Forestry resource data integrated management system

Abstract

The invention relates to the technical field of forestry data management, and particularly discloses a forestry resource data integrated management system, which is used for solving the problem that an existing traditional leaf loss monitoring method depends on spectral difference, but leaves do not fall off, so that effective identification is difficult to perform through single spectrum inversion. According to the method, the spectral data and the image data of the tree crown are obtained, the spectral data and the image data of the tree crown in the insect pest state and the healthy state are extracted, the pixel value is extracted according to the image data to preliminarily analyze whether the leaf has the disease, and then whether the tree crown has the disease is finally analyzed according to the spectral data. According to the method, the comprehensiveness and precision of disease detection are improved, misjudgment and missed judgment are reduced, sensitive recognition of early-stage diseases is ensured through a double analysis mechanism, and data support can be provided for timely intervention.

Description

Technical Field

[0001] The present invention relates to the technical field of forestry data management, and more specifically, to a comprehensive management system for forestry resource data. Background Art

[0002] Remote sensing monitoring of forest pests and diseases is an important part of forest resource protection and ecological management. However, remote sensing-based pest and disease monitoring, especially monitoring of tree crown leaf loss, has certain limitations in time and space due to the suddenness, concealment and rapid spread of pests and diseases. This leads to the inability to respond to pest and disease monitoring and prevention in a timely manner, increasing the risk of damage to forest ecosystems. The existing literature "Qi Xinglan, Cao Zuning, Liu Jian, et al. Research progress on forest pest and disease monitoring based on satellite remote sensing images [J]. Forestry Resources Management, 2020, (02): 181-186. DOI: 10.13466 / j.cnki.lyzygl.2020.02.027." comprehensively analyzes the current research status of using satellite remote sensing images to monitor forest pests and diseases at home and abroad, systematically summarizes the main technical methods for using satellite remote sensing images to monitor forest pests and diseases, deeply analyzes the main existing problems and makes research prospects. Some pests and diseases (such as longhorn beetles and spruce leaf rust) can cause tree leaves to turn yellow, wither or lose green, but the leaves remain on the crown for a certain period of time, and no significant leaf loss characteristics are formed. The traditional leaf loss monitoring method relies on spectral differences, but because the leaves have not fallen off, it is difficult to effectively identify them through a single spectral inversion. In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, the present invention provides a comprehensive management system for forestry resource data, which is used to solve the problem that the traditional leaf loss monitoring method relies on spectral differences, but because the leaves have not fallen off, it is difficult to effectively identify them through a single spectral inversion, so as to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions: A forestry resource data integrated management system includes a multi-dimensional data acquisition module, a diseased leaf distribution recognition module and a dynamic disease management module, wherein the multi-dimensional data acquisition module is used to acquire spectral data and image data of a tree crown; the diseased leaf distribution recognition module includes a first data acquisition unit, a data processing unit, a diseased leaf distribution analysis unit, a non-disease leaf distribution analysis unit and a dynamic leaf distribution analysis unit; the first data acquisition unit is used to extract first image data, second image data and third image data; the data processing unit is used to segment the first image data, the second image data and the third image data respectively and extract their pixel values ​​to obtain first pixel data, second pixel data and third pixel data; the diseased leaf distribution analysis unit is used to analyze the diseased leaf distribution coefficient according to the second pixel data; the non-disease leaf distribution analysis unit is used to analyze the non-disease leaf distribution coefficient according to the third pixel data; the dynamic leaf distribution analysis unit is used to preliminarily analyze whether a leaf has a disease based on the first pixel data, the diseased leaf distribution coefficient and the non-disease leaf distribution coefficient, and the formula of the primary discrimination model of leaf disease is: ; Where: is the primary leaf disease discrimination value, is the distribution coefficient of non-disease leaves, is the diseased leaf distribution coefficient, is the number of first pixel data in the third pixel sequence, is the qth first pixel data in the third pixel sequence, is the average value of the first pixel data in the third pixel sequence.

[0005] As a further solution of the present invention, the multi-dimensional data acquisition module includes a multi-spectral camera, a primary data extraction unit and a secondary data extraction unit; the multi-spectral camera is used to obtain first spectral data and first image data of tree crowns within the target range in real time; the primary data extraction unit is used to obtain second spectral data of tree crowns with a history of insect pests and third spectral data of tree crowns without a history of insect pests; the secondary data extraction unit is used to obtain second image data of tree crowns with a history of insect pests and third image data of tree crowns without a history of insect pests.

[0006] As a further solution of the present invention, the diseased leaf distribution analysis unit is used to analyze the diseased leaf distribution coefficient according to the second pixel data, specifically: the first pixel sequence is obtained by arranging the second pixel data in order from small to large, the maximum value in the first pixel sequence is extracted as the first pixel value, the minimum value in the first pixel sequence is extracted as the second pixel value, the mean of the second pixel data is calculated based on the first pixel sequence to obtain the first pixel distribution coefficient, and the diseased leaf distribution coefficient calculation model is constructed according to the second pixel data, the first pixel value, the second pixel value and the first pixel distribution coefficient to calculate the diseased leaf distribution coefficient. The calculation formula of the diseased leaf distribution coefficient calculation model is: ; Where: is the diseased leaf distribution coefficient, is the number of the second pixel data in the first pixel sequence, is the i-th second pixel data in the first pixel sequence, is the first pixel distribution coefficient, is the first pixel value, is the second pixel value.

[0007] As a further solution of the present invention, the non-diseased leaf distribution analysis unit is used to analyze the non-diseased leaf distribution coefficient according to the third pixel data, specifically: the third pixel data is arranged in order from small to large to obtain a second pixel sequence, the maximum value in the second pixel sequence is extracted as the third pixel value, the minimum value in the second pixel sequence is extracted as the fourth pixel value, the mean of the third pixel data is calculated based on the second pixel sequence to obtain the second pixel distribution coefficient, and a diseased leaf distribution coefficient calculation model is constructed according to the third pixel data, the fourth pixel value, the third pixel value and the second pixel distribution coefficient to calculate the non-diseased leaf distribution coefficient. The calculation formula of the non-diseased leaf distribution coefficient calculation model is: ; Where: is the distribution coefficient of non-disease leaves, is the number of the third pixel data in the second pixel sequence, is the jth third pixel data in the second pixel sequence, is the second pixel distribution coefficient, is the third pixel value, is the fourth pixel value.

[0008] As a further solution of the present invention, the dynamic leaf distribution analysis unit is used to analyze whether the leaves are diseased based on the first pixel data, the diseased leaf distribution coefficient and the non-diseased leaf distribution coefficient. Specifically, the first pixel data is extracted, and a third pixel sequence is obtained by arranging the first pixel data in order from small to large. Based on the third pixel sequence, the diseased leaf distribution coefficient and the non-diseased leaf distribution coefficient, a primary leaf disease discrimination model is constructed to preliminarily determine whether the leaves are diseased.

[0009] As a further solution of the present invention, the dynamic disease management module includes a second data acquisition unit, a spectrum curve drawing unit, a disease spectrum coefficient calculation unit and a secondary leaf spectrum analysis unit; The second data acquisition unit is used to extract the first spectrum data, the second spectrum data and the third spectrum data; The spectrum curve drawing unit is used to draw spectrum curves according to the first spectrum data, the second spectrum data and the third spectrum data respectively; The disease spectrum coefficient calculation unit is used to calculate the crown disease spectrum coefficient according to the second spectrum data and the third spectrum data; The secondary leaf spectrum analysis unit is used for secondary analysis of whether there is disease in the crown based on the first spectrum data and the crown disease spectrum coefficient.

[0010] As a further solution of the present invention, the disease spectrum coefficient calculation unit is used to calculate the crown disease spectrum coefficient according to the second spectrum data and the third spectrum data, specifically: based on the second spectrum data, a second reflection coefficient is obtained, based on the third spectrum data, a third reflection coefficient is obtained, the second reflection coefficient is arranged in order from small to large wavelength to obtain a second reflection sequence, the third reflection coefficient is arranged in order from small to large wavelength to obtain a third reflection sequence, based on the second reflection sequence and the third reflection sequence, they are imported into the crown disease spectrum coefficient calculation model to calculate the crown disease spectrum coefficient, and the formula of the crown disease spectrum coefficient calculation model is: ; Where: is the crown disease spectral coefficient, is the total number of wavelength points, is the weight factor of the rth wavelength point, is the reflection coefficient corresponding to the rth wavelength point in the second reflection sequence, is the reflection coefficient corresponding to the rth wavelength point in the third reflection sequence.

[0011] As a further solution of the present invention, the secondary leaf spectral analysis unit is used to perform a secondary analysis on whether the crown has a disease based on the first spectral data and the crown disease spectral coefficient. Specifically, the first reflection coefficient is arranged in order from small to large wavelength to obtain a first reflection sequence, and a secondary crown disease analysis model is constructed based on the first reflection sequence and the crown disease spectral coefficient to perform a secondary analysis on whether the crown has a disease. The formula of the secondary crown disease analysis model is: ; Where: is the secondary leaf disease discrimination value, is the crown disease spectral coefficient, is the reflection coefficient corresponding to the rth wavelength point in the first reflection sequence, is the mean value of the reflection coefficient corresponding to each wavelength point in the first reflection sequence, is the total number of wavelength points.

[0012] The technical effects and advantages of the comprehensive management system for forestry resource data of the present invention are as follows: the present invention obtains spectral data and image data of tree crowns, extracts spectral data and image data of tree crowns in pest states and healthy states, extracts pixel values ​​based on the image data to preliminarily analyze whether leaves have diseases, and then finally analyzes whether the tree crowns have diseases based on the spectral data. This helps to improve the comprehensiveness and accuracy of disease detection, reduce misjudgments and missed judgments, and the dual analysis mechanism ensures sensitive identification of early diseases, and can provide data support for timely intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A schematic diagram of the structure of a forestry resource data integrated management system provided by the present invention; Figure 2 A schematic diagram of the changes and characteristics of a tree crown from a healthy state to different disease stages provided by the present invention. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the present invention to clearly and completely describe the technical solution in the present invention. Obviously, the described technical solution is only a part of the present invention, not all of it. Based on the technical solution in the present invention, all other technical solutions obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0015] Figure 1 This is a schematic diagram of the structure of a forestry resource data integrated management system provided by the present invention. Figure 1As shown, a forestry resource data integrated management system includes a multi-dimensional data acquisition module, a diseased leaf distribution identification module and a dynamic disease management module; the multi-dimensional data acquisition module is connected to the diseased leaf distribution identification module and the dynamic disease management module respectively, and the diseased leaf distribution identification module is connected to the dynamic disease management module; The multi-dimensional data acquisition module is used to obtain the spectral data and image data of the tree crown; The diseased leaf distribution identification module is used to preliminarily analyze whether the leaves have diseases based on the image data; The dynamic disease management module is used to finally analyze whether there is disease in the tree crown based on the spectral data.

[0016] Specifically, the multi-dimensional data acquisition module includes a multi-spectral camera, a primary data extraction unit, and a secondary data extraction unit; The multispectral camera is used to obtain first spectral data and first image data of tree crowns within the target range in real time; The primary data extraction unit is used to obtain the second spectrum data of the tree crowns with historical insect pests and the third spectrum data of the tree crowns without historical insect pests; The secondary data extraction unit is used to obtain second image data of tree crowns with historical pests and third image data of tree crowns without historical pests.

[0017] It should be noted that the spectral data includes the leaf reflectance coefficients corresponding to different wavelengths.

[0018] The multispectral camera acquires the first spectral data and the first image data of the tree crown within the target range in real time, reflecting the current health status of the tree crown, helping to obtain the latest tree crown information in a timely manner, supporting dynamic monitoring and early warning of diseases, providing high-precision real-time reflection coefficients, and capturing the spectral characteristics of the tree crown; the primary and secondary data extraction units respectively provide spectral data and image data of historical pest-infested and pest-free tree crowns to form a comparison benchmark. A benchmark model is established through historical data to facilitate the analysis of deviations in real-time data, support machine learning or statistical modeling based on historical data, and improve the accuracy of disease identification; spectral data includes leaf reflection coefficients corresponding to different wavelengths, which can quantify the reflection characteristics of the tree crown in specific spectral bands. Spectral data is sensitive to the chlorophyll content, water content and health status of the leaves, and can identify early changes caused by diseases; image data provides spatial distribution information of the tree crown, supplements the lack of local characteristics of spectral data, locates the diseased area through image analysis, and clarifies the scope of the disease. The primary data extraction unit obtains the spectral data of historical pests and healthy crowns, forms a comparison sequence based on different wavelengths, and provides a baseline curve of pest characteristic spectra to facilitate the analysis of spectral shifts of real-time data, supports the training of machine learning models based on spectral reflectance differences, and improves the efficiency of disease identification. The secondary data extraction unit provides image data of pests and healthy crowns to form a historical image library, supports deep learning models to extract spatial features, identify crown disease patterns, and integrate spectral and image features to improve the accuracy of disease classification and positioning. By integrating real-time spectral and image data, historical pest and health data, and building a complete data link, it provides solid technical support for the accurate identification and dynamic monitoring of crown diseases. Spectral data is the core, which quantifies the changes in reflectance coefficients at different wavelengths, and cooperates with image data and historical comparison to achieve early, intelligent, and efficient disease diagnosis.

[0019] Specifically, the diseased leaf distribution identification module includes a first data acquisition unit, a data processing unit, a diseased leaf distribution analysis unit, a non-diseased leaf distribution analysis unit and a dynamic leaf distribution analysis unit; the first data acquisition unit is connected to the data processing unit, the diseased leaf distribution analysis unit, the non-diseased leaf distribution analysis unit and the dynamic leaf distribution analysis unit, and the diseased leaf distribution analysis unit and the non-diseased leaf distribution analysis unit are connected to the dynamic leaf distribution analysis unit, respectively.

[0020] The first data acquisition unit is used to extract the first image data, the second image data and the third image data; The data processing unit is used to segment the first image data, the second image data and the third image data and extract pixel values ​​thereof to obtain first pixel data, second pixel data and third pixel data; The diseased leaf distribution analysis unit is used to analyze the diseased leaf distribution coefficient according to the second pixel data; The non-disease leaf distribution analysis unit is used to analyze the non-disease leaf distribution coefficient according to the third pixel data; The dynamic leaf distribution analysis unit is used to preliminarily analyze whether the leaves have diseases based on the first pixel data, the diseased leaf distribution coefficient and the non-disease leaf distribution coefficient.

[0021] Specifically, the diseased leaf distribution analysis unit is used to analyze the diseased leaf distribution coefficient according to the second pixel data, specifically: the first pixel sequence is obtained by arranging the second pixel data in order from small to large, the maximum value in the first pixel sequence is extracted as the first pixel value, the minimum value in the first pixel sequence is extracted as the second pixel value, the mean of the second pixel data is calculated based on the first pixel sequence to obtain the first pixel distribution coefficient, and the diseased leaf distribution coefficient calculation model is constructed according to the second pixel data, the first pixel value, the second pixel value and the first pixel distribution coefficient to calculate the diseased leaf distribution coefficient. The calculation formula of the diseased leaf distribution coefficient calculation model is: ; Where: is the diseased leaf distribution coefficient, is the number of the second pixel data in the first pixel sequence, is the i-th second pixel data in the first pixel sequence, is the first pixel distribution coefficient, is the first pixel value, is the second pixel value.

[0022] The diseased leaf distribution identification module decomposes the task into multiple functional units, including data acquisition, processing, distribution analysis and dynamic analysis, which improves the efficiency of task allocation. Each unit focuses on a specific function and reduces error accumulation. It obtains the first image data (real-time monitoring), the second image data (disease history) and the third image data (health history), dynamically combines real-time data with historical data, supports more flexible disease analysis, provides a variety of input data sources, and enhances the applicability of the system. It combines the first pixel data, the diseased leaf distribution coefficient and the non-disease leaf distribution coefficient to dynamically determine whether the leaf has a disease, and realizes real-time dynamic analysis of the leaf disease distribution. The diseased leaf distribution analysis unit extracts the diseased leaf data. The system calculates the distribution coefficient of diseased leaves based on the optical or pixel characteristics of diseased leaves, quantifies the degree of disease through pixel-level distribution characteristics, and avoids subjective judgment or local errors. The non-diseased leaf distribution analysis unit extracts the characteristics of healthy leaves and compares them with the distribution coefficient of diseased leaves to provide a health benchmark, improve the accuracy of disease identification, and support fine-grained disease classification and distribution feature analysis. By integrating real-time data with historical data, it quantifies the distribution characteristics of diseased leaves and dynamically determines the disease status. Its modular architecture and scientific formula for the distribution coefficient of diseased leaves provide efficient and accurate disease diagnosis capabilities, which can support accurate positioning, dynamic monitoring and intelligent management of diseases, and are of great significance in disease prevention and control and ecological protection.

[0023] Specifically, the non-diseased leaf distribution analysis unit is used to analyze the non-diseased leaf distribution coefficient according to the third pixel data, specifically: the second pixel sequence is obtained by arranging the third pixel data in order from small to large, the maximum value in the second pixel sequence is extracted as the third pixel value, the minimum value in the second pixel sequence is extracted as the fourth pixel value, the mean of the third pixel data is calculated based on the second pixel sequence to obtain the second pixel distribution coefficient, and the diseased leaf distribution coefficient calculation model is constructed according to the third pixel data, the fourth pixel value, the third pixel value and the second pixel distribution coefficient to calculate the non-diseased leaf distribution coefficient. The calculation formula of the non-diseased leaf distribution coefficient calculation model is: ; Where: is the distribution coefficient of non-disease leaves, is the number of the third pixel data in the second pixel sequence, is the jth third pixel data in the second pixel sequence, is the second pixel distribution coefficient, is the third pixel value, is the fourth pixel value.

[0024] The statistical characteristics of the distribution of non-diseased leaves are used to analyze the changing trends of healthy leaves, assist in early disease detection, provide a comparison for the distribution coefficient of diseased leaves, and enhance the reliability of disease diagnosis; the dynamic comparison of the distribution coefficient of non-diseased leaves with the distribution coefficient of diseased leaves is helpful to identify the distribution differences between diseased areas and healthy areas, and enhance the ability to identify abnormal distribution of diseased leaves, especially in the early disease or mild disease stage. The statistical benchmark of non-diseased distribution is used to further refine the diagnosis results of the disease, such as distinguishing the subtle differences between mildly diseased and healthy leaves; the spatial distribution of the second pixel sequence is analyzed by sorting pixel data, the spatial distribution characteristics of non-diseased leaves are provided, and the spatial distribution characteristics of non-diseased areas are provided to provide a reference for the precise positioning of subsequent diseased areas, support the construction of a distribution comparison map of healthy and diseased leaves, and intuitively show the health status of the crown; the distribution of non-diseased leaves is captured by normalization and deviation analysis of pixel data. The normalization of the formula can reduce the risk of misjudgment and enhance the sensitivity of disease diagnosis, especially when the pixel value fluctuates due to environmental changes (such as light and humidity). Even if the leaves do not show obvious disease symptoms, potential abnormalities can be identified, thereby improving the system's adaptability to complex environments (such as uneven light and background interference). The real-time calculation of the distribution coefficient of non-diseased leaves supports dynamic monitoring of the changing trend of healthy leaves. When the distribution coefficient of non-diseased leaves changes significantly, an alarm can be triggered in combination with the distribution coefficient of diseased leaves to dynamically track the distribution changes of healthy leaves and provide data support for long-term monitoring. The distribution coefficient of non-diseased leaves can be scientifically calculated through the normalization of healthy leaf pixel data and the analysis of its distribution characteristics. The benefits include providing a distribution benchmark for healthy leaves, supporting accurate positioning of diseased areas, dynamically feeding back health status, improving diagnostic accuracy and sensitivity, and optimizing disease prediction models, which are of great significance in disease monitoring, early warning and system adaptability.

[0025] Specifically, the dynamic leaf distribution analysis unit is used to analyze whether the leaf has a disease according to the first pixel data, the diseased leaf distribution coefficient and the non-disease leaf distribution coefficient, specifically: extract the first pixel data, arrange the first pixel data in order from small to large to obtain a third pixel sequence, and construct a leaf disease primary discrimination model based on the third pixel sequence, the diseased leaf distribution coefficient and the non-disease leaf distribution coefficient to preliminarily judge whether the leaf has a disease. The formula of the leaf disease primary discrimination model is: ; Where: is the primary leaf disease discrimination value, is the distribution coefficient of non-disease leaves, is the diseased leaf distribution coefficient, is the number of first pixel data in the third pixel sequence, is the qth first pixel data in the third pixel sequence, is the mean value of the first pixel data in the third pixel sequence; Obtain a primary leaf disease discrimination value and a preset primary leaf disease discrimination threshold. If the primary leaf disease discrimination value is greater than or equal to the preset primary leaf disease discrimination threshold, it is preliminarily determined that the leaf has a disease; if the primary leaf disease discrimination value is less than the preset primary leaf disease discrimination threshold, it is preliminarily determined that the leaf does not have a disease.

[0026] By integrating the first pixel data, the distribution coefficient of diseased leaves and the distribution coefficient of non-disease leaves, the primary discrimination model is used to make a preliminary judgment on the disease status of leaves. The global distribution characteristics (disease and non-disease coefficients) and local distribution characteristics (first pixel data) are comprehensively considered to achieve the fusion of multi-dimensional features and enhance the adaptability of the disease discrimination model to complex distribution conditions. The disease distribution characteristics are compared with the healthy benchmark to improve the diagnostic accuracy and enhance the sensitivity to abnormal disease distribution characteristics, especially in the early stage of the disease or the stage of mild disease, to improve the discrimination ability of complex disease distribution (such as mixed disease and healthy areas). force; based on the dynamic calculation of the first pixel data, the third pixel sequence is arranged in order from small to large, the local distribution characteristics of the first pixel data are analyzed, and the dynamic changes of the pixel data are measured by the mean deviation. It can quickly capture abnormal fluctuations in real-time data, adapt to dynamic monitoring needs, and update the disease discrimination value in real time to provide support for the dynamic tracking of the health status of the crown; through the relative change of pixel values ​​(rather than the absolute value), the impact of light changes or noise on the monitoring results is reduced, the system's anti-interference ability is enhanced, it adapts to complex environmental conditions, and improves the sensitivity to minor diseases or potential diseases to avoid missed judgments.

[0027] Specifically, the dynamic disease management module includes a second data acquisition unit, a spectrum curve drawing unit, a disease spectrum coefficient calculation unit and a secondary leaf spectrum analysis unit; the second data acquisition unit is connected to the spectrum curve drawing unit, the disease spectrum coefficient calculation unit and the secondary leaf spectrum analysis unit respectively, and the disease spectrum coefficient calculation unit is connected to the secondary leaf spectrum analysis unit; The second data acquisition unit is used to extract the first spectrum data, the second spectrum data and the third spectrum data; The spectrum curve drawing unit is used to draw spectrum curves according to the first spectrum data, the second spectrum data and the third spectrum data respectively; The disease spectrum coefficient calculation unit is used to calculate the crown disease spectrum coefficient according to the second spectrum data and the third spectrum data; The secondary leaf spectrum analysis unit is used for secondary analysis of whether there is disease in the crown based on the first spectrum data and the crown disease spectrum coefficient.

[0028] Specifically, the disease spectrum coefficient calculation unit is used to calculate the crown disease spectrum coefficient according to the second spectrum data and the third spectrum data, specifically: obtain the second reflection coefficient based on the second spectrum data, obtain the third reflection coefficient based on the third spectrum data, arrange the second reflection coefficient in the order of wavelength from small to large to obtain a second reflection sequence, arrange the third reflection coefficient in the order of wavelength from small to large to obtain a third reflection sequence, import the second reflection sequence and the third reflection sequence into the crown disease spectrum coefficient calculation model, and calculate the crown disease spectrum coefficient. The formula of the crown disease spectrum coefficient calculation model is: ; Where: is the crown disease spectral coefficient, is the total number of wavelength points, is the weight factor of the rth wavelength point, is the reflection coefficient corresponding to the rth wavelength point in the second reflection sequence, is the reflection coefficient corresponding to the rth wavelength point in the third reflection sequence.

[0029] Through the collaborative work of multiple units, the spectral characteristics and dynamic changes of crown diseases are comprehensively analyzed, and the first spectral data (monitoring target), second spectral data (historical diseased crown) and third spectral data (historical healthy crown) are obtained in real time. The real-time data and historical data are integrated to provide a basis for dynamic analysis and support the timeliness and accuracy of disease monitoring. The spectral curve drawing unit draws healthy, diseased and real-time monitoring spectral curves respectively to intuitively display the differences in spectral characteristics. The changing trends of the spectral characteristics of the disease can be quickly identified through curve comparison, which is convenient for analysts to intuitively judge the distribution and severity of the disease. The disease spectral coefficient calculation formula integrates the differences between different wavelength points, quantifies the overall changes in the spectral characteristics of the disease, and assigns higher weights to sensitive wavelengths (such as the 680-750nm red edge band and the 750-900nm near-infrared band) to improve the sensitivity of disease detection. ; The secondary leaf spectral analysis unit combines the first spectral data of real-time monitoring with the crown disease spectral coefficient to further analyze the disease. The secondary analysis can refine the disease detection results and reduce misjudgments (such as spectral anomalies caused by changes in lighting conditions or background interference). It combines real-time spectral data with historical disease benchmark data to improve the reliability and stability of diagnosis. The real-time spectral data is visually compared with the healthy and diseased spectral data. The changes in spectral characteristics caused by the disease (such as red edge drift and decreased near-infrared reflectance) can be directly presented through curve differences, supporting early detection of the disease, especially in the early stages of the disease (such as mild chlorosis stage) when the leaves have not fallen significantly. According to the reflection differences at different wavelengths, a global quantitative indicator of the spectral characteristics of the disease is provided, which can refine the classification of disease types and severity, support the analysis of disease distribution characteristics by wavelength, and optimize prevention and control strategies.

[0030] Specifically, the secondary leaf spectral analysis unit is used to perform a secondary analysis on whether the crown has a disease based on the first spectral data and the crown disease spectral coefficient. Specifically, the first reflection coefficient is arranged in order from small to large wavelength to obtain a first reflection sequence, and a secondary crown disease analysis model is constructed based on the first reflection sequence and the crown disease spectral coefficient to perform a secondary analysis on whether the crown has a disease. The formula of the secondary crown disease analysis model is: ; Where: is the secondary leaf disease discrimination value, is the crown disease spectral coefficient, is the reflection coefficient corresponding to the rth wavelength point in the first reflection sequence, is the mean value of the reflection coefficient corresponding to each wavelength point in the first reflection sequence, is the total number of wavelength points; Extract the secondary leaf disease discrimination value, and compare the secondary leaf disease discrimination value with the preset secondary leaf disease discrimination threshold. If the secondary leaf disease discrimination value is greater than or equal to the preset secondary leaf disease discrimination threshold, it is determined that the leaf has a disease; if the secondary leaf disease discrimination value is less than the preset secondary leaf disease discrimination threshold, the leaf does not have a disease.

[0031] like Figure 2 The diagram of the crown changing from a healthy state to different disease stages is shown in Figure 2 (a) shows the changes of the crown from a healthy state to different disease stages. The leaves in A1 are in a healthy state and are bright green, which means that the tree is in the best state of health and disease-free. The leaves in A2 are in the green attack stage and begin to lose green but do not change color significantly. The leaves in A3 are in the red attack stage and gradually turn red, indicating obvious disease. The leaves in A4 are in the gray attack stage, at which time the leaves are further withered and the spectral reflectance is significantly reduced. Figure 2 (b) shows the spectral reflectance characteristics of the crown in a healthy state and at different disease stages. The spectral range covers 400–900nm, including visible light (400–700nm) and near-infrared light (700–900nm). Curves of different colors correspond to different crown states, among which the green curve is the spectral reflectance curve in state A1, the yellow curve is the spectral reflectance curve in state A2, the red curve is the spectral reflectance curve in state A3, and the gray curve is the spectral reflectance curve in state A4. The crown reflection of green light (near 500nm) is the strongest in A1, because healthy leaves contain a large amount of chlorophyll and the green light is partially reflected. The reflectance of other states gradually decreases with the worsening of the disease. The red edge (680–750nm) causes the red edge to drift in the early stage of the disease (A2), and the drift is more significant in A3 and A4. The near-infrared (750–900nm) disease causes a decrease in reflectance, especially in A4.

[0032] By using the first spectral data and the crown disease spectral coefficient, further disease analysis is performed based on the distribution characteristics of the reflectance coefficient. The disease spectral coefficient and real-time spectral data are combined to reduce misjudgment or missed judgment caused by a single analysis, and the global distribution characteristics and local abnormal characteristics of the wavelength points are considered to enhance the accuracy of diagnosis. The degree of deviation of the first reflection sequence from the mean captures the abnormal changes in the crown spectrum, the disease spectral coefficient, and weighs the contribution of each wavelength point to the disease characteristics. Even if the spectral changes caused by the early stage of the disease (such as slight chlorosis of leaves) are small, the secondary analysis model can still sensitively identify the disease characteristics, thereby improving the accuracy of the diagnosis. Adaptability to complex spectral distributions (such as differences in lighting conditions or background interference); the overall deviation of each wavelength point in the first reflection sequence from the mean reflects the global consistency of the crown spectrum, combining global and local characteristics to improve the detection capability of different types of diseases (such as local spot diseases or overall discoloration diseases) and enhance the system's robustness to data noise (such as changes in acquisition conditions); through secondary analysis of the first spectral data and the disease spectral coefficient, it is possible to quickly determine whether the crown has a disease, facilitate a rapid response to the risk of disease spread, dynamically track the progression of crown diseases, and support long-term monitoring and management.

[0033] The embodiment of the present invention obtains spectral data and image data of the tree crown, extracts spectral data and image data of the tree crown in the pest state and the healthy state, extracts pixel values ​​based on the image data to preliminarily analyze whether the leaves are diseased, and then finally analyzes whether the tree crown is diseased based on the spectral data. This helps to improve the comprehensiveness and accuracy of disease detection and reduce misjudgments and missed judgments. The dual analysis mechanism ensures sensitive identification of early diseases and can provide data support for timely intervention.

[0034] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0035] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A comprehensive forestry resource data management system, comprising a multi-dimensional data acquisition module, a diseased leaf distribution identification module and a dynamic disease management module, characterized in that: The multi-dimensional data acquisition module is used to obtain the spectral data and image data of the tree crown; the diseased leaf distribution identification module includes a first data acquisition unit, a data processing unit, a diseased leaf distribution analysis unit, a non-disease leaf distribution analysis unit and a dynamic leaf distribution analysis unit; the first data acquisition unit is used to extract the first image data, the second image data and the third image data; the data processing unit is used to segment the first image data, the second image data and the third image data respectively and extract their pixel values ​​to obtain the first pixel data, the second pixel data and the third pixel data; The diseased leaf distribution analysis unit is used to analyze the diseased leaf distribution coefficient according to the second pixel data; the non-disease leaf distribution analysis unit is used to analyze the non-disease leaf distribution coefficient according to the third pixel data; the dynamic leaf distribution analysis unit is used to preliminarily analyze whether the leaf has a disease based on the first pixel data, the diseased leaf distribution coefficient and the non-disease leaf distribution coefficient. The formula of the primary discrimination model of leaf disease is: ； Where: is the primary leaf disease discrimination value, is the distribution coefficient of non-disease leaves, is the diseased leaf distribution coefficient, is the number of first pixel data in the third pixel sequence, is the qth first pixel data in the third pixel sequence, is the average value of the first pixel data in the third pixel sequence.

2. The forestry resource data integrated management system according to claim 1, characterized in that: The multi-dimensional data acquisition module includes a multi-spectral camera, a primary data extraction unit and a secondary data extraction unit; the multi-spectral camera is used to obtain first spectral data and first image data of tree crowns within the target range in real time; the primary data extraction unit is used to obtain second spectral data of tree crowns with a history of insect pests and third spectral data of tree crowns without a history of insect pests; the secondary data extraction unit is used to obtain second image data of tree crowns with a history of insect pests and third image data of tree crowns without a history of insect pests.

3. The forestry resource data integrated management system according to claim 1, characterized in that: The diseased leaf distribution analysis unit is used to analyze the diseased leaf distribution coefficient according to the second pixel data, specifically: the first pixel sequence is obtained by arranging the second pixel data in order from small to large, the maximum value in the first pixel sequence is extracted as the first pixel value, the minimum value in the first pixel sequence is extracted as the second pixel value, the mean value of the second pixel data is calculated based on the first pixel sequence to obtain the first pixel distribution coefficient, and the diseased leaf distribution coefficient calculation model is constructed according to the second pixel data, the first pixel value, the second pixel value and the first pixel distribution coefficient to calculate the diseased leaf distribution coefficient. The calculation formula of the diseased leaf distribution coefficient calculation model is: ； Where: is the diseased leaf distribution coefficient, is the number of the second pixel data in the first pixel sequence, is the i-th second pixel data in the first pixel sequence, is the first pixel distribution coefficient, is the first pixel value, is the second pixel value.

4. The forestry resource data integrated management system according to claim 3 is characterized in that: The non-diseased leaf distribution analysis unit is used to analyze the non-diseased leaf distribution coefficient according to the third pixel data, specifically: the second pixel sequence is obtained by arranging the third pixel data in order from small to large, the maximum value in the second pixel sequence is extracted as the third pixel value, the minimum value in the second pixel sequence is extracted as the fourth pixel value, the mean value of the third pixel data is calculated based on the second pixel sequence to obtain the second pixel distribution coefficient, and the diseased leaf distribution coefficient calculation model is constructed according to the third pixel data, the fourth pixel value, the third pixel value and the second pixel distribution coefficient to calculate the non-diseased leaf distribution coefficient. The calculation formula of the non-diseased leaf distribution coefficient calculation model is: ； Where: is the distribution coefficient of non-disease leaves, is the number of the third pixel data in the second pixel sequence, is the jth third pixel data in the second pixel sequence, is the second pixel distribution coefficient, is the third pixel value, is the fourth pixel value.

5. The forestry resource data integrated management system according to claim 1 is characterized in that: The dynamic leaf distribution analysis unit is used to analyze whether the leaves are diseased based on the first pixel data, the diseased leaf distribution coefficient and the non-diseased leaf distribution coefficient. Specifically, the first pixel data is extracted, and a third pixel sequence is obtained by arranging the first pixel data in order from small to large. Based on the third pixel sequence, the diseased leaf distribution coefficient and the non-diseased leaf distribution coefficient, a primary leaf disease discrimination model is constructed to preliminarily judge whether the leaves are diseased.

6. The forestry resource data integrated management system according to claim 1, characterized in that: The dynamic disease management module includes a second data acquisition unit, a spectrum curve drawing unit, a disease spectrum coefficient calculation unit and a secondary leaf spectrum analysis unit; The second data acquisition unit is used to extract the first spectrum data, the second spectrum data and the third spectrum data; The spectrum curve drawing unit is used to draw spectrum curves according to the first spectrum data, the second spectrum data and the third spectrum data respectively; The disease spectrum coefficient calculation unit is used to calculate the crown disease spectrum coefficient according to the second spectrum data and the third spectrum data; The secondary leaf spectrum analysis unit is used for secondary analysis of whether there is disease in the crown based on the first spectrum data and the crown disease spectrum coefficient.

7. The forestry resource data integrated management system according to claim 6, characterized in that: The disease spectrum coefficient calculation unit is used to calculate the crown disease spectrum coefficient according to the second spectrum data and the third spectrum data, specifically: obtain the second reflection coefficient based on the second spectrum data, obtain the third reflection coefficient based on the third spectrum data, arrange the second reflection coefficient in the order of wavelength from small to large to obtain a second reflection sequence, arrange the third reflection coefficient in the order of wavelength from small to large to obtain a third reflection sequence, import the second reflection sequence and the third reflection sequence into the crown disease spectrum coefficient calculation model, and calculate the crown disease spectrum coefficient. The formula of the crown disease spectrum coefficient calculation model is: ； Where: is the crown disease spectral coefficient, is the total number of wavelength points, is the weight factor of the rth wavelength point, is the reflection coefficient corresponding to the rth wavelength point in the second reflection sequence, is the reflection coefficient corresponding to the rth wavelength point in the third reflection sequence.

8. The forestry resource data integrated management system according to claim 6, characterized in that: The secondary leaf spectral analysis unit is used to perform a secondary analysis on whether the crown has a disease based on the first spectral data and the crown disease spectral coefficient. Specifically, the first reflection coefficient is arranged in order from small to large wavelength to obtain a first reflection sequence. A secondary crown disease analysis model is constructed based on the first reflection sequence and the crown disease spectral coefficient to perform a secondary analysis on whether the crown has a disease. The formula of the secondary crown disease analysis model is: ； Where: is the secondary leaf disease discrimination value, is the crown disease spectral coefficient, is the reflection coefficient corresponding to the rth wavelength point in the first reflection sequence, is the mean value of the reflection coefficient corresponding to each wavelength point in the first reflection sequence, is the total number of wavelength points.

Images