Bursaphelenchus xylophilus infection stage monitoring identification method based on unmanned aerial vehicle visible light remote sensing

Abstract

The invention provides a pine wood nematode disease stage monitoring and identification method based on unmanned aerial vehicle visible light remote sensing, and particularly relates to the technical field of reading and identification of image data for pine wood nematode disease discoloration identification, and the method comprises the following steps: carrying out geometric registration, cutting and other preprocessing based on obtained unmanned aerial vehicle visible light remote sensing data; the method comprises the following steps: calculating vegetation indexes based on visible light three wave bands: a visible light wave band difference vegetation index (VDVI), an extra-green index (ExG), a visible light wave band difference vegetation index (VDVI), and a visible light wave band difference vegetation index (VDVI); converting the visible light image and the corresponding vegetation index image into a grayscale image, and performing multi-threshold segmentation on the grayscale image; and the color-changing standing tree is extracted according to the optimal threshold value, the extraction result is post-processed to realize single-plant color-changing standing tree identification, and the efficiency and precision of pine wood nematode disease color-changing wood identification based on the visible light unmanned aerial vehicle remote sensing image are further improved.

Description

Technical Field

[0001] The present application relates to the technical field of pest and disease identification and monitoring, specifically to the technical field of reading and identifying image data, and more specifically to a method for identifying and monitoring the diseased stage of standing trees with pine wood nematode disease based on visible light remote sensing by unmanned aerial vehicles. Background Art

[0002] Traditional monitoring and forecasting rely on manual surveys, which are not only time-consuming and labor-intensive, but also affected by factors such as topography. It is difficult to accurately grasp the occurrence, area, scope and extent of pine wood nematode disease in real time, resulting in untimely prevention and control, large-scale spread of disasters, and irreparable losses. Although satellite remote sensing can achieve large-scale monitoring, it is affected by factors such as revisit cycle, resolution, and weather, and cannot meet the needs of short-term disasters and high-precision monitoring. With the rapid development of remote sensing technology, drone remote sensing can obtain images with higher spatial resolution than satellite remote sensing, and has the advantages of high flexibility and strong real-time performance. The identification of discolored standing trees can be accurate to a single tree, and has become one of the important means of monitoring pine wood nematode disasters.

[0003] Using drones equipped with different cameras, a variety of data types can be obtained, such as visible light, multispectral, hyperspectral, thermal infrared and other drone remote sensing data. Multiple types of drone data are of great significance in the monitoring and identification of discolored standing trees with pine wood nematode disease. Considering the cost of sensors, the difficulty of obtaining data and the processing speed, drone visible light images are often used in actual business work to quickly identify discolored standing trees, while drone multispectral and hyperspectral data are mostly used in early monitoring research of pine wood nematode disease. Chen Weimei et al. used a two-level fusion deep learning model of VGG16 and improved YOLOv5 based on drone images to identify standing trees with pine wood nematode disease, with an identification accuracy of 85.58%. Zhang et al. used drone visible light images based on improved YOLOv5 to monitor standing trees with pine wood nematode disease, with an identification accuracy of 92.6%, an improvement of 3.3% over the original model. Su et al.

[20] proposed an aerial image detection model based on PWD-YOLOv8, which has an accuracy of 87.9% in identifying discolored standing trees. Liu Jincang et al. constructed feature vectors using the red, green, and blue bands and texture features of drones, and used a conditional random field model to classify discolored standing trees, with an average accuracy of 88.43%. The color of pine needles changes significantly after pine trees are infected with pine wilt disease. The spectral characteristics of pine trees infected with pine wilt disease in images can be used to realize remote sensing monitoring of discolored standing trees. Wang Xiaoqin et al. compared the vegetation index constructed based on the visible light band to extract healthy green vegetation information. The results showed that the visible-band difference vegetation index (VDVI) has higher extraction accuracy than the normalized red-green normalized difference index (RGNDI) and the excessgreen index (ExG). Zou Yuzhen et al. compared the accuracy of extracting discolored standing trees using four vegetation indices (RGRI, GRRI, RGNDI, and ExR) composed of red and green bands, among which the extraction accuracy based on ExR was the highest. Li Hao et al. used an image segmentation algorithm that combined the super green feature factor (ExG) and the maximum inter-class variance method to better realize the discriminant analysis of the disease degree of diseased pine trees.

[0004] In summary, the research on using drone visible light images to monitor standing trees with pine wood nematode disease has made a lot of progress, but there are two problems in the current research on drone identification of standing trees with pine wood nematode disease. First, the current research focuses on the improvement of model algorithms, but due to the lack of samples, it is difficult to promote to different regions; second, in the current research on monitoring and identifying discolored wood, there is still potential for the extraction and identification of vegetation indexes constructed from drone visible light images containing only red, green and blue bands. In response to the above problems, the present invention calculates vegetation index based on drone visible light images, uses threshold segmentation method to realize discolored wood identification and reaches the level of business application. Summary of the invention

[0005] The purpose of the present invention is to provide a method for identifying standing trees infected with pine wood nematodes based on visible light remote sensing images from unmanned aerial vehicles, so as to further improve the efficiency and accuracy of identifying standing trees infected with pine wood nematodes based on visible light remote sensing data from unmanned aerial vehicles.

[0006] The technical solution adopted by the present invention is as follows: S1. Obtain high-resolution UAV visible light remote sensing images within the detection area; S2, calculate vegetation index (ExG, VDVI) based on three bands of visible light; Furthermore, the formula for calculating the vegetation index (ExG, VDVI) based on the three bands of visible light in step S2 is: ; ; In the formula, , , Represents the pixel values ​​of the red, green and blue bands respectively.

[0007] S3, visible light image and vegetation index multi-threshold segmentation; Further, step S3 performs threshold segmentation based on the vegetation index and the visible light image, which specifically includes the following steps: S31, converting to grayscale value: converting the visible light image and the corresponding vegetation index image into a grayscale image, with a pixel value range of 0~255.

[0008] S32, threshold segmentation: The image is segmented by using the multi-threshold maximum inter-class variance method (Otsu) improved by the genetic algorithm. To avoid misclassification due to a small number of thresholds, the number of segmentation thresholds is set to 10. The visible light and vegetation index images converted to grayscale values ​​in step S31 are segmented by threshold.

[0009] S4. Extraction and post-processing of discolored standing timber.

[0010] Furthermore, in step 4, discolored standing trees are identified and the results are post-processed. The specific steps include: According to the threshold segmentation results of the visible light and vegetation index images converted to grayscale values ​​obtained in step 3, the vegetation and non-vegetation (shadow, etc.) area extraction results and the preliminary extraction results of discolored standing trees are obtained respectively. The vegetation area obtained by threshold segmentation of the pre-processed drone visible light image is used to mask the preliminary extraction raster map of discolored standing trees, and the masked results are converted into vectors, and the area of ​​each spot is calculated. Finally, the discolored standing trees are screened according to the spot area.

[0011] The vegetation index calculated based on the three visible light bands in step S2 includes the overgreen vegetation index, the normalized green-red difference index, the normalized green-blue difference index, the red-green ratio index and the visible light band difference vegetation index.

[0012] The calculation formula of the overgreen vegetation index is: ; Among them, G represents the reflectivity of the green light band, R represents the reflectivity of the red light band, and B represents the reflectivity of the blue light band; this index highlights the vegetation information by enhancing the relatively high reflectivity characteristics of green vegetation in the green light band.

[0013] The calculation formula of the normalized green-red difference index is: This index uses the difference between green and red light bands to reflect the growth status and coverage of vegetation. The green light band has a stronger reflection on vegetation, while the red light band is easily absorbed by vegetation. After normalization, the difference between the two can better reflect the characteristics of vegetation.

[0014] The calculation formula of the normalized green-blue difference index is: ; This index is based on the difference in reflectance between the green and blue light bands and can be used to analyze the characteristics of vegetation; similar to NGRDI, the difference between the green and blue light bands is normalized to highlight the different reflectance characteristics of vegetation and other land objects in these two bands.

[0015] The red-green ratio index calculation formula is: ; This index simply and intuitively reflects the ratio of the reflectance of the red light band and the green light band; because vegetation has strong absorption in the red light band and strong reflection in the green light band, this ratio can indicate the growth status and coverage of vegetation to a certain extent.

[0016] The calculation formula of the visible light band difference vegetation index is: ; The vegetation index of the three bands of visible light is comprehensively considered. By integrating and calculating the information of the three bands, it can more comprehensively reflect the characteristics of vegetation; its value range is the same as that of the normalized vegetation index.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention identifies standing trees with pine wood nematode disease color based on UAV visible light remote sensing images, adopts high-resolution UAV visible light data, and proposes a method for quickly extracting discolored standing trees based on vegetation index using threshold segmentation without constructing a sample data set, with good recognition effect.

[0018] Compared with the traditional regular inspection and monitoring of pine wood nematode disease by monitors, the present invention can discover discolored standing trees hidden in the forest, saving a lot of manpower and material resources. At the same time, the survey area covers a larger area, greatly improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 The present invention shows a flow chart of a method for identifying standing trees with pine wood nematode disease color based on UAV visible light remote sensing images.

[0020] Figure 2 A schematic diagram of the study area of ​​Example 2 is shown.

[0021] Figure 3 The figure shows the pixel value statistics of different ground objects in the three bands of visible light.

[0022] Figure 4 The statistical graphs of five vegetation indices of different land features converted into grayscale values ​​are shown.

[0023] Figure 5 The results of partial image threshold segmentation are shown.

[0024] Figure 6 The invention shows the extraction results of color-changing standing trees based on different vegetation indices.

[0025] Figure 7 A comparison of color-changing wood extraction results based on five vegetation indices in a local area is shown. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Example 1 like Figure 1 As shown, this embodiment discloses a method for remote sensing monitoring and identification of standing trees with pine wood nematode disease, comprising the following steps: S1. Obtain high-resolution UAV visible light remote sensing images within the detection area; S2, calculate vegetation index (ExG, VDVI) based on three bands of visible light; Furthermore, the formula for calculating the vegetation index (ExG, VDVI) based on the three bands of visible light in step S2 is: ; ; In the formula, , , Represents the pixel values ​​of the red, green and blue bands respectively.

[0028] S3, visible light image and vegetation index multi-threshold segmentation; Further, step S3 performs threshold segmentation based on the vegetation index and the visible light image, which specifically includes the following steps: S31, converting to grayscale value: converting the visible light image and the corresponding vegetation index image into a grayscale image, with a pixel value range of 0~255.

[0029] S32, threshold segmentation: The image is segmented by multi-threshold Otsu improved by genetic algorithm. To avoid misclassification due to a small number of thresholds, the number of segmentation thresholds is set to 10. The visible light and vegetation index images converted to grayscale values ​​in step S31 are segmented by threshold.

[0030] S4. Extraction and post-processing of discolored standing timber.

[0031] Furthermore, in step 4, discolored standing trees are identified and the results are post-processed. The specific steps include: According to the threshold segmentation results of the visible light and vegetation index images converted to grayscale values ​​obtained in step 3, the vegetation and non-vegetation (shadow, etc.) area extraction results and the preliminary extraction results of discolored standing trees are obtained respectively. The vegetation area obtained by threshold segmentation of the pre-processed drone visible light image is used to mask the preliminary extraction raster map of discolored standing trees, and the masked results are converted into vectors, and the area of ​​each spot is calculated. Finally, the discolored standing trees are screened according to the spot area.

[0032] The vegetation index calculated based on the three visible light bands in step S2 includes the overgreen vegetation index, the normalized green-red difference index, the normalized green-blue difference index, the red-green ratio index and the visible light band difference vegetation index.

[0033] The calculation formula of the overgreen vegetation index is: ; Among them, G represents the reflectivity of the green light band, R represents the reflectivity of the red light band, and B represents the reflectivity of the blue light band; this index highlights the vegetation information by enhancing the relatively high reflectivity characteristics of green vegetation in the green light band.

[0034] The calculation formula of the normalized green-red difference index is: This index uses the difference between green and red light bands to reflect the growth status and coverage of vegetation. The green light band has a stronger reflection on vegetation, while the red light band is easily absorbed by vegetation. After normalization, the difference between the two can better reflect the characteristics of vegetation.

[0035] The calculation formula of the normalized green-blue difference index is: ; This index is based on the difference in reflectance between the green and blue light bands and can be used to analyze the characteristics of vegetation; similar to NGRDI, the difference between the green and blue light bands is normalized to highlight the different reflectance characteristics of vegetation and other land objects in these two bands.

[0036] The red-green ratio index calculation formula is: ; This index simply and intuitively reflects the ratio of the reflectance of the red light band and the green light band; because vegetation has strong absorption in the red light band and strong reflection in the green light band, this ratio can indicate the growth status and coverage of vegetation to a certain extent.

[0037] The calculation formula of the visible light band difference vegetation index is: ; The vegetation index of the three bands of visible light is comprehensively considered. By integrating and calculating the information of the three bands, it can more comprehensively reflect the characteristics of vegetation; its value range is the same as that of the normalized vegetation index.

[0038] Example 2 This example takes Fushun City, Liaoning Province as the study area.

[0039] Fushun City is located in the mid-latitude region (E124°13′06″, N41°56′15″). The study area belongs to the temperate continental monsoon climate, showing the typical climatic characteristics of high temperature and heavy rain in summer and drought and little rain in winter. The average annual temperature is 6.8℃, and the average annual precipitation is 789.5 mm. The study area belongs to the plain area, with a gentle overall terrain and small undulations. The study area is rich in forest resources, mainly artificially planted Korean pine (Pinus koraiensis Siebold&Zuccarini), Chinese pine (Pinustabuliformis Carriere) and North China larch (Larix gmelinii var. principis-rupprechtii (Mayr) Pilger). The main soil types are brown soil, dark brown soil, meadow soil, etc. Due to the incomplete elimination of diseased trees, the presence of host plants (pine trees) and host insects (pine beetles) and a suitable living environment, pine wood nematode disease has not been completely eliminated in Fushun City.

[0040] In this example, a typical area of ​​Hadar Forest Farm was selected for drone data collection and manual verification.

[0041] The experimental case of this embodiment carried out a field observation experiment on pine wood nematode disease in the study area on July 18, 2023.

[0042] The drone visible light image in this embodiment is obtained by taking pictures with a DJI M300 drone equipped with a Zenmuse H20T camera. The collection of visible light remote sensing images in this example was carried out in a clear and windless environment, and the collection time was 10:00-14:00. The experiment finally obtained a spatial resolution of 4 cm, which can meet the monitoring needs of pixel-level indicator analysis.

[0043] The remote sensing images taken were checked and it was found that the images obtained could well cover the actual survey area. Based on the above operations, the usable drone visible light remote sensing images for color-changing standing tree identification were finally obtained.

[0044] The first step of the present invention is data collection. On July 18, 2023, a visible light image of the Hada Forest Farm area was obtained by drone. The original image data was preprocessed by splicing, geometric registration, cropping, etc., and finally a visible light remote sensing image of a drone with red, green, and blue bands was obtained ( Figure 1 ), with a spatial resolution of 4 cm. The background remote sensing images within the two months before the control experiment can confirm that the discolored standing trees in the area at this time are the newly infected pine wood nematode pine trees of the year. The real discolored standing trees in the study area are determined through visual interpretation and field investigation.

[0045] The second step of the present invention is to calculate the vegetation index based on the three bands of visible light: (1) spectral feature analysis; (2) vegetation index calculation. First, based on the visible light image of the drone, samples are selected with discolored standing trees, healthy pine trees, grasslands, and bare soil as research objects, and the pixel values ​​of the three bands of visible light corresponding to each pixel are counted, such as Figure 3 According to the spectral characteristics of the ground objects and the formulas of related vegetation indices, the red green normalized difference index (RGNDI), excess red index (ExR), vegetation atmospherically resistant index (VARI), visible-band difference vegetation index (VDVI), and excess green index (ExG) were calculated.

[0046]

[0047] The third step of the present invention is to screen the monitoring indicators and determine the classification threshold: threshold segmentation is performed based on the vegetation index and the visible light image: (1) conversion to grayscale value; (2) vegetation index analysis converted to grayscale value; (3) threshold segmentation. The conversion to grayscale value refers to converting the visible light image and the corresponding vegetation index image into grayscale images, with a pixel value range of 0 to 255. Figure 4 The grayscale values ​​of the vegetation indices corresponding to the pixels of discolored standing trees, healthy pine trees, grasslands, and bare soil samples were converted into grayscale images. The five vegetation indices can better distinguish discolored standing trees from the other three types of ground objects. Among them, the RGNDI, ExR, and VARI values ​​of discolored standing trees are significantly higher than those of the other three types of ground objects, and the ExG and VDVI values ​​are significantly lower than those of the other three types of ground objects. The image was threshold segmented using the multi-threshold Otsu improved by genetic algorithm. To avoid misclassification due to a small number of thresholds, the number of segmentation thresholds was set to 10. In order to extract discolored standing trees and vegetation and non-vegetation (shadow, etc.) areas based on vegetation index threshold segmentation, the Otsu improved by genetic algorithm was used to perform threshold segmentation on the images converted from the five vegetation indices to grayscale values ​​and the pre-processed drone visible light images to grayscale values.

[0048] The fourth step of the present invention is to extract and post-process the discolored standing trees, and conduct accuracy evaluation. According to the multi-threshold segmentation results, combined with the drone visible light image, the optimal thresholds for extracting discolored standing trees after the five vegetation indices RGNDI, ExR, VARI, VDVI, and ExG are converted into grayscale values ​​within the study area are obtained: 182, 144, 242, 39, and 82, respectively. Combined with the formulas and meanings of each vegetation index, pixels above the optimal threshold for VARI, RGNDI, and ExR are selected to extract discolored standing trees, and pixels below the optimal threshold for VDVI and ExG are selected to extract discolored standing trees. Pixels above the optimal threshold of 92 of the preprocessed drone visible light image converted to grayscale are vegetation areas, and the results of the discolored standing trees initially extracted using the vegetation index are subsequently masked based on this. The multi-threshold segmentation results and extraction results of ExR and ExG converted to grayscale values ​​and the preprocessed drone visible light images are shown as follows. Figure 5 shown.

[0049] The vegetation area obtained by threshold segmentation of the pre-processed drone visible light image was used to mask the initial extraction grid map of the color-changing trees. The masked result was converted into a vector, and the area of ​​each spot was calculated. Finally, the color-changing trees were screened according to the spot area. The color-changing trees in the final study area were obtained through threshold segmentation and post-processing ( Figure 6 ).

[0050] This invention selects three statistical indicators: precision, recall, and F1 score. Precision indicates the accuracy of positive samples in the prediction results; recall indicates the proportion of positive samples that are correctly predicted; F1 score is the harmonic mean of precision and recall. The calculation formulas for each indicator are as follows.

[0051] (1); (2); (3); In the formula, P represents positive samples, N represents negative samples, T represents correct prediction, F represents wrong prediction, TP represents true positive class, which refers to the number of trees identified as color-changing trees and are actually color-changing trees; FN represents false negative class, which refers to the number of trees identified as non-color-changing trees but are actually color-changing trees. Both represent actual positive samples; FP represents false positive class, which refers to the number of trees identified as color-changing trees but are actually not color-changing trees; TN represents true negative class, which refers to the number of trees identified as non-color-changing trees and are actually non-color-changing trees. Both represent actual negative samples.

[0052] The precision of VARI and RGNDI exceeded 90%, but the recall rate and F1 value were low. VDVI and ExG had better overall recognition effect and better completeness in extracting color-changing standing trees. The precision rates were higher than 85%, 88.14% and 87.70% respectively, and the recall rates were higher than 80%, 80.00% and 82.31% respectively. The highest F1 value of ExG was 84.92%. In this study area, the recognition effect of ExR was poor, and the recall rate and F1 value did not exceed 70%. In general, in the study area with sparse trees and abundant forest grass, VDVI and ExG were better for identifying color-changing standing trees.

[0053] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for monitoring and identifying the diseased stage of pine wood nematode disease based on UAV visible light remote sensing, characterized by: The following steps are involved: S1. Obtain high-resolution UAV visible light remote sensing images within the detection area; S2. Calculate vegetation index based on three visible light bands: visible light band difference vegetation index and super green index; S3, visible light image and vegetation index multi-threshold segmentation; S4, extraction and post-processing of discolored standing wood; The formula for calculating the vegetation index based on the three bands of visible light in step S2 is: ； ； In the formula, , , Represent the pixel values ​​of red, green and blue bands respectively; In step S3, threshold segmentation is performed based on the vegetation index and the visible light image, which specifically includes the following steps: S31, converting to grayscale value: converting the visible light image and the corresponding vegetation index image into a grayscale image, with a pixel value range of 0 to 255; S32, threshold segmentation: the image is segmented by a multi-threshold maximum inter-class variance method improved by a genetic algorithm. To avoid misclassification due to a small number of thresholds, the number of segmentation thresholds is set to 10; the visible light and vegetation index images converted to grayscale values ​​in step S31 are segmented by thresholds; In step 4, discolored standing trees are identified and the results are post-processed; the specific steps include: According to the threshold segmentation results of the visible light and vegetation index images converted into grayscale values ​​obtained in step 3, the vegetation and non-vegetation area extraction results and the preliminary extraction results of the color-changing standing trees are obtained respectively; the vegetation area obtained after threshold segmentation of the pre-processed drone visible light image is used to mask the preliminary extraction raster map of the color-changing standing trees, and the masked results are converted into vectors, the area of ​​each spot is calculated, and finally the color-changing standing trees are screened according to the spot area.

2. The method for monitoring and identifying the diseased stage of pine wood nematode disease based on UAV visible light remote sensing according to claim 1, characterized in that: The vegetation index calculated based on the three visible light bands in step S2 includes the overgreen vegetation index, the normalized green-red difference index, the normalized green-blue difference index, the red-green ratio index and the visible light band difference vegetation index.

3. The method for monitoring and identifying the diseased stage of pine wood nematode disease-infected trees based on visible light remote sensing by unmanned aerial vehicles according to claim 2, characterized in that: The calculation formula of the overgreen vegetation index is: ; Among them, G represents the reflectivity of the green light band, R represents the reflectivity of the red light band, and B represents the reflectivity of the blue light band; this index highlights the vegetation information by enhancing the relatively high reflectivity characteristics of green vegetation in the green light band.

4. The method for monitoring and identifying the diseased stage of pine wood nematode disease-infected trees based on visible light remote sensing by unmanned aerial vehicles according to claim 2, characterized in that: The calculation formula of the normalized green-red difference index is: This index uses the difference between green and red light bands to reflect the growth status and coverage of vegetation. The green light band has a stronger reflection on vegetation, while the red light band is easily absorbed by vegetation. After normalization, the difference between the two can better reflect the characteristics of vegetation.

5. The method for monitoring and identifying the diseased stage of pine wood nematode disease-infected trees based on visible light remote sensing by unmanned aerial vehicles according to claim 2, characterized in that: The calculation formula of the normalized green-blue difference index is: ; This index is based on the difference in reflectance between the green and blue light bands and can be used to analyze the characteristics of vegetation; similar to NGRDI, the difference between the green and blue light bands is normalized to highlight the different reflectance characteristics of vegetation and other land objects in these two bands.

6. The method for monitoring and identifying the diseased stage of pine wood nematode disease-infected trees based on visible light remote sensing by unmanned aerial vehicles according to claim 2, characterized in that: The red-green ratio index calculation formula is: ; This index simply and intuitively reflects the ratio of the reflectance of the red light band and the green light band; because vegetation has strong absorption in the red light band and strong reflection in the green light band, this ratio can indicate the growth status and coverage of vegetation to a certain extent.

7. The method for monitoring and identifying the diseased stage of pine wood nematode disease-infected trees based on visible light remote sensing by unmanned aerial vehicles according to claim 2, characterized in that: The calculation formula of the visible light band difference vegetation index is: ; The vegetation index of the three bands of visible light is comprehensively considered. By integrating and calculating the information of the three bands, it can more comprehensively reflect the characteristics of vegetation; its value range is the same as that of the normalized vegetation index.

Images