A remote sensing identification method and device for different growth periods of cladophora

Abstract

The application provides a remote sensing identification method and device for different growth period of Cladophora. After obtaining the Cladophora region in the remote sensing water area image under the growth environment of floating Cladophora, the floating Cladophora index of each pixel in the floating Cladophora region can be obtained based on the measured spectrum data of the growth environment of floating Cladophora, so as to accurately identify the floating Cladophora region in the floating Cladophora region and / or the floating growth period Cladophora region based on the comparison result of the floating Cladophora index and the floating classification threshold. Through the quantitative identification of the floating Cladophora in different growth periods, the spatial distribution of the floating Cladophora in different growth periods is accurately determined, and the remote sensing automation and business monitoring of the floating Cladophora in different growth periods in the lake are promoted.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer communication, in particular to a remote sensing identification method and device for different growth period of Cladophora. BACKGROUND

[0002] With the aggravation of water eutrophication, large filamentous algae proliferate in a large amount in the world, which causes quite serious influence on seawater aquaculture waters, lakes and ponds.

[0003] Among them, Cladophora is a common large filamentous algae, which grows in environments such as intertidal zone, stream and shore of lake and reservoir, and can grow in a large scale and form algal mat floating on the water surface in the suitable season from spring to early summer. Due to the short growth cycle, Cladophora quickly enters the growth decline stage in summer with high temperature, releases harmful substances, and emits unpleasant and pungent odor, and its biomass expands rapidly, which brings serious influence on the local ecological environment, aquaculture biodiversity and tourism of coastal cities. SUMMARY

[0004] To achieve the above object, the embodiments of the present application provide the following technical scheme.

[0005] On the one hand, the present application provides a remote sensing identification method for different growth period of Cladophora, which comprises:

[0006] obtaining a floating Cladophora region in a remote sensing water area image under a floating Cladophora growth environment;

[0007] obtaining a floating Cladophora index of each pixel in the floating Cladophora region based on measured spectral data of the floating Cladophora growth environment;

[0008] identifying a floating decline period Cladophora region and / or a floating growth period Cladophora region in the floating Cladophora region based on a comparison result of the floating Cladophora index and a floating classification threshold.

[0009] Optionally, the obtaining of the floating Cladophora index of each pixel in the floating Cladophora region based on the measured spectral data of the floating Cladophora growth environment comprises:

[0010] performing band equivalent processing on the measured spectral data of the floating Cladophora growth environment to obtain remote sensing emissivity and center wavelength of each satellite band of the floating Cladophora region;

[0011] inputting the remote sensing emissivity and center wavelength of each satellite band of the floating Cladophora region into a floating Cladophora feature extraction model to obtain the floating Cladophora index of each pixel in the floating Cladophora region.

[0012] Optionally, the remote sensing emission rate and the center wavelength of each of the plurality of satellite bands include: a first remote sensing reflectivity and a first center wavelength of a first band, a second remote sensing reflectivity and a second center wavelength of a second band, and a third remote sensing reflectivity and a third center wavelength of a third band in the remote sensing water area image; wherein the first band is a red light band, the second band is a band between the red light band and the near red band, and the third band is a near infrared band.

[0013] The inputting of the remote sensing emission rate and the center wavelength of each of the plurality of satellite bands into the floating cladophora characteristic extraction model to obtain the floating cladophora index of each pixel in the floating cladophora region comprises:

[0014] A first wavelength variable of the second center wavelength and the first center wavelength, and a second wavelength variable of the third center wavelength and the first center wavelength are obtained;

[0015] The first wavelength variable and the second wavelength variable are subjected to ratio operation to obtain a wavelength change coefficient;

[0016] A first reflectivity variable of the third remote sensing reflectivity and the first remote sensing reflectivity is obtained, and the first reflectivity variable and the wavelength change coefficient are subjected to product operation to obtain a second reflectivity variable;

[0017] The second remote sensing reflectivity, the first remote sensing reflectivity, and the second reflectivity variable are subjected to difference operation to obtain the floating cladophora index of the corresponding pixel in the floating cladophora region.

[0018] Optionally, the identifying of the floating dying cladophora region and / or the floating growing cladophora region in the floating cladophora region based on the comparison result of the floating cladophora index and the floating classification threshold value comprises:

[0019] A floating classification threshold value of the floating cladophora for different growth periods is obtained;

[0020] The floating cladophora index of each pixel in the floating cladophora region is compared with the floating classification threshold value respectively;

[0021] The region where the pixel with the floating cladophora index less than the floating classification threshold value is located is identified as the floating dying cladophora region, and the region where the pixel with the floating cladophora index greater than the floating classification threshold value is located is identified as the floating growing cladophora region.

[0022] Optionally, the obtaining of the floating classification threshold value of the floating cladophora for different growth periods comprises:

[0023] A remote sensing area image covering the floating cladophora is obtained;

[0024] based on the classification algorithm, classifying and identifying the remote sensing area image to obtain a plurality of groups of ground objects having a floating Cladophora glomerata index and a pixel value; the plurality of groups of ground objects include water bodies and Cladophora glomerata in different growth periods;

[0025] determining a non-overlapping range value of the pixel value of the plurality of groups of ground objects corresponding to the floating Cladophora glomerata index;

[0026] determining the maximum pixel value and the minimum pixel value of the plurality of groups of ground objects corresponding to the floating Cladophora glomerata index from the non-overlapping range value of the pixel value of the plurality of groups of ground objects;

[0027] performing mean operation on the maximum pixel value and the minimum pixel value of the plurality of groups of ground objects to obtain a floating classification threshold value of the floating Cladophora glomerata index.

[0028] Optionally, the obtaining of the floating Cladophora glomerata region in the remote sensing water area image under the floating Cladophora glomerata growth environment comprises:

[0029] obtaining a remote sensing water area image under a floating Cladophora glomerata growth environment;

[0030] based on the measured spectral data of the floating Cladophora glomerata growth environment, obtaining a chlorophyll a spectral index and at least one vegetation index of each pixel in the remote sensing water area image;

[0031] based on the comparison result of the chlorophyll a spectral index and the first classification threshold value, identifying the Cladophora glomerata region in different growth periods in the remote sensing water area image;

[0032] based on the comparison result of the vegetation index and the second classification threshold value, identifying the attached early Cladophora glomerata region and the floating Cladophora glomerata region in the Cladophora glomerata region in different growth periods;

[0033] The method further comprises:

[0034] based on the different growth period Cladophora glomerata region identified from the remote sensing water area image, determining the coverage area and / or coverage geographic location of the corresponding growth period Cladophora glomerata under the floating Cladophora glomerata growth environment;

[0035] outputting the determined coverage area and / or coverage geographic location of any growth period Cladophora glomerata.

[0036] In another aspect, the present application also provides a remote sensing identification device for Cladophora glomerata in different growth periods, the device comprising:

[0037] a floating Cladophora glomerata region obtaining module for obtaining a floating Cladophora glomerata region in a remote sensing water area image under a floating Cladophora glomerata growth environment;

[0038] The floating Cladophora index obtaining module is configured to obtain the floating Cladophora index of each pixel in the floating Cladophora region based on the measured spectral data of the floating Cladophora growth environment.

[0039] The region identifying module is configured to identify the floating dying Cladophora region and / or the floating growing Cladophora region in the floating Cladophora region based on the comparison result of the floating Cladophora index and the floating classification threshold.

[0040] In another aspect, the present application further provides a computer readable storage medium, which has computer instructions stored thereon, and the computer instructions are loaded and executed by a processor to implement the remote sensing identification method for Cladophora in different growth periods.

[0041] In another aspect, the present application further provides a computer device, which comprises:

[0042] a communication interface;

[0043] a memory configured to store a program for implementing the remote sensing identification method for Cladophora in different growth periods;

[0044] a processor configured to load and execute the program stored in the memory to implement the remote sensing identification method for Cladophora in different growth periods.

[0045] In another aspect, the present application further provides a remote sensing identification system for Cladophora in different growth periods, which comprises:

[0046] a remote sensing device configured to acquire an optical remote sensing image under the Cladophora growth environment to determine a remote sensing water area image of the floating Cladophora growth environment;

[0047] a spectral detection device configured to perform spectral data detection on the floating Cladophora growth environment to obtain measured spectral data;

[0048] a computer device as described above, which is in communication connection with the remote sensing device and the spectral detection device.

[0049] Based on the above technical scheme, the application provides a remote sensing identification method and device for different growth period Cladophora. The remote sensing water area image covering the different growth period Cladophora area and the water area is obtained under the floating Cladophora growth environment. After obtaining the floating Cladophora area in the remote sensing water area image, the floating Cladophora index of each pixel in the floating Cladophora area can be obtained based on the measured spectrum data of the floating Cladophora growth environment. Therefore, the floating dying period Cladophora area and / or the floating growth period Cladophora area in the floating Cladophora area can be accurately identified based on the comparison result of the floating Cladophora index and the floating classification threshold. Through the quantitative identification of the different growth period floating Cladophora, the spatial distribution of the different growth period floating Cladophora can be accurately determined, and the remote sensing automation and business monitoring of the different growth period floating Cladophora in the lake are promoted. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the provided drawings.

[0051] Figure 1a The measured reflectance spectrum curve of the early attached Cladophora;

[0052] Figure 1b The measured reflectance spectrum curve of the floating growth period Cladophora;

[0053] Figure 1c The measured reflectance spectrum curve of the floating dying period Cladophora;

[0054] Figure 1d The measured reflectance spectrum curve of the water body of A lake;

[0055] Figure 2 The flowchart of an optional example of the remote sensing identification method for different growth period Cladophora proposed in the present application;

[0056] Figure 3 The flowchart of another optional example of the remote sensing identification method for different growth period Cladophora proposed in the present application;

[0057] Figure 4a The measured reflectance spectrum curve of different growth period Cladophora and water body in the remote sensing identification method for different growth period Cladophora proposed in the present application;

[0058] Figure 4b The measured reflectance spectrum curve of different growth period Cladophora in the remote sensing identification method for different growth period Cladophora proposed in the present application;

[0059] Figure 4c The measured spectrum recognition index curve of floating Cladophora in the remote sensing recognition method for Cladophora proposed in the present application;

[0060] Figure 5 The flowchart of another optional example of the remote sensing recognition method for Cladophora proposed in the present application;

[0061] Figure 6 The flowchart of another optional example of the remote sensing recognition method for Cladophora proposed in the present application;

[0062] Figure 7a The box plot of each group of ground objects based on CSI in the remote sensing recognition method for Cladophora proposed in the present application;

[0063] Figure 7b The box plot of each group of ground objects based on NDVI in the remote sensing recognition method for Cladophora proposed in the present application;

[0064] Figure 7c The box plot of each group of ground objects based on FCI in the remote sensing recognition method for Cladophora proposed in the present application;

[0065] Figure 8 The flowchart of another optional example of the remote sensing recognition method for Cladophora proposed in the present application;

[0066] Figure 9a The reflected spectrum curves of different growth periods of Cladophora and water bodies based on Sentinel-2 equivalence shown in the present application;

[0067] Figure 9b The reflected spectrum curves on the optical remote sensing image of different growth periods of Cladophora and water bodies shown in the present application;

[0068] Figure 9c The measured reflected spectrum curves of different growth periods of Cladophora and water bodies shown in the present application;

[0069] Figure 10 The structural schematic diagram of an optional example of the remote sensing recognition device for Cladophora proposed in the present application;

[0070] Figure 11 The hardware structural schematic diagram of the computer device suitable for the remote sensing recognition method for Cladophora proposed in the present application. DETAILED DESCRIPTION

[0071] Because the damage types of Cladophora are different in different growth periods, through the analysis of the whole growth process of Cladophora, it can be known that the algal body in the early stage is green and attached to the substrate at the bottom of the pool (referred to as the attached early stage); in the growth period, the algal body is connected into a network and floats on the water surface and accumulates on the shore, and the color will gradually change to yellow-green (referred to as the floating growth period); in the decline period, the color of Cladophora will fade to gray-white like old cotton wool and float on the water surface with a foul and pungent odor (referred to as the floating decline period). It can be seen that with the change of time, Cladophora in different growth periods usually presents different morphological characteristics, and the target area where Cladophora in any growth period is located can be identified by monitoring the morphological characteristic changes of Cladophora, that is, the spatial distribution of Cladophora in different growth periods can be accurately identified, thereby promoting the remote sensing automation and business monitoring of Cladophora in different growth periods in lakes.

[0072] To this end, the biomass estimation method of harmful algae in remote sensing images based on the proposed underwater vegetation mapping algorithm (SAVMA) is to first correct the radiation value of the shallow water area by the radiation value of the deep water area, classify the reflectivity values of the blue, green and red bands under the condition that the water depth is unchanged, then generate different coverage density bottom algae type indexes by using the two-by-two combination of bands, and complete the biomass estimation and draw the spatial distribution of different types by threshold segmentation to classify the lake bottom into sand, dense algae and non-dense algae. However, due to the mixed pixels caused by the resolution of remote sensing images and atmospheric correction, the accuracy of SAVMA for algae estimation is not high, and this processing method can only estimate the biomass of algae with different density, but cannot estimate the biomass of algae in different growth periods, and therefore this method is not suitable for the remote sensing identification application scenario of Cladophora in different growth periods.

[0073] In addition, a pixel-based supervised random tree classifier is also proposed to quantitatively identify the benthic vegetation of a certain lake from the unmanned aerial vehicle image, which first classifies the image into several categories through supervised classification, then determines six categories of algae, aquatic plants, water, land, shadow and flare according to visual interpretation, classifies each image using the random tree classifier method according to the categories divided in the region, and finally completes the spatial distribution and quantity change of the six categories in the region. Experiments show that the overall accuracy of classifying and quantifying benthic algae or macrophytes in relatively shallow water is 82% using this method. However, this method is only suitable for classifying and quantitatively identifying benthic vegetation, and is not suitable for other different growth period aquatic vegetation, nor is it suitable for the remote sensing identification application scenario of Cladophora in different growth periods.

[0074] In order to improve the above problems, in combination with the analysis of Cladophora in different growth periods, the reflection spectrum of Cladophora in the early attachment stage, the floating growth stage, the floating decline stage and the water body of Lake A is measured, and the typical spectrum of Cladophora in different growth periods is extracted as the representative reflection spectrum (i.e. the relationship curve between different wavelengths and reflectivity), such as Figure 1a the reflection spectrum curve of Cladophora in the early attachment stage, Figure 1b the reflection spectrum curve of Cladophora in the floating growth stage, Figure 1c the reflection spectrum curve of Cladophora in the floating decline stage, Figure 1d the reflection spectrum curve of the water body of Lake A, by comparing the reflection spectrum of the water body and Cladophora in different growth periods (such as the early attachment stage, the floating growth stage and the floating decline stage), it can be found that there are differences in the spectral recognition index between the water body and Cladophora in different growth periods in Lake A, and between Cladophora in different growth periods. Therefore, the target area of Cladophora in different growth periods such as the early attachment stage and the floating stage can be accurately identified from the remote sensing water area image covering the water body area and Cladophora in different growth periods.

[0075] In order to further accurately identify the spatial distribution of Cladophora in the floating growth stage and the floating decline stage, the present application proposes to obtain the floating Cladophora index, a spectral recognition index, to realize further refined classification and regional identification of floating Cladophora. Then, the geographical position, coverage area, etc. of the required Cladophora in a certain growth period can be located, and the salvage work can be reasonably arranged accordingly, without the need to spend a lot of manpower and material resources to find, improve the processing efficiency, save the labor cost, and better meet the processing requirements of Cladophora in different growth periods in different scenarios.

[0076] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. It can be understood that the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0077] Referring to Figure 2 , the flowchart of an optional example of the remote sensing identification method for Cladophora in different growth periods proposed in the present application, which can be applied to a computer device, which can be a server or a terminal with certain data processing capability, or can be realized by cooperation of a terminal and a server, and the present application does not limit the application scenario of the method. As Figure 2 shown, the remote sensing identification method for Cladophora in different growth periods proposed in the present embodiment can include but is not limited to:

[0078] Step S21, obtaining the floating Cladophora region in the remote sensing water area image under the growth environment of the floating Cladophora;

[0079] In the scenario of identifying Cladophora in different growth periods, the region where the Cladophora grows can be preliminarily selected, and a matching, little cloudy optical remote sensing image of the region is collected by a remote sensing device such as a remote sensing satellite. After preprocessing, the remote sensing water area image covering the water area and the Cladophora region in different growth periods can be extracted by visual interpretation, that is, the non-land region of interest is extracted. The process of obtaining the remote sensing water area image is not described in detail.

[0080] According to the analysis of the technical solution of the present application above, the accuracy of the spectral recognition index of each pixel in the remote sensing water area image directly determines the recognition accuracy of the target region in the remote sensing water area image. If the feature extraction is directly performed on the remote sensing water area image, the spectral feature obtained is easily affected by the accuracy of the remote sensing water area image itself. In order to avoid this situation, the present application embodiment proposes to use a spectral detection device (such as a spectrometer) to detect the Cladophora growth environment to obtain the measured spectral data. Compared with the spectral data extracted from the remote sensing water area image, the accuracy and reliability of the spectral data are improved. The detection process of the measured spectral data is not described in detail.

[0081] Then, based on the measured spectral data of the Cladophora growth environment in different growth periods, the spectral recognition index of each pixel in the remote sensing water area image can be obtained, such as the Chlorophyll spectral index (CSI), at least one vegetation index (such as the Normalized Difference Vegetation Index (NDVI)), the Enhanced Vegetation Index (EVI), the Adjusted Floating Algae Index (AFAI), the Ratio Vegetation Index (RVI), the Difference Vegetation Index (DVI), the Floating Algae Index (FAI), and other vegetation indices, or the Virtual-Baseline Floating Macroalgae Height (VB-FAH) and the like. The calculation method of each spectral recognition index is not limited in the present application, and can be determined as appropriate.

[0082] Optionally, in combination with the related description of the technical solutions of the present application, the present application will classify and identify each pixel in the remote sensing water area image based on the spectral characteristic differences between the water body and the different growth periods of Cladophora. In order to accurately obtain the spectral identification index of each pixel and eliminate the differences in the satellite band width of the satellite image, the reflectivity actually measured by the spectral detection device can be converted into the equivalent reflectivity of the satellite band, that is, the band equivalent processing is performed on the actually measured spectral data. The obtained equivalent reflectivity is referred to as the remote sensing reflectivity. According to the needs, the center wavelength corresponding to the satellite band can also be determined, and one or more spectral identification indexes of the corresponding pixel in the remote sensing water area image are further calculated according to the center wavelength. The calculation process is not described in detail in this embodiment.

[0083] Based on this, the computer device can call the first classification threshold for distinguishing the water body area and the Cladophora area, and the second classification threshold for distinguishing the early growth period Cladophora area and the floating Cladophora area. In this way, the chlorophyll a spectral index of each pixel obtained can be compared with the first classification threshold, and the different growth period Cladophora areas are identified from the remote sensing water area image. Then, any one of the above-mentioned vegetation indexes of each pixel is compared with the corresponding second classification threshold, and the floating Cladophora area is identified from the Cladophora area. The implementation process of how to obtain the floating Cladophora area from the remote sensing water area image by using the CSI and any one of the vegetation indexes of the pixel is not described in detail in the present application.

[0084] In step S22, the floating Cladophora index of each pixel in the floating Cladophora area is obtained based on the actually measured spectral data of the floating Cladophora growth environment.

[0085] In combination with the spectral data comparison and analysis of the floating growth period Cladophora, the floating decline period Cladophora and the early growth period Cladophora, the spectral characteristics of the floating Cladophora are closer to the spectral characteristics of the vegetation than those of the early growth period Cladophora. The most obvious feature of the floating Cladophora and the early growth period Cladophora is the difference in the red light and near-infrared band. Therefore, the present application can calculate the floating Cladophora index for identifying the different growth periods of the floating Cladophora by using the remote sensing reflectivity, the center wavelength and other parameters of the first band (such as the red light band near 675 nm), the second band (such as the band between the red light band of 675 nm to 800 nm and the near-infrared band) and the third band (such as the near-infrared band of 700 nm to 850 nm) in the remote sensing water area image. The calculation method is not limited in the present application.

[0086] In step S23, the floating decline period Cladophora area and / or the floating growth period Cladophora area in the floating Cladophora area are identified based on the difference between the floating Cladophora index and the floating classification threshold.

[0087] The floating classification threshold can be used to distinguish the floating decline period Cladophora region and the floating growth period Cladophora region, and can be a critical value of the floating Cladophora index difference of the pixels in the two regions. In actual application, the floating classification threshold index can be reasonably selected according to the floating Cladophora index difference between the two objects to be distinguished. The present application does not limit the acquisition method and the value of the floating classification threshold, which can be determined as appropriate.

[0088] Based on this, after accurately determining the floating Cladophora index of each pixel in the floating Cladophora region in the remote sensing water area image according to the method described above, the floating classification threshold corresponding to the floating Cladophora index can be obtained. According to the comparison result between the two, the floating Cladophora region in the remote sensing water area image is further segmented and identified, and the target regions such as the floating growth period Cladophora region and the floating decline period Cladophora region are accurately and refined, so as to subsequently calculate the geographic area of the target region where the specified growth period Cladophora is located, positioning, etc., and better meet different remote sensing business processing needs.

[0089] As can be seen, the embodiments of the present application are based on the measured spectral data in the floating Cladophora generation environment. By analyzing the difference of the floating Cladophora index of the floating Cladophora in different growth periods, the floating Cladophora region in the remote sensing water area image in the floating Cladophora growth environment, which is in the floating growth period and / or the floating decline period, is accurately identified. Accordingly, the quantitative identification of the floating Cladophora in different growth periods is realized, the remote sensing automation and business monitoring of the floating Cladophora in different growth periods in the lake are efficiently and accurately realized, and the Cladophora salvage task can also be quickly and accurately deployed, etc. Various problems caused by manual observation of the growth and spatial distribution of Cladophora are solved.

[0090] Referring to Figure 3 The present application provides a flowchart of another optional example of the remote sensing identification method for Cladophora in different growth periods. The embodiments can describe an optional detailed implementation method of the remote sensing identification method for Cladophora in different growth periods described in the above embodiments, but are not limited to the detailed implementation method described in the embodiments, such as Figure 3 As shown in the figure, the method can include:

[0091] In step S31, the remote sensing water area image and the measured spectral data in the floating Cladophora growth environment are obtained.

[0092] In step S32, the measured spectral data and the remote sensing water area image are equivalently processed to obtain the chlorophyll a spectral index, the normalized vegetation index and the floating Cladophora index for each pixel in the remote sensing water area image.

[0093] The implementation process of steps S31 and S32 can be referred to the description in the corresponding part of the context, and the embodiments will not be described in detail here.

[0094] In the embodiments of the present application, the above-obtained spectral recognition indexes of each pixel, including the Cladophora glomerata index, the chlorophyll-a spectral index, and the normalized vegetation index (which can be replaced by other vegetation indexes or the remote sensing recognition index of plankton algae based on virtual baseline height), are taken as examples to illustrate the classification and recognition process of the remote sensing water area image in the Cladophora glomerata growth environment. The subsequent processing process of other vegetation indexes is similar, and the embodiments of the present application will not be described one by one.

[0095] The chlorophyll-a spectral index can be calculated by the remote sensing reflectivity of the first band and the fourth band (such as the band near 700 nm) in the remote sensing water area image; and the normalized vegetation index can be calculated by the remote sensing reflectivity of the first band and the third band in the remote sensing water area image. The calculation method of the spectral recognition indexes is not limited in the present application.

[0096] Optionally, the RVI and DVI that can replace the NDVI can be calculated by the remote sensing reflectivity of the first band and the third band; the FAI can be calculated by the remote sensing reflectivity and the center wavelength of the first band, the third band, and the fifth band (such as the wavelength near 1600 nm); and the VB-FAH can be calculated by the remote sensing reflectivity and the center wavelength of the first band, the third band, and the sixth band (such as the green band near 550 nm). The calculation process will not be described in detail in the embodiments.

[0097] It should be noted that the satellite band values involved in the calculation of the above-mentioned spectral recognition indexes, and the remote sensing reflectivity (i.e. equivalent reflectivity), center wavelength, and other parameter values of each satellite band are not limited in the present application. In the calculation process of each spectral recognition index, the bandmath tool in ENVI (The Environment for Visualizing Images, remote sensing image processing platform) can be called to calculate the above-mentioned indexes, and the implementation process will not be described in detail in the embodiments.

[0098] In step S33, the first classification threshold corresponding to the chlorophyll-a spectral index, the second classification threshold corresponding to the normalized vegetation index, and the floating classification threshold corresponding to the Cladophora glomerata index are obtained.

[0099] For different land cover (i.e., objects) in remotely sensed water images, a classification threshold can be set for each spectral recognition index (such as CSI, NDVI, and FCI mentioned above). This allows for subsequent identification of different land cover (e.g., filamentous algae at different growth stages) within the remotely sensed water image based on one or more classification thresholds and the corresponding spectral recognition indices. It is evident that the size of the classification threshold affects the accuracy of subsequent filamentous algae region identification; therefore, classification thresholds for different spectral recognition indices can be reasonably selected according to certain rules.

[0100] In some embodiments, the first classification threshold H can be used to distinguish between aquatic areas and filamentous algae areas, the second classification threshold I can be used to distinguish between early-stage filamentous algae areas and floating filamentous algae areas, and the floating classification threshold J can be used to distinguish between floating filamentous algae in their growth stage and floating filamentous algae in their decline stage. The first classification threshold determined according to preset rules can be selected from (0 to 0.2), the second classification threshold can also be selected from (0 to 0.2), and the floating classification threshold can also be selected from (-0.1 to 0.1). This application does not limit the value of each classification threshold.

[0101] Step S34: Compare the chlorophyll a spectral index of each pixel in the remotely sensed water area image with the first classification threshold.

[0102] Step S35: Identify the pixels in the remotely sensed water area image where the chlorophyll a spectral index is less than the first classification threshold as water areas;

[0103] Step S36: Identify the pixels in the remotely sensed water image where the chlorophyll a spectral index is greater than the first classification threshold as Cladophora regions.

[0104] Using the example of different growth stages of Cladophora observed in Lake A above, we will continue to illustrate this point. Figure 4a The measured reflectance spectra of Cladophora at different growth stages and the water body are shown. The spectral characteristics of the water body in Lake A (i.e., the measured spectral data) gradually approach 0 in the red light band (around 600 nm). The spectral characteristics of Cladophora at different growth stages show a reflectance peak in the green light band (around 550 nm), a reflectance valley in the red light band (around 675 nm), and a steep slope effect similar to the spectral characteristics of vegetation in the red to near-red light band (675 nm to 710 nm). The most obvious spectral characteristic that distinguishes Cladophora at different growth stages from the water body in Lake A is the steep slope effect in the red to near-red light band. Therefore, based on the CSI chlorophyll a spectral index established from the first band (around 675 nm) to the fourth band (around 700 nm), and by selecting a reasonable threshold range (i.e., the first classification threshold), Cladophora at different growth stages can be obtained without the influence of the water body in Lake A.

[0105] Therefore, to distinguish between water bodies and filamentous algae regions in remotely sensed water images, the chlorophyll a spectral index of each pixel in the remotely sensed water image can be obtained based on measured spectral data of the filamentous algae growth environment. This index is then compared with a first classification threshold. If the chlorophyll a spectral index of a pixel is less than the first classification threshold, the pixel can be considered to be located in a water body region; if the chlorophyll a spectral index of a pixel is greater than the first classification threshold, the pixel can be considered to be located in a filamentous algae region. Thus, this application can accurately identify water bodies and filamentous algae regions in remotely sensed water images based on measured chlorophyll a spectral index.

[0106] Optionally, in practical applications of this application, the Region of Interest (ROI) tool on the ENVI platform can be used to perform threshold segmentation on remotely sensed water images based on image segmentation algorithms, identifying which pixels belong to water areas and which pixels belong to filamentous algae areas. This application does not elaborate on the implementation method of identifying filamentous algae areas in remotely sensed water images based on image segmentation algorithms.

[0107] Step S37: Compare the normalized vegetation index of the pixels located in the Cladophora region with the second classification threshold.

[0108] Step S38: Identify the regions where the normalized vegetation index is less than the second classification threshold in the Cladophora region as early Cladophora attachment regions.

[0109] Step S39: Identify the regions where the normalized vegetation index is greater than the second classification threshold in the Cladophora region as floating Cladophora regions.

[0110] To further identify the spatial distribution of Cladophora at different growth stages within the Cladophora region, the region can be further subdivided based on the Normalized Difference Vegetation Index (NDVI) or its substitute index. (Refer to...) Figure 4b The measured reflectance spectra of Cladophora at different growth stages shown indicate that, compared to Cladophora in its early attached stage, the spectral characteristics of floating Cladophora are closer to those of vegetation. Specifically, there is a reflectance peak in the green light band (around 550 nm), a reflectance trough in the red light band (around 675 nm), and a high reflectance plateau in the near-infrared band (700 nm–850 nm). The most obvious difference between floating and early attached Cladophora lies in the differences in the red and near-infrared bands. Therefore, this application can effectively distinguish between floating and early attached Cladophora based on vegetation indices constructed using the first (around 675 nm) and third (700 nm–850 nm) bands, allowing for subsequent removal of floating Cladophora affected by early attached Cladophora.

[0111] Based on this, to further identify early-attached and floating filamentous algae regions within the preliminarily determined filamentous algae regions in the remotely sensed water images, the normalized vegetation index (NDI) of each pixel within the filamentous algae region (or alternatively, other vegetation indices listed above, or the phytoplankton remote sensing identification index based on virtual baseline height, etc.) can be compared with a second classification threshold. If the NDI of a pixel is less than the second classification threshold, the pixel can be identified as belonging to an early-attached filamentous algae region; conversely, if the NDI is greater than the second classification threshold, the pixel can be identified as belonging to a floating filamentous algae region. In application scenarios requiring the retrieval of floating filamentous algae, the obtained segmentation and identification results can be used to locate the geographical location and coverage area of ​​the floating filamentous algae in the water, thereby enabling the development of a reasonable retrieval plan.

[0112] The process of threshold segmentation of the early-attached filamentous algae region and the floating filamentous algae region based on the image segmentation algorithm in the above-mentioned filamentous algae region is similar to the process of identifying filamentous algae regions from remotely sensed water images, and will not be described in detail here.

[0113] Step S310: Compare the floating filamentous algae index of the pixels located in the floating filamentous algae region with the floating classification threshold.

[0114] Step S311: Identify the regions where the floating filamentous algae index is less than the floating classification threshold in the floating filamentous algae region as floating filamentous algae in the dying period.

[0115] Step S312: Identify the regions where the floating filamentous algae index is greater than the floating classification threshold in the floating filamentous algae region as floating filamentous algae growing period regions.

[0116] In practical applications, if it is necessary to further segment and identify the death and growth phases of floating filamentous algae, it is possible to perform the following steps: Figure 4c The measured spectral curves of the floating bristle algae shown were analyzed, from... Figure 4c It can be seen that, compared with the floating nematode phase, the floating growth phase of nematode has a higher overall remote sensing reflectance value in the near-infrared band (710nm~850nm). Although there is a reflection valley in the near-infrared band (around 783nm) and (around 833nm), and the reflection is smaller near 783nm than near 833nm, the overall reflectance value is higher. Therefore, based on the reflectance information obtained by linear interpolation in the second band (around 780nm) using the first band (around 675nm) and the third band (700nm~850nm), it is possible to distinguish between the floating nematode phase and the floating growth phase of nematode.

[0117] Based on the above analysis, the embodiments of the present application can obtain the Cladophora glomerata index of each pixel located in the Cladophora glomerata region based on the first wave band, the second wave band and the third wave band, compare it with the configured Cladophora glomerata classification threshold value, if the Cladophora glomerata index of a certain pixel located in the Cladophora glomerata region is less than the Cladophora glomerata classification threshold value, the pixel can be located in the Cladophora glomerata region in the Cladophora glomerata decline period; otherwise, if the Cladophora glomerata index of a certain pixel located in the Cladophora glomerata region is greater than the Cladophora glomerata classification threshold value, the pixel can be located in the Cladophora glomerata region in the Cladophora glomerata growth period. By comparing and analyzing the Cladophora glomerata index of each pixel located in the Cladophora glomerata region, the Cladophora glomerata region in the Cladophora glomerata decline period and the Cladophora glomerata region in the Cladophora glomerata growth period in the Cladophora glomerata region can be accurately identified in a finer granularity.

[0118] After the above method is used to analyze the remote sensing water area image covering the Cladophora glomerata in different growth periods and the water body, the spatial distribution of the Cladophora glomerata in different growth periods can be accurately identified, the technical problem that the current remote sensing identification method cannot distinguish the Cladophora glomerata in different growth periods in a lake is solved, and the remote sensing automation and business monitoring of the Cladophora glomerata in different growth periods in a lake can be achieved.

[0119] It should be noted that the process of obtaining the spectral identification index of each pixel in the remote sensing water area image and the identification process of the region to which the pixel belongs include but are not limited to the above-described acquisition method (for example, after all types of spectral identification indexes of each pixel in the remote sensing water area image are obtained, each region is identified according to the spectral identification indexes) and the execution order thereof. As described above in the comparison process, for each pixel in the remote sensing water area image, the spectral identification indexes of the pixel are not compared with the corresponding classification threshold value every time. Therefore, in some other embodiments, the chlorophyll a spectral index of each pixel in the remote sensing water area image can be obtained first, the Cladophora glomerata region is determined after the chlorophyll a spectral index is compared with the first classification threshold value, the vegetation index of each pixel located in the Cladophora glomerata region is obtained, the Cladophora glomerata region is determined after the vegetation index is compared with the second classification threshold value, the Cladophora glomerata index of each pixel located in the Cladophora glomerata region is obtained, and the Cladophora glomerata region in the Cladophora glomerata decline period / growth period is identified after the Cladophora glomerata index is compared with the Cladophora glomerata classification threshold value. It can be seen that the present application can selectively obtain the required spectral identification index of each pixel in the remote sensing water area image according to the region identification requirement, and it is not necessary to obtain all types of spectral identification indexes of each pixel, thereby reducing the calculation amount of the spectral identification index.

[0120] Reference Figure 5As shown in FIG. 15, the remote sensing recognition method for different growth periods of Cladophora presented in the present application can include the following steps. Figure 5

[0121] In step S51, a remote sensing water image in a growth environment of Cladophora and measured spectral data obtained by detecting the growth environment of Cladophora by a spectral detection device are acquired.

[0122] In step S52, the measured spectral data is subjected to band equivalence processing to obtain remote sensing emissivity and central wavelengths for different satellite bands in the remote sensing water image.

[0123] According to the description of the corresponding part of the above embodiments, after the band equivalence processing of the measured spectral data, the first remote sensing reflectivity and the first central wavelength for the first band, the second remote sensing reflectivity and the second central wavelength for the second band, the third remote sensing reflectivity and the third central wavelength for the third band, the fourth remote sensing reflectivity for the fourth band, the fifth remote sensing reflectivity and the fifth central wavelength for the fifth band, and the sixth remote sensing reflectivity and the sixth central wavelength for the sixth band in the remote sensing water image can be obtained. For the bands and the corresponding parameter values, refer to the description of the corresponding part above and below.

[0124] In step S53, a first wavelength variable between the second central wavelength and the first central wavelength and a second wavelength variable between the third central wavelength and the first central wavelength are acquired.

[0125] In step S54, the first wavelength variable and the second wavelength variable are subjected to ratio operation to obtain a wavelength change coefficient.

[0126] In step S55, a first reflectivity variable between the third remote sensing reflectivity and the first remote sensing reflectivity is acquired, and the first reflectivity variable and the wavelength change coefficient are subjected to product operation to obtain a second reflectivity variable.

[0127] In step S56, the second remote sensing reflectivity, the first remote sensing reflectivity and the second reflectivity variable are subjected to difference operation to obtain a Cladophora index of a corresponding pixel in the remote sensing water image.

[0128] ​In the process of band equivalent processing of the measured spectral data and obtaining the floating Cladophora sp. index FCI of each pixel in the remote sensing water area image of the same floating Cladophora sp. growth environment, the floating Cladophora sp. index FCI can be calculated according to the method described in the embodiment, but is not limited thereto, and is shown in formula (1) as follows:

[0129] FCI = p (第二波段) - p (第一波段) - (p (第三波段) - p (第一波段) ) x (l (第二波段) - l (第一波段) ) / (l (第三波段) - l (第一波段) ) (1)

[0130] As shown in formula (1), p can represent the remote sensing reflectivity, l can represent the central wavelength, (l (第二波段) - l (第一波段) ) can represent the first wavelength variable, and (l (第三波段) - l (第一波段) ) can represent the second wavelength variable.

[0131] According to the description of the above embodiment, the floating Cladophora sp. index can be used to refine the segmentation of the floating Cladophora sp. region. After obtaining the measured spectral data and performing band equivalent processing, the FCI of each pixel in the remote sensing water area image can be directly obtained. Alternatively, after identifying the floating Cladophora sp. region in the remote sensing water area image according to the method described above, the FCI of each pixel in the floating Cladophora sp. region can be calculated according to formula (1) above.

[0132] Optionally, other spectral identification indexes of the pixels in the remote sensing water area image can be determined according to the method described below, but are not limited thereto. In order to obtain the chlorophyll a spectral index CSI of the pixels in the remote sensing water area image, the first band and the fourth band of the pixels in the remote sensing water area image can be used to calculate the CSI, for example, the first remote sensing reflectivity of the first band and the remote sensing reflectivity of the fourth band can be used to calculate the CSI, and the CSI calculation method is shown in formula (2) as follows:

[0133]

[0134] Optionally, the third remote sensing reflectivity of the third band of the pixels in the remote sensing water area image and the first remote sensing reflectivity described above can be used to construct the normalized difference vegetation index NDVI of the corresponding pixels in the remote sensing water area image, and the calculation method is shown in formula (3) as follows:

[0135]

[0136] Optionally, if the present application uses the ratio vegetation index RVI to replace the normalized difference vegetation index NDVI, the following formula (4) can be used to calculate the ratio vegetation index RVI of each pixel in the remote sensing water area image:

[0137]

[0138] Optionally, the present application can also use formula (5) to calculate the difference vegetation index DVI of each pixel in the remote sensing water area image, and replace the normalized difference vegetation index in the above Cladophora remote sensing identification method with the DVI:

[0139] DVI = p (第三波段) - p (第一波段) (5)

[0140] Optionally, the present application can also use formula (6) to calculate the enhanced vegetation index EVI of each pixel in the remote sensing water area image, and replace the normalized difference vegetation index in the above Cladophora remote sensing identification method with the EVI:

[0141]

[0142] Optionally, the present application can also use formula (7) to calculate the alternative floating algae index AFAI of each pixel in the remote sensing water area image, and replace the normalized difference vegetation index in the above Cladophora remote sensing identification method with the AFAI:

[0143] AFAI = p (第三波段) - p (第一波段) + (p (第五波段) - p (第一波段) ) x 0.5 (7)

[0144] Optionally, the present application can also use formula (8) to calculate the phytoplankton index AFI of each pixel in the remote sensing water area image, and replace the normalized difference vegetation index in the above Cladophora remote sensing identification method with the AFI:

[0145] AFI = p (第三波段) - p' (第一波段)

[0146] p' (第一波段) = p (第一波段) + (p (第五波段) - p (第一波段) ) x (l (第三波段) - l (第一波段) ) x (l (第五波段) - l (第一波段) ) (8)

[0147] Wherein, l can represent the center wavelength, and the present application does not make a detailed description of the method for obtaining the remote sensing reflectivity of each waveband and the center wavelength.

[0148] Optionally, the present application can also calculate the virtual baseline height based phytoplankton remote sensing identification index VB-FAH of each pixel in the remote sensing water area image by formula (9), and replace the normalized vegetation index in the above-mentioned remote sensing identification method for different growth period Cladophora with the VB-FAH:

[0149] VB-FAH = (p (第四波长值) -p (第六波长值) ) + (p (第六波长值) -p (第一波长值) ) x (l (第四波长值) -l (第六波长值) ) / (2l (第四波长值) -l (第一波长值) -l (第六波长值) ) (9)

[0150] Referring to Figure 6 , the flowchart of another optional example of the remote sensing identification method for different growth period Cladophora proposed in the present application, the present embodiment can describe another optional refinement implementation method of the remote sensing identification method for different growth period Cladophora described in the above embodiment, and the present embodiment can describe the acquisition process of different classification thresholds in the above-mentioned remote sensing identification method for different growth period Cladophora, but is not limited to the classification threshold acquisition implementation manner described in the present embodiment, such as Figure 6 , the method can include:

[0151] Step S61, acquiring a remote sensing area image covering floating Cladophora;

[0152] Step S62, based on a classification algorithm, classifying and identifying the remote sensing area image to obtain different floating Cladophora indexes and pixel values possessed by multiple groups of ground objects;

[0153] The present embodiment can construct the threshold of the classification tree, and determine the classification threshold for different spectral identification indexes (such as CSI, NDVI, FCI, etc., and the present embodiment takes the classification threshold of the acquired FCI as an example for description). For this purpose, the present application can acquire a remote sensing area image covering the growth environment of different growth period floating Cladophora, use the classification tree method to classify and identify the remote sensing area image, determine multiple groups of ground objects (fixed objects on the ground surface, such as different growth period Cladophora (which includes floating decline period Cladophora area, floating growth period Cladophora area), water body, etc.) contained in the remote sensing area image, and can also obtain the pixel values with different spectral identification indexes in each group of ground objects in combination with the above-mentioned spectral identification index extraction method. The present application does not limit the implementation method of how to identify different ground objects from the remote sensing area image, and can determine it in combination with the operation principle of the selected image recognition algorithm.

[0154] Step S63, determining the non-overlapping range value of the pixel value of the multi-group ground objects corresponding to the floating Cladophora index;

[0155] Step S64, determining the maximum pixel value and the minimum pixel value of the multi-group ground objects corresponding to the floating Cladophora index from the non-overlapping range value of the pixel value of the multi-group ground objects.

[0156] Step S65, performing mean operation on the maximum pixel value and the minimum pixel value of the multi-group ground objects to obtain the floating classification threshold of the floating Cladophora index.

[0157] According to the method described above, after obtaining the pixel value of each group of ground objects in the remote sensing area image, it can be determined whether there is an overlapping range value between the pixel values of each group of ground objects in the range of different spectral recognition indexes (the floating Cladophora index is taken as an example in the present application, and the classification threshold obtaining process of other types of spectral recognition indexes is similar). Then, the non-overlapping range value between the pixel values of each group of ground objects can be selected to distinguish different growth period Cladophora and water body.

[0158] In order to improve the accuracy of the obtained classification threshold, mean calculation method can be used to determine, therefore, the present embodiment can determine the maximum pixel value and the minimum pixel value of the multi-group ground objects corresponding to the same spectral recognition index (such as the floating Cladophora index).

[0159] For example, based on the obtained remote sensing water area image of A lake, the reflectance spectrum of the attached early Cladophora, the floating growth period Cladophora, the floating decline period Cladophora and the water body of A lake can be obtained. After determining any one of CSI, NDVI, FCI, the box plot of each ground object can be calculated, such as the box plot of each group of ground objects based on CSI as shown in Figure 7a the box plot of each group of ground objects based on NDVI as shown in Figure 7b the box plot of each group of ground objects based on FCI as shown in Figure 7c In each box plot shown in the figure, the solid line in the box represents the median, the bottom of the upper and lower parts represents the fourth and third quartiles, respectively, and the upper and lower edges represent the maximum pixel value and the minimum pixel value of the group of data, respectively. Then, the average of the two can be determined as the classification threshold corresponding to the spectral recognition index, thereby determining the first classification threshold corresponding to CSI, the second classification threshold corresponding to NDVI, and the floating classification threshold corresponding to FCI.

[0160] To further calibrate the determined classification thresholds, the application can use a remote sensing test image to verify the determined classification thresholds. Based on the determined classification thresholds, the different growth period Cladophora regions in the remote sensing test image are identified and segmented according to the method described above. The verification result is compared with the actual region of the different growth period Cladophora in the real environment to determine whether they are consistent. If they are consistent, it is considered that the determined classification thresholds are accurate. Otherwise, the corresponding classification threshold can be adaptively adjusted to improve the accuracy of Cladophora remote sensing identification. The method for obtaining the classification threshold corresponding to other types of spectral recognition indexes is similar, and the application will not be described one by one.

[0161] Referring to Figure 8 The flowchart of another optional example of the Cladophora remote sensing identification method proposed in the application can describe another optional detailed implementation method of the Cladophora remote sensing identification method described in the above embodiment. As shown in the figure, the method can include: Figure 8

[0162] Step S81: obtaining an optical remote sensing image of a region to be identified;

[0163] Step S82: preprocessing the optical remote sensing image to convert the digital quantization value of the optical remote sensing image into a reflectance value;

[0164] In actual application, the optical remote sensing image collected by the remote sensing satellite can be preprocessed in combination with the geographical location and environmental climate of the region to be identified (such as a water area where Cladophora grows, etc.) to improve the clarity of the Cladophora-related feature information in the optical remote sensing image. For example, the Sen2cor software is used to perform atmospheric correction on a certain type of data in the optical remote sensing image to obtain ground reflectance data. For optical remote sensing images of certain special geographical locations, the Sentinel Application Platform (SNAP) can be used to resample and tile the cloud-free image collected on the same day for preprocessing, and the application does not limit the image preprocessing implementation method, which can be determined as appropriate. For the preprocessed optical remote sensing image, the digital quantization DN value can be converted into a reflectance value, and the conversion process will not be described in detail in the embodiment.

[0165] Step S83: identifying a region of interest in the preprocessed optical remote sensing image to obtain a remote sensing water area image covering different growth period Cladophora regions and water body regions;

[0166] ​With the description of the corresponding part of the above embodiment, the present application can use the region of interest tool such as ENVI to identify the region of interest of the processed optical remote sensing image, identify the boundary of the region containing the different growth periods of Cladophora and the water body through visual interpretation, crop the pre-processed remote sensing data, and obtain the remote sensing water area image covering the different growth periods of Cladophora and the water body. The present application does not make a detailed description of the operation principle of visual interpretation.

[0167] Step S84, inputting the remote sensing water area image into a spectral recognition index extraction model to obtain the spectral recognition index of each pixel in the remote sensing water area image;

[0168] The spectral recognition index can at least include the floating Cladophora index and the chlorophyll a spectral index, and the vegetation index (which can include but is not limited to any index in the normalized difference vegetation index, the enhanced vegetation index, the alternative floating algae index, the ratio vegetation index, the difference vegetation index, and the phytoplankton index) or the phytoplankton remote sensing recognition index based on the virtual baseline height. The spectral recognition index extraction model can be obtained by learning based on the sample remote sensing water area image of the floating Cladophora in different growth environments, and the learning method of the model is not limited by the present application.

[0169] Optionally, the spectral recognition index extraction model can be one model capable of identifying multiple spectral recognition indexes obtained according to the learning method, or can include multiple sub-models for extracting different spectral recognition indexes, and the structure of the spectral recognition index extraction model is not limited by the present application and can be determined as needed.

[0170] The sub-model for extracting the floating Cladophora index (i.e., the floating Cladophora feature extraction model) can be obtained by learning based on the remote sensing image covering the floating Cladophora in different growth periods, and the structure of the sub-model can refer to but is not limited to the calculation formula of the corresponding part of the above embodiment. Based on this, the present application can perform band equivalent processing on the measured spectral data of the floating Cladophora growth environment to obtain the remote sensing emissivity and the center wavelength of each satellite band for the floating Cladophora region, and then input the remote sensing emissivity and the center wavelength of each satellite band into the floating Cladophora feature extraction model to obtain the floating Cladophora index of each pixel in the floating Cladophora region, and the implementation process is not described in detail.

[0171] Step S85, obtaining the classification threshold value constructed for different spectral recognition indexes;

[0172] Step S86, comparing the different spectral recognition indexes with the corresponding classification threshold values to obtain the corresponding comparison results;

[0173] Step S87, based on the comparison results corresponding to different classification thresholds, identifying a target region in the remote sensing water area image where the Cladophora glomerata in any growth period is located, the target region at least including the Cladophora glomerata region in the floating decline period and / or the Cladophora glomerata region in the floating growth period;

[0174] For the implementation process of steps S85-S87, refer to the description of the corresponding part of the above embodiments, which will not be repeated here.

[0175] Step S88, based on the identified different target regions, determining the coverage area and / or coverage geographical location of the Cladophora glomerata in the corresponding growth period under the floating Cladophora glomerata growth environment;

[0176] Step S89, outputting the determined coverage area and / or coverage geographical location of the Cladophora glomerata in any growth period.

[0177] For different remote sensing business needs, the region where the Cladophora glomerata in any growth period is located is identified from the remote sensing water area image of the floating Cladophora glomerata growth environment, i.e., the spatial distribution of the Cladophora glomerata in different growth periods such as the early attachment period, the floating growth period, and the floating decline period is determined, and then the Cladophora glomerata in a certain growth period can be located, the Cladophora glomerata in the growth period is processed, and the automatic monitoring and management of the Cladophora glomerata in different growth periods are promoted.

[0178] The coverage area can be converted from the area of the target region in the remote sensing water area image based on the collection parameters of the optical remote sensing image, or the coverage area of the Cladophora glomerata in a certain growth period can be calculated after the coverage geographical location of the Cladophora glomerata in the growth period is located, and the method for obtaining the coverage area and the coverage geographical location of the Cladophora glomerata in any growth period is not limited.

[0179] Based on the above embodiments, the remote sensing identification method for the Cladophora glomerata in different growth periods will be described based on the sentinel-2 (i.e., Sentinel-2 high-resolution multispectral imaging satellite) remote sensing image, and the Cladophora glomerata in Lake A is taken as an example. If the spectral resolution of the remote sensing reflectivity obtained by ground observation is 1 nm, the satellite image has different numbers of bands and the band width of each satellite is different, the reflectivity measured by the spectrometer needs to be converted into the equivalent reflectivity of the satellite band, and the band equivalent calculation method can be used to equivalent the measured reflectivity of the Cladophora glomerata and the water body in different growth periods to the reflectivity of the Sentinel-2 satellite band, and the equivalent reflectivity spectrum curve of the Cladophora glomerata and the water body in different growth periods based on the Sentinel-2 is obtained as shown in FIG. 8. Figure 9a

[0180] ​In this example, the Sentinel-2 remote sensing data is acquired, and after the DN value is converted into the reflectance value through a series of remote sensing data preprocessing, the chlorophyll-a spectral index, the normalized vegetation index, and the floating Cladophora glomerata index of each pixel can be acquired according to the method described in the above embodiment. The selected wavelength values and their remote sensing reflectance in the process of acquiring each index can include: selecting the remote sensing reflectance of the 4th band of Sentinel-2 as the first remote sensing reflectance of the first band, selecting the remote sensing reflectance of the 5th band as the fourth remote sensing reflectance of the fourth band, selecting the remote sensing reflectance of the 7th band as the second remote sensing reflectance of the second band, and selecting the remote sensing reflectance of the 8th band as the third remote sensing reflectance of the third band. The center wavelength of the 4th band is 665 nm, the center wavelength of the 5th band is 705 nm, the center wavelength of the 7th band is 783 nm, and the center wavelength of the 8th band is 842 nm.

[0181] In order to verify the consistency of the spectral curves of different growth periods of Cladophora glomerata and A lake water body on the image with the measured equivalent spectral curves, the spectral curves of different growth periods and A lake water body on the preprocessed Sentinel-2 can be selected for comparison, and the representative bands (2nd, 3rd, 4th, 5th, 6th, 7th, 8th, 11th, and 22nd bands) are shown in FIGS. 8A, 8B, 8C, 8D, 8E, 8F, 8G, 8H, and 8I. Figure 9b and Figure 9c Based on the above analysis, the present application can accurately identify the Cladophora glomerata regions of different growth periods and estimate the coverage area according to the characteristic differences of the spectral curves of Cladophora glomerata of different growth periods and A lake water body.

[0182] Referring to Figure 10 The structure of an optional example of a remote sensing recognition device for Cladophora glomerata of different growth periods proposed in the present application is shown in FIG. 9. The device can include:

[0183] The floating Cladophora glomerata region obtaining module 101 is configured to obtain the floating Cladophora glomerata region in the remote sensing water image under the growth environment of floating Cladophora glomerata.

[0184] The floating Cladophora glomerata index obtaining module 102 is configured to obtain the floating Cladophora glomerata index of each pixel in the floating Cladophora glomerata region based on the measured spectral data of the growth environment of floating Cladophora glomerata.

[0185] The region recognition module 103 is configured to recognize the floating decline period Cladophora glomerata region and / or the floating growth period Cladophora glomerata region in the floating Cladophora glomerata region based on the comparison result of the floating Cladophora glomerata index and the floating classification threshold.

[0186] In some embodiments, the floating Cladophora glomerata index obtaining module 102 described above can include:

[0187] an equivalent processing unit, configured to perform band equivalent processing on the measured spectrum data of the floating Cladophora growth environment to obtain respective remote sensing emissivity and center wavelength of each of a plurality of satellite bands for the floating Cladophora region;

[0188] an index calculation unit, configured to input the respective remote sensing emissivity and center wavelength of each of the plurality of satellite bands into a floating Cladophora feature extraction model to obtain a floating Cladophora index of each pixel in the floating Cladophora region.

[0189] Optionally, the respective remote sensing emissivity and center wavelength of each of the plurality of satellite bands include: a first remote sensing reflectivity and a first center wavelength of a first band, a second remote sensing reflectivity and a second center wavelength of a second band, and a third remote sensing reflectivity and a third center wavelength of a third band in the remote sensing water area image; the first band is a red light band, the second band is a band between the red light band and the near red band, and the third band is a near-infrared band; based on this, the index calculation unit can include:

[0190] a wavelength variable acquisition unit, configured to acquire a first wavelength variable of the second center wavelength and the first center wavelength, and a second wavelength variable of the third center wavelength and the first center wavelength;

[0191] a wavelength change coefficient acquisition unit, configured to perform ratio operation on the first wavelength variable and the second wavelength variable to obtain a wavelength change coefficient;

[0192] a reflectivity variable obtaining unit, configured to acquire a first reflectivity variable of the third remote sensing reflectivity and the first remote sensing reflectivity, and perform product operation on the first reflectivity variable and the wavelength change coefficient to obtain a second reflectivity variable;

[0193] a floating Cladophora index operation unit, configured to perform difference operation on the second remote sensing reflectivity, the first remote sensing reflectivity, and the second reflectivity variable to obtain the floating Cladophora index of the corresponding pixel of the floating Cladophora region.

[0194] In still some embodiments, the region identification module 103 can include:

[0195] a floating classification threshold acquisition unit, configured to acquire a floating classification threshold of the floating Cladophora for different growth periods;

[0196] a first comparison unit, configured to compare the floating Cladophora index of each pixel in the floating Cladophora region with the floating classification threshold, respectively;

[0197] The first identification unit is configured to identify a region where the pixel with the floating Chara index less than the floating classification threshold as the floating decline period Chara region, and identify a region where the pixel with the floating Chara index greater than the floating classification threshold as the floating growth period Chara region.

[0198] Based on this, the floating classification threshold obtaining unit can include:

[0199] The remote sensing region image obtaining unit is configured to obtain a remote sensing region image covering the floating Chara;

[0200] The pixel value obtaining unit is configured to obtain, based on a classification algorithm, the floating Chara index and the pixel value of the multiple groups of ground objects by classifying and identifying the remote sensing region image; the multiple groups of ground objects include water bodies and Chara in different growth periods;

[0201] The overlap range detecting unit is configured to determine the non-overlapping range value of the pixel value of the multiple groups of ground objects corresponding to the floating Chara index;

[0202] The pixel maximum and minimum value determining unit is configured to determine the maximum pixel value and the minimum pixel value of the multiple groups of ground objects corresponding to the floating Chara index from the non-overlapping range value of the pixel value of the multiple groups of ground objects;

[0203] The floating classification threshold obtaining unit is configured to obtain the floating classification threshold of the floating Chara index by performing mean value operation on the maximum pixel value and the minimum pixel value of the multiple groups of ground objects.

[0204] In some embodiments, the floating Chara region obtaining module 101 can include:

[0205] The remote sensing water area image obtaining unit is configured to obtain a remote sensing water area image in a floating Chara growth environment;

[0206] The spectral index obtaining unit is configured to obtain the chlorophyll-a spectral index and at least one vegetation index of each pixel in the remote sensing water area image based on the measured spectral data of the floating Chara growth environment;

[0207] The Chara region identification unit is configured to identify the Chara region in different growth periods in the remote sensing water area image based on the comparison result of the chlorophyll-a spectral index and the first classification threshold;

[0208] The floating Chara identification unit is configured to identify the attached early Chara region and the floating Chara region in the Chara region in different growth periods based on the comparison result of the vegetation index and the second classification threshold;

[0209] Optionally, the remote sensing water area image obtaining unit can include:

[0210] An optical remote sensing image acquisition unit is configured to acquire an optical remote sensing image of a region to be identified.

[0211] A preprocessing unit is configured to preprocess the optical remote sensing image to convert digital quantization values of the optical remote sensing image into reflectivity values.

[0212] An area of interest identification unit is configured to identify an area of interest in the preprocessed optical remote sensing image to obtain a remote sensing water area image covering different growth period Cladophora regions and water body regions.

[0213] A coverage area determination module is configured to determine a coverage area of a growth period Cladophora in the floating Cladophora growth environment based on the different growth period Cladophora regions identified from the remote sensing water area image, and / or

[0214] A coverage area determination module is configured to determine a coverage geographical position of a growth period Cladophora in the floating Cladophora growth environment based on the different growth period Cladophora regions identified from the remote sensing water area image.

[0215] An output module is configured to output the determined coverage area and / or coverage geographical position of any growth period Cladophora.

[0216] It should be noted that the various modules, units, etc. in the above device embodiments can be stored in the memory as program modules, and the processor can execute the above program modules stored in the memory to achieve the corresponding functions, or the program modules and hardware can be combined to achieve the functions, and the functions achieved by the program modules and their combinations can be referred to the descriptions of the corresponding parts of the above method embodiments, and the present embodiment will not be described again.

[0217] The present application also provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is loaded and executed by a processor to implement the steps of the above remote sensing identification method for different growth period Cladophora, and the specific implementation process can be referred to the descriptions of the corresponding parts of the above embodiments, and the present embodiment will not be described again.

[0218] The embodiment of the present application also provides a remote sensing identification system for different growth period Cladophora, which can comprise a remote sensing device, a spectrum detection device and a computer device suitable for the remote sensing identification method for different growth period Cladophora proposed in the present application, wherein the remote sensing device can be used to obtain optical remote sensing images in the growth environment of Cladophora to determine a remote sensing water area image of the floating Cladophora growth environment; the spectrum detection device can be used to detect spectrum data of the floating Cladophora growth environment to obtain measured spectrum data. For the remote sensing device, the type and working content of the spectrum detection device, reference can be made to the description of the corresponding part of the method embodiment above, and the embodiment will not be described in detail here.

[0219] In actual application, in the remote sensing identification process for different growth period Cladophora, the computer device can be in communication connection with the remote sensing device and the spectrum detection device to realize data transmission between each other, for example, the computer device receives the optical remote sensing images sent by the remote sensing device and receives the measured spectrum data sent by the spectrum detection device, and the present application does not limit the communication mode between different devices, which can be determined according to the situation. It should be understood that the structure of the remote sensing identification system for different growth period Cladophora described in the system embodiment does not constitute a limitation on the remote sensing identification system for different growth period Cladophora in the embodiment of the present application. In actual application, the remote sensing identification system for different growth period Cladophora can comprise more or fewer devices than the above example, such as monitoring devices, databases and the like, which will not be enumerated one by one herein.

[0220] Reference Figure 11 For the hardware structure diagram of the computer device suitable for the remote sensing identification method for different growth period Cladophora proposed in the present application, the computer device can comprise a communication interface 111, a memory 112 and a processor 113, wherein:

[0221] The communication interface 111 can comprise a communication module capable of realizing data interaction by using a wireless communication network, such as a data transmission interface of a WIFI module, a 5G / 6G (fifth generation mobile communication network / sixth generation mobile communication network) module, a GPRS module, a remote sensing communication module and the like, and the communication interface 111 can also comprise a data transmission interface for realizing data interaction between internal components of the computer device, such as a USB interface, a serial / parallel port and the like, and the present application does not limit the specific content contained in the communication interface 111.

[0222] The memory 112 can be configured to store a program for implementing the remote sensing identification method for the different growth periods of Cladophora sp. described in the above embodiments; and the processor 113 can be configured to load and execute the program stored in the memory, so as to implement the steps of the remote sensing identification method for the different growth periods of Cladophora sp. described in the above embodiments. For the specific implementation process, reference can be made to the descriptions of the corresponding parts in the above embodiments, and details are not described herein again.

[0223] In the embodiments of the present application, the memory 112 can include a high-speed random access memory, and can also include a non-volatile memory, for example, at least one magnetic disk storage device or other volatile solid-state storage device. The processor 113 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a field programmable gate array (FPGA), or other programmable logic devices, etc.

[0224] It can be understood that the computer device described above can be a server or a terminal with certain data processing capability. The server can be a stand-alone physical server, a server cluster composed of multiple physical servers, or a cloud server capable of implementing cloud computing, etc. The terminal can include, but is not limited to, a smart phone, a notebook computer, a desktop computer, a robot, etc. In the case where the computer device described above is a terminal, it can further include at least one input device such as a touch sensing unit for sensing a touch event on a touch display panel, a keyboard, a mouse, a camera, a sound pickup device, etc.; at least one output device such as a display, a speaker, a vibration mechanism, a lamp, etc. That is, Figure 11 The structure of the computer device shown does not constitute a limitation on the computer device in the embodiments of the present application. In actual applications, the computer device can include more or fewer components than those shown, or combine certain components, which are not listed one by one herein. Figure 11 The structure of the computer device shown does not constitute a limitation on the computer device in the embodiments of the present application. In actual applications, the computer device can include more or fewer components than those shown, or combine certain components, which are not listed one by one herein.

[0225] Finally, it should be noted that, in the above embodiments, unless the context clearly indicates otherwise, the words "one", "a", "an", and / or "the" do not specifically refer to the singular, but also include the plural. Generally, the terms "comprise" and "include" only indicate the inclusion of the steps and elements explicitly identified, and these steps and elements do not constitute an exclusive list. The elements defined by the statement "comprise one" can also include other same elements in the process, method, product or device comprising the elements.

[0226] In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" herein is only a description of the relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0227] The terms such as "first", "second" and the like involved in the present application are only for the purpose of description, used to distinguish one operation, unit or module from another operation, unit or module, and do not necessarily require or imply any such actual relationship or sequence between the units, operations or modules. And it cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features, so the features with "first", "second" can explicitly or implicitly include one or more features.

[0228] In addition, each embodiment in the specification is described in a progressive or parallel manner, and each embodiment focuses on the difference from other embodiments, and the same or similar parts between each embodiment can be referred to each other. For the device, system, medium, computer device disclosed by the embodiment, since it corresponds to the method disclosed by the embodiment, the description is relatively simple, and the related parts can be referred to the method part.

[0229] The skilled person can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly show the interchangeability of hardware and software, the components and steps of each example have been described in the above description. Whether the functions are executed in hardware or software depends on the specific application and design of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0230] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the core idea or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A remote sensing method for identifying Cladophora of different growth stages, characterized in that, The method comprises: obtaining a remote sensing water area image under a floating cladophora growth environment; based on the measured spectral data of the floating cladophora growth environment, obtaining the chlorophyll a spectral index and at least one vegetation index of each pixel in the remote sensing water area image; based on the comparison result of the chlorophyll a spectral index and the first classification threshold, identifying the cladophora area in different growth periods in the remote sensing water area image; based on the comparison result of the vegetation index and the second classification threshold, identifying the attached early cladophora area and the floating cladophora area in the cladophora area in different growth periods; the measured spectral data of the floating cladophora growth environment is subjected to band equivalent processing to obtain the remote sensing emissivity and center wavelength of each satellite band for the floating cladophora area; the remote sensing emissivity and center wavelength of each satellite band include: the first remote sensing reflectivity and the first center wavelength of the first band, the second remote sensing reflectivity and the second center wavelength of the second band, the third remote sensing reflectivity and the third center wavelength of the third band in the remote sensing water area image; wherein the first band is a red light band, the second band is a band between a red light band and a near red band, and the third band is a near infrared band; obtaining a first wavelength variable of the second center wavelength and the first center wavelength, and a second wavelength variable of the third center wavelength and the first center wavelength; ratio operation is performed on the first wavelength variable and the second wavelength variable to obtain a wavelength change coefficient; obtaining a first reflectivity variable of the third remote sensing reflectivity and the first remote sensing reflectivity, and performing product operation on the first reflectivity variable and the wavelength change coefficient to obtain a second reflectivity variable; difference operation is performed on the second remote sensing reflectivity, the first remote sensing reflectivity and the second reflectivity variable to obtain the floating cladophora index of the corresponding pixel of the floating cladophora area; based on the comparison result of the floating cladophora index and the floating classification threshold, identifying the floating decline period cladophora area and / or the floating growth period cladophora area in the floating cladophora area.

2. The method of claim 1, wherein, The comparison result of the floating cladophora index and the floating classification threshold is used to identify the floating decline period cladophora area and / or the floating growth period cladophora area in the floating cladophora area, which comprises: obtaining the floating classification threshold for floating cladophora in different growth periods; comparing the floating cladophora index of each pixel in the floating cladophora area with the floating classification threshold respectively; the region where the pixel with the floating cladophora index less than the floating classification threshold is located is identified as the floating decline period cladophora area, and the region where the pixel with the floating cladophora index greater than the floating classification threshold is located is identified as the floating growth period cladophora area.

3. The method of claim 2, wherein, The floating classification threshold for floating cladophora in different growth periods is obtained, which comprises: obtaining a remote sensing area image covering the floating cladophora; based on a classification algorithm, classifying and identifying the remote sensing area image to obtain a plurality of groups of floating cladophora indexes and pixel values possessed by ground objects; the plurality of groups of ground objects include water bodies and cladophora in different growth periods; determining a non-overlapping range value of the pixel values of the plurality of ground objects corresponding to the floating Cladophora glomerata index; determining a maximum pixel value and a minimum pixel value of the plurality of ground objects corresponding to the floating Cladophora glomerata index from the non-overlapping range value of the pixel values of the plurality of ground objects; performing mean operation on the maximum pixel value and the minimum pixel value of the plurality of ground objects to obtain a floating classification threshold value of the floating Cladophora glomerata index.

4. The method of claim 1, wherein the method further comprises: determining a coverage area and / or a coverage geographical location of the Cladophora glomerata in a growth period based on the Cladophora glomerata regions in different growth periods identified from the remote sensing water area image; and outputting the determined coverage area and / or the coverage geographical location of the Cladophora glomerata in any growth period. The device comprises:

5. A device for remote sensing of Cladophora growth, characterized in that a floating Cladophora glomerata region obtaining module configured to obtain a floating Cladophora glomerata region in a remote sensing water area image in a floating Cladophora glomerata growth environment; a floating Cladophora glomerata index obtaining module configured to obtain a floating Cladophora glomerata index of each pixel in the floating Cladophora glomerata region based on measured spectral data of the floating Cladophora glomerata growth environment; a region identifying module configured to identify a floating decline period Cladophora glomerata region and / or a floating growth period Cladophora glomerata region in the floating Cladophora glomerata region based on a comparison result of the floating Cladophora glomerata index and a floating classification threshold value; wherein the floating Cladophora glomerata region obtaining module comprises: a remote sensing water area image obtaining unit configured to obtain a remote sensing water area image in a floating Cladophora glomerata growth environment; a spectral index obtaining unit configured to obtain a chlorophyll-a spectral index and at least one vegetation index of each pixel in the remote sensing water area image based on measured spectral data of the floating Cladophora glomerata growth environment; a Cladophora glomerata region identifying unit configured to identify Cladophora glomerata regions in different growth periods in the remote sensing water area image based on a comparison result of the chlorophyll-a spectral index and a first classification threshold value; a floating Cladophora glomerata identifying unit configured to identify an attached early stage Cladophora glomerata region and a floating Cladophora glomerata region in the Cladophora glomerata regions in different growth periods based on a comparison result of the vegetation index and a second classification threshold value; the floating Cladophora glomerata index obtaining module comprises: an equivalent processing unit configured to perform band equivalent processing on the measured spectral data of the floating Cladophora glomerata growth environment to obtain a remote sensing emissivity and a center wavelength of each of a plurality of satellite bands for the floating Cladophora glomerata region; the remote sensing emissivity and the center wavelength of each of the plurality of satellite bands comprise: a first remote sensing reflectivity and a first center wavelength of a first band, a second remote sensing reflectivity and a second center wavelength of a second band, and a third remote sensing reflectivity and a third center wavelength of a third band; wherein the first band is a red light band, the second band is a band between a red light band and a near red band, and the third band is a near infrared band; a wavelength variable acquisition unit configured to acquire a first wavelength variable of the second center wavelength and the first center wavelength, and a second wavelength variable of the third center wavelength and the first center wavelength; ​ a wavelength change coefficient obtaining unit configured to obtain a wavelength change coefficient by performing a ratio operation on the first wavelength variable and the second wavelength variable; a reflectivity variable obtaining unit configured to obtain a first reflectivity variable of the third remote sensing reflectivity and the first remote sensing reflectivity, and obtain a second reflectivity variable by performing a product operation on the first reflectivity variable and the wavelength change coefficient; a floating Cladophora glomerata index operation unit configured to obtain the floating Cladophora glomerata index of the pixel corresponding to the floating Cladophora glomerata region by performing a difference operation on the second remote sensing reflectivity, the first remote sensing reflectivity, and the second reflectivity variable.

6. A computer-readable storage medium, characterized in that, A computer device has computer instructions stored thereon, and the computer instructions are loaded and executed by a processor to implement the remote sensing recognition method for Cladophora glomerata in different growth periods according to any one of claims 1-4.

7. A computer device, comprising: The computer device comprises: a communication interface; a memory configured to store a program for implementing the remote sensing recognition method for Cladophora glomerata in different growth periods according to any one of claims 1-4; a processor configured to load and execute the program stored in the memory to implement the remote sensing recognition method for Cladophora glomerata in different growth periods according to any one of claims 1-4.

8. A remote sensing recognition system for different growth stages of Cladophora, characterized by, The system comprises: a remote sensing device configured to obtain an optical remote sensing image of a Cladophora glomerata growth environment to determine a remote sensing water area image of the floating Cladophora glomerata growth environment; a spectrum detection device configured to perform spectrum data detection on the floating Cladophora glomerata growth environment to obtain actual spectrum data; a computer device according to claim 7, which is in communication connection with the remote sensing device and the spectrum detection device.

Images