Real-time forest vegetation parameter monitoring method based on unmanned aerial vehicle image

Abstract

The invention relates to the technical field of forest vegetation monitoring, in particular to a forest vegetation parameter real-time monitoring method based on unmanned aerial vehicle images, which comprises the following steps: starting an unmanned aerial vehicle, carrying out real-time image acquisition on a predetermined forest area through a camera, carrying out continuous image capture, synchronously calibrating the camera and setting matched differentiated illumination and depth-of-field conditions; and generating forest image acquisition data. According to the method, the chlorophyll concentration and the leaf area index can be accurately measured through analysis of different color wavelength reflectance, the understanding and tracking precision of the vegetation physiological state is improved, long-term vegetation changes can be carefully monitored through time sequence analysis, the prediction capacity of forest ecological behaviors is enhanced, and the method is suitable for popularization and application. Drought response and pest and disease damage signs are monitored in real time, the timeliness and accuracy of health state evaluation are enhanced, the real-time performance and continuity of data are ensured by dynamically updating a forest vegetation database, and the dynamic monitoring and decision support capacity of forest management is remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of forest vegetation monitoring, and in particular to a forest vegetation parameter real-time monitoring method based on unmanned aerial vehicle images. BACKGROUND

[0002] The technical field of forest vegetation monitoring involves the use of various sensors and remote sensing technologies to collect, analyze and interpret data related to forest vegetation. The technology has a wide range of applications, including satellite imaging, unmanned aerial vehicle aerial photography, ground sensor networks and advanced computing models, which can monitor key parameters such as changes in forest coverage, vegetation health, biomass estimation and carbon storage assessment. Through real-time monitoring of forest vegetation, it is possible to effectively predict and manage forest fire risks, pest and disease spread, and adaptation and mitigation measures for climate change.

[0003] Among them, the forest vegetation parameter real-time monitoring method refers to a method for tracking and evaluating vegetation changes in forest ecosystems in real time, including the use of real-time data transmission technologies such as satellite links or wireless sensor networks to quickly obtain data and respond. The main purpose is to improve the efficiency and speed of forest management, especially in the case of extreme weather events and sudden natural disasters, so that timely disaster warnings and management decision support can be taken to protect forest resources and maintain ecological balance.

[0004] Although the existing technology uses a variety of sensors and remote sensing technologies for forest monitoring, it still has deficiencies in real-time data acquisition and processing. The time delay and lower update frequency of satellite imaging often result in a lack of responsiveness to rapid environmental changes, limiting the ability to respond immediately to extreme weather events. Although ground sensor networks can provide detailed data, they face challenges in providing comprehensive coverage of vast forest areas, leaving data collection gaps. The limitations of the technology can lead to a slow response in emergency situations, increasing the difficulty of managing natural disasters such as forest fires and pest infestations, and affecting the efficiency of forest resource protection and the maintenance of ecological balance. SUMMARY

[0005] The purpose of the present application is to solve the shortcomings of the prior art and to propose a forest vegetation parameter real-time monitoring method based on unmanned aerial vehicle images.

[0006] In order to achieve the above-mentioned purpose, the present application adopts the following technical solution: a forest vegetation parameter real-time monitoring method based on unmanned aerial vehicle images, comprising the following steps: S1: Start the unmanned aerial vehicle, collect real-time images of the predetermined forest area through the camera, continuously capture images, synchronize the camera settings to match the differentiated lighting and depth of field conditions, and generate forest image acquisition data; S2: transmit the forest image acquisition data to the ground station, perform image sharpening processing on the image data, automatically adjust the contrast and brightness of the image, remove image noise caused by weather or equipment, and output the preprocessed forest image data; S3: perform feature analysis on the preprocessed forest image data, perform color change recognition, evaluate chlorophyll concentration by analyzing the reflectivity of different color wavelengths, calculate leaf area index, and quantitatively record the parameters to generate vegetation physiological parameter analysis results; S4: based on the vegetation physiological parameter analysis results, perform data fusion and model mapping, perform time series analysis, compare data in consecutive periods, analyze long-term trends of forest vegetation, and generate ecological behavior prediction analysis results; S5: based on the ecological behavior prediction analysis results, monitor abnormal changes including drought response and signs of pests and diseases, analyze the deviation of abnormal changes from known health standards, and real-time evaluate the health status of forest vegetation to generate forest health diagnosis results; S6: based on the forest health diagnosis results, monitor changes and patterns of forest health trends, and update vegetation ecological parameters in the database in synchronization, verify data persistence and accuracy, and generate forest vegetation dynamic monitoring records.

[0007] As a further scheme of the present application, the forest image acquisition data includes regional positioning information, light intensity data and depth of field adjustment parameters, the preprocessed forest image data includes adjusted contrast value, brightness level and noise removal record, the vegetation physiological parameter analysis results include chlorophyll concentration value, leaf area index and color wavelength reflectivity, the ecological behavior prediction analysis results include long-term trend data, time series analysis record and periodic comparison results, the forest health diagnosis results include drought response evaluation record, pest index and health standard deviation analysis results, and the forest vegetation dynamic monitoring records include health trend change data, ecological parameter update log and persistence verification results.

[0008] As a further scheme of the present application, the specific steps for starting the unmanned aerial vehicle, capturing real-time images of the predetermined forest area through the camera, and continuously capturing images, synchronously calibrating the camera settings to match the differentiated light and depth of field conditions, and generating forest image acquisition data are as follows, S101: start the unmanned aerial vehicle, set the flight height and speed to match the panoramic coverage of the forest area, optimize the flight path by positioning the flight route through GPS, and obtain flight coverage image data; S102: start the camera to continuously capture images through the flight coverage image data, adjust the aperture and shutter speed to match the light condition changes, and obtain real-time calibration image data; S103: using the real-time calibration image data, continuously monitoring the image quality, synthesizing continuous frames and constructing a complete forest coverage map, and obtaining forest image acquisition data.

[0009] As a further scheme of the present application, the forest image acquisition data is transmitted to the ground station, the image data is processed for image sharpening, the contrast and brightness of the image are automatically adjusted, the image noise caused by weather or equipment is removed, and the specific steps for outputting the preprocessed forest image data are, S201: starting data transmission between the unmanned aerial vehicle and the ground station, transmitting the forest image acquisition data to the ground station using an encrypted data communication protocol, monitoring the transmission state of the data packet to identify packet loss or errors, and implementing error correction measures to obtain complete transmission data; S202: based on the complete transmission data, analyzing the contrast and brightness level of the image data, adjusting the image parameters one by one to match the changes in external light, monitoring the image color saturation in real time and fine-tuning, and obtaining adjusted image data; S203: using the adjusted image data, identifying and removing noise in the image caused by weather or equipment failure, refining the image texture, and outputting the preprocessed forest image data.

[0010] As a further scheme of the present application, the preprocessed forest image data is analyzed for features, color change recognition is performed, the reflectivity of different color wavelengths is analyzed to evaluate the chlorophyll concentration, the leaf area index is calculated, and the parameters are quantitatively recorded to generate vegetation physiological parameter analysis results, and the specific steps are, S301: based on the preprocessed forest image data, extracting the reflectivity of all color wavelengths, quantitatively distinguishing colors through spectral analysis, recording the reflectivity data of different colors, and obtaining color wavelength analysis data; S302: using the color wavelength analysis data, evaluating the chlorophyll concentration by analyzing the reflectivity of green wavelength, integrating the reflectivity data and calculating the leaf area index, and obtaining the chlorophyll concentration and leaf area data; S303: integrating the chlorophyll concentration and leaf area data, recording all physiological parameters collected through quantitative analysis, organizing the data and unifying the format, and outputting the vegetation physiological parameter analysis results.

[0011] As a further scheme of the present application, the leaf area index is calculated according to the formula, ; wherein, represents the leaf area index, represents the reflectivity of green wavelength, represents the total ground area covered by the image, representing the number of pixels participating in the calculation, representing the difference value of reflectivity between wavelengths.

[0012] As a further scheme of the present application, based on the vegetation physiological parameter analysis result, data fusion and model mapping are performed, time series analysis is executed, data in a continuous period are compared, long-term change trend of forest vegetation is analyzed, and the specific steps for generating an ecological behavior prediction analysis result are, S401: The vegetation physiological parameter analysis result and historical ecological data are integrated, time series variation of seasonal chlorophyll concentration is identified through data docking, a preliminary time series model data is constructed and outputted; S402: Based on the preliminary time series model data, a trend line fitting is performed on long-term data, influence of key time nodes and environmental factors is calibrated, long-term change of periodic data is analyzed, and comprehensive trend analysis data is obtained; S403: The comprehensive trend analysis data is used to predict ecological change of vegetation, behavior patterns of vegetation growth and degradation are analyzed through comparison and analysis of data at key time points, and an ecological behavior prediction analysis result is generated.

[0013] As a further scheme of the present application, based on the ecological behavior prediction analysis result, abnormal changes including drought response and signs of disease and insect pests are monitored, deviation of abnormal changes from known health standards is analyzed, health status of forest vegetation is evaluated in real time, and the specific steps for generating a forest health diagnosis result are, S501: Based on the ecological behavior prediction analysis result, abnormal changes in the forest including drought response and signs of disease and insect pests are identified, images and geographic information of a target area are collected, time stamp and actual position are recorded, and abnormal monitoring data are obtained; S502: Using the abnormal monitoring data, standard indicators of healthy vegetation are used as a reference, color difference of abnormal areas is analyzed through visual comparison, change amount of chlorophyll concentration is calculated, influence range and degree of disease and insect pests are evaluated, and abnormal and health deviation analysis data are obtained; S503: Combined with the abnormal and health deviation analysis data, overall health status of the forest area is comprehensively evaluated, health indicators of each affected area are sorted out, and a forest health diagnosis result is generated.

[0014] As a further scheme of the present application, the change amount of chlorophyll concentration is calculated according to the formula, ; the percentage of change in chlorophyll concentration , wherein, representing the normalized vegetation index of healthy vegetation area, Normalized difference vegetation index representing the affected vegetation area is the difference value of the health and abnormal vegetation area value.

[0015] As a further scheme of the present application, based on the forest health diagnosis result, the change and mode of the forest health trend are monitored, and the vegetation ecological parameters in the database are updated synchronously, the data continuity and accuracy are verified, and the specific steps for generating the forest vegetation dynamic monitoring record are, S601: Based on the forest health diagnosis result, the associated remote sensing data and ground observation data are collected, the same period ecological parameters are compared, the dynamic change of the health condition is monitored, and the monitoring trend analysis data are acquired; S602: The ecological parameters of the vegetation are updated in the ecological database by using the monitoring trend analysis data, the data entries are manually reviewed and automatically checked for consistency, and the data update verification record is acquired; S603: According to the data update verification record, the continuity and accuracy of the vegetation ecological parameters in the database are continuously verified, and the forest vegetation dynamic monitoring record is output.

[0016] Compared with the prior art, the present application has the advantages and positive effects that: In the present application, the chlorophyll concentration and leaf area index can be accurately determined through the analysis of the difference color wavelength reflectivity, the understanding and tracking accuracy of the vegetation physiological state are improved, the time series analysis can monitor the long-term vegetation change in detail, the prediction ability of the forest ecological behavior is enhanced, the real-time monitoring of the drought response and the signs of disease and insect pests strengthens the timeliness and accuracy of the health state evaluation, the real-time and continuity of the data are ensured through the dynamic update of the forest vegetation database, and the dynamic monitoring and decision support ability of the forest management is significantly improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is a step flowchart of the present application; Figure 2 is a step flowchart of S1 of the present application; Figure 3 is a step flowchart of S2 of the present application; Figure 4 is a step flowchart of S3 of the present application; Figure 5 is a step flowchart of S4 of the present application; Figure 6 is a step flowchart of S5 of the present application; Figure 7 is a step flowchart of S6 of the present application. DETAILED DESCRIPTION

[0018] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0019] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0020] Please refer to Figure 1 A forest vegetation parameter real-time monitoring method based on unmanned aerial vehicle images, comprising the following steps: S1: Start the unmanned aerial vehicle, collect real-time images of the predetermined forest area through the camera, continuously capture images, synchronize the camera settings, match the differentiated lighting and depth of field conditions, and generate forest image collection data; S2: Transmit the forest image collection data to the ground station, perform image sharpening processing on the image data, automatically adjust the contrast and brightness of the image, eliminate image noise caused by weather or equipment, and output the preprocessed forest image data; S3: Perform feature analysis on the preprocessed forest image data, perform color change recognition, evaluate chlorophyll concentration by analyzing the reflectivity of different color wavelengths, calculate leaf area index, and quantitatively record the parameters to generate vegetation physiological parameter analysis results; S4: Based on the vegetation physiological parameter analysis results, perform data fusion and model mapping, perform time series analysis, compare the data in the continuous period, analyze the long-term change trend of the forest vegetation, and generate ecological behavior prediction analysis results; S5: Based on the ecological behavior prediction analysis results, monitor abnormal changes including drought response and signs of disease and insect pests, analyze the deviation of abnormal changes from known healthy standards, and perform real-time evaluation of the health status of the forest vegetation to generate forest health diagnosis results; S6: Based on the forest health diagnosis results, monitor the changes and patterns of the forest health trend, and update the vegetation ecological parameters in the database in synchronization, verify the data persistence and accuracy, and generate forest vegetation dynamic monitoring records.

[0021] The forest image acquisition data includes regional positioning information, light intensity data and depth of field adjustment parameters, the preprocessed forest image data includes adjusted contrast value, brightness level and noise elimination record, the vegetation physiological parameter analysis result includes chlorophyll concentration value, leaf area index and color wavelength reflectivity, the ecological behavior prediction analysis result includes long-term change trend data, time series analysis record and periodic comparison result, the forest health diagnosis result includes drought response evaluation record, pest index and health standard deviation analysis result, and the forest vegetation dynamic monitoring record includes health trend change data, ecological parameter update log and continuous test result.

[0022] Please refer to Figure 2 The specific steps of S1 are as follows: S101: Start the unmanned aerial vehicle, set the flight height and speed to match the panoramic coverage of the forest area, optimize the flight path through GPS positioning, and obtain flight coverage image data; Start the unmanned aerial vehicle, and comprehensively use the set parameters of flight height and speed to ensure that the unmanned aerial vehicle covers the forest area comprehensively. The unmanned aerial vehicle optimizes its flight path by loading previously formulated GPS coordinate data. The flight height adjustment of the unmanned aerial vehicle uses air pressure sensing technology, which can adjust the flight height by reading the current altitude air pressure, to ensure that the unmanned aerial vehicle automatically adjusts the flight height according to the ups and downs of different terrains. The flight speed is adjusted through data feedback of the wind speed sensor and the flight power system to adapt to the flight requirements under different wind conditions. The comprehensive use of technical details can effectively control the stability and coverage effect of the unmanned aerial vehicle in complex terrain, and obtain flight coverage image data.

[0023] S102: Start the camera to capture continuous images based on the flight coverage image data, adjust the aperture and shutter speed to match the changes in light conditions, and obtain real-time calibration image data; Through the flight coverage image data, the camera on the unmanned aerial vehicle automatically adjusts the aperture and shutter speed according to the received light condition data. This adjustment is based on the feedback of the real-time light intensity sensor. The adjustment of the camera aperture uses a stepper motor control system to accurately control the aperture size. The aperture size directly affects the amount of light entering and the depth of field of the image. The shutter speed is adjusted by an electronic controller to match the speed of light changes, ensuring that each captured image meets the preset exposure standard. In addition, color deviation and noise are corrected in real time during image capture. An image processing chip is used to analyze and adjust the obtained image data, thereby producing high-quality real-time calibration image data, which is then used to generate more complete visual records and analysis data.

[0024] S103: Use real-time calibration image data to continuously monitor image quality, synthesize consecutive frames and build a complete forest coverage map, and obtain forest image acquisition data; Using real-time calibration image data, the unmanned aerial vehicle system continuously monitors the quality of each frame of image received, real-time detects the definition, contrast and color saturation of the image during the monitoring process, including sharpness evaluation and color deviation correction, can identify and correct any quality decline in the image in time, to maintain the continuity and accuracy of the data, at the same time, the system synthesizes a complete forest coverage map by continuously merging image frames, the synthesis process uses image stitching technology, by comparing and merging the edge areas of adjacent image frames to generate seamless large-scale coverage map, the final obtained forest image acquisition data can provide detailed visual information for subsequent environmental monitoring and resource management.

[0025] Please refer to Figure 3 The specific steps of S2 are: S201: Start data transmission between unmanned aerial vehicle and ground station, use encrypted data communication protocol to transmit forest image acquisition data to ground station, monitor the transmission state of data packet to identify packet loss or error, and implement error correction measures to obtain complete transmission data; Start data transmission between unmanned aerial vehicle and ground station, the data transmission process uses Advanced Encryption Standard (AES) protocol to ensure data security and prevent data interception during transmission. In the encryption process, each data packet is assigned a unique key, which can reduce the impact of encryption process on speed when transmitting large amounts of data. At the same time, the transmission state of each data packet is monitored in real time. Once packet loss or error is detected, an automatic retransmission mechanism is started, which is based on data packet sequence number and checksum to identify the data packet that needs to be retransmitted. This not only ensures the integrity of the data, but also optimizes the bandwidth usage during transmission, obtaining complete transmission data.

[0026] S202: Based on the complete transmission data, analyze the contrast and brightness level of the image data, adjust the image parameters one by one to match the changes of external light, monitor the color saturation of the image in real time and make fine adjustments, and obtain the adjusted image data; Based on the complete transmission data, the image data received by the ground station is first subjected to preliminary analysis of contrast and brightness. The brightness and contrast of the image are adjusted according to the data input of the external light conditions. The required adjustment degree is determined by analyzing the pixel value distribution in the image. The brightness value of each pixel is adjusted to adapt to the wide dynamic range from highlight to shadow. In addition, the adjustment of color saturation is carried out through the Color Management System (CMS). The color distribution in the image is evaluated and the color saturation is adjusted appropriately to make the image more realistic and reduce color distortion. The details of this process include adjusting each segment of the color wheel individually to ensure the consistency and naturalness of the color under different lighting conditions, and obtaining the adjusted image data.

[0027] S203: Utilizing the adjusted image data, identify and remove noise points caused by weather effects or equipment failure in the image, refine the image texture, and output the pre-processed forest image data; Using the adjusted image data, start identifying and removing noise points caused by weather effects or equipment failure, by analyzing the relationship between each pixel point in the image and its surrounding pixels, it can be determined whether the pixel is a noise point, once the noise point is identified, it is corrected through smoothing processing or replacement technology, smoothing processing uses local mean filtering, while replacement is based on the color and brightness value of the surrounding effective pixels, in addition, by enhancing the contrast of the edge part of the image to improve the clarity of the overall image, thus outputting the pre-processed forest image data, not only reduces the visual interference caused by environmental factors, but also improves the usability and analysis value of the image.

[0028] Please refer to Figure 4 , the specific steps of S3 are: S301: Based on the pre-processed forest image data, extract the reflectivity of all color wavelengths, quantitatively distinguish colors through spectral analysis, record the reflectivity data of different colors, and obtain color wavelength analysis data; Based on the pre-processed forest image data, use a spectral analyzer to accurately measure the color wavelength of each pixel in the image, through the wavelength sensor of the spectral analyzer, the reflectivity of each color wavelength is continuously recorded and converted into numerical data, in this process, the unique spectral characteristics of each color can be distinguished and identified from the input data of multiple wavelengths, through this method, the reflectivity data of each color is sorted and mapped to the corresponding color wavelength, and the final output color wavelength analysis data will record the reflectivity difference of each color in detail, providing a basic data set for subsequent analysis.

[0029] S302: Using color wavelength analysis data, evaluate chlorophyll concentration by analyzing green wavelength reflectivity, integrate reflectivity data and calculate leaf area index, and obtain chlorophyll concentration and leaf area data; Leaf area index, according to the formula, ; for calculation, where, represents the leaf area index, represents the reflectivity of green wavelength, reflecting the light absorption ability of chlorophyll, used to improve the estimation accuracy of leaf area index, represents the total ground area covered by the image, providing the spatial range for estimating the leaf area index, represents the number of pixels participating in the calculation, enhancing the data support basis of the formula, represents the difference value of reflectivity between different wavelengths, improving the sensitivity and adaptability of the calculation through absolute value.

[0030] Reflectance of green wavelength, a value obtained through multispectral image analysis, according to published actual agricultural monitoring data, the reflectance of green wavelength is in the range of 0.20 to 0.30, 0.25 is selected as the value of .

[0031] Total ground area covered by the image, in square meters, calculated by geographic information system (GIS), the total area of the target region is 5000 square meters.

[0032] Represents the number of pixels involved in the calculation. This number can be derived from the resolution of the image and the area covered, with 100 pixels per square meter, so a 5000 square meter area would correspond to 500000 pixels, therefore, 500000.

[0033] Represents the difference in reflectance between different wavelengths. Obtained by analyzing the standard deviation of image data of different wavelengths in the same area, it is determined that the difference is between 0.02 and 0.05, 0.03 is selected as the value of .

[0034] Substitute these values into the formula to calculate: First, calculate the numerator part: ; Then calculate the denominator part: ; Finally, calculate the value of the entire formula: ; The result shows that the calculated leaf area index is 0.89, indicating that about 89% of the total ground area is covered by vegetation, which helps to evaluate the growth and density of vegetation, and is of great significance for forest ecological monitoring.

[0035] S303: Integrate chlorophyll concentration and leaf area data, record all physiological parameters collected through quantitative analysis, organize and format the data, and output the results of vegetation physiological parameter analysis; The chlorophyll concentration and leaf area data are integrated, and all collected physiological parameters are quantitatively analyzed. Data normalization and statistical analysis are used to process and record the chlorophyll concentration and leaf area data. Then, the system organizes the data and converts it into a unified format. The formatting process includes standardizing the type, scale, and precision of the data to ensure consistency and comparability in subsequent processing and analysis. All physiological parameters are summarized and output. The output vegetation physiological parameter analysis results show various physiological data points in detail, providing basic data support for further ecological research and resource management.

[0036] Please refer to Figure 5 The specific steps of S4 are as follows: S401: Integrate vegetation physiological parameter analysis results and historical ecological data, identify seasonal chlorophyll concentration time series changes through data docking, and output preliminary time series model data; Integrate vegetation physiological parameter analysis results and historical ecological data. During data integration, archive and index current vegetation physiological parameters and past data records. Data includes but is not limited to historical records of seasonal changes and past chlorophyll concentration data. Through time series analysis, automatically identify and mark the trend of chlorophyll concentration changes with seasons, help identify and simulate the periodic fluctuations of chlorophyll concentration. Finally, the system builds and outputs a preliminary time series model based on dynamic data, which reflects the relationship between seasonal changes and chlorophyll concentration, providing a basic framework for further analysis.

[0037] S402: Based on the preliminary time series model data, trend line fitting is performed on long-term data, key time nodes are calibrated, and the influence of environmental factors is determined, long-term changes of periodic data are analyzed, and comprehensive trend analysis data are obtained; Based on the preliminary time series model data, trend line fitting is performed on long-term data. First, linear regression analysis is applied to calibrate key time nodes, which represent important turning points of vegetation physiological changes, such as the time points of spring growth start and autumn degradation start. Environmental factors such as temperature and precipitation are also considered, and the influence of factors is clearly represented through the coefficients of the regression model. Further analysis of long-term changes of periodic data is performed using trend analysis techniques such as seasonal adjustment and difference method to determine the persistence and change range of vegetation growth and degradation trends. Finally, comprehensive trend analysis data are obtained, which record the long-term patterns of vegetation ecological changes and the comprehensive influence of environmental factors in detail.

[0038] S403: Use comprehensive trend analysis data to predict vegetation ecological changes, compare and analyze key time point data, analyze vegetation growth and degradation behavior patterns, and generate ecological behavior prediction analysis results; Using integrated trend analysis data, by comparing data changes at key time points, identify and simulate the behavior patterns of vegetation growth and degradation, in the process, using multiple regression analysis, can handle multiple variables at the same time, and consider the interaction between them, can accurately describe the possible changes of future vegetation state, while analyzing the vegetation response under different environmental conditions, such as the impact of extreme climate events on vegetation ecology, through detailed analysis, generate ecological behavior prediction analysis results, provide managers with detailed predictions of future changes in vegetation, and point out possible management strategies that need to be taken.

[0039] Please refer to Figure 6 , the specific steps of S5 are: S501: Based on the ecological behavior prediction analysis results, identify abnormal changes in the forest, including drought response and signs of pests and diseases, collect images and geographic information of the target area, record the timestamp and actual location, and obtain abnormal monitoring data; Based on the ecological behavior prediction analysis results, use unmanned aerial vehicle and satellite image technology to collect images and geographic information of the specified area in the forest, identify drought response and signs of pests and diseases through preliminary analysis, and each image data is equipped with timestamp and actual location information to ensure that the recorded data can accurately track to a specific forest area. In this process, the high-resolution camera equipped on the unmanned aerial vehicle captures detailed images of the forest, while the geographic information system (GIS) is used for accurate map positioning. After synchronous processing and labeling, the abnormal monitoring data containing abnormal change information are generated, providing key information for further analysis and intervention.

[0040] S502: Use abnormal monitoring data to compare with standard indicators of healthy vegetation, analyze color differences in abnormal areas through visual comparison, calculate the change amount of chlorophyll concentration, evaluate the scope and degree of pest and disease impact, and obtain abnormal and healthy deviation analysis data; The change amount of chlorophyll concentration is calculated according to the formula, ; The percentage change of chlorophyll concentration , wherein, represents the normalized difference vegetation index of healthy vegetation area, reflecting the ratio of typical green reflectance to near-infrared band of healthy vegetation area, represents the normalized difference vegetation index of affected vegetation area, showing the change of spectral characteristics due to pests and diseases, is the difference value of the normalized difference vegetation index of healthy and abnormal vegetation areas , the difference value is extracted by absolute value to highlight the difference, so that the formula is more sensitive to small changes in vegetation state.

[0041] The normalized difference vegetation index (NDVI) is calculated by the spectral reflectance of infrared and red bands, and the formula is: NIR represents the reflectivity in the near-infrared band, and Red represents the reflectivity in the red band. These two parameters are usually measured precisely using multispectral sensors carried by satellites or drones.

[0042] It was learned that in a certain monitoring, the NDVI value of healthy vegetation was 0.86, while the NDVI value of the diseased and pest-infested area was 0.76.

[0043] Substitute these actual measurements into the NDVI difference calculation: ; Calculate the absolute value inside the square root: ; Calculate the denominator: ; Calculate the entire fraction: ; Convert the results to a percentage to represent the change in chlorophyll concentration: ; The results showed that the chlorophyll concentration in vegetation areas affected by pests and diseases was approximately 7.6% lower than that in healthy areas. This percentage difference clearly indicates the severity of pests and diseases and provides clear data support for agricultural managers to determine whether treatment or other management measures are necessary. It also provides an accurate quantitative method for environmental and ecological research, which helps monitor the long-term trends of vegetation health and environmental changes.

[0044] S503: Combining abnormal and health deviation analysis data, comprehensively assess the overall health status of the forest area, compile health indicators for each affected area, and summarize and generate forest health diagnosis results; By combining data from anomaly and health deviation analysis, a systematic evaluation of the overall health status of forest areas is conducted. Health indicators for each affected area are compiled and processed, including changes in chlorophyll concentration, color differences, and geographical location information. Each data item is uniformly formatted for analysis. During this process, all relevant health indicators can be automatically aggregated and summarized. The output forest health diagnosis results include detailed data tables and visual charts, providing a detailed health status report and potential management strategy recommendations for forest management.

[0045] Please see Figure 7 The specific steps of S6 are as follows: S601: Based on the forest health diagnosis results, collect relevant remote sensing data and ground observation data, compare ecological parameters of the same period, monitor the dynamic changes in health status, and obtain monitoring trend analysis data; Based on the forest health diagnosis results, remote sensing satellites and drones were deployed to collect data, providing multi-band images and geographic information. The images and data underwent preliminary screening and processing using a Geographic Information System (GIS) to identify specific areas related to dynamic changes in health status. The collected data was then compared with historical ecological parameters. The comparative analysis employed time series analysis techniques to identify seasonal and long-term trends in ecological parameters such as chlorophyll concentration and soil moisture, thereby monitoring and assessing dynamic changes in health status. The output monitoring trend analysis data provided crucial evidence for subsequent research and management.

[0046] S602: Utilize monitoring trend analysis data to update the ecological parameters of vegetation in the ecological database, perform manual review and automatic consistency verification of data entries, and obtain data update verification records; By using monitoring trend analysis data, the ecological parameters of vegetation are updated in the ecological database. The update process involves multiple steps: First, the newly collected data items are manually reviewed to ensure the accuracy and completeness of the information. Then, an automated tool is used for consistency verification. The tool compares the consistency and logical relationship between the old and new data items. During the verification process, any data that does not meet the standards is marked and re-examined. In addition, after each data update, the system automatically generates an update verification record, which details the status and time of each data update, ensuring the timeliness and accuracy of the vegetation ecological parameters in the database, which is crucial for maintaining the integrity of the database.

[0047] S603: Update and verify records based on data, continuously check the continuity and accuracy of vegetation ecological parameters in the database, and output dynamic monitoring records of forest vegetation; Based on the data update verification records, the continuity and accuracy of vegetation ecological parameters in the database are continuously checked, including regular data review and error correction. Historical data records are automatically compared with the latest updates to identify possible data breakpoints or inconsistencies. The review process ensures that all ecological parameters, such as chlorophyll concentration and soil moisture, are continuously updated and error-free. In addition, any data anomalies will trigger a detailed investigation, the results of which will be recorded and corresponding data corrections will be made. Ultimately, a dynamic monitoring record of forest vegetation is generated, providing a scientific basis for the formulation of forest management and protection strategies.

[0048] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for real-time monitoring of forest vegetation parameters based on UAV images, characterized in that, Includes the following steps: Launch the drone to collect real-time images of the designated forest area through the camera, capture continuous images, and simultaneously calibrate the camera settings to match different lighting and depth-of-field conditions to generate forest image collection data. The forest image acquisition data is transmitted to the ground station, and the image data is processed to enhance the image clarity, automatically adjust the image contrast and brightness, remove image noise caused by weather or equipment, and output the preprocessed forest image data. Feature analysis is performed on the preprocessed forest image data to identify color changes. Chlorophyll concentration is assessed by analyzing the reflectance of different color wavelengths, leaf area index is calculated, and parameters are quantified and recorded to generate vegetation physiological parameter analysis results. Based on the analysis results of the vegetation physiological parameters, data fusion and model mapping are performed, time series analysis is executed, data within consecutive periods are compared, the long-term change trend of forest vegetation is analyzed, and ecological behavior prediction analysis results are generated. Based on the ecological behavior prediction and analysis results, by monitoring abnormal changes, including drought response and signs of pests and diseases, analyzing the deviation between abnormal changes and known health standards, the health status of forest vegetation is assessed in real time, and forest health diagnosis results are generated. Based on the forest health diagnosis results, the changes and patterns of forest health trends are monitored, and the vegetation ecological parameters in the database are updated synchronously to verify the data continuity and accuracy, and generate dynamic monitoring records of forest vegetation.

2. The method for real-time monitoring of forest vegetation parameters based on UAV images according to claim 1, characterized in that, The forest image acquisition data includes regional positioning information, light intensity data, and depth-of-field adjustment parameters. The preprocessed forest image data includes adjusted contrast values, brightness levels, and noise removal records. The vegetation physiological parameter analysis results include chlorophyll concentration values, leaf area index, and color wavelength reflectance. The ecological behavior prediction analysis results include long-term change trend data, time series analysis records, and periodic comparison results. The forest health diagnosis results include drought response assessment records, pest and disease indicators, and health standard deviation analysis results. The forest vegetation dynamic monitoring records include health trend change data, ecological parameter update logs, and continuous verification results.

3. The method for real-time monitoring of forest vegetation parameters based on UAV images according to claim 1, characterized in that, The specific steps for launching a drone to capture real-time images of a predetermined forest area using its camera, continuously capturing images, and simultaneously calibrating camera settings to match differentiated lighting and depth-of-field conditions to generate forest image data are as follows. Start the drone, set the flight altitude and speed to match the panoramic coverage of the forest area, optimize the flight path by locating the flight route using GPS, and obtain flight coverage image data; Using the flight coverage image data, the camera is activated to continuously capture images, and the aperture and shutter speed are adjusted to match changes in lighting conditions to obtain real-time calibration image data. Using the real-time calibrated image data, continuous monitoring of image quality is performed, continuous frames are synthesized, and a complete forest cover map is constructed to obtain forest image acquisition data.

4. The method for real-time monitoring of forest vegetation parameters based on UAV images according to claim 1, characterized in that, The specific steps for transmitting the acquired forest image data to a ground station, performing image sharpening processing on the image data, automatically adjusting the image contrast and brightness, removing image noise caused by weather or equipment, and outputting the pre-processed forest image data are as follows: Initiate data transmission between the UAV and the ground station, use an encrypted data communication protocol to transmit the forest image acquisition data to the ground station, monitor the transmission status of the data packets to identify packet loss or errors, implement error correction measures, and obtain complete transmission data; Based on the complete transmitted data, the contrast and brightness levels in the image data are analyzed, the image parameters are adjusted one by one to match the changes in external light, the image color saturation is monitored in real time and fine-tuned, and the adjusted image data is obtained. Using the adjusted image data, noise in the image caused by weather or equipment failure is identified and removed, the image texture is refined, and the preprocessed forest image data is output.

5. The method for real-time monitoring of forest vegetation parameters based on UAV images according to claim 1, characterized in that, The specific steps for performing feature analysis on the preprocessed forest image data, identifying color changes, assessing chlorophyll concentration by analyzing the reflectance of different color wavelengths, calculating the leaf area index, quantifying and recording the parameters, and generating vegetation physiological parameter analysis results are as follows: Based on the preprocessed forest image data, the reflectance of all color wavelengths is extracted, colors are quantitatively distinguished through spectral analysis, the reflectance data of different colors are recorded, and color wavelength analysis data is obtained. Using the color wavelength analysis data, chlorophyll concentration is assessed by analyzing the reflectance of green wavelengths, and the reflectance data is integrated and the leaf area index is calculated to obtain chlorophyll concentration and leaf area data. Based on the chlorophyll concentration and leaf area data, all collected physiological parameters were recorded through quantitative analysis, the data were organized and formatted in a standardized manner, and the analysis results of vegetation physiological parameters were summarized and output.

6. The method for real-time monitoring of forest vegetation parameters based on UAV images according to claim 5, characterized in that, The leaf area index, according to the formula... ； Calculations are performed, in which, Indicates leaf area index, Reflectivity representing the green wavelength, This represents the total ground area covered by the image. This represents the number of pixels involved in the calculation. This represents the difference in reflectivity between wavelengths.

7. The method for real-time monitoring of forest vegetation parameters based on UAV images according to claim 1, characterized in that, Based on the analysis results of the aforementioned vegetation physiological parameters, the specific steps for data fusion and model mapping, time series analysis, comparison of data within consecutive periods, analysis of long-term forest vegetation change trends, and generation of ecological behavior prediction analysis results are as follows: By integrating the analysis results of the vegetation physiological parameters with historical ecological data, the time series changes of seasonal chlorophyll concentration are identified through data docking, and preliminary time series model data are constructed and output. Based on the preliminary time series model data, trend lines are fitted to long-term data to identify the influence of key time nodes and environmental factors, analyze the long-term changes of periodic data, and obtain comprehensive trend analysis data. Using the comprehensive trend analysis data, vegetation ecological changes are predicted. By comparing and analyzing data at key time points, the behavioral patterns of vegetation growth and degradation are analyzed, and ecological behavior prediction analysis results are generated.

8. The method for real-time monitoring of forest vegetation parameters based on UAV images according to claim 1, characterized in that, Based on the aforementioned ecological behavior prediction and analysis results, the specific steps for monitoring abnormal changes, including drought responses and signs of pests and diseases, analyzing the deviations of these abnormal changes from known health standards, and generating real-time assessments of forest vegetation health status to generate forest health diagnostic results are as follows: Based on the ecological behavior prediction and analysis results, abnormal changes in the forest are identified, including drought response and signs of pests and diseases. Images and geographic information of the target area are collected, timestamps and actual locations are recorded, and abnormal monitoring data are obtained. Using the aforementioned abnormal monitoring data, and comparing it with the standard indicators of healthy vegetation, the color difference in abnormal areas is visually compared and analyzed to calculate the change in chlorophyll concentration, assess the scope and extent of the impact of pests and diseases, and obtain abnormal and healthy deviation analysis data. By combining the abnormal and health deviation analysis data, a comprehensive assessment of the overall health status of the forest area is conducted, health indicators for each affected area are compiled, and forest health diagnosis results are generated.

9. The method for real-time monitoring of forest vegetation parameters based on UAV images according to claim 8, characterized in that, The change in chlorophyll concentration is calculated according to the formula. ； Percentage change in chlorophyll concentration ,in, Normalized Difference Vegetation Index (NDVI) represents healthy vegetation areas. Normalized Difference Vegetation Index (NDVI) representing the affected vegetation area Areas with healthy and abnormal vegetation The difference in values.

10. The method for real-time monitoring of forest vegetation parameters based on UAV images according to claim 1, characterized in that, Based on the forest health diagnosis results, the specific steps for monitoring changes and patterns in forest health trends, synchronously updating vegetation ecological parameters in the database, verifying data continuity and accuracy, and generating dynamic monitoring records of forest vegetation are as follows: Based on the forest health diagnosis results, related remote sensing data and ground observation data are collected, ecological parameters of the same period are compared, dynamic changes in health status are monitored, and monitoring trend analysis data are obtained. Using the monitoring trend analysis data, the ecological parameters of vegetation are updated in the ecological database, and the data entries are manually reviewed and automatically verified for consistency to obtain data update verification records. The data is updated and verified to continuously check the continuity and accuracy of vegetation ecological parameters in the database, and outputs dynamic monitoring records of forest vegetation.

Images