Forestry environment monitoring sampling system and method

Abstract

The invention provides a forestry environment monitoring sampling system and method, and the method comprises the steps: collecting multispectral image data and laser radar point cloud data of a target forest region, extracting a vegetation characteristic wave band of the target forest region from the multispectral image data, and generating a vegetation index map and a tree species distribution map; generating a canopy height model based on the vegetation height feature point cloud, and performing spatial registration fusion on the vegetation index map, the tree species distribution map and the canopy height model to generate a forest canopy structure fusion map, performing segmentation processing on the forest canopy structure fusion image according to vegetation index attributes, canopy height attributes and tree species attributes of all grid units, and extracting forest stand unit areas; and the forest health state of each forest stand unit area is judged, and if it is determined that the forest in the forest stand unit area has pest and disease damage abnormities, the forest stand structure regulation and control technical regulation corresponding to the forest stand unit area is generated. By adopting the above prevention, accurate judgment of the forestry environment under multi-source data fusion can be realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of forestry environment monitoring, and more particularly, to a forestry ecological environment monitoring sampling system and method. BACKGROUND

[0002] Forestry environment monitoring is a key technical field for maintaining the sustainable development of forestry resources and ecological balance. With the influence of global climate change and human activities, forestry environments are facing multiple threats such as pest attacks and vegetation degradation. Timely and accurate monitoring of the health status of forest vegetation, canopy structure and potential abnormalities is crucial for developing scientific forest stand control strategies.

[0003] Traditional forestry ecological monitoring mainly relies on manual field investigation or single remote sensing data analysis, such as using only multispectral images to calculate vegetation indices or only using laser radar to obtain height information. These methods can provide basic information, but have significant limitations: on the one hand, a single data source cannot fully capture the complexity of the canopy structure in the forest area, resulting in insufficient monitoring accuracy; on the other hand, it is difficult to effectively fuse multi-source data for spatial analysis, accurately segment forest stand units and judge pest abnormalities, and further generate targeted control technical procedures. This makes forestry management personnel inefficient in dealing with ecological problems, making it difficult to achieve precise management and rapid response. Therefore, how to achieve high-precision forestry environment monitoring under multi-source data fusion has become a problem to be solved in the industry. SUMMARY

[0004] The present application provides a forestry environment monitoring sampling system and method, which can realize accurate judgment of forestry environment under multi-source data fusion and generate corresponding control technical procedures.

[0005] In a first aspect, the present application provides a forestry environment monitoring method, comprising the following steps: Collecting multispectral image data and laser radar point cloud data of a target forest area, extracting a target forest vegetation characteristic band from the multispectral image data, operating the vegetation characteristic band through a preset vegetation index calculation model to generate a vegetation index map, and simultaneously performing tree species identification based on the band reflectivity characteristics of the multispectral data to generate a tree species distribution map; Generating a digital elevation model based on the laser radar point cloud data and performing normalization processing to obtain a vegetation height feature point cloud, generating a canopy height model based on the vegetation height feature point cloud, and spatially registering and fusing the vegetation index map, the tree species distribution map and the canopy height model to generate a forest canopy structure fusion map, wherein the canopy structure fusion map is a two-dimensional grid map, and each grid cell in the two-dimensional grid map stores vegetation index attributes, canopy height attributes and tree species attributes; segmenting the forest canopy structure fusion map according to the vegetation index attribute, the canopy height attribute, and the tree species attribute of all grid cells; judging the forest health state of each forest stand unit region, and if it is determined that the forest in the forest stand unit region has abnormal diseases and pests, generating a forest stand structure regulation and control technical procedure corresponding to the forest stand unit region.

[0006] In some embodiments, the vegetation feature band is operated by a preset vegetation index calculation model to generate a vegetation index map, specifically including: calling a corresponding preset vegetation index calculation model according to the vegetation type of the target forest area; selecting a specified band combination required by the preset vegetation index calculation model from the extracted vegetation feature band; inputting the reflectivity data of the specified band combination into the preset vegetation index calculation model; operating the reflectivity data by the preset vegetation index calculation model to output the vegetation index value of each pixel; rasterizing and reorganizing the vegetation index value according to the pixel spatial coordinates to generate a vegetation index map.

[0007] In some embodiments, the vegetation index map, the tree species distribution map, and the canopy height model are spatially registered and fused to generate a forest canopy structure fusion map, specifically including: unifying the spatial coordinate systems of the vegetation index map, the tree species distribution map, and the canopy height model; selecting common geographical control points to spatially register the vegetation index map, the tree species distribution map, and the canopy height model, so that each map accurately coincides with the ground position; unifying the grid size and spatial resolution of the vegetation index map, the tree species distribution map, and the canopy height model to form a same-scale grid matrix; associating and storing the vegetation index attribute, the tree species attribute, and the canopy height attribute according to the spatial position of the grid cell; integrating the associated attributes of all grid cells to generate a forest canopy structure fusion map.

[0008] In some embodiments, the forest stand unit region is extracted by segmenting the forest canopy structure fusion map according to the vegetation index attribute, the canopy height attribute, and the tree species attribute of all grid cells, specifically including: setting the segmentation rule of the forest stand unit region based on the vegetation index attribute, the canopy height attribute, and the tree species attribute of all grid cells; performing attribute matching and classification on each grid cell in the forest canopy structure fusion map according to the segmentation rule; Raster cells with the same attributes and spatial adjacency after classification are merged into a continuous region; Filter out discrete regions whose area after merging is smaller than a preset threshold; Continuous areas that conform to the characteristics of forest stand units are retained, identified as forest stand unit regions, and forest stand unit region distribution maps are generated.

[0009] In some embodiments, the forest stand unit characteristics are a set of attributes common to all grid units within the same forest stand unit area and distinguishable from other forest stand unit areas, including: overall consistency of vegetation index attributes, interval similarity of canopy height attributes, type uniformity of tree species attributes, and continuity of grid unit spatial distribution.

[0010] In some embodiments, determining the forest health status of each forest stand unit area includes: For each forest stand unit area, a vegetation health status index is determined based on its vegetation index attribute. When the vegetation health status index is lower than a preset health threshold, it is marked as abnormal vegetation vitality. Canopy height changes are detected based on canopy height attributes, and when the changes exceed a preset range, they are marked as canopy structure anomalies. Based on the tree species attributes, a preset pest and disease susceptibility database is queried to determine the pest and disease risk level. When the risk level is higher than a preset risk threshold, it is marked as an abnormal tree species risk. If there are abnormalities in vegetation vitality, canopy structure, or tree species risk, it is determined that the trees in that forest stand unit area have abnormalities in pests and diseases.

[0011] In some embodiments, the technical procedures for generating the forest stand structure regulation corresponding to the forest stand unit area specifically include: Preset control types are matched based on the identified types of abnormal vegetation vitality, abnormal canopy structure, or abnormal tree species risk. Based on the tree species attributes of the forest stand unit area, a preset tree species regulation strategy library is queried to determine the target regulation measures; The regulation intensity parameters are calculated based on the canopy height attributes of the forest stand unit area; The aforementioned control types, target control measures, and control intensity parameters are integrated to generate a structured control instruction set; The spatial location information of the associated forest stand unit area is encapsulated into an executable technical procedure document for forest stand structure regulation.

[0012] Secondly, this application provides a forestry environmental monitoring sampling system, including a forestry monitoring unit, wherein the forestry monitoring unit includes: The acquisition module is used to acquire multispectral image data and lidar point cloud data of the target forest area, extract vegetation feature bands of the target forest area from the multispectral image data, perform calculations on the vegetation feature bands through a preset vegetation index calculation model to generate a vegetation index map, and identify tree species based on the band reflectance characteristics of the multispectral data to generate a tree species distribution map. The processing module is used to generate a digital elevation model based on the lidar point cloud data, and perform normalization processing to obtain a vegetation height feature point cloud. Based on the vegetation height feature point cloud, a canopy height model is generated. The vegetation index map, tree species distribution map and canopy height model are spatially registered and fused to generate a forest area canopy structure fusion map. The canopy structure fusion map is a two-dimensional raster map. Each raster cell in the two-dimensional raster map stores vegetation index attributes, canopy height attributes and tree species attributes. The processing module is also used to segment the forest canopy structure fusion map based on the vegetation index attribute, canopy height attribute and tree species attribute of all grid units, and extract forest stand unit areas; The execution module is used to determine the health status of trees in each forest stand unit area. If it is determined that there are abnormalities in the trees of the forest stand unit area due to diseases and pests, the corresponding forest stand structure regulation technical procedure is generated.

[0013] Thirdly, this application provides a computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described forestry environment monitoring method.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described forestry environment monitoring method.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: This application first collects multispectral image data and lidar point cloud data of the target forest area. Vegetation feature bands are extracted from the multispectral image data to generate a vegetation index map, and tree species identification is performed to generate a tree species distribution map, thus achieving the quantification and identification of vegetation health and species distribution. Second, a digital elevation model is generated based on the lidar point cloud data and normalized to obtain vegetation height feature point clouds, which in turn generate a canopy height model. The vegetation index map, tree species distribution map, and canopy height model are then spatially registered and fused to generate a fused canopy structure map of the forest area. This fused map is a two-dimensional raster map, with each raster cell storing vegetation index attributes, canopy height attributes, and tree species attributes, providing a comprehensive canopy structure view based on multi-source data. Third, the fusion is performed based on the multiple attributes of all raster cells. The image is segmented to extract forest stand unit regions, achieving refined regional division of the forest area. Finally, the health status of trees in each forest stand unit region is assessed. If abnormalities in pests and diseases are found, corresponding forest stand structure regulation technical procedures are generated. This automates the process from data acquisition to anomaly assessment and regulation, solving the problems of low accuracy, poor timeliness, and excessive manual intervention in traditional monitoring methods. Specifically, this application collects multi-source remote sensing information such as multispectral image data and lidar point cloud data to calculate vegetation indices, identify tree species, and construct canopy height models. Through spatial registration and fusion, a multi-attribute canopy structure fusion map is generated (where each grid cell stores vegetation indices, canopy height, and tree species attributes), thereby achieving refined forest stand unit segmentation, health status assessment, and regulation procedure generation. This multi-source fusion mechanism effectively integrates spectral, structural, and spatial information, improving the accuracy and automation level of monitoring, achieving high-precision forestry environmental monitoring under multi-source data fusion, and providing direct evidence for sustainable forestry management. Attached Figure Description

[0016] Figure 1 This is an exemplary flowchart of a forestry environmental monitoring method according to some embodiments of this application; Figure 2 This is an exemplary flowchart illustrating the generation of vegetation index maps according to some embodiments of this application; Figure 3 This is a schematic diagram of the generated forest canopy structure fusion diagram according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of a forestry monitoring unit according to some embodiments of this application; Figure 5 This is a schematic diagram of the structure of a computer device for implementing a forestry environmental monitoring method according to some embodiments of this application. Detailed Implementation

[0017] To better understand the above technical solutions, a detailed description of the solutions will be provided below in conjunction with the accompanying drawings and specific implementation methods. (Reference)Figure 1 The figure is an exemplary flowchart of a forestry environmental monitoring method according to some embodiments of this application. The method mainly includes the following steps: In step 101, multispectral image data and lidar point cloud data of the target forest area are collected. Vegetation feature bands of the target forest area are extracted from the multispectral image data. The vegetation feature bands are calculated using a preset vegetation index calculation model to generate a vegetation index map. At the same time, tree species are identified based on the band reflectance characteristics of the multispectral data to generate a tree species distribution map.

[0018] Multispectral image data refers to image data containing multiple bands (such as visible light and near-infrared) collected by multispectral sensors carried by drones or satellites, used to reflect the spectral characteristics of vegetation. LiDAR point cloud data refers to a set of points containing three-dimensional coordinates and intensity information obtained through scanning by LiDAR equipment, used to construct terrain and vegetation height models. Vegetation characteristic bands refer to designated bands selected from multispectral images that are sensitive to vegetation health, such as green light, red edge, and near-infrared bands.

[0019] refer to Figure 2 In some embodiments, generating a vegetation index map by calculating the vegetation feature bands using a preset vegetation index calculation model specifically includes: In step 1011, the corresponding preset vegetation index calculation model is called according to the vegetation type of the target forest area; Predefined vegetation index calculation models refer to predefined algorithm models used in the field of remote sensing image processing to quantify vegetation health status, cover density, or biomass characteristics. Existing models include Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), and Soil-Adjusted Vegetation Index (SAVI). In specific implementations, for example, for coniferous forests, the NDVI model is used. NDVI, or Normalized Difference Vegetation Index, is a quantitative indicator reflecting vegetation vitality, calculated using (near-infrared - red light) / (near-infrared + red light). No specific limitations are made here. In step 1012, a specified band combination required by the preset vegetation index calculation model is selected from the extracted vegetation feature bands. The specified band combination refers to a specific subset of spectral bands required by the preset vegetation index calculation model (such as NDVI, EVI, or SAVI). These bands are selected from the extracted vegetation feature bands (such as visible light, red edge, near-infrared, etc.) and are used for reflectance calculation. For example, the normalized vegetation index selects near-infrared (NIR, usually 0.7-1.1μm) and red (usually 0.6-0.7μm) bands to quantify vegetation health. In step 1013, the reflectance data of the specified band combination is input into the preset vegetation index calculation model; the reflectance data is processed by the preset vegetation index calculation model to output the vegetation index value of each pixel. In practice, image processing software such as ENVI can be used to perform band calculations. By quantifying the chlorophyll content and coverage of vegetation through differences in band reflectance, the health of vegetation can be assessed, thereby improving the accuracy of vegetation status monitoring.

[0020] In step 1014, the vegetation index values ​​are rasterized and reorganized according to the pixel spatial coordinates to generate a vegetation index map. Specifically, after calculating the vegetation index value (such as NDVI) of each pixel, these calculation results are reorganized into a two-dimensional raster format image file according to the pixel spatial coordinates (i.e., row number, column number or geographic reference coordinates) of the original multispectral image. This will not be elaborated here.

[0021] In addition, in some embodiments, tree species identification is performed based on the band reflectance characteristics of multispectral data to generate a tree species distribution map. This can be achieved in various ways, such as using supervised classification algorithms like support vector machines (SVM) to distinguish tree species using the reflectance spectrum curves of training samples (e.g., pine trees have high reflectance in the near-infrared band). In other words, the spectral differences between tree species are learned through training samples to achieve pixel-level classification and generate a spatial distribution map, which facilitates subsequent fusion analysis. This will not be elaborated further here.

[0022] In step 102, a digital elevation model is generated based on the lidar point cloud data and normalized to obtain a vegetation height feature point cloud. A canopy height model is generated based on the vegetation height feature point cloud. The vegetation index map, tree species distribution map and canopy height model are spatially registered and fused to generate a forest area canopy structure fusion map. The canopy structure fusion map is a two-dimensional raster map. Each raster cell in the two-dimensional raster map stores vegetation index attributes, canopy height attributes and tree species attributes.

[0023] Among them, the Digital Elevation Model (DEM) refers to a ground elevation raster map generated based on point cloud data interpolation; normalization processing refers to subtracting the DEM elevation from the point cloud to obtain the vegetation height relative to the ground; and the Canopy Height Model (CHM) refers to a raster model representing the height of the tree canopy top.

[0024] In some embodiments, a digital elevation model (DEM) is generated based on the lidar point cloud data and normalized to obtain a vegetation height feature point cloud. Specifically, LAStools software can be used to filter ground points to generate a DEM. Then, the DEM elevation is subtracted from the lidar point cloud to obtain the vegetation height feature point cloud, which is a three-dimensional point set containing all points (including ground points and non-ground points such as vegetation points), with each point having X, Y, and Z coordinates (Z being the absolute elevation). During the normalization process, the DEM elevation value at the corresponding location is subtracted from the Z coordinate of each point in the original lidar point cloud, thereby converting the lidar point cloud into a height representation relative to the ground (Z≈0 for ground points, Z for non-ground points is the relative height), to eliminate terrain influence and extract the vegetation height feature point cloud. This will not be elaborated further here.

[0025] The canopy height model is generated based on the vegetation height feature point cloud. In specific implementation, CHM grids can be generated by maximum height interpolation. Specifically, the highest point in each grid is counted as the canopy height to characterize the canopy structure.

[0026] refer to Figure 3 In some embodiments, the vegetation index map, tree species distribution map, and canopy height model are spatially registered and fused to generate a forest canopy structure fusion map. This can be achieved in the following ways: In step 1031, the spatial coordinate system of the vegetation index map, the tree species distribution map and the canopy height model is unified. In specific implementation, for example, the spatial coordinate system is the WGS84 coordinate system. In step 1032, common geographic control points are selected to spatially register the vegetation index map, the tree species distribution map, and the canopy height model so that the corresponding ground locations of each map accurately overlap. In step 1033, the grid size and spatial resolution of the vegetation index map, the tree species distribution map, and the canopy height model are unified to form a grid matrix of the same scale; the vegetation index attribute, tree species attribute, and canopy height attribute are associated and stored according to the spatial position of the grid cells. In step 1034, the associated attributes of all raster units are integrated to generate a fused map of the forest canopy structure. Specifically, ArcGIS can be used for registration and fusion. Spatial registration calculates the coordinate mapping of raster pixels based on a geometric transformation matrix, ensuring that rasters from different sources (such as multispectral and LiDAR-derived rasters) overlap at the same geographic location. Fusion is based on pixel-level overlay and combination logic, utilizing the row and column indices of the raster data to achieve a one-to-one correspondence between locations, ensuring that multiple attributes of each geographic location are integrated into a single structured data set. This multi-source integration is achieved through geometric transformation and attribute overlay, providing a comprehensive view that facilitates subsequent segmentation and analysis.

[0027] In step 103, the forest area canopy structure fusion map is segmented based on the vegetation index attribute, canopy height attribute, and tree species attribute of all grid cells to extract forest stand unit regions.

[0028] Among them, a forest stand unit area refers to a continuous area in a forest with similar vegetation characteristics, such as a forest block of the same tree species.

[0029] In some embodiments, the forest canopy structure fusion map is segmented based on the vegetation index attribute, canopy height attribute, and tree species attribute of all raster units. The extraction of forest stand unit areas can be achieved using the following methods: Based on the vegetation index attributes, canopy height attributes, and tree species attributes of all raster units, the segmentation rules for forest stand unit areas are set. In specific implementation, for example, the segmentation rules are vegetation index similarity > 0.8, canopy height difference < 2m, and the same tree species. This is only an example and is not a specific limitation. Based on the segmentation rules, attribute matching and classification are performed on each grid cell in the forest canopy structure fusion map; After classification, grid cells with consistent attributes and spatial adjacency are merged into continuous regions. In practice, a region growth algorithm can be used for merging. The region growth algorithm uses attribute thresholds and spatial connectivity clustering to automatically extract forest stands, thereby improving the accuracy of monitoring. This will not be elaborated further here. Filter out discrete regions whose area after merging is smaller than a preset threshold (for example, the threshold can be set to 100㎡). Continuous areas that conform to the characteristics of forest stand units are retained, identified as forest stand unit regions, and forest stand unit region distribution maps are generated.

[0030] In some embodiments, the forest stand unit features are a set of attributes common to all raster units within the same forest stand unit area and distinguishable from other forest stand unit areas, including: overall consistency of vegetation index attributes (e.g., average NDVI deviation <0.1), interval similarity of canopy height attributes (e.g., height standard deviation <1m), type uniformity of tree species attributes (e.g., 100% the same tree species), and continuity of the spatial distribution of raster units (e.g., no isolated pixels).

[0031] In step 104, the health status of trees in each forest stand unit area is determined. If it is determined that there are abnormal pests and diseases in the trees in the forest stand unit area, the corresponding forest stand structure regulation technical procedure is generated.

[0032] In some embodiments, the health status of trees in each forest stand unit area can be determined in the following manner: For each forest stand unit area, vegetation health status indicators (e.g., average NDVI as an indicator) are determined based on its vegetation index attributes. When the vegetation health status indicator is lower than a preset health threshold (e.g., NDVI < 0.6), it is marked as abnormal vegetation vitality. Canopy height changes are detected based on canopy height attributes (e.g., compared with historical data, change rate > 10%), and when the change exceeds a preset change range, it is marked as an abnormal canopy structure. Based on the tree species attributes, a preset pest and disease susceptibility database (e.g., pine trees are susceptible to pine caterpillars, risk level 1-5) is queried to determine the pest and disease risk level. When the risk level is higher than a preset risk threshold (e.g., >3), it is marked as an abnormal tree species risk. If abnormal vegetation vitality, canopy structure, or tree species risk is detected, the forest units in that forest stand area are deemed to have abnormal pest and disease conditions. In practice, threshold judgments and database queries can be used; that is, anomalies can be identified through a comprehensive evaluation of multiple indicators, achieving an early warning system.

[0033] In some embodiments, the technical procedures for generating the forest stand structure regulation corresponding to the forest stand unit area can be specifically adopted in the following manner, namely: Based on the identified abnormal vegetation vitality, abnormal canopy structure, or abnormal tree species risk, a preset control type is matched (e.g., abnormal vitality is matched with fertilization type); based on the tree species attributes of the forest stand unit area, a preset tree species control strategy library is queried to determine the target control measures. For example, pine tree strategies include spraying insecticides, which are not specifically limited here. The intensity control parameter is calculated based on the canopy height attribute of the forest stand unit area (e.g., the intensity is moderate when the height is >10m). The structured control instruction set is generated by integrating the control type, target control measures, and control intensity parameters. This structured control instruction set refers to integrating the control type (e.g., fertilization or pest control), target control measures (e.g., spraying specific pesticides), and control intensity parameters (e.g., moderate intensity) into an ordered, hierarchical set of instructions. It can be organized in data structure form (e.g., JSON, XML, or tables) for easy automated processing or manual execution. For example, it might include an instruction sequence: {Type: "Vegetation vitality control", Measures: "Apply nitrogen fertilizer", Intensity: "Moderate (dosage 20 kg / ha)", Execution steps: ["Prepare fertilizer", "Evenly spread"]}, which will not be elaborated further here. The spatial location information of the forest stand unit area is encapsulated into an executable forest stand structure regulation technical procedure document. The forest stand structure regulation technical procedure document refers to an executable document or file that encapsulates a structured regulation instruction set and associates the spatial location information of the forest stand unit area (such as GPS coordinates or grid boundaries) to guide the standardization of actual forestry operations.

[0034] In practice, templates can be used to fill in generated files, and exception type-driven strategy matching can be used to generate targeted procedures, supporting automated forestry management.

[0035] In another aspect, in some embodiments, this application provides a forestry environmental monitoring sampling system, which includes a forestry monitoring unit, with reference to... Figure 4 The figure is a schematic diagram of the structure of a forestry monitoring unit according to some embodiments of this application. The forestry monitoring unit 400 includes: a data acquisition module 401, a processing module 402, and an execution module 403, which are described below: The acquisition module 401 in this application is mainly used to acquire multispectral image data and lidar point cloud data of the target forest area, extract vegetation feature bands of the target forest area from the multispectral image data, perform calculations on the vegetation feature bands through a preset vegetation index calculation model to generate a vegetation index map, and identify tree species based on the band reflectance characteristics of the multispectral data to generate a tree species distribution map. Processing module 402 in this application is mainly used to generate a digital elevation model based on the lidar point cloud data, and perform normalization processing to obtain a vegetation height feature point cloud. Based on the vegetation height feature point cloud, a canopy height model is generated, and the vegetation index map, tree species distribution map and canopy height model are spatially registered and fused to generate a forest area canopy structure fusion map. The canopy structure fusion map is a two-dimensional raster map. Each raster cell in the two-dimensional raster map stores vegetation index attributes, canopy height attributes and tree species attributes. It should be noted that the processing module 402 described in this application is also used to segment the forest area canopy structure fusion map based on the vegetation index attribute, canopy height attribute and tree species attribute of all grid units, and extract the forest stand unit area; The execution module 403 in this application is mainly used to determine the health status of trees in each forest stand unit area. If it is determined that there are abnormal pests and diseases in the trees in the forest stand unit area, the corresponding forest stand structure regulation technical procedure is generated.

[0036] In addition, this application also provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described forestry environment monitoring method.

[0037] In some embodiments, reference Figure 5 The figure is a schematic diagram of the structure of a computer device for implementing a forestry environmental monitoring method according to some embodiments of this application. The method in the above embodiments can be implemented through... Figure 5 The computer device shown is used to implement this, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0038] The processor 501 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the forestry environmental monitoring method in this application.

[0039] The communication bus 502 may include a path for transmitting information between the aforementioned components.

[0040] Memory 503 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CDROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 503 may exist independently and be connected to processor 501 via communication bus 502. Memory 503 may also be integrated with processor 501.

[0041] The memory 503 stores program code for executing the scheme of this application, and its execution is controlled by the processor 501. The processor 501 executes the program code stored in the memory 503. The program code may include one or more software modules. In the above embodiment, the generation of the vegetation index map can be achieved by the processor 501 and one or more software modules in the program code in the memory 503.

[0042] Communication interface 504 uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0043] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core processor or a multi-core processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0044] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0045] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described forestry environment monitoring method.

[0046] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0047] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of the invention. Therefore, if these modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A method for monitoring forestry environment, characterized in that, Includes the following steps: Multispectral image data and lidar point cloud data of the target forest area are collected. Vegetation feature bands of the target forest area are extracted from the multispectral image data. The vegetation feature bands are calculated using a preset vegetation index calculation model to generate a vegetation index map. At the same time, tree species are identified based on the band reflectance characteristics of the multispectral data to generate a tree species distribution map. A digital elevation model is generated based on the lidar point cloud data and normalized to obtain a vegetation height feature point cloud. A canopy height model is then generated based on the vegetation height feature point cloud. The vegetation index map, tree species distribution map, and canopy height model are spatially registered and fused to generate a forest area canopy structure fusion map. The canopy structure fusion map is a two-dimensional raster map, and each raster cell in the two-dimensional raster map stores vegetation index attributes, canopy height attributes, and tree species attributes. The forest canopy structure fusion map is segmented based on the vegetation index attribute, canopy height attribute, and tree species attribute of all grid cells to extract forest stand unit regions; Assess the health status of trees in each forest stand unit area. If it is determined that there are abnormalities in the trees of a forest stand unit area due to diseases and pests, generate the corresponding forest stand structure regulation technical procedure for that forest stand unit area.

2. The method as described in claim 1, characterized in that, The vegetation index map is generated by performing calculations on the vegetation feature bands using a preset vegetation index calculation model, specifically including: The corresponding preset vegetation index calculation model is invoked based on the vegetation type of the target forest area; Select the specified band combination required by the preset vegetation index calculation model from the extracted vegetation feature bands; Input the reflectance data of the specified band combination into the preset vegetation index calculation model; The reflectance data is processed by a preset vegetation index calculation model to output the vegetation index value for each pixel. The vegetation index values ​​are rasterized and recombined according to the pixel spatial coordinates to generate a vegetation index map.

3. The method as described in claim 1, characterized in that, The spatial registration and fusion of the vegetation index map, tree species distribution map, and canopy height model to generate a forest area canopy structure fusion map specifically includes: Unify the spatial coordinate system of the vegetation index map, the tree species distribution map, and the canopy height model; A common geographic control point is selected to spatially register the vegetation index map, the tree species distribution map, and the canopy height model, so that the corresponding ground locations of each map accurately overlap. The grid size and spatial resolution of the vegetation index map, the tree species distribution map, and the canopy height model are unified to form a grid matrix of the same scale; The vegetation index attribute, tree species attribute and canopy height attribute are associated and stored by matching the spatial location of each grid cell; By integrating the associated attributes of all raster cells, a fused map of the forest canopy structure is generated.

4. The method as described in claim 1, characterized in that, The forest canopy structure fusion map is segmented based on the vegetation index attributes, canopy height attributes, and tree species attributes of all raster units. The extracted forest stand unit regions specifically include: Based on the vegetation index attributes, canopy height attributes, and tree species attributes of all grid cells, the division rules for forest stand unit areas are set. Based on the segmentation rules, attribute matching and classification are performed on each grid cell in the forest canopy structure fusion map; Raster cells with the same attributes and spatial adjacency after classification are merged into a continuous region; Filter out discrete regions whose area after merging is smaller than a preset threshold; Continuous areas that conform to the characteristics of forest stand units are retained, identified as forest stand unit regions, and forest stand unit region distribution maps are generated.

5. The method as described in claim 4, characterized in that, The forest stand unit characteristics are a set of attributes common to all grid units within the same forest stand unit area and distinguishable from other forest stand unit areas, including: overall consistency of vegetation index attributes, interval similarity of canopy height attributes, type uniformity of tree species attributes, and continuity of grid unit spatial distribution.

6. The method as described in claim 1, characterized in that, Assessing the health status of trees in each forest stand unit area includes: For each forest stand unit area, a vegetation health status index is determined based on its vegetation index attribute. When the vegetation health status index is lower than a preset health threshold, it is marked as abnormal vegetation vitality. Canopy height changes are detected based on canopy height attributes, and when the changes exceed a preset range, they are marked as canopy structure anomalies. Based on the tree species attributes, a preset pest and disease susceptibility database is queried to determine the pest and disease risk level. When the risk level is higher than a preset risk threshold, it is marked as an abnormal tree species risk. If there are abnormalities in vegetation vitality, canopy structure, or tree species risk, it is determined that the trees in that forest stand unit area have abnormalities in pests and diseases.

7. The method as described in claim 6, characterized in that, The specific technical procedures for generating the forest stand structure regulation corresponding to this forest stand unit area include: Preset control types are matched based on the identified types of abnormal vegetation vitality, abnormal canopy structure, or abnormal tree species risk. Based on the tree species attributes of the forest stand unit area, a preset tree species regulation strategy library is queried to determine the target regulation measures; The regulation intensity parameters are calculated based on the canopy height attributes of the forest stand unit area; The aforementioned control types, target control measures, and control intensity parameters are integrated to generate a structured control instruction set; The spatial location information of the associated forest stand unit area is encapsulated into an executable technical procedure document for forest stand structure regulation.

8. A forestry environmental monitoring sampling system, comprising a forestry monitoring unit, characterized in that, The forestry monitoring unit includes: The acquisition module is used to acquire multispectral image data and lidar point cloud data of the target forest area, extract vegetation feature bands of the target forest area from the multispectral image data, perform calculations on the vegetation feature bands through a preset vegetation index calculation model to generate a vegetation index map, and identify tree species based on the band reflectance characteristics of the multispectral data to generate a tree species distribution map. The processing module is used to generate a digital elevation model based on the lidar point cloud data, and perform normalization processing to obtain a vegetation height feature point cloud. Based on the vegetation height feature point cloud, a canopy height model is generated. The vegetation index map, tree species distribution map and canopy height model are spatially registered and fused to generate a forest area canopy structure fusion map. The canopy structure fusion map is a two-dimensional raster map. Each raster cell in the two-dimensional raster map stores vegetation index attributes, canopy height attributes and tree species attributes. The processing module is also used to segment the forest canopy structure fusion map based on the vegetation index attribute, canopy height attribute and tree species attribute of all grid units, and extract forest stand unit areas; The execution module is used to determine the health status of trees in each forest stand unit area. If it is determined that there are abnormalities in the trees of the forest stand unit area due to diseases and pests, the corresponding forest stand structure regulation technical procedure is generated.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the forestry environment monitoring method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the forestry environment monitoring method as described in any one of claims 1 to 7.

Images