Species information collection method, system, electronic device and medium based on drone

Abstract

A method, system, electronic device and medium for collecting species information based on drones, relating to the field of drone control technology. The method comprises: obtaining forest spatial information of a target area, and generating a forest layer distribution map of the target area based on the forest layer height data and inter-layer distance data in the forest spatial information; determining the first hovering position of a master drone and the second hovering position of sub-drones corresponding to multiple forest layers according to the forest layer distribution map, and receiving the initial species coordinate information of each forest layer collected by the master drone; determining the travel path of the sub-drones corresponding to each forest layer in combination with the initial species coordinate information and the second hovering position of each forest layer; controlling the corresponding sub-drones to collect species according to each travel path, obtaining the species image and species distribution position corresponding to each forest layer, and generating a species distribution report of the target area. The implementation of the technical solution provided by the present application achieves the effect of improving the accuracy of species information collection.

Description

Technical Field

[0001] The present application relates to the field of drone control technology, and specifically to a species information collection method, system, electronic device and medium based on drones. Background Art

[0002] With the increasing importance of ecological protection and natural resource management, the accurate collection and analysis of species information in forests has become an important part of scientific research and conservation work. Especially in forest ecosystems, the detailed collection of species information is crucial for the assessment of biodiversity and the formulation of conservation strategies.

[0003] At present, drone technology is widely used in forest species information collection around the world due to its high efficiency and wide range of applications. Existing drone-based species information collection methods mainly rely on setting fixed routes to collect information over a large area using a single drone. However, in actual applications, due to the wide distribution of species in forests, it is often difficult to comprehensively collect species information at different levels in the forest by only using a single drone along a fixed route to collect information over a large area, thereby reducing the accuracy of species information collection. Summary of the invention

[0004] The present application provides a species information collection method, system, electronic device and medium based on drones, which can improve the accuracy of species information collection.

[0005] In a first aspect, the present application provides a method for collecting species information based on a drone, comprising:

[0006] Acquire forest spatial information of a target area, and generate a forest layer distribution map of the target area based on forest layer height data and interlayer distance data in the forest spatial information;

[0007] Determine, according to the forest layer distribution map, a first hovering position of the master drone and second hovering positions of the slave drones corresponding to the plurality of forest layers, and receive initial species coordinate information of each of the forest layers collected after the master drone moves to the first hovering position;

[0008] Determine the travel path of the sub-UAV corresponding to each forest layer by combining the initial species coordinate information of each forest layer and the second hovering position;

[0009] According to each of the travel paths, the corresponding sub-drones are controlled to collect species in each of the forest layers, so as to obtain species images and species distribution positions corresponding to each of the forest layers;

[0010] Based on the species images and species distribution positions corresponding to each of the forest layers, a species distribution report for the target area is generated.

[0011] In a second aspect of the present application, a species information collection system based on a drone is provided, the system comprising:

[0012] An information acquisition module, used to acquire forest spatial information of a target area, and generate a forest layer distribution map of the target area based on forest layer height data and interlayer distance data in the forest spatial information;

[0013] A path determination module is used to determine the first hovering position of the master drone and the second hovering positions of the sub-drones corresponding to the multiple forest layers according to the forest layer distribution map, and receive the initial species coordinate information of each of the forest layers collected after the master drone moves to the first hovering position; and determine the travel path of the sub-drones corresponding to each of the forest layers in combination with the initial species coordinate information of each of the forest layers and the second hovering position;

[0014] A species collection module controls the corresponding sub-UAVs according to the travel paths to collect species in each forest layer, and obtains species images and species distribution positions corresponding to each forest layer;

[0015] The report generation module is used to generate a species distribution report for the target area based on the species images and species distribution locations corresponding to each of the forest layers.

[0016] In a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program can implement a species information collection method based on a drone when loaded and executed by the processor.

[0017] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements a species information collection method based on a drone.

[0018] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0019] By adopting the above technical solution, the forest spatial information of the target area is obtained, and the forest layer height data and inter-layer distance data are used to generate a detailed forest layer distribution map to ensure a comprehensive understanding of the forest structure. Then, according to the forest layer distribution map, the first hovering position of the main control drone and the second hovering position of the sub-drone corresponding to each forest layer are accurately determined, and the initial species coordinate information of each forest layer is collected by the main control drone, providing the initial basis for data collection. Subsequently, the travel path of each sub-drone is intelligently planned in combination with the initial species coordinate information and the hovering position of the sub-drone, and the flight route is optimized. Finally, the sub-drone is controlled to collect species according to the planned travel path to obtain the species images and distribution positions of each forest layer. Based on the collected species images and distribution positions, a species distribution report for the target area is generated. Through the multi-level and multi-drone collaborative working mechanism, combined with intelligent path planning and automated data processing, the accuracy of species information collection is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flowchart of a method for collecting species information based on drones provided in an embodiment of the present application;

[0021] Figure 2 It is a structural schematic diagram of a species information collection system based on a drone provided in an embodiment of the present application;

[0022] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0023] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0024] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0025] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0026] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0027] The present application embodiment provides a method for collecting species information based on drones. In one embodiment, please refer to Figure 1 , Figure 1 This is a flow chart of a method for collecting species information based on drones provided in an embodiment of the present application. The method can be implemented by a computer program, which can be integrated into an application or run as an independent tool application. The method can also be implemented by a single-chip microcomputer or run on a drone-based species information collection system based on a von Neumann system. Specifically, the method can include the following steps:

[0028] Step 101: Acquire forest spatial information of a target area, and generate a forest layer distribution map of the target area based on forest layer height data and inter-layer distance data in the forest spatial information.

[0029] Among them, forest spatial information refers to the three-dimensional structure data of the forest obtained by scanning the target area with the laser radar equipment carried by the master control drone, including but not limited to the spatial characteristic information such as tree height distribution, canopy density, vertical hierarchical structure, etc. This information forms a complete digital expression of the forest spatial structure.

[0030] The forest layer height data refers to the specific height values ​​of each vertical layer in the forest. For example, the canopy layer may be located 20-30 meters above the ground, the sub-canopy layer is located at 10-20 meters, and the shrub layer is located at 2-5 meters. These data reflect the vertical stratification characteristics of the forest.

[0031] Interlayer distance data refers to the vertical distance between adjacent forest layers, which is used to characterize the degree of spatial separation between different forest layers. For example, there may be a 3-5 meter distance between the canopy layer and the sub-canopy layer.

[0032] Specifically, it is necessary to first obtain the forest spatial information of the target area. This can be obtained by carrying out a preliminary scan with a laser radar device on the master control drone. The collected data includes spatial structural information such as forest layer height data and interlayer distance data. The purpose of obtaining these basic data is to accurately grasp the vertical layered structure of the forest in the target area and lay the foundation for subsequent layered collection. After obtaining the forest spatial information, the collected data needs to be reconstructed in three dimensions to generate three-dimensional point cloud data of the target area. By analyzing the three-dimensional point cloud data, the system can extract vegetation density information at different height positions. This processing method can clearly show the structural characteristics of the forest in the vertical direction and help to accurately identify the distribution of different forest layers. Based on the extracted vegetation density information and combined with the interlayer distance data, the system can determine the boundary position of each forest layer through density threshold analysis. In the process of determining the boundary position, it is necessary to consider the interval requirements between adjacent forest layers to ensure the accuracy of the division. Finally, the identified boundary positions of each forest layer are mapped to the preset plane image to generate a forest layer distribution map of the target area. This mapping process needs to maintain the accuracy of the spatial position relationship to ensure that the generated forest layer distribution map can truly reflect the vertical structural characteristics of the forest. The forest layer distribution map generated in this way can intuitively display the spatial distribution of each forest layer, providing an important basis for subsequently determining the working position of the drone and planning the collection path.

[0033] Based on the above embodiment, as an optional embodiment, in step 101: generating a forest layer distribution map of the target area based on the forest layer height data and interlayer distance data in the forest spatial information, this step may also include the following steps:

[0034] Step 201: Perform three-dimensional reconstruction on the forest spatial information to obtain three-dimensional point cloud data of the target area.

[0035] Specifically, in order to convert the acquired forest spatial information into a processable digital model, it is necessary to perform three-dimensional reconstruction processing on the laser radar data collected by the master control drone. In the specific implementation, the distance data and angle data collected by the laser radar are first converted into spatial coordinate points, and then the point cloud data obtained from multiple scanning positions are fused through the point cloud registration algorithm. Finally, the point cloud filtering algorithm is used to remove noise points to obtain high-precision three-dimensional point cloud data of the target area. This processing method can truly restore the three-dimensional spatial structure of the forest and provide an accurate data basis for subsequent forest layer analysis.

[0036] Step 202: Extract vegetation density information at multiple height positions based on the three-dimensional point cloud data; determine the boundary positions of multiple forest layers based on the vegetation density information and inter-layer distance data.

[0037] Specifically, it is first necessary to extract vegetation density information at different heights from the three-dimensional point cloud data. In specific implementation, the three-dimensional point cloud data is horizontally sliced ​​by setting a fixed height interval (such as 1 meter), and the density distribution of the point cloud in each slice is calculated to obtain the vegetation density information at different heights. Subsequently, based on the acquired vegetation density information, combined with the pre-set density threshold (such as the number of point clouds per cubic meter) and inter-layer distance data, a density clustering algorithm is used to identify locations with significant density changes, and these locations are determined as the boundary locations of adjacent forest layers. This method can accurately identify the vertical layered structure of the forest and provide an accurate height reference for subsequent layered acquisition.

[0038] Step 203: Map the boundary position of each forest layer to a preset plane image to obtain a forest layer distribution map of the target area.

[0039] Specifically, first establish a preset two-dimensional grid plane, and the grid size is determined according to the required accuracy (such as 10 meters × 10 meters). Then, the boundary positions of each forest layer are mapped to this preset plane by orthographic projection to form a two-dimensional forest layer outline. For each grid unit, the corresponding forest layer type and height information are recorded, and finally a plane image containing complete forest layer distribution information is generated. This mapping method not only retains the spatial distribution characteristics of the forest layer, but also facilitates subsequent drone path planning and navigation. The forest layer distribution map generated in this way can intuitively display the vertical structural characteristics of the forest, providing an important reference for subsequent collection work.

[0040] Step 102: According to the forest layer distribution map, determine the first hovering position of the master drone and the second hovering positions of the sub-drones corresponding to the multiple forest layers, and receive the initial species coordinate information of each forest layer collected after the master drone moves to the first hovering position.

[0041] The master control drone refers to a drone equipped with a high-resolution camera, multispectral sensor and lidar equipment. It is mainly responsible for obtaining forest spatial information, generating forest layer distribution maps, and performing preliminary scans of each forest layer at the first hovering position to obtain initial species coordinate information, playing a command and coordination role in the entire collection system.

[0042] The first hovering position refers to the working position selected by the master drone above the highest forest layer. This position needs to meet the requirement of obtaining the maximum vertical connectivity area coverage, so that the master drone can effectively observe and record the species distribution of each forest layer below.

[0043] A sub-UAV refers to an executive UAV that is responsible for the detailed collection of species information at each forest layer under the command of the main control UAV. Each sub-UAV is responsible for collecting species information at a specific forest layer and is equipped with special image acquisition equipment and sensors.

[0044] The second hovering position refers to the working position assigned to each sub-UAV. These positions are usually located in the center of the horizontal activity range of the forest layer they are responsible for, and maintain an appropriate observation altitude so that the sub-UAV can effectively complete the task of collecting species information on the designated forest layer.

[0045] Forest layer refers to the natural layered structure of the forest in the vertical direction, including vegetation layers of different heights such as the canopy layer, subcanopy layer, and shrub layer. Each forest layer has a specific height range and vegetation density characteristics.

[0046] The initial species coordinate information refers to the species spatial distribution data collected by the master drone through a high-resolution camera and a multispectral sensor at the first hovering position, including the position coordinates of the target species in three-dimensional space and preliminary distribution density information. This information provides a reference for the subsequent detailed collection of the sub-drone.

[0047] Specifically, before determining the hovering position of the drone, the system first needs to analyze the vertically connected areas in the forest layer distribution map. These areas refer to the gaps between different forest layers in the forest, which can ensure the safe passage of the drone. To achieve this goal, the system analyzes the forest layer distribution map through an image processing algorithm to extract the vertically connected areas between the forest layers. At the same time, based on the boundary position information of each forest layer, the system calculates the horizontal activity range of each forest layer. This range information will be used to ensure that the sub-drone can effectively cover the target area. When determining the first hovering position of the master drone, the system first determines multiple candidate hovering positions above the forest layer with the highest height. For each candidate position, the system calculates the area of ​​the vertically connected area that can be covered at this position based on the camera parameters and shooting angle of the master drone. By comparing the coverage effects of different candidate positions, the position that can obtain the largest vertically connected area coverage is selected as the first hovering position of the master drone. This selection method can ensure that the master drone obtains the best observation angle when collecting initial species information.

[0048] For the second hovering position of the sub-drone, the system needs to consider the specific height and horizontal range of each forest layer. In specific implementation, the system will assign an optimized hovering position to each sub-drone based on the center position and height data of each forest layer. These positions are usually selected at the center of the horizontal range of each forest layer, and maintain an appropriate observation height to ensure that the sub-drone can efficiently carry out subsequent species information collection. When the master drone reaches the first hovering position, it will use its high-resolution camera and multispectral sensor to conduct a preliminary scan of each forest layer to obtain the initial coordinate information of the species in each forest layer. These initial species coordinate information includes the approximate location and distribution density of the species, providing important reference data for the subsequent detailed collection of the sub-drone. This layered collection strategy not only improves the efficiency of species information collection, but also ensures the integrity and accuracy of the collected data, providing reliable data support for subsequent species distribution research. Through the collaborative work of the master drone and the sub-drone, the system can achieve comprehensive and accurate collection of species information at all levels of the forest.

[0049] Based on the above embodiment, as an optional embodiment, in step 102: determining the first hovering position of the master UAV and the second hovering positions of the slave UAVs corresponding to the plurality of forest layers according to the forest layer distribution map, this step may also include the following steps:

[0050] Step 301: Extract the vertically connected areas between the forest layers according to the forest layer distribution map; and determine the horizontal activity range of each forest layer based on the boundary position of each forest layer.

[0051] Specifically, the system first needs to extract vertically connected areas from the forest layer distribution map. These areas are the key channels for drones to safely pass through. In specific implementation, the image segmentation algorithm is used to process the forest layer distribution map, and the position and range of the vertically connected areas are identified by detecting the gap areas between adjacent forest layers. At the same time, based on the boundary position information of each forest layer in the forest layer distribution map, the system calculates the horizontal coverage range of each forest layer through the boundary contour analysis algorithm, and determines the range as the horizontal activity range of the corresponding forest layer. This processing method not only ensures the safety of subsequent drone operations, but also clarifies the operating area of ​​each forest layer, laying the foundation for planning the drone's hovering position.

[0052] Step 302: Determine multiple candidate hovering positions above the forest layer with the highest height, and based on the shooting angle of the master control drone, determine the vertically connected area covered by the master control drone at each candidate hovering position.

[0053] Specifically, the system needs to determine the candidate hovering position of the master drone above the forest layer with the highest height. In the specific implementation, a grid search space is first set above the highest forest layer, and multiple evenly distributed candidate hovering positions are generated in this space. Then, each candidate hovering position is evaluated based on the camera parameters of the master drone (such as field of view angle, focal length, etc.) and the preset shooting angle. The observation field of the master drone at each candidate position is simulated by a ray tracing algorithm, and the area of ​​the vertically connected area that can be covered from this position is calculated. This evaluation method can accurately calculate the observation effect of each candidate position and provide a quantitative basis for selecting the optimal hovering position.

[0054] Step 303: The candidate hovering position with the largest vertically connected area is used as the first hovering position of the master UAV; based on the height of each forest layer and the center position of the horizontal activity range, the second hovering position of the corresponding sub-UAV is determined.

[0055] Specifically, the calculated coverage areas are compared, and the candidate hovering position that can cover the largest vertically connected area is selected as the first hovering position of the master drone. This selection method ensures that the master drone can obtain the best observation effect at this position. Subsequently, the system calculates the coordinates of the center position of each forest layer based on the height data and horizontal activity range of each forest layer. When determining the second hovering position of the sub-drone, the system uses the center position of each forest layer as the reference point, and combines the height of the forest layer to assign an optimal working position to each sub-drone. This position allocation scheme can ensure that the sub-drone is in the most favorable position for data collection, and improve the efficiency and accuracy of subsequent species information collection. Through this systematic position planning, the comprehensiveness of the collection work is guaranteed, and the work efficiency is improved.

[0056] Step 103: Determine the travel path of the sub-UAV corresponding to each forest layer by combining the initial species coordinate information and the second hovering position of each forest layer.

[0057] The travel path refers to the flight trajectory from the second hovering position of each sub-UAV to each collection area in the forest layer for which it is responsible.

[0058] Specifically, before the sub-UAVs carry out fine collection work, it is necessary to plan the optimal travel path for each sub-UAV based on the initial species coordinate information obtained by the master UAV and the determined second hovering position. The system first performs cluster analysis on the initial species coordinate information of each forest layer, and divides species with similar spatial positions into several collection areas, which will be the key collection targets of the sub-UAVs. In specific implementation, the density clustering algorithm is used to process the initial species coordinate points in each forest layer, and the scope and boundary of each collection area are determined according to the spatial distribution characteristics of the coordinate points. After determining the collection area, the system needs to plan a travel path from its second hovering position to each collection area for each sub-UAV. In the path planning process, the system first constructs a three-dimensional path planning space based on the vertically connected areas in the forest layer distribution map, and marks the densely vegetationed areas in each forest layer as no-fly areas. Then, the improved A* algorithm is used for path search, which simultaneously considers multiple constraints such as path length, energy consumption and safety. By setting an appropriate cost function, it is ensured that the generated path can avoid the no-fly area and ensure the efficiency of reaching the target collection area. To improve collection efficiency, the system will also prioritize each collection area, with the priority determined mainly based on factors such as species density, collection difficulty, and energy consumption. Based on this priority sequence, the system generates a closed path for each sub-drone that connects multiple collection areas. This path planning method not only ensures the integrity of the collection work, but also minimizes energy consumption. By adopting this systematic path planning method, the sub-drones can operate efficiently and safely in the forest layers they are responsible for, improving the work efficiency of the entire species information collection system.

[0059] Based on the above embodiment, as an optional embodiment, in step 103: combining the initial species coordinate information of each forest layer and the second hovering position to determine the travel path of the sub-UAV corresponding to each forest layer, this step may also include the following steps:

[0060] Step 401: Obtain obstacle distribution data in each forest layer; perform density clustering on the species distribution of each forest layer based on the initial species coordinate information of each forest layer to obtain corresponding multiple species aggregation areas.

[0061] Specifically, the system first collects point cloud data of each forest layer through the laser radar equipment carried by the master drone, identifies and extracts obstacle information within the forest layer through the point cloud data processing algorithm, and generates obstacle distribution data, which contains characteristic information such as the location, size and shape of the obstacles. Subsequently, the system performs density clustering analysis on the initial species coordinate information of each forest layer collected by the master drone, and processes these coordinate points using a density-based spatial clustering algorithm. The algorithm automatically clusters species coordinate points with similar spatial positions into several species aggregation areas by setting appropriate density thresholds and distance parameters. This clustering method can effectively identify areas with dense species distribution in each forest layer and provide target location information for subsequent path planning.

[0062] Step 402: In each forest layer, combining the obstacle distribution data and the second hovering position, generate multiple candidate paths for the sub-UAV to reach the gathering areas of each species.

[0063] Specifically, the system needs to plan candidate paths for each sub-UAV from its second hovering position to the gathering areas of each species. In specific implementation, the obstacle distribution data is first converted into a three-dimensional grid map, in which the grid where the obstacle is located is marked as an impassable area. Then, the system uses a fast random exploration tree algorithm for path planning, which generates multiple possible candidate paths at the same time by randomly sampling and connecting feasible points in space. During the path generation process, the system will consider factors such as the UAV's motion constraints, obstacle avoidance requirements, and energy consumption to ensure that the generated candidate paths meet both safety requirements and practical operability. This multi-path planning method provides ample selection space for subsequent path optimization.

[0064] Step 403: Select the candidate path with the shortest path length as the travel path of the sub-UAV corresponding to the forest layer.

[0065] Specifically, the system evaluates and screens the generated candidate paths. The evaluation process is mainly based on the key indicator of path length. The system calculates the actual length of each candidate path and selects the shortest path as the final travel path for the sub-UAV corresponding to the forest layer. The reason for choosing the shortest path is that it can not only save flight time and energy consumption to the greatest extent, but also improve the efficiency of species information collection. When determining the final travel path, the system will also smooth the path, eliminate mutation points in the path, and enable the UAV to perform flight missions more smoothly. This optimization method based on path length not only ensures the efficient completion of the collection task, but also minimizes energy consumption and improves the work efficiency of the entire system.

[0066] Step 104: Control the corresponding sub-UAVs according to each travel path to collect species in each forest layer, and obtain the species image and species distribution position corresponding to each forest layer.

[0067] Among them, species images refer to high-definition photos of target species taken by the sub-UAV through the high-resolution camera carried during the flight path. These images include not only visible light images of species, but also multi-band image data collected by multispectral sensors, which are used to comprehensively record visual information such as the appearance characteristics, morphological structure, etc. of the species.

[0068] Species distribution refers to the three-dimensional coordinate information of the species' location recorded by the drone based on the onboard positioning system (such as GPS, RTK, etc.) while collecting species images. These coordinate information accurately records the spatial position of each photographed species in the corresponding forest layer, including its longitude, latitude and altitude values, thereby constructing a detailed distribution map of the species in the three-dimensional space of the forest.

[0069] Specifically, after determining the path through each forest layer, the system needs to control the sub-UAV to collect species information along the planned path. In specific implementation, the system first converts each path into a series of waypoint coordinates, each of which contains control parameters such as position, heading and flight speed. Based on these parameters, the system sends flight control instructions to each sub-UAV through the wireless communication network, driving them to start from their respective second hovering positions and carry out collection work according to the preset path. During the collection process, each sub-UAV is equipped with a high-resolution camera and a multispectral sensor to collect image information of species. The system dynamically adjusts the flight attitude and camera parameters of the sub-UAV according to the distribution characteristics of the species gathering area. When the sub-UAV approaches the target species, it will automatically reduce the flight speed and adjust to the best shooting angle, while triggering the camera and sensor to collect data. The collected data includes high-definition images, multispectral information and corresponding spatial position coordinates of the species. To ensure the accuracy of the data, the system will also record the timestamp and environmental parameters of the collection. Through this precise control and automatic collection method, each sub-UAV can complete high-quality species information collection in the forest layer it is responsible for. The collected species images and distribution location data not only contain the morphological characteristics of the species, but also record their precise location information in three-dimensional space. The collection process of these data fully utilizes the pre-planned travel path, which not only ensures the integrity of the collection but also improves work efficiency.

[0070] Based on the above embodiment, as an optional embodiment, in step 104: controlling the corresponding sub-UAVs to collect species in each forest layer according to each travel path to obtain the species image and species distribution position corresponding to each forest layer, this step may also include the following steps:

[0071] Step 501: In each forest layer, the travel path is divided into multiple image acquisition points; the sub-UAV is controlled to arrive at each image acquisition point to hover and collect image samples at multiple angles.

[0072] Specifically, the system needs to refine the planned travel path into multiple specific image collection points to achieve accurate species information collection. In specific implementation, the system first sets image collection points at preset intervals on the travel path according to the distribution density and collection requirements of the species gathering area, ensuring that the distribution of these collection points can cover all target species around the path. When the sub-UAV arrives at each image collection point, the system will control it to enter a hovering state, and drive the camera to rotate 360 ​​degrees through the onboard gimbal system to collect multiple sets of image samples from different perspectives. This multi-angle acquisition method can ensure the acquisition of complete visual information of the species and improve the accuracy of subsequent identification. Through precise position control and attitude adjustment, the system ensures the quality and integrity of the image samples at each collection point.

[0073] Step 502: Perform image recognition on each collected image sample to determine the corresponding species type and species spatial position.

[0074] Specifically, the system performs intelligent processing and recognition on the collected image samples. First, the system uses an image preprocessing algorithm to reduce noise, enhance and correct the original image to improve image quality. Then, the processed image is analyzed using a deep learning species recognition model, which extracts image features through a pre-trained convolutional neural network and matches these features with a species feature library to determine the specific type of species in the image. At the same time, the system combines the real-time location information, camera parameters and shooting angle of the sub-UAV, and calculates the precise spatial position of each identified species through a three-dimensional space coordinate conversion algorithm. This deep learning-based recognition method can not only accurately determine the species type, but also determine its specific spatial location information in the forest layer.

[0075] Step 503: associate each species type with the corresponding image sample to obtain the species image of the forest layer, and combine the spatial positions of each species into the species distribution position of the forest layer.

[0076] Specifically, the system systematically organizes and associates the recognition results. First, the type information of each identified species is associated with its corresponding multi-angle image sample to form a complete species image data set. This data set not only contains the basic image information of the species, but also includes supporting information such as shooting parameters and environmental conditions. At the same time, the system integrates the spatial location information of each species to generate the overall species distribution location data of the forest layer. This data organization method not only ensures the integrity of species information, but also establishes a corresponding relationship between image data and spatial distribution data, providing systematic data support for subsequent species distribution analysis and ecological research. Through this association and organization method, the system finally formed a complete data set containing species images and distribution locations, realizing the comprehensive recording and effective management of forest layer species information.

[0077] Based on the above embodiment, as an optional embodiment, in step 104: controlling the corresponding sub-UAVs to collect species in each forest layer according to each travel path to obtain the species image and species distribution position corresponding to each forest layer, this step may also include the following steps:

[0078] Step 504: Obtain the remaining power and remaining travel path length of each sub-UAV; and calculate the remaining flight mileage of each sub-UAV based on the remaining power.

[0079] Specifically, the system needs to monitor the energy status and remaining mission volume of the sub-UAV in real time to ensure that the flight mission can be completed safely. In specific implementation, the system first obtains real-time power data through the battery management system of each sub-UAV, and calculates the remaining travel path length based on the distance from the current position to the end of the travel path. Subsequently, based on the battery characteristics, load conditions and environmental parameters of the sub-UAV, the system calculates the maximum flight mileage that can be supported by the current remaining power through an energy consumption model. This real-time monitoring and calculation mechanism can accurately evaluate the remaining operating capacity of the sub-UAV, provide a basis for subsequent flight parameter adjustments, and effectively prevent mission interruptions or safety accidents caused by insufficient power.

[0080] Step 505: For each sub-UAV, when the remaining flight mileage is less than a preset multiple of the remaining travel path length, the flight speed and flight altitude of the sub-UAV are adjusted according to the remaining power.

[0081] Specifically, the system needs to dynamically adjust the flight parameters of the sub-UAVs according to the energy assessment results to optimize energy use and ensure mission completion. In specific implementation, the system first compares the remaining flight mileage of each sub-UAV with its remaining path length. When the remaining flight mileage is less than a preset multiple (e.g., 1.5 times) of the remaining path length, the system starts the energy-saving control strategy. According to the specific level of remaining power, the system calculates the best combination of flight speed and flight altitude through an optimization algorithm. Usually, the system will appropriately reduce the flight speed to reduce air resistance consumption, and adjust the flight altitude to the optimal energy-saving altitude. This adaptive parameter adjustment strategy can not only effectively extend the flight time, but also ensure that the sub-UAV has enough power to return safely, while ensuring that the necessary image acquisition tasks are completed. Through this intelligent energy management method, the system significantly improves the reliability and completion rate of the task.

[0082] Step 105: Generate a species distribution report for the target area based on the species images and species distribution locations corresponding to each forest layer.

[0083] Among them, the species distribution report refers to a systematic report document generated by the system after data processing and analysis based on the species images and species distribution location data collected by the sub-UAV in each forest layer. The report comprehensively displays the distribution characteristics and resource status of species in the target area in various forms such as text, data, and charts.

[0084] Specifically, after completing the collection of species information of each forest layer, the system needs to integrate and analyze the collected data and generate a species distribution report for the target area in order to comprehensively display and analyze the species resources in the target area. In the specific implementation, the system first imports the species images and species distribution location data collected from each forest layer into the data processing platform. For the species image data, the system classifies and organizes them, centrally displays the multi-angle images of the same species, and attaches detailed feature descriptions of the species. For the species distribution location data, the system constructs a three-dimensional distribution model through a spatial analysis algorithm to calculate the spatial distribution density, aggregation degree and vertical stratification characteristics of each species. The system then automatically generates a species distribution report containing multiple dimensions based on these processed data. The report includes multiple parts such as a species resource list, quantity statistics, spatial distribution map, and density heat map. In the species resource list, the system lists all species types identified in the target area, and is accompanied by corresponding typical images and feature descriptions. In the quantity statistics part, the system calculates the number, density and proportion of each species, and displays them intuitively in the form of charts. In the spatial distribution map, the system converts the species distribution location data into a three-dimensional visualization model to clearly display the distribution of each species in different forest layers. In the density heat map section, the system uses color depth to indicate the species density in different areas, helping to identify species-rich areas. Through this systematic data integration and analysis, the species distribution report generated not only intuitively displays the spatial distribution characteristics of species in the target area, but also provides detailed species resource statistics, providing a decision-making basis for subsequent ecological monitoring, species protection and resource management.

[0085] Based on the above embodiment, as an optional embodiment, in step 105: generating a species distribution report of the target area based on the species images and species distribution positions corresponding to each forest layer, this step may also include the following steps:

[0086] Step 601: extracting features from species images of each forest layer to obtain species feature information of each forest layer; classifying and counting the species feature information to obtain species type distribution of each forest layer.

[0087] Specifically, the system first needs to conduct an in-depth analysis of the collected species images to obtain the characteristic information of the species and perform classification statistics. In the specific implementation, the system uses a deep learning feature extraction algorithm to process the species images of each forest layer, and extracts multi-dimensional feature parameters including morphological features, texture features, color features, etc. The system extracts these features through a convolutional neural network to form feature vectors, and matches these feature vectors with the pre-trained species feature library to complete the accurate identification and classification of species. Based on the identification results, the system conducts a statistical analysis of the species types in each forest layer, calculates the number, density and distribution ratio of each species, and thus obtains the distribution of species types in each forest layer. This feature extraction and classification method based on deep learning can accurately identify and count the species types in each forest layer, providing a reliable data basis for subsequent distribution analysis.

[0088] Step 602: Generate a species spatial distribution heat map of the target area based on the species distribution locations of each forest layer.

[0089] Specifically, the system needs to visualize the spatial distribution information of species and generate an intuitive heat map. In specific implementation, the system first integrates the species distribution location data of each forest layer into a unified three-dimensional coordinate system. Then, the system uses the kernel density estimation algorithm to calculate the species density values ​​at different locations in the target area. Based on these density values, the system uses a color gradient mapping method to convert the species density into the color depth of the heat map, where high-density areas are displayed as warm colors and low-density areas are displayed as cold colors. The system also generates multi-layer heat maps based on the height information of different forest layers, and forms a complete spatial distribution heat map through three-dimensional superposition. This visualization method can intuitively display the distribution patterns and aggregation characteristics of species in space, effectively supporting ecological analysis and management decisions.

[0090] Step 603: Integrate the species type distribution of each forest layer and the species spatial distribution heat map into a species distribution report of the target area.

[0091] Specifically, the system will systematically integrate the obtained species type distribution and spatial distribution heat map to form a complete species distribution report. In the specific implementation, the system first constructs the basic framework of the report, including species overview, distribution characteristics, statistical analysis and other main parts. Then, the system inserts the species type distribution data of each forest layer into the report in the form of tables and charts, clearly showing the quantity and proportional relationship of each species. At the same time, the system adds the species spatial distribution heat map to the report as an important visualization content, and provides a detailed distribution characteristic analysis description. The system also automatically generates relevant statistical charts and analysis conclusions to form a complete report document. This systematic integration method not only realizes the comprehensive display of species distribution information, but also provides a scientific analysis basis, which can effectively support the development of ecological monitoring and protection work.

[0092] Reference Figure 2 , is a species information collection system based on drones provided in an embodiment of the present application, the system comprises: an information acquisition module, a path determination module, a species collection module, and a report generation module, wherein:

[0093] An information acquisition module is used to acquire forest spatial information of a target area, and generate a forest layer distribution map of the target area based on forest layer height data and interlayer distance data in the forest spatial information;

[0094] A path determination module is used to determine the first hovering position of the master drone and the second hovering positions of the sub-drones corresponding to the multiple forest layers according to the forest layer distribution map, and receive the initial species coordinate information of each forest layer collected after the master drone moves to the first hovering position; and determine the travel path of the sub-drones corresponding to each forest layer by combining the initial species coordinate information of each forest layer and the second hovering position;

[0095] The species collection module controls the corresponding sub-UAVs according to each travel path to collect species in each forest layer, and obtains the species images and species distribution locations corresponding to each forest layer;

[0096] The report generation module is used to generate a species distribution report for the target area based on the species images and species distribution locations corresponding to each forest layer.

[0097] Based on the above embodiments, the information acquisition module is also used to perform three-dimensional reconstruction processing on the forest spatial information to obtain three-dimensional point cloud data of the target area; based on the three-dimensional point cloud data, the vegetation density information at multiple height positions is extracted; according to the vegetation density information and the inter-layer distance data, the boundary positions of multiple forest layers are determined; the boundary positions of each forest layer are mapped to a preset plane image to obtain a forest layer distribution map of the target area.

[0098] On the basis of the above embodiments, the path determination module is also used to extract the vertical connection areas between the forest layers according to the forest layer distribution map; determine the horizontal activity range of each forest layer based on the boundary position of each forest layer; determine multiple candidate hovering positions above the forest layer with the highest height, and based on the shooting angle of the master drone, determine the area of ​​the vertical connection area covered by the master drone at each candidate hovering position; use the candidate hovering position with the largest covered vertical connection area as the first hovering position of the master drone; determine the second hovering position of the corresponding sub-drone based on the height of each forest layer and the center position of the horizontal activity range.

[0099] Based on the above embodiments, the path determination module is also used to obtain obstacle distribution data within each forest layer; based on the initial species coordinate information of each forest layer, the species distribution of each forest layer is density clustered to obtain corresponding multiple species aggregation areas; in each forest layer, combined with the obstacle distribution data and the second hovering position, multiple candidate paths are generated for the sub-UAV to reach each species aggregation area; the candidate path with the shortest path length is selected as the travel path of the sub-UAV corresponding to the forest layer.

[0100] Based on the above embodiments, the species collection module is also used to divide the travel path into multiple image collection points in each forest layer; control the sub-UAV to reach each image collection point to hover and collect image samples at multiple angles; perform image recognition on each collected image sample to determine the corresponding species type and species spatial position; associate each species type with the corresponding image sample to obtain the species image of the forest layer, and combine the spatial positions of each species into the species distribution position of the forest layer.

[0101] Based on the above embodiments, the species collection module is also used to obtain the remaining power and remaining travel path length of each sub-UAV; based on the remaining power, the remaining flight mileage of each sub-UAV is calculated; for each sub-UAV, when the remaining flight mileage is less than a preset multiple of the remaining travel path length, the flight speed and flight altitude of the sub-UAV are adjusted according to the remaining power.

[0102] Based on the above embodiments, the report generation module is also used to extract features from species images of each forest layer to obtain species characteristic information of each forest layer; classify and count the characteristic information of each species to obtain the species type distribution of each forest layer; combine the species distribution positions of each forest layer to generate a species spatial distribution heat map of the target area; integrate the species type distribution of each forest layer and the species spatial distribution heat map into a species distribution report for the target area.

[0103] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0104] The present application also discloses an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0105] The communication bus 302 is used to realize the connection and communication between these components.

[0106] The user interface 303 may include a display interface and a camera interface. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0107] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0108] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 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 (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface diagrams and applications, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0109] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 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 a touch function, a sound playback function, an image playback function, 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 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a method for collecting species information based on a drone.

[0110] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program stored in the memory 305 for a species information collection method based on a drone. When executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0111] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0112] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which 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 service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0113] 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.

[0114] In addition, each functional unit in each embodiment of the present application 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.

[0115] If the integrated 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 memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0116] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0117] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not recorded in the present disclosure. The description and examples are to be regarded as exemplary only.

Claims

1. A method for collecting species information based on drones, characterized in that: include: Acquire forest spatial information of a target area, and generate a forest layer distribution map of the target area based on forest layer height data and interlayer distance data in the forest spatial information; Determine, according to the forest layer distribution map, a first hovering position of the master drone and second hovering positions of the slave drones corresponding to the plurality of forest layers, and receive initial species coordinate information of each of the forest layers collected after the master drone moves to the first hovering position; Determine the travel path of the sub-UAV corresponding to each forest layer by combining the initial species coordinate information of each forest layer and the second hovering position; According to each of the travel paths, the corresponding sub-drones are controlled to collect species in each of the forest layers, so as to obtain species images and species distribution positions corresponding to each of the forest layers; Based on the species images and species distribution positions corresponding to each of the forest layers, a species distribution report for the target area is generated.

2. The method for collecting species information based on drones according to claim 1, characterized in that: The generating of the forest layer distribution map of the target area based on the forest layer height data and the inter-layer distance data in the forest spatial information includes: Performing three-dimensional reconstruction processing on the forest spatial information to obtain three-dimensional point cloud data of the target area; Extracting vegetation density information at multiple height positions based on the three-dimensional point cloud data; Determining the boundary positions of multiple forest layers according to the vegetation density information and the inter-layer distance data; The boundary position of each forest layer is mapped to a preset plane image to obtain a forest layer distribution map of the target area.

3. The method for collecting species information based on drones according to claim 1, characterized in that: The determining, according to the forest layer distribution map, a first hovering position of the master UAV and second hovering positions of the slave UAVs corresponding to the plurality of forest layers comprises: Extracting vertically connected areas between the forest layers according to the forest layer distribution map; Based on the boundary position of each of the forest layers, determining the horizontal activity range of each of the forest layers; Determine a plurality of candidate hovering positions above the forest layer with the highest height, and determine the vertically connected area covered by the master control drone at each of the candidate hovering positions based on the shooting angle of the master control drone; The candidate hovering position with the largest vertically connected area covered is used as the first hovering position of the master control drone; Based on the height of each forest layer and the center position of the horizontal activity range, the second hovering position of the corresponding sub-UAV is determined.

4. The method for collecting species information based on drones according to claim 1, characterized in that: The step of combining the initial species coordinate information of each forest layer and the second hovering position to determine the travel path of the sub-UAV corresponding to each forest layer includes: Obtaining obstacle distribution data within each of the forest layers; Based on the initial species coordinate information of each forest layer, density clustering is performed on the species distribution of each forest layer to obtain a corresponding plurality of species aggregation areas; In each of the forest layers, combining the obstacle distribution data and the second hovering position, generating a plurality of candidate paths for the sub-UAV to reach each of the species gathering areas; The candidate path with the shortest path length is selected as the travel path of the sub-UAV corresponding to the forest layer.

5. The method for collecting species information based on drones according to claim 1, characterized in that: The controlling of the corresponding sub-drones according to each of the travel paths to collect species in each of the forest layers to obtain species images and species distribution positions corresponding to each of the forest layers includes: In each of the forest layers, the travel path is divided into a plurality of image acquisition points; Controlling the sub-drone to arrive at each of the image collection points to hover and collect image samples at multiple angles; Performing image recognition on each of the collected image samples to determine the corresponding species type and species spatial position; Each of the species types is associated with a corresponding image sample to obtain a species image of the forest layer, and the spatial positions of each of the species are combined into a species distribution position of the forest layer.

6. The method for collecting species information based on drones according to claim 1, characterized in that: Generating a species distribution report of the target area based on the species images and species distribution positions corresponding to each of the forest layers includes: Extracting features from the species images of each forest layer to obtain species feature information of each forest layer; Classify and count the characteristic information of each species to obtain the species type distribution of each forest layer; Combining the species distribution positions of each of the forest layers, generating a species spatial distribution heat map of the target area; The species type distribution of each forest layer and the species spatial distribution heat map are integrated into a species distribution report of the target area.

7. The method for collecting species information based on drones according to claim 1, characterized in that: The controlling the corresponding sub-drones to collect species in each forest layer according to each of the travel paths also includes: Obtaining the remaining power and remaining travel path length of each of the sub-drones; Calculating the remaining flight mileage of each of the sub-drones based on the remaining power; For each of the sub-drones, when the remaining flight mileage is less than a preset multiple of the remaining travel path length, the flight speed and flight altitude of the sub-drone are adjusted according to the remaining power.

8. A species information collection system based on drones, characterized in that: The system comprises: An information acquisition module, used to acquire forest spatial information of a target area, and generate a forest layer distribution map of the target area based on forest layer height data and interlayer distance data in the forest spatial information; A path determination module is used to determine the first hovering position of the master drone and the second hovering positions of the sub-drones corresponding to the multiple forest layers according to the forest layer distribution map, and receive the initial species coordinate information of each of the forest layers collected after the master drone moves to the first hovering position; and determine the travel path of the sub-drones corresponding to each of the forest layers in combination with the initial species coordinate information of each of the forest layers and the second hovering position; A species collection module controls the corresponding sub-UAVs according to the travel paths to collect species in each forest layer, and obtains species images and species distribution positions corresponding to each forest layer; The report generation module is used to generate a species distribution report for the target area based on the species images and species distribution locations corresponding to each of the forest layers.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the drone-based species information collection method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the drone-based species information collection method as described in any one of claims 1-7 is executed.

Images