Forest ecological environment monitoring method and device based on data analysis and electronic equipment

Abstract

The application provides a forest ecological environment monitoring method and device based on data analysis and electronic equipment, the method comprises the following steps: obtaining sensing data of sensors distributed in a honeycomb grid; performing data cleaning and signal filtering on each sensing data to obtain filtered denoising sensing data; performing feature analysis on the denoising sensing data to obtain feature data; obtaining video images collected by a UAV in the honeycomb grid, and fusing the feature data in the video images. By obtaining sensing data collected by multiple types of sensors distributed in a honeycomb grid, it can be ensured that the forest to be measured is globally covered, and systematic observation of the forest to be measured is realized. Moreover, the UAV collects video images of the forest to be measured in the honeycomb grid, which can improve the flight efficiency of the UAV and realize full coverage of the forest to be measured, and the linkage of ground sensing data and sky video images can be realized, so that the environment detection of the forest to be measured is more efficient and accurate.

Description

Technical Field

[0001] This invention relates to the field of environmental monitoring technology, and in particular to a method, device, and electronic equipment for monitoring forest ecological environment based on data analysis. Background Technology

[0002] In the face of the challenges of global climate change and sustainable development, forest ecological environment monitoring has become increasingly important. The integrated application of new technologies such as the Internet of Things, satellite remote sensing, drones, and artificial intelligence has made forest monitoring more accurate, efficient, and intelligent.

[0003] Currently, forest ecological environment monitoring mainly relies on fixed-location sensors for data collection and analysis using deep learning models. The resulting analysis often reflects only a localized forest ecosystem, failing to provide comprehensive global ecological environment monitoring and analysis, leading to significant errors. Furthermore, achieving full forest coverage presents challenges. The scattered deployment of sensors, coupled with the fact that existing technologies using latitude and longitude grids are affected by terrain variations and unequal spatial distances between adjacent sensors, results in monitoring blind spots in certain areas. This leads to inaccurate global forest monitoring and analysis, and also hinders effective integration with drone monitoring. Summary of the Invention

[0004] Therefore, it is necessary to provide a data analysis-based method, device, and electronic equipment for monitoring the forest ecological environment to address the aforementioned technical problems.

[0005] A data analysis-based method for monitoring forest ecological environment includes: Acquire sensing data from multiple types of sensors distributed in a cellular grid pattern; Data cleaning and signal filtering are performed on the sensor data of each type to obtain the filtered denoised sensor data of each type. Feature analysis is performed on various types of denoised sensor data to obtain feature data; The system acquires video images collected by a drone in a cellular grid pattern, fuses the feature data into the video images, and outputs the video images with the fused feature data.

[0006] In one embodiment, the step of acquiring video images collected by the drone in a cellular grid pattern and fusing the feature data in the video images includes: Obtain the geographic features corresponding to the cellular grid; Based on the geographical features, a flight path for the UAV is generated, and the UAV is controlled to fly along the flight path and collect video images. The video images captured by the drone are acquired, and the feature data is fused into the video images.

[0007] In one embodiment, the step of acquiring sensing data from multiple types of sensors distributed in a cellular grid pattern further includes: The geographical features of the forest to be tested are obtained, including geographical coordinates, geographical elevation, and vegetation type. Based on the aforementioned geographical features, a cellular grid is established for the forest under test in planar projection; Based on the cellular grid, the various types of sensors are deployed to the forest to be tested.

[0008] In one embodiment, the step of establishing a cellular grid of the forest to be measured under planar projection based on the geographical features includes: Based on the digital elevation model, according to the geographic coordinates and the geographic altitude, the contour projection of the forest to be measured on the plane is generated to obtain the coordinate plane of the forest to be measured. Based on the vegetation type and the geographic coordinates, the cellular grid is defined, and the coordinate plane of the forest to be measured is divided according to the cellular grid to obtain the cellular grid of the forest to be measured under the plane projection.

[0009] In one embodiment, the step of performing feature analysis on various types of denoised sensor data to obtain feature data includes: Obtain the weighting factors for each type of sensor data; Based on the weighting factors of each type, the denoised sensor data of each type are weighted and fused to obtain the fused weighted data of each type. The fused and weighted data of various types are input into the prediction model to make predictions and obtain the predicted data. Feature analysis is performed on the various types of fused weighted data to obtain the feature data; The step of acquiring video images collected by the drone in a cellular grid pattern and fusing the feature data in the video images includes: The predicted data and the feature data are fused together in the video images collected by the drone in a cellular grid pattern.

[0010] In one embodiment, the plurality of sensors include at least a negative ion sensor, a pressure sensor, a temperature sensor, a humidity sensor, a wind speed sensor, and a dust sensor.

[0011] In one embodiment, the step of performing data cleaning and signal filtering on the various types of sensor data to obtain filtered denoised sensor data of various types includes: The sensor data of each type is cleaned using a threshold rule filtering method, and then the moving average method is used to filter the signal of each type of sensor data to obtain the filtered denoised sensor data of each type.

[0012] A forest ecological environment monitoring device based on data analysis, comprising: The sensor data acquisition module is used to acquire sensor data from multiple types of sensors distributed in a cellular grid pattern. The noise reduction data processing module is used to perform data cleaning and signal filtering on the various types of sensor data to obtain the filtered noise reduction sensor data of each type. The feature data acquisition module is used to perform feature analysis on various types of denoised sensor data to obtain feature data. The fusion module is used to acquire video images collected by the UAV in a cellular grid pattern, fuse the feature data into the video images, and output the video images with the fused feature data.

[0013] An electronic device includes a memory and a processor, the memory storing a computer program, characterized in that the processor executes the computer program to perform the following steps: Acquire sensing data from multiple types of sensors distributed in a cellular grid pattern; Data cleaning and signal filtering are performed on the sensor data of each type to obtain the filtered denoised sensor data of each type. Feature analysis is performed on various types of denoised sensor data to obtain feature data; The system acquires video images collected by a drone in a cellular grid pattern, fuses the feature data into the video images, and outputs the video images with the fused feature data.

[0014] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Acquire sensing data from multiple types of sensors distributed in a cellular grid pattern; Data cleaning and signal filtering are performed on the sensor data of each type to obtain the filtered denoised sensor data of each type. Feature analysis is performed on various types of denoised sensor data to obtain feature data; The system acquires video images collected by a drone in a cellular grid pattern, fuses the feature data into the video images, and outputs the video images with the fused feature data.

[0015] The aforementioned data analysis-based forest ecological environment monitoring methods, devices, and electronic equipment, by acquiring sensor data collected from multiple types of sensors distributed in a cellular grid, can ensure global coverage of the forest under test, enabling systematic observation of the forest under test. Furthermore, the UAV's acquisition of video images of the forest under test according to the cellular grid can improve the UAV's flight efficiency and achieve full coverage of the forest under test. It can also realize the linkage between ground sensor data and aerial video images, thereby making the environmental detection of the forest under test more efficient and accurate. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a data analysis-based forest ecological environment monitoring method in one embodiment; Figure 2 This is a diagram of the internal structure of an electronic device in one embodiment. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] Example 1 In this embodiment, please refer to Figure 1 This paper provides a data analysis-based method for monitoring the forest ecological environment, which includes: Step 110: Acquire sensing data from multiple types of sensors distributed in a cellular grid pattern.

[0019] In this embodiment, various types of sensors are deployed in the forest to be tested in a cellular grid layout. Multiple types of sensors are deployed within each cellular grid.

[0020] In one embodiment, the plurality of sensors include at least a negative ion sensor, a pressure sensor, a temperature sensor, a humidity sensor, a wind speed sensor, and a dust sensor.

[0021] In this embodiment, negative ion concentration, air pressure, temperature, humidity, wind speed (direction), and PM2.5 dust content of the forest under test are collected in a honeycomb grid pattern using negative ion sensors, air pressure sensors, temperature sensors, humidity sensors, wind speed sensors, and dust sensors. In this embodiment, each honeycomb grid contains a negative ion sensor, air pressure sensor, temperature sensor, humidity sensor, wind speed sensor, and dust sensor. This allows for the collection of different data for each honeycomb grid of the forest under test.

[0022] In this embodiment, the sensors are distributed in a honeycomb grid, enabling more accurate and comprehensive collection of data on the forest under test. For example, each cell in the honeycomb grid is a regular hexagon or octagon. It is worth noting that in traditional forest ecological monitoring, sensors are distributed according to latitude and longitude. This has problems, as the deployment density of sensors is affected by terrain, making it impossible to accurately reflect the various values ​​of the forest under different terrain conditions. In this embodiment, the honeycomb grid deployment of sensors ensures optimized and non-overlapping global coverage of the monitoring area, eliminating blind spots and being unaffected by terrain. Furthermore, it minimizes the number of nodes and integrates previously scattered and isolated monitoring points into a systematic observation network.

[0023] Step 120: Perform data cleaning and signal filtering on the sensor data of each type to obtain the filtered denoised sensor data of each type.

[0024] In this embodiment, data cleaning of the sensor data collected by the sensor can effectively remove outliers; while filtering of the sensor data can remove random noise interference during the data acquisition process and make the effective sensor data smoother, which is convenient for subsequent processing.

[0025] Step 130: Perform feature analysis on the various types of denoised sensor data to obtain feature data.

[0026] In this embodiment, feature analysis is performed on various types of denoised sensor data, including calculating the mean, variance, maximum and minimum values ​​of each type of fused weighted data, and analyzing the average value, fluctuation, extreme values ​​and distribution patterns of each fused weighted data to obtain feature data. In some embodiments, principal component analysis can also be used to calculate the comprehensive index data of multiple different types of fused weighted data to obtain feature data.

[0027] Step 140: Acquire video images collected by the drone in a cellular grid pattern, fuse the feature data into the video images, and output the video images fused with the feature data.

[0028] In this embodiment, the drone flies along a honeycomb grid, capturing video images during flight to achieve comprehensive coverage of the forest under test. Notably, the honeycomb grid establishes a regular coordinate reference system on the ground. This coordinate reference system allows the video and image data collected by the drone while flying along the grid to be precisely matched and fused spatially with ground-based sensor data. This allows the video images to display the characteristic data, and finally, the video images fused with the characteristic data are output, presenting the ecological environment monitoring results of the forest under test. For example, real-time temperature and humidity data within the honeycomb grid can be overlaid on video images of the area captured by the drone, enabling linked analysis of ground and air data.

[0029] In the above embodiments, by acquiring sensor data collected by multiple types of sensors distributed in a cellular grid, it is possible to ensure that the forest under test is globally covered, enabling systematic observation of the forest under test. Furthermore, the UAV's acquisition of video images of the forest under test according to the cellular grid can improve the flight efficiency of the UAV and achieve full coverage of the forest under test. It can also realize the linkage between ground sensor data and sky video images, thereby making the environmental detection of the forest under test more efficient and accurate.

[0030] In one embodiment, the step of acquiring video images collected by the drone in a cellular grid pattern and fusing the feature data in the video images includes: Obtain the geographic features corresponding to the cellular grid; Based on the geographical features, a flight path for the UAV is generated, and the UAV is controlled to fly along the flight path and collect video images. The video images captured by the drone are acquired, and the feature data is fused into the video images.

[0031] In this embodiment, the cellular grid is first analyzed to obtain the geographical features corresponding to each cellular grid. Based on the geographical features, the center of each cellular grid is determined and designated as a central node. Based on the geographical elevation within each cellular grid, the Dijkstra algorithm is used to calculate the shortest path traversing each central node. The flight order of each cellular grid is determined based on the shortest path. Based on the real-time wind speed data collected by the wind speed sensor and the vegetation type, the intra-grid path within each cellular grid is determined. The real-time wind data includes wind force data, wind speed data, and wind direction data. Within the grid, the flight direction is determined along the downwind direction. When the vegetation types in two adjacent cellular grids are the same, the intra-grid path within that cellular grid is determined as the diagonal line connecting the cellular grids, and the endpoint of the diagonal line connecting the current cellular grid is used as the starting point of the diagonal line connecting the next cellular grid to determine the intra-grid path. When the vegetation types in two adjacent cellular grids are different, the intra-grid path is formed by traversing along the edges of the cellular grid. The flight route of the UAV is generated according to the flight order and intra-grid path of each cellular grid.

[0032] In this embodiment, Dijkstra's algorithm, combined with the geographical elevation within the cell grid, is used to calculate the shortest path for the UAV to traverse all cell grids, thereby determining the flight order across each cell grid. Subsequently, the flight path within each cell grid is determined; this flight path is called the intra-grid path, which is determined based on the vegetation type within the cell grid. If adjacent cell grids have the same vegetation type, the UAV flies diagonally, i.e., from southeast to northwest within this cell grid, and from southwest to northeast upon entering the next cell grid. This allows for rapid flight due to the same vegetation type, enabling comprehensive imaging within the cell grid. When the vegetation types differ, the UAV needs to fly in a circumferential pattern along the edge of the cell grid. Between adjacent cell grids, the UAV flies in a figure-eight pattern; for example, it flies clockwise within one cell grid, completes one circle, and then enters the next cell grid, flying counterclockwise. This reduces errors caused by different vegetation types. It is worth noting that different vegetation types have vastly different three-dimensional structures. For example, a simple diagonal flight path can only capture video footage of a narrow strip of land, such as tall trees and low shrubs, which may not be representative of the entire grid. However, a circular flight path (such as a figure-eight pattern) can cover a wider variety of points within the grid, thereby obtaining richer and more representative spatial distribution information on canopy height, canopy closure, leaf area index, and other parameters.

[0033] In one embodiment, the step of acquiring sensing data from multiple types of sensors distributed in a cellular grid pattern further includes: The geographical features of the forest to be tested are obtained, including geographical coordinates, geographical elevation, and vegetation type. Based on the aforementioned geographical features, a cellular grid is established for the forest under test in planar projection; Based on the cellular grid, the various types of sensors are deployed to the forest to be tested.

[0034] In this embodiment, the geographic features include geographic coordinates, geographic altitude, and vegetation type. The geographic coordinates are the longitude and latitude coordinates of the geographical location covered by the forest to be measured, and the geographic altitude is the elevation of the terrain where the forest is located. It is worth noting that forests are generally located in mountainous or hilly areas, resulting in uneven terrain with significant variations in elevation. Therefore, obtaining the geographic altitude when acquiring geographic features allows for more precise sensor deployment within the cellular grid and enables the UAV to adapt to different forest altitudes, resulting in more accurate flight. In this embodiment, the geographic features also include vegetation type. It should be understood that different vegetation types also affect sensor deployment and UAV flight. Therefore, in this embodiment, the coverage area of ​​the forest to be measured is projected onto a plane based on geographic coordinates and geographic altitude, and a cellular grid is drawn, with corresponding vegetation types associated within the cellular grid. This method of dividing the honeycomb grid comprehensively covers the area of ​​the forest to be measured and can adapt to different terrains and vegetation. Furthermore, projecting the forest and its geographical elevation onto a plane and dividing the grid on this plane eliminates errors caused by elevation variations. It's worth noting that in this embodiment, the honeycomb grid is divided on the planar projection of the forest, i.e., on a plane. This eliminates errors caused by elevation variations, ensuring that each honeycomb grid is distributed in a regular hexagon or octagon. However, after dividing the honeycomb grid, the vegetation type corresponding to the geographical coordinates of each point within the grid is associated. If vegetation type were considered during the division of the honeycomb grid, distortion and deformation would occur, leading to inaccurate grid division. Therefore, in this embodiment, when projecting the forest to be measured onto the plane and dividing it into a honeycomb grid, the vegetation type is not considered. The vegetation type is only associated after the honeycomb grid is divided. In this way, the honeycomb grid can be accurately divided on the plane, and the geographical elevation and vegetation type can be presented within the honeycomb grid. This allows the deployment of sensors and the flight of drones to take into account both geographical elevation and vegetation type, and avoids the drone's flight being hindered due to ignoring elevation.

[0035] In one embodiment, the step of establishing a cellular grid of the forest to be measured under planar projection based on the geographical features includes: Based on the digital elevation model, according to the geographic coordinates and the geographic altitude, the contour projection of the forest to be measured on the plane is generated to obtain the coordinate plane of the forest to be measured. Based on the vegetation type and the geographic coordinates, the cellular grid is defined, and the coordinate plane of the forest to be measured is divided according to the cellular grid to obtain the cellular grid of the forest to be measured under the plane projection.

[0036] In this embodiment, the forest to be measured is projected onto a plane, and the geographical elevations corresponding to different geographical coordinates are also projected onto the plane to form contour lines, thus obtaining the contour projection of the forest to be measured on the plane, thereby creating the coordinate plane of the forest to be measured. Subsequently, vegetation type and geographical coordinates are associated with a cellular grid, dividing the coordinate plane of the forest to be measured into multiple cellular grids. In this way, cellular grids can be accurately divided on the plane, and geographical elevation and vegetation type can be presented within the cellular grids. This allows the deployment of sensors and the flight of drones to take into account geographical elevation and vegetation type, avoiding flight obstacles caused by ignoring elevation.

[0037] In one embodiment, the step of performing feature analysis on various types of denoised sensor data to obtain feature data includes: Obtain the weighting factors for each type of sensor data; Based on the weighting factors of each type, the denoised sensor data of each type are weighted and fused to obtain the fused weighted data of each type. The fused and weighted data of various types are input into the prediction model to make predictions and obtain the predicted data. Feature analysis is performed on the various types of fused weighted data to obtain the feature data; The step of acquiring video images collected by the drone in a cellular grid pattern and fusing the feature data in the video images includes: The predicted data and the feature data are fused together in the video images collected by the drone in a cellular grid pattern.

[0038] In this embodiment, the weighting factors of each sensor data point represent the weight of the sensor data's impact on the forest ecological environment. For example, when assessing the comfort level of the forest ecological environment, negative oxygen ions and humidity have higher weights, while in forest fire risk early warning, humidity, temperature, and dust sensors have higher weights. In this embodiment, a dynamic weighting method is used to process the sensor data. For example, the current forest assessment model is obtained, and the weighting factors of each type of sensor data are obtained based on the current forest assessment model. This current forest assessment model includes forest ecological environment comfort assessment, forest fire risk assessment, and forest rainfall assessment. After obtaining the weighting factors of each sensor data point, the collected sensor data is weighted and fused to obtain fused weighted data. Subsequently, the fused weighted data undergoes prediction processing and feature analysis processing. In the prediction processing, the fused weighted data is input into a pre-trained prediction model to predict future forest ecological environment data. In the feature analysis processing, the mean, variance, maximum value, and minimum value of each type of fused weighted data are first calculated. The mean, variance, maximum value, and minimum value of each fused weighted data are then analyzed to obtain the average value, fluctuation, extreme values, and distribution pattern of each fused weighted data, thus obtaining feature data. In addition, in some embodiments, principal component analysis is used to calculate the comprehensive index data of multiple different types of fused weighted data to obtain feature data.

[0039] Subsequently, the predicted data and feature data are simultaneously displayed in the video images, enabling the video images to comprehensively showcase the monitoring results of the forest ecological environment.

[0040] In one embodiment, the step of performing data cleaning and signal filtering on the various types of sensor data to obtain filtered denoised sensor data of various types includes: The sensor data of each type is cleaned using a threshold rule filtering method, and then the moving average method is used to filter the signal of each type of sensor data to obtain the filtered denoised sensor data of each type.

[0041] In this embodiment, the threshold rule involves setting a maximum and a minimum filtering threshold. Data exceeding the maximum threshold and falling below the minimum threshold are cleaned and filtered, thus removing abnormal data. The moving average method calculates the average of multiple continuously collected data points within a fixed time window, using this average to represent the current measurement value. New data arrives, the oldest data is discarded, and the window is updated by sliding. This effectively suppresses random white noise, resulting in smoother data curves. Through data cleaning and signal filtering, the collected environmental data becomes more accurate, leading to more precise environmental data predictions and analysis results.

[0042] It should be understood that, althoughFigure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0043] Example 2 In this embodiment, a forest ecological environment monitoring device based on data analysis is provided, comprising: The sensor data acquisition module is used to acquire sensor data from multiple types of sensors distributed in a cellular grid pattern. The noise reduction data processing module is used to perform data cleaning and signal filtering on the various types of sensor data to obtain the filtered noise reduction sensor data of each type. The feature data acquisition module is used to perform feature analysis on various types of denoised sensor data to obtain feature data. The fusion module is used to acquire video images collected by the UAV in a cellular grid pattern and fuse the feature data into the video images.

[0044] In one embodiment, the fusion module includes: A geographic feature acquisition unit is used to acquire the geographic features corresponding to the cellular grid. A video image acquisition unit is used to generate a flight path for the UAV based on the geographical features, and to control the UAV to fly along the flight path and acquire video images. A data fusion unit is used to acquire video images collected by the UAV and fuse the feature data into the video images.

[0045] In one embodiment, the apparatus further includes: The geographic feature acquisition module is used to acquire the geographic features of the forest to be tested, wherein the geographic features include geographic coordinates, geographic altitude, and vegetation type; A cellular grid establishment module is used to establish a cellular grid of the forest to be measured under a planar projection based on the geographical features; The deployment module is used to deploy the various types of sensors to the forest to be tested based on the cellular grid.

[0046] In one embodiment, the cellular mesh establishment module includes: The plane generation unit is used to generate contour projections of the forest to be measured on a plane based on the digital elevation model, according to the geographic coordinates and the geographic altitude, to obtain the coordinate plane of the forest to be measured. A cellular grid establishment unit is used to define the cellular grid according to the vegetation type and the geographic coordinates, and to divide the coordinate plane of the forest to be measured according to the cellular grid to obtain the cellular grid of the forest to be measured under the plane projection.

[0047] In one embodiment, the feature data acquisition module includes: The weighting factor acquisition unit is used to acquire the weighting factors of various types of sensor data. The fusion weighted data acquisition unit is used to weight and fuse various types of denoised sensor data according to the weight factors of each type to obtain fusion weighted data of each type. The model prediction unit is used to input various types of fused weighted data into the prediction model to make predictions and obtain predicted data. The feature data acquisition unit is used to perform feature analysis on various types of fused weighted data to obtain the feature data; The fusion module is also used to acquire video images collected by the UAV in a cellular grid pattern, and to fuse the prediction data and the feature data in the video images.

[0048] In one embodiment, the plurality of sensors include at least a negative ion sensor, a pressure sensor, a temperature sensor, a humidity sensor, a wind speed sensor, and a dust sensor.

[0049] In one embodiment, the denoising data processing module is further configured to perform data cleaning on the various types of sensor data based on a threshold rule filtering method, and then use a moving average method to perform signal filtering on the various types of sensor data to obtain filtered denoised sensor data of various types.

[0050] Specific limitations regarding data analysis-based forest ecological environment monitoring devices can be found in the above-mentioned limitations on data analysis-based forest ecological environment monitoring methods, and will not be repeated here. Each unit in the aforementioned data analysis-based forest ecological environment monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These units can be embedded in or independent of the processor in the electronic device, or stored in the memory of the electronic device as software, so that the processor can call and execute the corresponding operations of each unit.

[0051] Example 3 In this embodiment, an electronic device is provided. Its internal structure diagram can be shown as follows: Figure 2As shown, the electronic device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs, and a database is deployed on the non-volatile storage medium. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with other electronic devices that have deployed application software. When the computer program is executed by the processor, it implements a data analysis-based forest ecological environment monitoring method. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0052] Those skilled in the art will understand that Figure 2 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0053] In one embodiment, an electronic device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the data analysis-based forest ecological environment monitoring method of any of the above embodiments. In one embodiment, the electronic device is a computer device.

[0054] Example 4 In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps in the data analysis-based forest ecological environment monitoring method in any of the above embodiments.

[0055] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0056] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0057] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A data analysis-based method for monitoring forest ecological environment, characterized in that, include: Acquire sensing data from multiple types of sensors distributed in a cellular grid pattern; Data cleaning and signal filtering are performed on the sensor data of each type to obtain the filtered denoised sensor data of each type. Feature analysis is performed on various types of denoised sensor data to obtain feature data; The system acquires video images collected by a drone in a cellular grid pattern, fuses the feature data into the video images, and outputs the video images with the fused feature data.

2. The method according to claim 1, characterized in that, The step of acquiring video images collected by the drone in a cellular grid pattern and fusing the feature data in the video images includes: Obtain the geographic features corresponding to the cellular grid; Based on the geographical features, a flight path for the UAV is generated, and the UAV is controlled to fly along the flight path and collect video images. The video images captured by the drone are acquired, and the feature data is fused into the video images.

3. The method according to claim 1, characterized in that, The step of acquiring sensing data from multiple types of sensors distributed in a cellular grid pattern also includes: The geographical features of the forest to be tested are obtained, including geographical coordinates, geographical elevation, and vegetation type. Based on the aforementioned geographical features, a cellular grid is established for the forest under test in planar projection; Based on the cellular grid, the various types of sensors are deployed to the forest to be tested.

4. The method according to claim 3, characterized in that, The step of establishing a cellular grid of the forest to be measured under planar projection based on the geographical features includes: Based on the digital elevation model, according to the geographic coordinates and the geographic altitude, the contour projection of the forest to be measured on the plane is generated to obtain the coordinate plane of the forest to be measured. Based on the vegetation type and the geographic coordinates, the cellular grid is defined, and the coordinate plane of the forest to be measured is divided according to the cellular grid to obtain the cellular grid of the forest to be measured under the plane projection.

5. The method according to claim 1, characterized in that, The steps for performing feature analysis on various types of denoised sensor data to obtain feature data include: Obtain the weighting factors for each type of sensor data; Based on the weighting factors of each type, the denoised sensor data of each type are weighted and fused to obtain the fused weighted data of each type. The fused and weighted data of various types are input into the prediction model to make predictions and obtain the predicted data. Feature analysis is performed on the various types of fused weighted data to obtain the feature data; The step of acquiring video images collected by the drone in a cellular grid pattern and fusing the feature data in the video images includes: The predicted data and the feature data are fused together in the video images collected by the drone in a cellular grid pattern.

6. The method according to any one of claims 1-5, characterized in that, The multiple sensors include at least a negative oxygen ion sensor, an air pressure sensor, a temperature sensor, a humidity sensor, a wind speed sensor, and a dust sensor.

7. The method according to any one of claims 1-5, characterized in that, The steps of performing data cleaning and signal filtering on the various types of sensor data to obtain filtered, denoised sensor data of various types include: The sensor data of each type is cleaned using a threshold rule filtering method, and then the moving average method is used to filter the signal of each type of sensor data to obtain the filtered denoised sensor data of each type.

8. A forest ecological environment monitoring device based on data analysis, characterized in that, include The sensor data acquisition module is used to acquire sensor data from multiple types of sensors distributed in a cellular grid pattern. The noise reduction data processing module is used to perform data cleaning and signal filtering on the various types of sensor data to obtain the filtered noise reduction sensor data of each type. The feature data acquisition module is used to perform feature analysis on various types of denoised sensor data to obtain feature data. The fusion module is used to acquire video images collected by the UAV in a cellular grid pattern and fuse the feature data into the video images.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images