Intelligent forest pest and disease damage identification method based on unmanned aerial vehicle remote sensing

Abstract

The invention relates to the technical field of image processing, in particular to a forest pest intelligent identification method based on unmanned aerial vehicle remote sensing, which comprises the following steps: analyzing the position distribution condition of pixel points in each suspected pest connected domain in an LAB color space coordinate system, and obtaining the green sensitivity of each suspected pest connected domain; dividing all suspected pest and disease connected domains into high green sensitivity connected domains and low green sensitivity connected domains based on green sensitivity; acquiring an enhancement coefficient of a remote sensing grayscale image of the to-be-detected man-made forest according to a grayscale difference condition of pixel points between the high green sensitivity connected domain and the low green sensitivity connected domain and the edge feature parameters; enhancing the remote sensing grayscale image of the to-be-detected man-made forest according to the enhancement coefficient to obtain an enhanced remote sensing image of the to-be-detected man-made forest; and performing intelligent forest disease and insect pest identification based on the enhanced remote sensing image of the to-be-detected man-made forest. According to the invention, the recognition degree of the forest regions with diseases and pests in the man-made forest is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to an intelligent identification method for forest pests and diseases based on unmanned aerial vehicle remote sensing. Background Art

[0002] Since trees with pests and diseases in forests are usually difficult to detect in a timely and effective manner, forest pests and diseases have intensified, causing serious losses to forests and bringing immeasurable damage to the ecological environment. Therefore, monitoring of forest pests and diseases is extremely important. Pine nematode disease, a common forest pest, is often found in artificial forests with a single planting structure. The forest pest and disease monitoring method using drone remote sensing images mainly relies on color filtering for detection, that is, using drones to shoot forests, and then enhancing the obtained images. The color difference between normal trees and pest and disease trees on the enhanced remote sensing images is analyzed to distinguish. When performing image enhancement, a linear grayscale transformation algorithm is often used for processing. The traditional linear grayscale transformation algorithm is a global linear enhancement of the image, so it can only increase the overall brightness of the image, and cannot locally enhance the pest and disease tree area, resulting in insufficient distinction between the pest and disease tree area and the normal tree area, making the pest and disease tree area identified from the artificial forest inaccurate. Summary of the invention

[0003] In order to solve the above problems, the present invention provides an intelligent identification method for forest pests and diseases based on UAV remote sensing, the method comprising: Obtaining a remote sensing grayscale image of the artificial forest to be detected; By performing connected domain analysis on the remote sensing grayscale image of the artificial forest to be detected, several circle-like connected domains in the remote sensing grayscale image of the artificial forest to be detected are obtained; by performing edge concave-convex feature analysis on each circle-like connected domain, edge feature parameters of each circle-like connected domain are obtained; all circle-like connected domains are screened by edge feature parameters to obtain all suspected pest and disease connected domains; Each suspected pest and disease connected domain is transformed into the LAB color space, and the position distribution of the pixel points in each suspected pest and disease connected domain in the LAB color space coordinate system is analyzed to obtain the green sensitivity of each suspected pest and disease connected domain; based on the green sensitivity, all suspected pest and disease connected domains are divided into high green sensitivity connected domains and low green sensitivity connected domains; according to the grayscale difference of the pixel points between the high green sensitivity connected domain and the low green sensitivity connected domain, as well as the edge feature parameters, the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected is obtained; The remote sensing grayscale image of the artificial forest to be detected is enhanced according to the enhancement coefficient to obtain an enhanced remote sensing image of the artificial forest to be detected; and intelligent identification of forest diseases and insect pests is performed based on the enhanced remote sensing image of the artificial forest to be detected.

[0004] Preferably, the method of performing connected domain analysis on the remote sensing grayscale image of the artificial forest to be detected to obtain a plurality of circle-like connected domains in the remote sensing grayscale image of the artificial forest to be detected includes the following specific methods: A gradient image of a remote sensing grayscale image of an artificial forest to be detected is obtained, and a watershed segmentation algorithm is performed on the gradient image to obtain multiple regions of the remote sensing grayscale image of the artificial forest to be detected. Each region is used as a quasi-circle connected domain, and then several quasi-circle connected domains in the remote sensing grayscale image of the artificial forest to be detected are obtained.

[0005] Preferably, the edge feature parameters of each quasi-circle connected domain are obtained by performing edge concave-convex feature analysis on each quasi-circle connected domain, and the specific method includes: For any quasi-circle connected domain in the remote sensing grayscale image of the artificial forest to be detected, edge detection is performed on the quasi-circle connected domain to obtain all edge pixel points in the quasi-circle connected domain; Obtaining the center position of the circle-like connected domain; According to the position distribution between the center position of the quasi-circle connected domain and the edge pixel points, all salient point angles of the quasi-circle connected domain are obtained; The normalized value of the average of the angle values ​​of all salient points in the quasi-circle connected domain is used as the edge feature parameter of the quasi-circle connected domain.

[0006] Preferably, the obtaining of the center position of the quasi-circle connected domain includes the following specific methods: All edge pixel points in the quasi-circle connected domain are arbitrarily combined in pairs to obtain several edge point combinations of the quasi-circle connected domain; for any edge point combination, the Euclidean distance between two edge pixel points in the edge point combination is recorded as the first distance of the edge point combination; among all edge point combinations in the quasi-circle connected domain, the edge point combination with the largest first distance is recorded as the target edge point combination of the quasi-circle connected domain; the center point of the straight line between two edge pixel points in the target edge point combination is used as the center position of the quasi-circle connected domain.

[0007] Preferably, the method of obtaining all salient point angles of the quasi-circle connected domain according to the position distribution between the center position of the quasi-circle connected domain and the edge pixel points includes: For any edge pixel point in the quasi-circle connected domain, the Euclidean distance between the edge pixel point and the center position of the quasi-circle connected domain is recorded as the target distance of the edge pixel point; the left adjacent edge pixel point and the right adjacent edge pixel point of the edge pixel point are both used as comparison pixel points of the edge pixel point; Among the edge pixel points and the compared edge pixel points, if the target distance of the edge pixel point is the maximum value, the edge pixel point is recorded as a convex point of the quasi-circular connected domain; if the target distance of the edge pixel point is the minimum value, the edge pixel point is recorded as a concave point of the quasi-circular connected domain; For any convex point of the quasi-circular connected domain, an angle formed by the convex point and two adjacent concave points with the convex point as the vertex is recorded as the convex point angle of the quasi-circular connected domain.

[0008] Preferably, the method of screening all the circle-like connected domains by edge feature parameters to obtain all the suspected pests and diseases connected domains includes the following specific methods: Preset a feature threshold parameter For any circle-like connected domain in the remote sensing grayscale image of the artificial forest to be detected, if the edge feature parameter of the circle-like connected domain is less than the feature threshold parameter , and record the circle-like connected domain as the suspected pest and disease connected domain.

[0009] Preferably, the method of converting each suspected pest and disease connected domain into the LAB color space, analyzing the position distribution of the pixel points in each suspected pest and disease connected domain in the LAB color space coordinate system, and obtaining the green sensitivity of each suspected pest and disease connected domain includes the following specific methods: For any pixel point in any suspected pest and disease connected domain, the absolute value of the difference between the chromaticity value of positive green on the a-axis of the LAB color space coordinate system and the chromaticity value of the pixel point on the a-axis of the LAB color space coordinate system is recorded as the green difference value of the pixel point; the normalized value of the cumulative sum of the green difference values ​​of all pixels in the suspected pest and disease connected domain is used as the green sensitivity of the suspected pest and disease connected domain.

[0010] Preferably, the method of dividing all suspected pest and disease connected domains into high green sensitivity connected domains and low green sensitivity connected domains based on green sensitivity includes the following specific methods: Preset a sensitive threshold parameter For any suspected pest connected domain, if the green sensitivity of the suspected pest connected domain is less than the sensitivity threshold parameter , the suspected pest connected domain is recorded as a low green sensitivity connected domain; if the green sensitivity of the suspected pest connected domain is greater than or equal to the sensitivity threshold parameter , the suspected pest and disease connected domain is recorded as a high green sensitivity connected domain.

[0011] Preferably, the method of obtaining the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected according to the grayscale difference of the pixel points between the high green sensitivity connected domain and the low green sensitivity connected domain, and the edge feature parameters, includes the following specific methods: The mean of the grayscale values ​​of all pixels in all high green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected is recorded as the first mean; the mean of the edge feature parameters of all high green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected is recorded as the second mean; the product of the first mean and the second mean is recorded as the first product; the mean of the grayscale values ​​of all pixels in all low green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected is recorded as the third mean; the mean of the edge feature parameters of all low green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected is recorded as the fourth mean; the product of the third mean and the fourth mean is recorded as the second product; the ratio of the first product to the second product is used as the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected.

[0012] Preferably, the intelligent identification of forest pests and diseases based on the enhanced remote sensing image of the artificial forest to be detected includes the following specific methods: The enhanced remote sensing image of the artificial forest to be detected is input into the trained neural network to obtain the forest area with pests and diseases in the enhanced remote sensing image of the artificial forest to be detected.

[0013] The beneficial effects of the technical solution of the present invention are as follows: the present invention obtains the green sensitivity of each suspected pest and disease connected domain by analyzing the position distribution of pixel points in each suspected pest and disease connected domain in the LAB color space coordinate system; based on the green sensitivity, all suspected pest and disease connected domains are divided into high green sensitivity connected domains and low green sensitivity connected domains; according to the grayscale difference of pixel points between the high green sensitivity connected domain and the low green sensitivity connected domain, and the edge feature parameters, the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected is obtained; according to the enhancement coefficient, the remote sensing grayscale image of the artificial forest to be detected is enhanced to obtain the enhanced remote sensing image of the artificial forest to be detected; intelligent identification of forest pests and diseases is performed based on the enhanced remote sensing image of the artificial forest to be detected; the traditional linear grayscale transformation algorithm is avoided to only enhance the image as a whole; the distinction between the pest and disease tree area and the normal tree area is increased by the enhancement coefficient, thereby improving the recognition of the tree area with pests and diseases in the artificial forest. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 The present invention is a flowchart of the steps of the intelligent identification method of forest pests and diseases based on UAV remote sensing; Figure 2 The present invention is a characteristic relationship flow chart of the method for intelligent identification of forest pests and diseases based on UAV remote sensing. DETAILED DESCRIPTION

[0016] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, features and effects of the intelligent identification method of forest pests and diseases based on drone remote sensing proposed by the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0017] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0018] The specific scheme of the intelligent identification method of forest pests and diseases based on UAV remote sensing provided by the present invention is described in detail below with reference to the accompanying drawings.

[0019] See also Figure 1 , which shows a flowchart of a method for intelligent identification of forest pests and diseases based on drone remote sensing provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Acquire a remote sensing grayscale image of the artificial forest to be detected.

[0020] It should be noted that the pests and diseases detected in this embodiment are common forest pests and diseases, such as pine nematode disease, which often occurs in artificial forests with a single planting structure. Due to the planting rules of artificial forests, the color changes are not obvious in the early stages of pests and diseases. Therefore, it is necessary to enhance the trees that may have pests and diseases in the remote sensing images of the artificial forests to be detected, so that it is easier to identify the trees with pests and diseases from the enhanced remote sensing images.

[0021] Specifically, we first need to collect the remote sensing grayscale image of the artificial forest to be detected. The specific process is as follows: A drone carrying a high-pixel camera is used to obtain remote sensing images of the artificial forest to be detected, and median filtering, denoising and grayscale operations are performed on the remote sensing images of the artificial forest to be detected to obtain a remote sensing grayscale image of the artificial forest to be detected.

[0022] Among them, median filtering and grayscale operations are existing technologies, and will not be described in detail in this embodiment.

[0023] So far, the remote sensing grayscale image of the artificial forest to be detected is obtained through the above method.

[0024] Step S002: by performing connected domain analysis on the remote sensing grayscale image of the artificial forest to be detected, a number of circle-like connected domains in the remote sensing grayscale image of the artificial forest to be detected are obtained; by performing edge feature analysis on each circle-like connected domain, edge feature parameters of each circle-like connected domain are obtained; all circle-like connected domains are screened by edge feature parameters to obtain all suspected pest and disease connected domains.

[0025] It should be noted that due to the planting rules of artificial forests, in order to make the trees grow evenly, there are strict planting specifications and standards for the spacing between trees. The distance between trees is large, there are fewer debris in the forest, the trees are planted at the same time, and the growth conditions of the trees are basically similar. Therefore, after using edge detection, evenly distributed circular-like connected domains are obtained; and because the edges of trees without pests and diseases have good ductility and grow evenly, the edges of their connected domains are relatively smooth; while the edges of trees with pests and diseases have poor ductility and grow unevenly, the edges of their connected domains are jagged, that is, there are more protrusions and depressions and a lower degree of smoothness; therefore, the edge feature parameters can be obtained by performing edge feature analysis on the circular-like connected domains in the remote sensing grayscale image; the circular-like connected domains are screened based on the edge feature parameters to obtain the suspected pest and disease connected domains.

[0026] Preferably, in some implementations of the embodiments of the present invention, by performing connected domain analysis on the remote sensing grayscale image of the artificial forest to be detected, a specific method for obtaining a plurality of circle-like connected domains in the remote sensing grayscale image of the artificial forest to be detected is: A gradient image of a remote sensing grayscale image of an artificial forest to be detected is obtained, and a watershed segmentation algorithm is performed on the gradient image to obtain multiple regions of the remote sensing grayscale image of the artificial forest to be detected. Each region is used as a quasi-circle connected domain, and then several quasi-circle connected domains in the remote sensing grayscale image of the artificial forest to be detected are obtained.

[0027] Among them, the watershed segmentation algorithm is a prior art and will not be described in detail in this embodiment.

[0028] Preferably, in some implementations of the embodiments of the present invention, since the edges of trees with pests and diseases have poor ductility and uneven growth, the edges of their quasi-circular connected domains are uneven, that is, there are more protrusions and depressions, and the smoothness is low; therefore, the specific method of obtaining the edge feature parameters of each quasi-circular connected domain by performing edge concave-convex feature analysis on each quasi-circular connected domain is as follows: For any quasi-circular connected domain in the remote sensing grayscale image of the artificial forest to be detected, the Canny edge detection algorithm is used to perform edge detection on the quasi-circular connected domain to obtain all edge pixel points in the quasi-circular connected domain; all edge pixel points in the quasi-circular connected domain are arbitrarily combined in pairs to obtain several edge point combinations of the quasi-circular connected domain; for any edge point combination, the Euclidean distance between two edge pixel points in the edge point combination is recorded as the first distance of the edge point combination; among all edge point combinations of the quasi-circular connected domain, the edge point combination with the largest first distance is recorded as the target edge point combination of the quasi-circular connected domain; the center point of the straight line connecting two edge pixel points in the target edge point combination is taken as the center position of the quasi-circular connected domain; Among them, the Canny edge detection algorithm is an existing technology and will not be described in detail in this embodiment.

[0029] For any edge pixel point in the quasi-circle connected domain, the Euclidean distance between the edge pixel point and the center position of the quasi-circle connected domain is recorded as the target distance of the edge pixel point; the left adjacent edge pixel point and the right adjacent edge pixel point of the edge pixel point are both used as comparison pixel points of the edge pixel point; Among the edge pixel points and the compared edge pixel points, if the target distance of the edge pixel point is the maximum value, the edge pixel point is recorded as a convex point of the quasi-circular connected domain; if the target distance of the edge pixel point is the minimum value, the edge pixel point is recorded as a concave point of the quasi-circular connected domain; For any convex point of the quasi-circular connected domain, an angle formed by the convex point and its two adjacent concave points with the convex point as the vertex is recorded as the convex point angle of the quasi-circular connected domain; Taking the normalized value of the average of the angle values ​​of all salient points in the quasi-circle connected domain as the edge feature parameter of the quasi-circle connected domain; The specific formula is: In the formula, Indicates The edge feature parameters of the circle-like connected domain; Indicates The number of angles between all convex points in a connected domain of a class circle; Indicates The first The angle value of the convex point angle; Represents the preset hyperparameters. This implementation presets , used to prevent the denominator from being 0; Represents the normalization function.

[0030] It should be noted that since the edges of the quasi-circular connected domains of normal trees are relatively smooth, the mean value of the angles of the salient points will be relatively large, that is, the edge feature parameters will be relatively large; while the edges of the quasi-circular connected domains of trees with pests and diseases are relatively smooth, the mean value of the angles of the salient points will be relatively small, that is, the edge feature parameters will be relatively small.

[0031] Preferably, in some implementations of the embodiments of the present invention, the specific method of screening all quasi-circle connected domains by edge feature parameters to obtain all suspected pest connected domains is: Preset a feature threshold parameter , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. Depends on the specific implementation situation; For any circle-like connected domain in the remote sensing grayscale image of the artificial forest to be detected, if the edge feature parameter of the circle-like connected domain is less than the feature threshold parameter , and record the circle-like connected domain as the suspected pest and disease connected domain.

[0032] So far, all the connected domains of suspected pests and diseases in the remote sensing grayscale image of the artificial forest to be detected are obtained through the above method.

[0033] Step S003: convert each suspected pest and disease connected domain into the LAB color space, analyze the position distribution of the pixel points in each suspected pest and disease connected domain in the LAB color space coordinate system, and obtain the green sensitivity of each suspected pest and disease connected domain; divide all suspected pest and disease connected domains into high green sensitivity connected domains and low green sensitivity connected domains based on the green sensitivity; obtain the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected according to the grayscale difference of the pixel points between the high green sensitivity connected domain and the low green sensitivity connected domain, as well as the edge feature parameters.

[0034] It should be noted that in the LAB color space coordinate system, the value range of a is -128 to +127, and the color change it represents is from green to magenta. Normally growing trees appear green, and green is on the negative half axis of the a (chromaticity) axis in the LAB color space coordinate system. Trees with pests and diseases appear red, brown, and purple, which is on the positive half axis of the a (chromaticity) axis in the color space. Therefore, the suspected pest and disease connected domain can be transformed into the LAB color space, and the position distribution of the pixels in the suspected pest and disease connected domain in the LAB color space can be analyzed to obtain the green sensitivity of the suspected pest and disease connected domain. Based on the green sensitivity, all suspected pest and disease connected domains are divided into high green sensitivity connected domains and low green sensitivity connected domains.

[0035] Preferably, in some implementations of the embodiments of the present invention, each suspected pest connected domain is converted into the LAB color space, and the position distribution of the pixels in each suspected pest connected domain in the LAB color space coordinate system is analyzed. The specific method for obtaining the green sensitivity of each suspected pest connected domain is: For any pixel point in any suspected pest and disease connected domain, the absolute value of the difference between the chromaticity value of positive green on the a-axis of the LAB color space coordinate system and the chromaticity value of the pixel point on the a-axis of the LAB color space coordinate system is recorded as the green difference value of the pixel point; the normalized value of the cumulative sum of the green difference values ​​of all pixels in the suspected pest and disease connected domain is taken as the green sensitivity of the suspected pest and disease connected domain; The specific formula is: In the formula, Indicates Green sensitivity of connected domains of suspected pests and diseases; Indicates The number of all pixels in the connected domain of suspected pests and diseases; Represents the chromaticity value of positive green on the a-axis of the LAB color space coordinate system; Indicates The first The chromaticity value of the pixel on the a-axis of the LAB color space coordinate system; Indicates taking the absolute value; represents an exponential function with a natural constant as the base, and the embodiment adopts Model to present inverse proportional relationship and normalization processing, As the input of the model, the implementer can choose the inverse proportional function and the normalization function according to the actual situation.

[0036] It should be noted that The larger the value, the The farther the chromaticity distance between the pixel point and the positive green on the a-axis of the LAB color space coordinate system, that is, the The lower the green sensitivity of the connected domain of suspected pests and diseases, the The more connected domains suspected of being infected with pests and diseases, the higher the possibility that they are infected trees.

[0037] Preferably, in some implementations of the embodiments of the present invention, the specific method of dividing all suspected pest and disease connected domains into high green sensitivity connected domains and low green sensitivity connected domains based on green sensitivity is: Preset a sensitive threshold parameter , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. Depends on the specific implementation situation; For any suspected pest connected domain, if the green sensitivity of the suspected pest connected domain is less than the sensitivity threshold parameter , the suspected pest connected domain is recorded as a low green sensitivity connected domain; if the green sensitivity of the suspected pest connected domain is greater than or equal to the sensitivity threshold parameter , the suspected pest and disease connected domain is recorded as a high green sensitivity connected domain.

[0038] At this point, all high green sensitivity connected domains and low green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected are obtained.

[0039] It should be noted that the enhancement effect of the linear grayscale transformation algorithm can be quantified by the degree of distinction between the high green sensitivity connected domain and the low green sensitivity connected domain, that is, the greater the degree of distinction between the two, the better the enhancement effect; in order to prevent the image from being over-enhanced, it is necessary to weaken the edge feature parameters of the connected domain, so that the enhanced low green sensitivity connected domain can preserve a better level of detail.

[0040] Preferably, in some implementations of the embodiments of the present invention, according to the grayscale difference of the pixels between the high green sensitivity connected domain and the low green sensitivity connected domain, and the edge feature parameters, the specific method for obtaining the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected is: The mean of the grayscale values ​​of all pixels in all high green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected is recorded as the first mean; the mean of the edge feature parameters of all high green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected is recorded as the second mean; the product of the first mean and the second mean is recorded as the first product; the mean of the grayscale values ​​of all pixels in all low green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected is recorded as the third mean; the mean of the edge feature parameters of all low green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected is recorded as the fourth mean; the product of the third mean and the fourth mean is recorded as the second product; the ratio of the first product to the second product is used as the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected; The specific formula is: In the formula, represents the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected; Represents the mean gray value of all pixels in all high green sensitivity connected domains in the remote sensing gray image of the artificial forest to be detected; Represents the mean value of the edge feature parameters of all high green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected; Represents the mean value of the grayscale values ​​of all pixels in all low green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected; Represents the mean of the edge feature parameters of all low green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected.

[0041] It should be noted that The larger the ratio is, the greater the difference in grayscale values ​​between the low green sensitivity connected domain and the high green sensitivity connected domain in the image, that is, the greater the difference between the insect-infested tree area and the normal tree area, and the greater the degree of distinction; and then the ratio between the edge feature parameters of the low green sensitivity connected domain and the high green sensitivity connected domain is used as the confidence level, so that the insect-infested tree area can preserve better details.

[0042] So far, the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected is obtained through the above method.

[0043] Step S004: enhancing the remote sensing grayscale image of the artificial forest to be detected according to the enhancement coefficient to obtain an enhanced remote sensing image of the artificial forest to be detected; and performing intelligent identification of forest pests and diseases based on the enhanced remote sensing image of the artificial forest to be detected.

[0044] Preferably, the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected is input into a linear grayscale transformation algorithm to enhance the remote sensing grayscale image of the artificial forest to be detected, so as to obtain an enhanced remote sensing image of the artificial forest to be detected.

[0045] Among them, the linear grayscale transformation algorithm is a prior art and will not be described in detail in this embodiment.

[0046] The enhanced remote sensing image of the artificial forest to be detected is input into the trained neural network to obtain the forest area with pests and diseases in the enhanced remote sensing image of the artificial forest to be detected; the neural network used in this embodiment is YOLOv3, and the method for obtaining the data set for training the neural network is: A large number of remote sensing grayscale images of the artificial forests to be detected are collected, and the forest areas with pests and diseases in the remote sensing grayscale images of each artificial forest to be detected are artificially marked with bounding boxes, and the marking results are recorded as the labels of the remote sensing grayscale images of each artificial forest to be detected; a large number of remote sensing grayscale images of the artificial forests to be detected and their corresponding labels are collected to form a data set; the neural network is trained using the data set, and the loss function used in the training process is a mean square error loss function; the specific training process is a well-known content of the neural network, and the specific training process will not be repeated in this embodiment.

[0047] See also Figure 2 , which shows a characteristic relationship flow chart of the intelligent identification method of forest pests and diseases based on UAV remote sensing.

[0048] At this point, this embodiment is completed.

[0049] 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 principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent identification method for forest pests and diseases based on UAV remote sensing, characterized in that: The method comprises the following steps: Obtaining a remote sensing grayscale image of the artificial forest to be detected; By performing connected domain analysis on the remote sensing grayscale image of the artificial forest to be detected, several circle-like connected domains in the remote sensing grayscale image of the artificial forest to be detected are obtained; by performing edge concave-convex feature analysis on each circle-like connected domain, edge feature parameters of each circle-like connected domain are obtained; all circle-like connected domains are screened by edge feature parameters to obtain all suspected pest and disease connected domains; Each suspected pest and disease connected domain is transformed into the LAB color space, and the position distribution of the pixel points in each suspected pest and disease connected domain in the LAB color space coordinate system is analyzed to obtain the green sensitivity of each suspected pest and disease connected domain; based on the green sensitivity, all suspected pest and disease connected domains are divided into high green sensitivity connected domains and low green sensitivity connected domains; according to the grayscale difference of the pixel points between the high green sensitivity connected domain and the low green sensitivity connected domain, as well as the edge feature parameters, the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected is obtained; The remote sensing grayscale image of the artificial forest to be detected is enhanced according to the enhancement coefficient to obtain an enhanced remote sensing image of the artificial forest to be detected; and intelligent identification of forest diseases and insect pests is performed based on the enhanced remote sensing image of the artificial forest to be detected.

2. The method for intelligent identification of forest pests and diseases based on UAV remote sensing according to claim 1 is characterized in that: The method of performing connected domain analysis on the remote sensing grayscale image of the artificial forest to be detected to obtain a plurality of circle-like connected domains in the remote sensing grayscale image of the artificial forest to be detected includes the following specific methods: A gradient image of a remote sensing grayscale image of an artificial forest to be detected is obtained, and a watershed segmentation algorithm is performed on the gradient image to obtain multiple regions of the remote sensing grayscale image of the artificial forest to be detected. Each region is used as a quasi-circle connected domain, and then several quasi-circle connected domains in the remote sensing grayscale image of the artificial forest to be detected are obtained.

3. The method for intelligent identification of forest pests and diseases based on UAV remote sensing according to claim 1 is characterized in that: The edge feature parameters of each quasi-circle connected domain are obtained by performing edge concave-convex feature analysis on each quasi-circle connected domain, and the specific method includes: For any quasi-circle connected domain in the remote sensing grayscale image of the artificial forest to be detected, edge detection is performed on the quasi-circle connected domain to obtain all edge pixel points in the quasi-circle connected domain; Obtaining the center position of the circle-like connected domain; According to the position distribution between the center position of the quasi-circle connected domain and the edge pixel points, all salient point angles of the quasi-circle connected domain are obtained; The normalized value of the average of the angle values ​​of all salient points in the quasi-circle connected domain is used as the edge feature parameter of the quasi-circle connected domain.

4. The method for intelligent identification of forest pests and diseases based on UAV remote sensing according to claim 3 is characterized in that: The specific method of obtaining the center position of the quasi-circle connected domain includes: All edge pixel points in the quasi-circle connected domain are arbitrarily combined in pairs to obtain several edge point combinations of the quasi-circle connected domain; for any edge point combination, the Euclidean distance between two edge pixel points in the edge point combination is recorded as the first distance of the edge point combination; among all edge point combinations in the quasi-circle connected domain, the edge point combination with the largest first distance is recorded as the target edge point combination of the quasi-circle connected domain; the center point of the straight line between two edge pixel points in the target edge point combination is used as the center position of the quasi-circle connected domain.

5. The method for intelligent identification of forest pests and diseases based on UAV remote sensing according to claim 3 is characterized in that: The method of obtaining all salient point angles of the quasi-circle connected domain according to the position distribution between the center position of the quasi-circle connected domain and the edge pixel points includes: For any edge pixel point in the quasi-circle connected domain, the Euclidean distance between the edge pixel point and the center position of the quasi-circle connected domain is recorded as the target distance of the edge pixel point; the left adjacent edge pixel point and the right adjacent edge pixel point of the edge pixel point are both used as comparison pixel points of the edge pixel point; Among the edge pixel points and the compared edge pixel points, if the target distance of the edge pixel point is the maximum value, the edge pixel point is recorded as a convex point of the quasi-circular connected domain; if the target distance of the edge pixel point is the minimum value, the edge pixel point is recorded as a concave point of the quasi-circular connected domain; For any convex point of the quasi-circular connected domain, an angle formed by the convex point and two adjacent concave points with the convex point as the vertex is recorded as the convex point angle of the quasi-circular connected domain.

6. The method for intelligent identification of forest pests and diseases based on UAV remote sensing according to claim 1 is characterized in that: The specific method of screening all the circle-like connected domains by edge feature parameters to obtain all the suspected pests and diseases connected domains includes: Preset a feature threshold parameter For any circle-like connected domain in the remote sensing grayscale image of the artificial forest to be detected, if the edge feature parameter of the circle-like connected domain is less than the feature threshold parameter , and record the circle-like connected domain as the suspected pest and disease connected domain.

7. The method for intelligent identification of forest pests and diseases based on UAV remote sensing according to claim 1 is characterized in that: The specific method of converting each suspected pest connected domain into the LAB color space, analyzing the position distribution of the pixel points in each suspected pest connected domain in the LAB color space coordinate system, and obtaining the green sensitivity of each suspected pest connected domain includes: For any pixel point in any suspected pest and disease connected domain, the absolute value of the difference between the chromaticity value of positive green on the a-axis of the LAB color space coordinate system and the chromaticity value of the pixel point on the a-axis of the LAB color space coordinate system is recorded as the green difference value of the pixel point; the normalized value of the cumulative sum of the green difference values ​​of all pixels in the suspected pest and disease connected domain is used as the green sensitivity of the suspected pest and disease connected domain.

8. The method for intelligent identification of forest pests and diseases based on UAV remote sensing according to claim 1 is characterized in that: The method of dividing all suspected pest and disease connected domains into high green sensitivity connected domains and low green sensitivity connected domains based on green sensitivity includes: Preset a sensitive threshold parameter For any suspected pest connected domain, if the green sensitivity of the suspected pest connected domain is less than the sensitivity threshold parameter , the suspected pest connected domain is recorded as a low green sensitivity connected domain; if the green sensitivity of the suspected pest connected domain is greater than or equal to the sensitivity threshold parameter , the suspected pest and disease connected domain is recorded as a high green sensitivity connected domain.

9. The method for intelligent identification of forest pests and diseases based on UAV remote sensing according to claim 1 is characterized in that: The method of obtaining the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected according to the grayscale difference of the pixel points between the high green sensitivity connected domain and the low green sensitivity connected domain, and the edge feature parameters, includes the following specific methods: The mean of the grayscale values ​​of all pixels in all high green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected is recorded as the first mean; the mean of the edge feature parameters of all high green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected is recorded as the second mean; the product of the first mean and the second mean is recorded as the first product; the mean of the grayscale values ​​of all pixels in all low green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected is recorded as the third mean; the mean of the edge feature parameters of all low green sensitivity connected domains in the remote sensing grayscale image of the artificial forest to be detected is recorded as the fourth mean; the product of the third mean and the fourth mean is recorded as the second product; the ratio of the first product to the second product is used as the enhancement coefficient of the remote sensing grayscale image of the artificial forest to be detected.

10. The method for intelligent identification of forest pests and diseases based on UAV remote sensing according to claim 1, characterized in that: The specific method of intelligently identifying forest pests and diseases based on the enhanced remote sensing image of the artificial forest to be detected includes: The enhanced remote sensing image of the artificial forest to be detected is input into the trained neural network to obtain the forest area with pests and diseases in the enhanced remote sensing image of the artificial forest to be detected.

Images