An automatic identification method and system for floating leaf vegetation and emergent vegetation

Abstract

The present application provides a kind of floating leaf vegetation and emergent vegetation automatic identification method and automatic identification system, it is related to ecological environment monitoring technical field.The identification method provided by the present application includes the following steps: obtaining the target radar image of target area, based on the gray value of target radar image, gray threshold is demarcated, and the target radar image is reclassified based on gray threshold, and obtain emergent vegetation area and area to be distinguished;Obtain multispectral remote sensing data of target area, calculate the normalized vegetation index of each pixel in target area image based on multispectral remote sensing data, and divide water area and vegetation mixed area based on normalized vegetation index;The overlapping area of area to be distinguished and the vegetation mixed area is floating leaf vegetation area.The present application can effectively identify floating leaf vegetation and emergent vegetation by combining radar image technology and multispectral remote sensing technology, provide technical support for large-scale aquatic vegetation investigation and water ecological detection, with high accuracy and high efficiency identification ability.

Description

Technical Field

[0001] This invention relates to the field of ecological environment monitoring technology, and in particular to an automatic identification method and system for floating-leaved vegetation and emergent vegetation. Background Technology

[0002] Aquatic vegetation plays an indispensable role in maintaining water quality, improving the regional aquatic environment, protecting the health of aquatic ecosystems, and safeguarding biodiversity. In ecosystem research and management, floating-leaved vegetation and emergent vegetation play distinct roles in aquatic ecosystems, each making unique contributions to water purification, ecological balance maintenance, and biodiversity conservation. Therefore, accurately identifying floating-leaved vegetation and emergent vegetation is crucial for a deeper understanding of the structure and function of aquatic ecosystems, formulating scientifically sound protection and management measures, ensuring the sustainable use of water resources, and maintaining ecological balance.

[0003] Traditional aquatic vegetation monitoring primarily relies on manual field surveys. While these surveys offer high accuracy and can identify specific species, they are time-consuming, labor-intensive, and have a limited monitoring range. Satellite remote sensing technology, on the other hand, provides a rapid and wide-area method for monitoring aquatic vegetation. It offers advantages such as real-time monitoring and spatiotemporal continuity, enabling long-term observation of the area and spatiotemporal trends of aquatic vegetation within a specific region. Remote sensing technology effectively monitors aquatic vegetation, providing crucial data support for the protection and research of aquatic ecosystems such as lakes and wetlands.

[0004] Multispectral remote sensing technology identifies aquatic vegetation groups by analyzing the differences in spectral characteristics of different aquatic vegetation in satellite imagery. Therefore, a series of vegetation indices have been developed to extract different groups, such as the Normalized Difference Vegetation Index (NDVI), the Floating Leaf Vegetation Sensitive Spectral Index (FVSI), and the Floating Algae Index (FAI).

[0005] Aquatic vegetation can be extracted using decision tree classification or thresholding methods based on relevant vegetation indices. However, since emergent vegetation and floating-leaved vegetation have relatively small differences in spectral reflectance in the near-infrared band, there is a problem of "different objects sharing the same spectrum," making it impossible to effectively distinguish between emergent vegetation and floating-leaved vegetation based on spectral characteristics using vegetation indices. Therefore, there is an urgent need to provide a solution to improve the above problems. Summary of the Invention

[0006] The purpose of this invention is to provide an automatic identification method and system for floating-leaved vegetation and emergent vegetation.

[0007] In a first aspect, the present invention provides an automatic identification method for floating-leaved vegetation and emergent vegetation, comprising the following steps: acquiring a target radar image of a target area; defining a grayscale threshold based on the grayscale value of the target radar image; and reclassifying the target radar image based on the grayscale threshold to obtain an emergent vegetation area and a region to be distinguished; acquiring multispectral remote sensing data of the target area; calculating the normalized vegetation index (NDI) of each pixel in the target area image based on the NDI; and dividing a water body area and a mixed vegetation area based on the NDI; and identifying the overlapping area between the region to be distinguished and the mixed vegetation area as a floating-leaved vegetation area.

[0008] The identification method provided by this invention, by combining radar imagery technology and multispectral remote sensing technology, can effectively identify floating-leaved vegetation and emergent vegetation, providing technical support for large-scale aquatic vegetation surveys and aquatic ecological monitoring, and has high accuracy and efficient identification capabilities.

[0009] Optionally, when acquiring a target radar image of a target area, when determining a grayscale threshold based on the grayscale value of the target radar image, the grayscale value of each pixel in the target radar image is acquired, and a grayscale histogram is constructed based on the grayscale value. The valley point of two intersecting peaks in the grayscale histogram is selected as the grayscale threshold.

[0010] Optionally, the gray value of each pixel in the emergent vegetation area is greater than or equal to the gray value threshold, and the gray value of each pixel in the area to be distinguished is less than the gray value threshold.

[0011] Optionally, after acquiring the target radar image, the target radar image is preprocessed, and grayscale thresholds are defined based on the preprocessed target radar image.

[0012] Optionally, the preprocessing includes radiometric correction, speckle noise suppression, image registration, geometric correction, and linear scale conversion.

[0013] Optionally, when calculating the normalized vegetation index for each pixel in the target area based on the multispectral remote sensing data, the following formula is used:

[0014]

[0015] Among them: NDVI i Let NIR be the normalized vegetation index of the i-th pixel; i RED is the near-infrared reflectance of the i-th pixel; i Let be the infrared reflectance of the i-th pixel.

[0016] Secondly, the present invention also provides an automatic identification system for floating-leaved vegetation and emergent vegetation, comprising:

[0017] The data acquisition module acquires radar images and multispectral remote sensing data of the target area;

[0018] The grayscale processing module determines a grayscale threshold based on the grayscale values ​​of the target radar image;

[0019] The emergent vegetation identification module reclassifies the target radar image based on a grayscale threshold to obtain the emergent vegetation area and the area to be distinguished.

[0020] The normalized vegetation index (NVI) calculation module calculates the NVI of each pixel in the target area image based on the multispectral remote sensing data.

[0021] The floating leaf vegetation identification module divides the water area and the vegetation mixed area based on the normalized vegetation index, and obtains the overlapping area between the area to be identified and the vegetation mixed area as the floating leaf vegetation area. Attached Figure Description

[0022] Figure 1 A flowchart illustrating an automatic identification method for floating-leaved vegetation and emergent vegetation provided by the present invention;

[0023] Figure 2 This is a flowchart illustrating the automatic identification method for floating-leaved vegetation and emergent vegetation provided by the present invention.

[0024] Figure 3 The diagram shows the identification process when the automatic identification method provided by this invention is applied to a part of Poyang Lake to identify floating-leaved vegetation and emergent vegetation.

[0025] Figure 4 This is a schematic diagram of the grayscale histogram and grayscale threshold when the automatic identification method provided by this invention is applied to a part of Poyang Lake to identify floating-leaved vegetation and emergent vegetation.

[0026] Figure 5 This is a schematic diagram of the structure of an automatic identification system for floating-leaved vegetation and emergent vegetation provided by the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Unless otherwise defined, the technical or scientific terms used herein should have the ordinary meaning understood by those skilled in the art to which this invention pertains.

[0028] See Figure 1 and Figure 2This invention provides an automatic identification method for floating-leaved vegetation and emergent vegetation, comprising the following steps:

[0029] S1. Acquire target radar images of the target area and determine grayscale thresholds based on the grayscale values ​​of the target radar images.

[0030] S2. Reclassify the target radar image based on grayscale threshold to obtain the emergent vegetation area and the area to be distinguished.

[0031] S3. Acquire multispectral remote sensing data of the target area, and calculate the normalized vegetation index of each pixel in the target area image based on the multispectral remote sensing data.

[0032] S4. Divide the water body area and the mixed vegetation area based on the normalized vegetation index;

[0033] S5. Obtain the overlapping area between the area to be distinguished and the mixed vegetation area as the floating leaf vegetation area.

[0034] In fact, the target radar image acquired in step S1 records the backscattering information of the target object in the target area to the radar beam. Since this scattering information is affected by the roughness of the target object, it can show different features in the radar image. Therefore, targets with different roughness can be identified from the target radar image.

[0035] In fact, both emergent vegetation and floating-leaved vegetation grow in water, but the stems and leaves of emergent vegetation extend above the water surface, while floating-leaved vegetation floats on the water surface. Furthermore, the roughness of floating-leaved vegetation is similar to that of the water surface. In addition, environmental factors can also cause changes in the roughness of the water surface, such as wind, rain, and ripples.

[0036] In some embodiments, when determining the grayscale threshold based on the grayscale value of the target radar image in step S1, the grayscale value of each pixel in the target radar image is obtained, and a grayscale histogram is constructed based on the grayscale value. The valley point of the two cross peaks in the grayscale histogram is selected as the grayscale threshold.

[0037] In fact, the grayscale histogram constructed when defining the grayscale threshold shows the frequency of occurrence of different grayscale values ​​in the target radar image. Therefore, the concentration trend and dispersion of grayscale values ​​in the target radar image can be quickly understood from the grayscale histogram, which is helpful in determining the category of target objects in the target radar image.

[0038] Specifically, when defining the grayscale threshold, the peak positions of different grayscale peaks in the grayscale histogram reflect the main grayscale value distribution, which corresponds to the regions of different targets in the target radar image. The two grayscale peaks can be accurately divided by the valley point between the two intersecting peaks. In fact, in step S2, the grayscale value of each pixel in the emergent vegetation area is greater than or equal to the grayscale threshold, while the grayscale value of each pixel in the area to be distinguished is less than the grayscale threshold.

[0039] In some embodiments, after acquiring the target radar image in step S1, the target radar image is preprocessed, and grayscale thresholds are defined based on the preprocessed target radar image. Specifically, the preprocessing includes radiometric correction, speckle noise suppression, image registration, geometric correction, and linear scale conversion.

[0040] In fact, preprocessing target radar images can significantly improve the data quality of radar images, which helps to compare and analyze image data acquired by the same and different sensors at multiple time phases, and can highlight the differences in radar intensity, which helps to distinguish ground features with large differences in brightness on radar images.

[0041] In some embodiments, when calculating the normalized vegetation index for each pixel in the target area based on multispectral remote sensing data in step S3, the following formula is used:

[0042]

[0043] Among them: NDVI i Let NIR be the normalized vegetation index of the i-th pixel; i RED is the near-infrared reflectance of the i-th pixel; i Let be the infrared reflectance of the i-th pixel.

[0044] In fact, by calculating the normalized vegetation index of the target area, the growth status and coverage of vegetation in the target area can be effectively reflected, and the value of the normalized vegetation index can effectively distinguish the vegetation coverage area from the water area in the target area.

[0045] In practice, when dividing the water body area and the mixed vegetation area based on the normalized vegetation index (NVI) in step S4, since the NVI of the water body and the vegetation area differs significantly, a classification threshold can be preset or the classification threshold can be adaptively adjusted through a model. For example, the classification threshold can be set by referring to existing research results and experience in this field, or a supervised machine learning model can be used, employing sample data of known target categories as the training set, thereby adaptively adjusting the classification threshold.

[0046] In some embodiments, see Figure 3When using the identification method provided by this invention to identify floating-leaved vegetation and emergent vegetation in a certain area of ​​Poyang Lake, the following steps are included:

[0047] S1. Select a clear Landsat-8 image (20141008) with few clouds and the corresponding target radar image (20141008). Perform radiometric correction, speckle noise suppression, image registration, geometric correction, and linear scale transformation on the target radar image. After converting the backscattering coefficient of the target radar image into logarithmic scale form, obtain the gray value of each pixel in the image. Construct a gray-level histogram of the target radar image based on the gray-level values, and select the valley point of the two cross peaks in the gray level as the gray-level threshold (-21). Figure 4 As shown;

[0048] S2. In ArcGIS software, the reclassification tool is used to reclassify the target radar image based on the gray value threshold, thereby obtaining the emergent vegetation area where the gray value is greater than or equal to the gray value threshold, and the area to be distinguished where the gray value is less than the gray value threshold.

[0049] S3. Acquire multispectral remote sensing data of the Landsat-8 image (20141008), construct a normalized vegetation index model using the raster calculator tool in ArcGIS software, and calculate the normalized vegetation index of each pixel in the image using the normalized vegetation index model.

[0050] S4. Set the classification threshold to 0. Based on the classification threshold, areas with a normalized vegetation index greater than or equal to 0 are classified as mixed vegetation areas, and areas with a normalized vegetation index less than 0 are classified as water areas.

[0051] S5. In ArcGIS software, use the intersection tool to perform intersection processing on the area to be distinguished and the mixed vegetation area to obtain the overlapping area as the floating leaf vegetation area.

[0052] The accuracy of the above classification results was verified by a confusion matrix. 600 sample points were randomly generated in the Poyang Lake area using ArcGIS software. These 600 sample points were visually identified and compared with the above classification results. The verification sample confusion matrix shown in Table 1 below was constructed. It can be seen that the overall accuracy of the identification method provided by this invention is 93.33%, and the Kappa coefficient is 0.8798. This indicates that the identification method provided by this invention can accurately classify floating-leaved vegetation and emergent vegetation.

[0053] Table 1 Evaluation of Extraction Accuracy of Floating-leaved Vegetation and Emergent Vegetation

[0054]

[0055] See Figure 5The present invention also provides an automatic identification system for floating-leaved vegetation and emergent vegetation, comprising:

[0056] Data acquisition module 100 acquires target radar images and multispectral remote sensing data of the target area;

[0057] Grayscale processing module 200 determines grayscale thresholds based on the grayscale values ​​of the target radar image;

[0058] The emergent vegetation identification module 300 reclassifies the target radar image based on grayscale thresholds to obtain the emergent vegetation area and the area to be distinguished.

[0059] The Normalized Difference Vegetation Index (NDVI) calculation module 400 calculates the NDVI of each pixel in the target area image based on multispectral remote sensing data.

[0060] The floating leaf vegetation identification module 500 divides the water area and the mixed vegetation area based on the normalized vegetation index, and obtains the overlapping area between the area to be identified and the mixed vegetation area as the floating leaf vegetation area.

[0061] While embodiments of the present invention have been described in detail above, it will be apparent to those skilled in the art that various modifications and variations can be made to these embodiments. However, it should be understood that such modifications and variations fall within the scope and spirit of the invention as set forth in the claims. Furthermore, the invention described herein may have other embodiments and can be implemented or carried out in various ways.

Claims

1. An automatic identification method for floating-leaved vegetation and emergent vegetation, characterized in that, Includes the following steps: Acquire target radar images of the target area, define a grayscale threshold based on the grayscale values ​​of the target radar images, and reclassify the target radar images based on the grayscale thresholds to obtain emergent vegetation areas and areas to be distinguished; acquire multispectral remote sensing data of the target area, calculate the normalized vegetation index (NDI) of each pixel in the target area image based on the multispectral remote sensing data, and divide the water body area and mixed vegetation area based on the NDI; obtain the overlapping area between the area to be distinguished and the mixed vegetation area as the floating leaf vegetation area; Specifically, when determining the grayscale threshold based on the grayscale value of the target radar image, the grayscale value of each pixel in the target radar image is obtained, and a grayscale histogram is constructed based on the grayscale value. The valley point of the two cross peaks in the grayscale histogram is selected as the grayscale threshold. When calculating the normalized vegetation index for each pixel in the target region based on the multispectral remote sensing data, the following formula is used: ； in: For the first Normalized vegetation index of each pixel; For the first Near-infrared reflectance of each pixel; For the first The infrared reflectance of each pixel.

2. The automatic identification method according to claim 1, characterized in that, The grayscale value of each pixel in the emergent vegetation zone is greater than or equal to the grayscale threshold, and the grayscale value of each pixel in the area to be distinguished is less than the grayscale threshold.

3. The automatic identification method according to claim 1, characterized in that, After acquiring the target radar image, the target radar image is preprocessed, and grayscale thresholds are defined based on the preprocessed target radar image.

4. The automatic identification method according to claim 3, characterized in that, The preprocessing includes radiometric correction, speckle noise suppression, image registration, geometric correction, and linear scale conversion.

5. An automatic identification system for floating-leaved vegetation and emergent vegetation, used to implement the method described in any one of claims 1 to 4, characterized in that, include: The data acquisition module acquires radar images and multispectral remote sensing data of the target area; The grayscale processing module determines a grayscale threshold based on the grayscale values ​​of the target radar image; The emergent vegetation identification module reclassifies the target radar image based on a grayscale threshold to obtain the emergent vegetation area and the area to be distinguished. The normalized vegetation index (NVI) calculation module calculates the NVI of each pixel in the target area image based on the multispectral remote sensing data. The floating leaf vegetation identification module divides the water area and the vegetation mixed area based on the normalized vegetation index, and obtains the overlapping area between the area to be identified and the vegetation mixed area as the floating leaf vegetation area.

Images