of the present application provides a mangrove interspecific classification device based on drone remote sensing, comprising:

[0011] A data acquisition module, used to obtain a multi-source remote sensing sample data set of several mangrove plant categories and an initial multimodal plant knowledge graph, wherein the initial multimodal plant knowledge graph includes feature correspondences of several mangrove plant categories, and the feature correspondences include several types of feature data and corresponding feature thresholds;

[0012] A first feature extraction module is used to extract mangrove plant features based on the drone remote sensing data and the elevation data in the multi-source remote sensing sample data set to obtain sample feature data sets of several mangrove plant categories, wherein the sample feature data sets include feature data of several types;

[0013] A feature threshold updating module is used to update the feature threshold corresponding to the feature data in the feature correspondence relationship of several mangrove plant categories in the initial multimodal plant knowledge graph using a decision tree learning algorithm according to the sample feature data sets of several mangrove plant categories, so as to obtain an updated multimodal plant knowledge graph;

[0014] A second feature extraction module is used to obtain multi-source remote sensing data of the area to be classified, perform feature extraction based on the UAV remote sensing data and elevation data in the multi-source remote sensing data, and obtain a feature data set of the area to be classified;

[0015] The interspecific classification result module is used to perform interspecific classification reasoning based on several types of feature data in the feature data set of the area to be classified, the feature values ​​corresponding to the feature data, and several types of feature data in the feature correspondence relationship of several mangrove plant categories in the updated multimodal plant knowledge graph, and the feature thresholds corresponding to the feature data, so as to obtain the interspecific classification result of mangroves in the area to be classified.

[0016] In a third aspect, an embodiment of the present application provides a computer device comprising: a processor, a memory, and a computer program stored on the memory and executable on the processor; when the computer program is executed by the processor, the steps of the mangrove interspecies classification method based on drone remote sensing as described in the first aspect are implemented.

[0017] In a fourth aspect, an embodiment of the present application provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the mangrove interspecies classification method based on drone remote sensing as described in the first aspect.

[0018] In an embodiment of the present application, a method, apparatus, computer equipment and storage medium for interspecific classification of mangroves based on unmanned aerial vehicle remote sensing are provided, which adopts a decision tree learning algorithm to update the feature thresholds in the feature correspondence relationship of several mangrove plant categories in the initial multimodal plant knowledge graph to obtain an updated multimodal plant knowledge graph, and perform interspecific classification reasoning based on several types of feature data in the feature data set of the extracted area to be classified, the feature values ​​corresponding to the feature data and the updated multimodal plant knowledge graph to obtain the interspecific classification results of mangroves, integrate classification knowledge, overcome the shortcomings of methods that rely solely on data, and improve the accuracy, efficiency and reliability of interspecific classification of mangroves.

[0019] For better understanding and implementation, the present invention is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of a flow chart of a method for interspecific classification of mangroves based on UAV remote sensing provided in one embodiment of the present application;

[0021] Figure 2 A schematic diagram of the process of S3 in the mangrove interspecific classification method based on UAV remote sensing provided in one embodiment of the present application;

[0022] Figure 3 A schematic diagram of the process of S31 in the mangrove interspecific classification method based on UAV remote sensing provided in one embodiment of the present application;

[0023] Figure 4A schematic diagram of the process of S32 in the method for interspecific classification of mangroves based on UAV remote sensing provided in one embodiment of the present application;

[0024] Figure 5 A schematic diagram of the process of S4 in the mangrove interspecific classification method based on UAV remote sensing provided in one embodiment of the present application;

[0025] Figure 6 A schematic diagram of the process of S5 in the mangrove interspecific classification method based on UAV remote sensing provided in one embodiment of the present application;

[0026] Figure 7 A schematic diagram of the structure of a mangrove interspecific classification device based on drone remote sensing provided in one embodiment of the present application;

[0027] Figure 8 A schematic diagram of the structure of a computer device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0028] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0029] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0030] It should be understood that, although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" / "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determination".

[0031] The data sending end may be a computer device or a mobile terminal device, which is used to establish a network connection with the data receiving end, and can encode data information sent to the data receiving end, and parse data information sent from the data receiving end.

[0032] The data receiving end may be a computer device or a mobile terminal device, which is used to establish a network connection with the data sending end, and can encode the data information sent to the data sending end, and parse the data information sent from the data sending end.

[0033] See also Figure 1 , Figure 1 A flow chart of a method for interspecific classification of mangroves based on UAV remote sensing provided in one embodiment of the present application, the method comprising the following steps:

[0034] S1: Obtain multi-source remote sensing sample datasets of several mangrove plant categories and an initial multimodal plant knowledge graph.

[0035] The executor of the mangrove interspecific classification method based on UAV remote sensing of the present application is a classification device of the mangrove interspecific classification method based on UAV remote sensing (hereinafter referred to as the classification device). In an optional embodiment, the classification device can be a computer device, a server, or a server cluster composed of multiple computer devices.

[0036] In this embodiment, the classification device obtains a multi-source remote sensing sample data set of several mangrove plant categories, wherein the multi-source remote sensing sample data set includes drone remote sensing data and elevation data. The drone remote sensing data is a variety of different types of remote sensing data collected by different sensors carried by drones, including multi-spectral, LiDAR, hyperspectral, video, etc. The elevation data is a digital simulation of the ground terrain through limited terrain elevation data.

[0037] The classification device obtains an initial multimodal plant knowledge graph, wherein the initial multimodal plant knowledge graph includes feature correspondences of several mangrove plant categories, and the feature correspondences include several types of feature data and corresponding feature thresholds.

[0038] In an optional embodiment, the classification device can obtain interspecific classification knowledge data described in natural language including expert experience from a preset database, and the interspecific classification knowledge data includes classification information, morphological characteristics, habitat characteristics and spatial distribution characteristics of all mangrove plant categories obtained from flora and literature. Morphological characteristics include tree height, crown width, life form (shrubs or trees, etc.); habitat characteristics include tidal level of growth, cold resistance (the coldest monthly average temperature that can be tolerated), etc.; spatial distribution characteristics refer to the place names of the current and historical distribution areas of the species.

[0039] The classification device converts the interspecific classification knowledge data into rules described by the above features and corresponding feature thresholds, and expresses them according to the syntax of the Semantic Web Rule Language (SWRL), obtains the feature correspondence of several mangrove plant categories, and constructs the initial multimodal plant knowledge graph.

[0040] S2: Extracting mangrove plant features based on the UAV remote sensing data and elevation data in the multi-source remote sensing sample data set to obtain sample feature data sets of several mangrove plant categories.

[0041] In this embodiment, the classification device performs feature extraction based on the UAV remote sensing data and elevation data in the multi-source remote sensing sample data set of several mangrove plant categories to obtain sample feature data sets of several mangrove plant categories, wherein the sample feature data sets include several types of feature data.

[0042] Specifically, the classification device uses OTB (Orfeo Toolbox), which is an open source high-performance image processing system used in the remote sensing field. It can process high-resolution optical, multispectral and radar images. The classification device uses the feature extraction algorithm in OTB to extract features from the UAV remote sensing data and elevation data, obtain several types of feature data of several mangrove plant categories, and use fragtats software to calculate the connectivity features of the objects. Each feature extraction result is saved as an independent layer for subsequent use, wherein the feature data comprises several feature vectors, the feature data comprises spectral feature data, texture feature data, shape feature data and height feature data, the spectral feature data comprises hue feature vector, saturation feature vector, brightness feature vector, spectral mean feature vector and spectral standard deviation feature vector; the texture feature data comprises homogeneity feature vector, contrast feature vector, dissimilarity feature vector, entropy feature vector, angular matrix feature vector, texture mean feature vector, texture standard deviation feature vector and autocorrelation feature vector; the shape feature data comprises asymmetry feature vector, boundary index feature vector, compactness feature vector, density feature vector, ellipse fit feature vector, main direction feature vector, maximum closed ellipse radius feature vector, minimum closed ellipse radius feature vector, rectangle fit feature vector, circularity feature vector and shape index feature vector; the height feature data comprises elevation standard deviation feature vector, elevation variance feature vector, altitude feature vector, elevation mean absolute deviation feature vector, elevation L2 feature vector, canopy undulation rate feature vector and canopy height model feature vector.

[0043] In an optional embodiment, before the classification device performs feature extraction on the UAV remote sensing data in the multi-source remote sensing sample data set of several mangrove plant categories, the classification device preprocesses the UAV remote sensing data, including image stitching, data cropping, geometric correction, radiation correction, point cloud denoising and filtering, etc., to improve the accuracy of feature extraction.

[0044] S3: Based on the sample feature data sets of several mangrove plant categories, a decision tree learning algorithm is used to update the feature thresholds corresponding to the feature data in the feature correspondence relationship of several mangrove plant categories in the initial multimodal plant knowledge graph to obtain an updated multimodal plant knowledge graph.

[0045] The decision tree learning algorithm is based on the Classification and Regression Trees (CART) algorithm, which is called machine learning or expert system and provides a non-parametric method for determining the statistical relationship between multiple data layers to generate a binary decision tree.

[0046] In this embodiment, the classification device uses a decision tree learning algorithm based on sample feature data sets of several mangrove plant categories to update the feature thresholds corresponding to the feature data in the feature correspondence of several mangrove plant categories in the initial multimodal plant knowledge graph to obtain an updated multimodal plant knowledge graph.

[0047] See also Figure 2 , Figure 2 The flowchart of S3 in the method for interspecific classification of mangroves based on UAV remote sensing provided in one embodiment of the present application includes steps S31 to S32, which are specifically as follows:

[0048] S31: Based on sample feature data sets of several mangrove plant categories, several feature vectors are extracted from the sample feature data sets as training features of several mangrove plant categories, and based on the sample feature data sets of several mangrove plant categories and the training features, a classification tree of several mangrove plant categories is constructed using a Gini index minimization criterion method.

[0049] In this embodiment, the classification device extracts a number of feature vectors from the sample feature data sets as training features for the several mangrove plant categories based on the sample feature data sets of the several mangrove plant categories. Specifically, the classification device extracts a number of feature data from the sample feature data sets of the several mangrove plant categories in a sampling with replacement manner, and also obtains a number of feature vectors from the feature data in a sampling with replacement manner as training features for the several mangrove plant categories.

[0050] The classification device constructs classification trees of several mangrove plant categories based on sample feature data sets and training features of several mangrove plant categories and adopts a Gini index minimization criterion method.

[0051] See also Figure 3 , Figure 3 The flowchart of S31 in the method for interspecific classification of mangroves based on UAV remote sensing provided in one embodiment of the present application includes steps S311 to S312, which are specifically as follows:

[0052] S311: According to the plurality of training features, the sample feature data sets are respectively classified into two categories to obtain a first sub-sample feature data set and a second sub-sample feature data set of the plurality of training features; according to a preset Gini index algorithm, the Gini index after the sample feature data sets are classified into two categories under any feature value is calculated; the training feature with the smallest Gini index and its corresponding feature value are taken as the optimal splitting point for the current round.

[0053] In this embodiment, the classification device performs binary classification on the sample feature data set according to the plurality of training features to obtain a first sub-sample feature data set and a second sub-sample feature data set of the plurality of training features.

[0054] For the training features and the corresponding first sub-sample feature data set and second sub-sample feature data set, the classification device calculates the Gini index after the sample feature data set is binary classified under any feature value according to a preset Gini index algorithm, and the classification device uses the training feature with the smallest Gini index and its corresponding feature value as the optimal split point for the current round, wherein the Gini index algorithm is:

[0055]

[0056] In the formula, Gini represents the Gini index, Z represents the training feature, T represents the sample feature data set, T1 represents the first sub-sample feature data set, T2 represents the second sub-sample feature data set, K represents the number of classification categories, and p i represents the probability of belonging to the i-th category.

[0057] S312: The first sub-sample feature data set and the second sub-sample feature data set of the training feature with the smallest Gini index are used as sample feature data sets of the left and right nodes respectively, and the optimal splitting points for the next round are obtained until all nodes no longer meet the node re-divisibility condition, and classification trees of several mangrove plant categories are obtained.

[0058] In this embodiment, the classification device uses the first sub-sample feature data set and the second sub-sample feature data set of the training feature with the smallest Gini index as the sample feature data sets of the left and right nodes, respectively, to obtain the optimal splitting points for the next round until all nodes no longer meet the node divisibility condition, and obtains a classification tree of several mangrove plant categories.

[0059] S32: According to the classification trees of several mangrove plant categories, several target feature vectors and corresponding target feature thresholds of several mangrove plant categories are obtained, and the feature thresholds corresponding to the corresponding feature vectors in the initial feature correspondence relationship of the corresponding mangrove plant category in the initial multimodal plant knowledge graph are updated to obtain an updated multimodal plant knowledge graph.

[0060] In this embodiment, the classification device obtains several target feature vectors and corresponding target feature thresholds of several mangrove plant categories based on the classification trees of several mangrove plant categories, updates the feature thresholds corresponding to the corresponding feature vectors in the initial feature correspondence of the corresponding mangrove plant categories in the initial multimodal plant knowledge graph, and obtains an updated multimodal plant knowledge graph.

[0061] See also Figure 4 , Figure 4 The flowchart of S32 in the method for interspecific classification of mangroves based on drone remote sensing provided in one embodiment of the present application includes step S321, which is as follows:

[0062] S321: According to the classification trees of several mangrove plant categories, the training features and feature values ​​corresponding to the optimal splitting points of all rounds of the classification trees of several mangrove plant categories are obtained, the training features are used as the target feature vectors, and the feature values ​​are used as the target feature thresholds, to obtain several target feature vectors and corresponding target feature thresholds of several mangrove plant categories.

[0063] In this embodiment, the classification device obtains training features and feature values ​​corresponding to the optimal splitting points of all rounds of the classification trees of several mangrove plant categories based on the classification trees of several mangrove plant categories, uses the training features as the target feature vectors, and the feature values ​​as the target feature thresholds, to obtain several target feature vectors and corresponding target feature thresholds of several mangrove plant categories.

[0064] S4: Obtain multi-source remote sensing data of the area to be classified, perform feature extraction based on the UAV remote sensing data and elevation data in the multi-source remote sensing data, and obtain a feature data set of the area to be classified.

[0065] In this embodiment, the classification device obtains multi-source remote sensing data of the area to be classified, performs feature extraction based on the UAV remote sensing data and elevation data in the multi-source remote sensing data, and obtains a feature data set of the area to be classified.

[0066] See also Figure 5 , Figure 5 The flowchart of S4 in the method for interspecific classification of mangroves based on UAV remote sensing provided in one embodiment of the present application includes step S41, which is as follows:

[0067] S41: Obtain the mangrove vegetation index of the area to be classified, confirm the mangrove area in the area to be classified according to the mangrove vegetation index, perform feature extraction based on the UAV remote sensing data and elevation data in the multi-source remote sensing data corresponding to the mangrove area in the area to be classified, and obtain a feature data set of the area to be classified.

[0068] In this embodiment, the classification device obtains the mangrove vegetation index of the area to be classified, and confirms the mangrove area in the area to be classified according to the mangrove vegetation index, so as to improve the accuracy of feature extraction and the efficiency of reasoning.

[0069] The classification device extracts features based on the UAV remote sensing data and elevation data in the multi-source remote sensing data corresponding to the mangrove area in the area to be classified, and obtains a feature data set of the area to be classified. For a specific implementation example, refer to step S2 and will not be repeated here.

[0070] S5: Perform interspecific classification reasoning based on several types of feature data in the feature data set of the area to be classified, feature values ​​corresponding to the feature data, and several types of feature data in the updated feature correspondence relationship of several mangrove plant categories, and feature thresholds corresponding to the feature data, to obtain the interspecific classification result of mangroves in the area to be classified.

[0071] In this embodiment, the classification device performs inter-specific classification inference based on several types of feature data in the feature data set of the area to be classified, the feature values ​​corresponding to the feature data, and several types of feature data and feature thresholds corresponding to the feature data in the updated feature correspondence relationship of several mangrove plant categories to obtain the inter-specific classification result of mangroves in the area to be classified.

[0072] A decision tree learning algorithm is used to update the feature thresholds in the feature correspondence of several mangrove plant categories in the initial multimodal plant knowledge graph to obtain an updated multimodal plant knowledge graph. Interspecific classification reasoning is performed based on several types of feature data in the extracted feature data set of the area to be classified, the feature values ​​corresponding to the feature data, and the updated multimodal plant knowledge graph to obtain the interspecific classification results of mangroves. This integrates classification knowledge, overcomes the shortcomings of methods that rely solely on data, and improves the accuracy, efficiency, and reliability of interspecific classification of mangroves.

[0073] See also Figure 6 , Figure 6 The flowchart of S5 in the method for interspecific classification of mangroves based on UAV remote sensing provided in one embodiment of the present application includes steps S51 to S52, which are specifically as follows:

[0074] S51: determining a plurality of candidate feature correspondences of the area to be classified from the updated multimodal plant knowledge graph, and determining a target feature correspondence of a mangrove plant category having corresponding feature vectors according to all feature vectors of all types of feature data in the feature data set of the area to be classified and a plurality of candidate feature correspondences;

[0075] In this embodiment, the classification device determines several candidate feature correspondences of the area to be classified from the updated multimodal plant knowledge graph. Specifically, the classification device can obtain geographical information of the mangrove area of ​​the area to be classified, wherein the geographical information indicates the mangrove plant categories that may appear in the mangrove area, and determine several candidate feature correspondences of the area to be classified according to the geographical information and the spatial distribution characteristics corresponding to the feature correspondences of several mangrove plant categories in the updated multimodal plant knowledge graph.

[0076] The classification device determines the target feature correspondence of the mangrove plant category that also has corresponding feature vectors based on all feature vectors of all types of feature data in the feature data set of the area to be classified and a number of candidate feature correspondences, so as to perform inter-species classification, thereby reducing the search space and the probability of misclassification and omission, and improving reasoning efficiency and accuracy.

[0077] S52: According to the feature values ​​corresponding to all feature vectors of all types of feature data in the feature data set of the area to be classified, if the feature values ​​all satisfy the feature thresholds corresponding to the corresponding feature vectors in the target feature correspondence, the mangrove plant category corresponding to the target feature correspondence is used as the mangrove interspecies classification result to obtain the mangrove interspecies classification result of the area to be classified.

[0078] In this embodiment, the classification device determines the feature values ​​corresponding to all feature vectors of all types of feature data in the feature data set of the area to be classified. If the feature values ​​all satisfy the feature thresholds corresponding to the corresponding feature vectors in the target feature correspondence, the mangrove plant category corresponding to the target feature correspondence is used as the mangrove interspecies classification result to obtain the mangrove interspecies classification result of the area to be classified.

[0079] Please refer to Figure 7 , Figure 7 A schematic diagram of the structure of a mangrove interspecific classification device based on UAV remote sensing provided by an embodiment of the present application. The device can implement all or part of the mangrove interspecific classification device based on UAV remote sensing through software, hardware, or a combination of both. The device 7 includes:

[0080] A data acquisition module 71 is used to obtain a multi-source remote sensing sample data set of several mangrove plant categories and an initial multimodal plant knowledge graph, wherein the initial multimodal plant knowledge graph includes feature correspondences of several mangrove plant categories, and the feature correspondences include several types of feature data and corresponding feature thresholds;

[0081] A first feature extraction module 72 is used to extract mangrove plant features based on the drone remote sensing data and the elevation data in the multi-source remote sensing sample data set to obtain sample feature data sets of several mangrove plant categories, wherein the sample feature data sets include feature data of several types;

[0082] A feature threshold updating module 73 is used to update the feature threshold corresponding to the feature data in the feature correspondence relationship of several mangrove plant categories in the initial multimodal plant knowledge graph using a decision tree learning algorithm according to the sample feature data sets of several mangrove plant categories, so as to obtain an updated multimodal plant knowledge graph;

[0083] The second feature extraction module 74 is used to obtain multi-source remote sensing data of the area to be classified, and perform feature extraction based on the UAV remote sensing data and elevation data in the multi-source remote sensing data to obtain a feature data set of the area to be classified;

[0084] The interspecific classification result module 75 is used to perform interspecific classification reasoning based on several types of feature data in the feature data set of the area to be classified, the feature values ​​corresponding to the feature data, and several types of feature data in the feature correspondence relationship of several mangrove plant categories in the updated multimodal plant knowledge graph, and the feature thresholds corresponding to the feature data, so as to obtain the interspecific classification result of mangroves in the area to be classified.

[0085] In this embodiment, a multi-source remote sensing sample data set of several mangrove plant categories and an initial multimodal plant knowledge graph are obtained through a data acquisition module, wherein the initial multimodal plant knowledge graph includes feature correspondences of several mangrove plant categories, and the feature correspondences include several types of feature data and corresponding feature thresholds; through a first feature extraction module, mangrove plant features are extracted according to the UAV remote sensing data and elevation data in the multi-source remote sensing sample data set to obtain sample feature data sets of several mangrove plant categories, wherein the sample feature data sets include several types of feature data; through a feature threshold updating module, a decision tree learning algorithm is used to update the initial multimodal plant knowledge graph according to the sample feature data sets of several mangrove plant categories. The feature threshold corresponding to the feature data in the feature correspondence relationship of several mangrove plant categories in the multimodal plant knowledge graph is updated to obtain an updated multimodal plant knowledge graph; through the second feature extraction module, multi-source remote sensing data of the area to be classified is obtained, and feature extraction is performed according to the UAV remote sensing data and elevation data in the multi-source remote sensing data to obtain the feature data set of the area to be classified; through the interspecific classification result module, interspecific classification reasoning is performed according to several types of feature data in the feature data set of the area to be classified, feature values ​​corresponding to the feature data, and several types of feature data in the feature correspondence relationship of several mangrove plant categories in the updated multimodal plant knowledge graph, and feature thresholds corresponding to the feature data to obtain the interspecific classification result of mangroves in the area to be classified. A decision tree learning algorithm is used to update the feature thresholds in the feature correspondence of several mangrove plant categories in the initial multimodal plant knowledge graph to obtain an updated multimodal plant knowledge graph. Interspecific classification reasoning is performed based on several types of feature data in the extracted feature data set of the area to be classified, the feature values ​​corresponding to the feature data, and the updated multimodal plant knowledge graph to obtain the interspecific classification results of mangroves. This integrates classification knowledge, overcomes the shortcomings of methods that rely solely on data, and improves the accuracy, efficiency, and reliability of interspecific classification of mangroves.

[0086] Please refer to Figure 8 , Figure 8 The computer device 8 is a schematic diagram of a structure of a computer device provided in an embodiment of the present application. The computer device 8 includes: a processor 81, a memory 82, and a computer program 83 stored in the memory 82 and executable on the processor 81; the computer device may store multiple instructions, which are suitable for being loaded and executed by the processor 81. Figures 1 to 6 For the specific implementation process, please refer to Figures 1 to 6 The specific description is not repeated here.

[0087] Among them, the processor 81 may include one or more processing cores. The processor 81 uses various interfaces and lines to connect various parts in the server, and executes various functions and processes data of the mangrove interspecific classification device 7 based on drone remote sensing by running or executing instructions, programs, code sets or instruction sets stored in the memory 82, and calling the data in the memory 82. Optionally, the processor 81 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programble Logic Array, PLA). The processor 81 can integrate one or more combinations of a central processing unit 81 (Central Processing Unit, CPU), an image processor 81 (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the touch display; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 81, but implemented separately by a chip.

[0088] Among them, the memory 82 may include a random access memory 82 (Random Access Memory, RAM), and may also include a read-only memory 82 (Read-Only Memory). Optionally, the memory 82 includes a non-transitory computer-readable storage medium. The memory 82 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 82 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch instructions, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 82 may also be optionally at least one storage device located away from the aforementioned processor 81.

[0089] The present application also provides a storage medium that can store multiple instructions, which are suitable for the processor to load and execute the above-mentioned Figures 1 to 6 For the specific implementation process, please refer to Figures 1 to 6 The specific description is not repeated here.

[0090] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0091] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraint algorithm of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0093] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0094] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0096] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.

[0097] The present invention is not limited to the above-mentioned embodiments. If various changes or modifications to the present invention do not depart from the spirit and scope of the present invention, and if these changes and modifications fall within the scope of the claims and equivalent technologies of the present invention, the present invention is also intended to include these changes and modifications.

Claims

1. A method for interspecific classification of mangroves based on UAV remote sensing, characterized in that: The following steps are involved: Obtaining a multi-source remote sensing sample data set of several mangrove plant categories and an initial multimodal plant knowledge graph, wherein the initial multimodal plant knowledge graph includes feature correspondences of several mangrove plant categories, and the feature correspondences include several types of feature data and corresponding feature thresholds; Extracting mangrove plant features based on the drone remote sensing data and elevation data in the multi-source remote sensing sample data set to obtain sample feature data sets of several mangrove plant categories, wherein the sample feature data sets include feature data of several types; According to the sample feature data sets of several mangrove plant categories, a decision tree learning algorithm is used to update the feature thresholds corresponding to the feature data in the feature correspondence relationship of several mangrove plant categories in the initial multimodal plant knowledge graph to obtain an updated multimodal plant knowledge graph; Obtain multi-source remote sensing data of the area to be classified, perform feature extraction based on the drone remote sensing data and elevation data in the multi-source remote sensing data, and obtain a feature data set of the area to be classified; Interspecific classification reasoning is performed based on several types of feature data and feature values ​​corresponding to the feature data in the feature data set of the area to be classified, as well as several types of feature data and feature thresholds corresponding to the feature data in the feature correspondence relationship of several mangrove plant categories in the updated multimodal plant knowledge graph, to obtain the interspecific classification result of mangroves in the area to be classified.

2. The method for mangrove interspecific classification based on UAV remote sensing according to claim 1 is characterized by: The characteristic data includes a plurality of characteristic vectors, wherein the characteristic data includes spectral characteristic data, texture characteristic data, shape characteristic data and height characteristic data, and the spectral characteristic data includes a hue characteristic vector, a saturation characteristic vector, a brightness characteristic vector, a spectral mean characteristic vector and a spectral standard deviation characteristic vector; The texture feature data includes a homogeneity feature vector, a contrast feature vector, a dissimilarity feature vector, an entropy feature vector, an angular two-matrix feature vector, a texture mean feature vector, a texture standard deviation feature vector and an autocorrelation feature vector; The shape feature data includes an asymmetry feature vector, a boundary index feature vector, a compactness feature vector, a density feature vector, an ellipse fit feature vector, a main direction feature vector, a maximum closed ellipse radius feature vector, a minimum closed ellipse radius feature vector, a rectangle fit feature vector, a circularity feature vector and a shape index feature vector; The height characteristic data includes an elevation standard deviation characteristic vector, an elevation variance characteristic vector, an altitude elevation characteristic vector, an elevation mean absolute deviation characteristic vector, an elevation L2 characteristic vector, a canopy undulation rate characteristic vector, and a canopy height model characteristic vector.

3. The method for mangrove interspecific classification based on UAV remote sensing according to claim 2 is characterized by: The decision tree learning algorithm adopts a classification and regression tree algorithm; The method uses a decision tree learning algorithm based on sample feature data sets of several mangrove plant categories to update feature thresholds corresponding to feature data in initial feature correspondences of several mangrove plant categories to obtain updated feature correspondences of several mangrove plant categories, including the steps of: According to the sample feature data sets of several mangrove plant categories, a number of feature vectors are extracted from the sample feature data sets as training features of several mangrove plant categories, and according to the sample feature data sets of several mangrove plant categories and the training features, a Gini index minimization criterion method is used to construct classification trees of several mangrove plant categories; According to the classification trees of several mangrove plant categories, several target feature vectors and corresponding target feature thresholds of several mangrove plant categories are obtained, and the feature thresholds corresponding to the corresponding feature vectors in the initial feature correspondence relationship of the corresponding mangrove plant category in the initial multimodal plant knowledge graph are updated to obtain an updated multimodal plant knowledge graph.

4. The method for mangrove interspecific classification based on UAV remote sensing according to claim 3 is characterized in that: The method of constructing classification trees of several mangrove plant categories by using a Gini index minimization criterion method based on sample feature data sets and training features of several mangrove plant categories comprises the following steps: According to the plurality of the training features, the sample feature data sets are respectively classified into two categories to obtain a first sub-sample feature data set and a second sub-sample feature data set of the plurality of the training features, and according to a preset Gini index algorithm, the Gini index after the sample feature data sets are classified into two categories under any feature value is calculated, and the training feature with the smallest Gini index and its corresponding feature value are used as the optimal split point for the current round; The first sub-sample feature data set and the second sub-sample feature data set of the training feature with the smallest Gini index are used as the sample feature data sets of the left and right nodes respectively to obtain the optimal splitting points for the next round until all nodes no longer meet the node divisibility condition, and classification trees of several mangrove plant categories are obtained.

5. The method for mangrove interspecific classification based on UAV remote sensing according to claim 4 is characterized in that: The method of obtaining a plurality of target feature vectors and corresponding target feature thresholds of a plurality of mangrove plant categories according to the classification trees of the plurality of mangrove plant categories comprises the following steps: According to the classification trees of several mangrove plant categories, the training features and feature values ​​corresponding to the optimal splitting points of all rounds of the classification trees of several mangrove plant categories are obtained, the training features are used as the target feature vectors, and the feature values ​​are used as the target feature thresholds, to obtain several target feature vectors and corresponding target feature thresholds of several mangrove plant categories.

6. The method for mangrove interspecific classification based on UAV remote sensing according to claim 5 is characterized in that: The method of extracting features based on the UAV remote sensing data and the elevation data in the multi-source remote sensing data to obtain a feature data set of the area to be classified includes the following steps: Obtain a mangrove vegetation index for the area to be classified, confirm the mangrove area in the area to be classified based on the mangrove vegetation index, perform feature extraction based on UAV remote sensing data and elevation data in the multi-source remote sensing data corresponding to the mangrove area in the area to be classified, and obtain a feature data set for the area to be classified.

7. The method for mangrove interspecific classification based on UAV remote sensing according to claim 6 is characterized in that: The method performs interspecific classification reasoning based on several types of feature data in the feature data set of the area to be classified, feature values ​​corresponding to the feature data, and several types of feature data in the feature correspondence relationship of several mangrove plant categories in the updated multimodal plant knowledge graph, and feature thresholds corresponding to the feature data, to obtain the interspecific classification result of mangroves in the area to be classified, including the steps of: Determine a plurality of candidate feature correspondences of the area to be classified from the updated multimodal plant knowledge graph, and determine a target feature correspondence of a mangrove plant category having corresponding feature vectors according to all feature vectors of all types of feature data in a feature data set of the area to be classified and a plurality of candidate feature correspondences; According to the eigenvalues ​​corresponding to all eigenvectors in all types of feature data in the feature data set of the area to be classified, if the eigenvalues ​​all satisfy the feature thresholds corresponding to the corresponding eigenvectors in the target feature correspondence, the mangrove plant category corresponding to the target feature correspondence is taken as the inter-species classification result of the mangroves, and the inter-species classification result of the mangroves in the area to be classified is obtained.

8. A mangrove interspecific classification device based on drone remote sensing, characterized in that: include: A data acquisition module, used to obtain a multi-source remote sensing sample data set of several mangrove plant categories and an initial multimodal plant knowledge graph, wherein the initial multimodal plant knowledge graph includes feature correspondences of several mangrove plant categories, and the feature correspondences include several types of feature data and corresponding feature thresholds; A first feature extraction module is used to extract mangrove plant features based on the drone remote sensing data and the elevation data in the multi-source remote sensing sample data set to obtain sample feature data sets of several mangrove plant categories, wherein the sample feature data sets include feature data of several types; A feature threshold updating module is used to update the feature threshold corresponding to the feature data in the feature correspondence relationship of several mangrove plant categories in the initial multimodal plant knowledge graph using a decision tree learning algorithm according to the sample feature data sets of several mangrove plant categories, so as to obtain an updated multimodal plant knowledge graph; A second feature extraction module is used to obtain multi-source remote sensing data of the area to be classified, perform feature extraction based on the UAV remote sensing data and elevation data in the multi-source remote sensing data, and obtain a feature data set of the area to be classified; The interspecific classification result module is used to perform interspecific classification reasoning based on several types of feature data in the feature data set of the area to be classified, the feature values ​​corresponding to the feature data, and several types of feature data in the feature correspondence relationship of several mangrove plant categories in the updated multimodal plant knowledge graph, and the feature thresholds corresponding to the feature data, so as to obtain the interspecific classification result of mangroves in the area to be classified.

9. A computer device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the mangrove interspecific classification method based on UAV remote sensing as described in any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the mangrove interspecific classification method based on drone remote sensing as described in any one of claims 1 to 7.

Images