A multispectral remote sensing method and system for detecting enteromorpha prolifera red tide

Abstract

The application discloses a kind of multispectral remote sensing enteromorpha red tide detection method and system, the multispectral remote sensing enteromorpha red tide detection method of the present application includes the multispectral image of input marine water color remote sensing satellite is carried out pseudo-exposure and generates pseudo-exposure multispectral image sequence, pseudo-exposure multispectral image is decomposed into structure block, signal intensity, average intensity, signal structure three components are decomposed to each structure block and are fused and are reconstructed into enhanced multispectral remote sensing image;Based on reference image, using dark target subtraction, the fog intensity of enhanced multispectral remote sensing image, fog abundance estimation is carried out and the interference of thin cloud fog in multispectral remote sensing image is removed, and the multispectral image after removing cloud fog interference is obtained to be used for enteromorpha red tide detection.The present application is aimed at long time sequence, large scale enteromorpha red tide detection, improves the information extraction precision of enteromorpha red tide, improves the efficiency of enteromorpha red tide detection.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a multispectral remote sensing enteromorpha red tide detection method and system. Background Art

[0002] Due to unusual or drastic changes in the marine environment, Enteromorpha blooms are particularly severe, posing a threat to local ecosystems and property. Over the past decade, Enteromorpha blooms have frequently occurred in my country, accumulating in the Yellow Sea each summer and gradually dispersing. Mapping the primary distribution areas of Enteromorpha blooms is crucial for disaster prevention and mitigation. Therefore, long-term, large-scale monitoring of Enteromorpha blooms can provide effective scientific evidence for local government response and mitigation efforts. With the advancement of remote sensing imagery, the means of detecting Enteromorpha blooms have become increasingly diverse, offering greater convenience and speed than previous monitoring stations and vessels. Compared to optical remote sensing satellites, multispectral remote sensing records information across multiple spectral bands, encompassing a wider range of spectral information. Furthermore, sensors such as the Korean Ocean Color Remote Sensing Satellite and the US MODIS satellite offer wide coverage and short revisit periods, making multispectral satellites suitable for long-term, large-scale monitoring of Enteromorpha blooms. However, remote sensing imagery faces two major challenges in detecting Enteromorpha blooms: First, due to the transmissive nature of ocean water, reflected signals are weak, weakening hydrological information such as Enteromorpha blooms. Second, remote sensing images are often obscured by fog and cloud, resulting in poor contrast and visibility in captured Enteromorpha blooms, severely hindering their identification and detection. While existing techniques for remote sensing image processing have documented image enhancement or declouding, including those based on image fusion, image transformation, and deep learning, aiming to improve the visualization and information extraction accuracy of remote sensing images, these methods face numerous limitations and are difficult to implement for long-term, large-scale Enteromorpha bloom detection applications. Summary of the Invention

[0003] The technical problem to be solved by the present invention is as follows: In response to the above-mentioned problems of the prior art, a multispectral remote sensing enteromorpha red tide detection method and system are provided. The present invention aims to improve the information extraction accuracy of enteromorpha red tide and the efficiency of enteromorpha red tide detection for long-term and large-scale detection.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0005] A multispectral remote sensing enteromorpha red tide detection method and system, comprising the following steps:

[0006] S1, the multispectral image of the ocean color remote sensing satellite is input Normalization is performed, and then pseudo-exposure image processing is performed to generate pseudo-exposure multispectral image sequences with different exposure levels , and there are ,in ~ is a pseudo-exposure multispectral image sequence No. 1~ pseudo-exposure multispectral images;

[0007] S2, the pseudo-exposure multispectral image sequence The pseudo-exposure multispectral image in the image is decomposed into structural blocks, and the signal intensity, average intensity and signal structure components of each structural block are decomposed and fused to reconstruct the enhanced multispectral remote sensing image. ;

[0008] S3, based on a reference image with the same viewpoint, scene, and satellite, without cloud or fog interference As a reference object, dark target subtraction is used to enhance the multispectral remote sensing image. Estimating fog intensity and fog abundance and removing the interference of thin clouds and fog in multispectral remote sensing images to obtain multispectral images after removing cloud and fog interference ;

[0009] S4, remove the multispectral image after cloud and fog interference The input image is classified using a pre-trained classifier to obtain the distribution map of the Enteromorpha red tide.

[0010] Optionally, the normalized function expression in step S1 is:

[0011] ,

[0012] In the above formula, is the normalized multispectral image, For multispectral images Matrix data obtained after matrix transformation The Rank List, Representing matrix data Middle The minimum value of the column, Representing matrix data Middle The maximum value of the column.

[0013] Optionally, in step S1, pseudo-exposure image processing is performed to generate pseudo-exposure multispectral image sequences with different exposure levels. Time, before The generating function expression of the pseudo-exposure multispectral image is:

[0014] ,

[0015] In the above formula, For the pseudo-exposure multispectral images, is the logarithmic coefficient of variation, is the normalized multispectral image, The pseudo-exposure multispectral image is a normalized multispectral image. It is obtained by using adaptive histogram equalization.

[0016] Optionally, step S2 includes:

[0017] S2.1, pseudo-exposure multispectral image sequence The pseudo-exposure multispectral image in is decomposed into structural blocks, and the signal intensity of each structural block is decomposed , average intensity , signal structure Three components;

[0018] S2.2: The signal intensity, average intensity, and signal structure components of each pseudo-exposure multispectral image are fused to generate the fused signal intensity according to the following formula: , signal structure and average intensity ;

[0019] , , ,

[0020] In the above formula, Indicates taking the maximum value, and is an intermediate variable, and there are:

[0021] , ,

[0022] in, and is a constant, is the standard deviation of the building blocks, Indicates summation, is the inverse tangent function;

[0023] Solve the intermediate variables according to the following formula :

[0024] ,

[0025] in, is the signal strength;

[0026] S2.3, intermediate variables of all pseudo-exposure multispectral images The stitching is restored to the original image size and represented as a feature , intermediate variables The stitching is restored to the original image size and represented as a feature , intermediate variables The stitching is restored to the original image size and represented as a feature , the enhanced multispectral remote sensing image is reconstructed according to the following formula ;

[0027] ,

[0028] In the above formula, Indicates summation, The kernel size is The mean filter, Represents element-wise multiplication operation, feature This is the result obtained by aggregating the original structural blocks and performing mean filtering;

[0029] S2.4, will enhance multispectral remote sensing images Perform multi-scale decomposition and fusion to enhance the spatial detail information of multispectral images, thereby obtaining the final enhanced multispectral remote sensing image. .

[0030] Optionally, step S2.1 includes: based on a given structural block size parameter , the pseudo-exposure multispectral image sequence The pseudo-exposure multispectral image in is decomposed into The structural blocks, where For multispectral images The number of bands; for each structural block, the signal strength, average strength, and signal structure components are decomposed according to the following formula:

[0031] ,

[0032] ,

[0033] ,

[0034] In the above formula, 、 and Respectively Pseudo-exposure multispectral images The signal strength, average strength and signal structure are the three components. For the Pseudo-exposure multispectral images A collection of structural blocks, is equal to The intermediate variable, express norm, Indicates finding the mean of the structural blocks.

[0035] Optionally, step S2.4 includes:

[0036] S2.4.1, Initialization Iterations is 1, feature No. Layer Features Value is a feature ,feature No. Layer Features The value is the original feature , the features No. Layer Features Value is a feature , the features No. Layer Features Value is a feature ;

[0037] S2.4.2, calculate the Image detail layer after layer decomposition and image base layer :

[0038] ,

[0039] ,

[0040] In the above formula, Indicates summation, The kernel size is The mean filter, Represents element-wise multiplication operation, feature This is the result obtained by aggregating the original structural blocks and performing mean filtering;

[0041] S2.4.3, the number of iterations Add 1 to determine the number of iterations Equal to the preset decomposition level threshold Is it true? If not, then the feature No. Layer Features ,feature No. Layer Features ,feature No. Layer Features ,feature No. Layer Features After downsampling by a specified multiple, they are used as new features No. Layer Features ,feature No. Layer Features ,feature No. Layer Features ,feature No. Layer Features , jump to step S2.4.2; otherwise jump to step S2.4.4; where the decomposition level threshold The calculation function expression is:

[0042] ,

[0043] In the above formula, Indicates rounding down. To get the minimum value, and Multispectral images width and height;

[0044] S2.4.4, the final enhanced multispectral remote sensing image is obtained according to the following formula: :

[0045] + ,

[0046] ,

[0047] In the above formula, For the The image base layer after layer decomposition, For upsampling, For the Image detail layer after layer decomposition, For the The image base layer after layer decomposition, For the Image detail layer after layer decomposition, For multispectral images The original size of the base layer image, For multispectral images The original size of the image detail layer, .

[0048] Optionally, step S3 includes:

[0049] S3.1, based on a reference image with the same viewpoint, scene, and satellite, without cloud or fog interference As a reference object, dark target subtraction is used to enhance the multispectral remote sensing image. Estimation of fog intensity and fog abundance to obtain enhanced multispectral remote sensing images Fog intensity map and fog abundance map :

[0050] ,

[0051] ,

[0052] In the above formula, Represents the reference image The bands that do not contain information on the red tide of Enteromorpha and Represents the reference image The number of bands that do not contain information on Enteromorpha red tides, Represents multispectral remote sensing images The bands that do not contain information on the red tide of Enteromorpha and Represents multispectral remote sensing images The number of bands that do not contain information on Enteromorpha red tide; To enhance multispectral remote sensing images Water body normalization index The average value of the pixels in the cloud area with a specified percentage before Fog intensity map Water body normalization index The average value of the pixels in the cloud area with a specified percentage before To enhance multispectral remote sensing images Water body normalization index The average value of the pixels in the cloud-free area before the specified percentage, Fog intensity map Water body normalization index The average value of pixels in the cloud-free area with a specified percentage;

[0053] S3.2, calculate the multispectral image after removing cloud and fog interference according to the following formula :

[0054] ，

[0055] In the above formula, To enhance multispectral remote sensing images, is the fog abundance map, This is the fog intensity map.

[0056] In addition, the present invention also provides a multi-spectral remote sensing enteromorpha red tide detection system, comprising a microprocessor and a memory connected to each other, wherein the microprocessor is programmed or configured to execute the multi-spectral remote sensing enteromorpha red tide detection method.

[0057] In addition, the present invention also provides a computer-readable storage medium, which stores a computer program or instruction, and the computer program or instruction is programmed or configured to execute the multi-spectral remote sensing enteromorpha red tide detection method through a processor.

[0058] In addition, the present invention also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the multi-spectral remote sensing enteromorpha red tide detection method through a processor.

[0059] Compared with the prior art, the present invention has the following advantages: the present invention includes the input of multi-spectral images of ocean water color remote sensing satellites Perform pseudo exposure to generate pseudo exposure multispectral image sequence The pseudo-exposure multispectral image is decomposed into structural blocks, and each structural block is decomposed into three components: signal intensity, average intensity, and signal structure, and fused to reconstruct the enhanced multispectral remote sensing image. ; Based on the reference image Enhancement of multispectral remote sensing images using dark object subtraction Estimating fog intensity and fog abundance and removing the interference of thin clouds and fog in multispectral remote sensing images to obtain multispectral images after removing cloud and fog interference For use in detection of Enteromorpha red tides. The present invention is aimed at long-term, large-scale Enteromorpha red tide detection, solving the problem of complex ocean background environment, often interfered by clouds and fog, as well as the problem of weak image reflection signals and small spectral differences between phenomena. It can quickly and efficiently restore Enteromorpha red tide information in images, enhance the category differences between Enteromorpha red tides, clouds and fog, land, and seawater, making it applicable to large-scale, long-term Enteromorpha red tide detection through traditional classification methods, effectively enhancing the contrast between Enteromorpha red tides and other landforms, and being able to detect them from large-scale remote sensing images. It has the advantages of high information extraction accuracy of Enteromorpha red tides and high efficiency of Enteromorpha red tide detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 Schematic diagram of the basic process of the method of the embodiment of the present invention.

[0061] Figure 2 is a multispectral image in an embodiment of the present invention Schematic diagram (false color map composed of bands 7, 6, and 3).

[0062] Figure 3 is the pseudo-exposure multispectral image sequence in the embodiment of the present invention Schematic diagram, where (a) to (f) are six pseudo-exposure multispectral images (false color images composed of the 7th, 6th, and 3rd bands).

[0063] Figure 4 The enhanced multispectral remote sensing image obtained in the embodiment of the present invention is Schematic diagram (false color map composed of bands 7, 6, and 3).

[0064] Figure 5 The multispectral image after removing the cloud and fog interference obtained in the embodiment of the present invention is Schematic diagram (false color map composed of bands 7, 6, and 3).

[0065] Figure 6 3 is a distribution map of Enteromorpha red tide obtained in an embodiment of the present invention, wherein (a) is the result of classification using support vector machine before image enhancement, and (b) is the result of classification using support vector machine after image enhancement. DETAILED DESCRIPTION

[0066] like Figure 1 As shown, the multispectral remote sensing enteromorpha red tide detection method of this embodiment includes the following steps:

[0067] S1, the multispectral image of the ocean color remote sensing satellite is input Normalization is performed, and then pseudo-exposure image processing is performed to generate pseudo-exposure multispectral image sequences with different exposure levels , and there are ,in ~ is a pseudo-exposure multispectral image sequence No. 1~ pseudo-exposure multispectral images;

[0068] S2, the pseudo-exposure multispectral image sequence The pseudo-exposure multispectral image in the image is decomposed into structural blocks, and the signal intensity, average intensity and signal structure components of each structural block are decomposed and fused to reconstruct the enhanced multispectral remote sensing image. ;

[0069] S3, based on a reference image with the same viewpoint, scene, and satellite, without cloud or fog interference As a reference object, dark target subtraction is used to enhance the multispectral remote sensing image. Estimating fog intensity and fog abundance and removing the interference of thin clouds and fog in multispectral remote sensing images to obtain multispectral images after removing cloud and fog interference ;

[0070] S4, remove the multispectral image after cloud interference The input image is classified using a pre-trained classifier to obtain the distribution map of the Enteromorpha red tide.

[0071] The multispectral image of the ocean color remote sensing satellite input in step S1 of this embodiment like Figure 2 As shown, the multispectral image For low-resolution, large-scale multispectral images of ocean color remote sensing satellites, the images are normalized and then pseudo-exposure image processing is performed to generate multispectral image sequences with different exposure levels. In step S1, a normalization operation is performed to scale the data to the same range. The normalization operation is performed on the original multispectral image. , perform image matrix transformation operation to make its matrix length , width is the number of bands , and scale the data to In the range of , the normalized function expression in step S1 of this embodiment is:

[0072] ,

[0073] In the above formula, is the normalized multispectral image, For multispectral images Matrix data obtained after matrix transformation The Rank List, Representing matrix data Middle The minimum value of the column, Representing matrix data Middle The maximum value of the column. After normalizing the data, restore it to its original width, height, and number of bands.

[0074] In order to obtain images with high dynamic range, in step S1 of this embodiment, pseudo-exposure image processing is performed to generate pseudo-exposure multispectral image sequences with different exposure levels. The multi-exposure sequence image generation operation is performed, and the normalized multispectral data is subjected to logarithmic transformation and adaptive histogram equalization processing. Specifically, in step S1 of this embodiment, pseudo-exposure image processing is performed to generate pseudo-exposure multispectral image sequences with different exposure levels. Time, before The generating function expression of the pseudo-exposure multispectral image is:

[0075] ,

[0076] In the above formula, For the pseudo-exposure multispectral images, is the logarithmic coefficient of variation, is the normalized multispectral image, The pseudo-exposure multispectral image is a normalized multispectral image. Adaptive histogram equalization is used to obtain the ,therefore Using the logarithmic transformation above, Adaptive histogram equalization is used, as shown in the following example: Figure 3 shown.

[0077] In this embodiment, step S2 includes:

[0078] S2.1, pseudo-exposure multispectral image sequence The pseudo-exposure multispectral image in is decomposed into structural blocks, and the signal intensity of each structural block is decomposed , average intensity , signal structure Three components;

[0079] S2.2: The signal intensity, average intensity, and signal structure components of each pseudo-exposure multispectral image are fused to generate the fused signal intensity according to the following formula: , signal structure and average intensity ;

[0080] , , ,

[0081] In the above formula, Indicates taking the maximum value, and is an intermediate variable, and there are:

[0082] , ,

[0083] in, and is a constant, is the standard deviation of the building blocks, Indicates summation, is the inverse tangent function;

[0084] Solve the intermediate variables according to the following formula :

[0085] ,

[0086] in, is the signal strength;

[0087] S2.3, intermediate variables of all pseudo-exposure multispectral images The stitching is restored to the original image size and represented as a feature , intermediate variables The stitching is restored to the original image size and represented as a feature , intermediate variables The stitching is restored to the original image size and represented as a feature , the enhanced multispectral remote sensing image is reconstructed according to the following formula ;

[0088] ,

[0089] In the above formula, Indicates summation, The kernel size is The mean filter, Represents element-wise multiplication operation, feature This is the result obtained by aggregating the original structural blocks and performing mean filtering;

[0090] S2.4, will enhance multispectral remote sensing images Perform multi-scale decomposition and fusion to enhance the spatial detail information of multispectral images, thereby obtaining the final enhanced multispectral remote sensing image. .

[0091] In this embodiment, step S2.1 includes: based on a given structural block size parameter , the pseudo-exposure multispectral image sequence The pseudo-exposure multispectral image in is decomposed into The structural blocks, where For multispectral images The number of bands; for each structural block, the signal strength, average strength, and signal structure components are decomposed according to the following formula:

[0092] ,

[0093] ,

[0094] ,

[0095] In the above formula, 、 and Respectively Pseudo-exposure multispectral images The signal strength, average strength and signal structure are the three components. For the Pseudo-exposure multispectral images A collection of structural blocks (including multiple-exposure image sequences), is equal to The intermediate variable, express norm, Indicates the mean of the structure block. Each image in The image is divided into structural blocks of size , the size of each image block is , is the number of bands of the multispectral image, then the structural block It can be expressed as:

[0096] ,

[0097] In the above formula, the meaning of each symbol is explained in detail in the previous text.

[0098] In step S2.2 of this embodiment, the signal intensity, average intensity, and signal structure components of each pseudo-exposure multispectral image are fused to generate a fused signal intensity , signal structure and average intensity When the signal intensity of different image sequences is fused Signal strength by building block The maximum value in determines the signal structure after fusion of different image sequences. Signal structure by structure block The average intensity after fusion of different image sequences is obtained by power weighting and normalization. The average strength of the structural block The signal strength after fusion is obtained by weighted normalization. , the higher the contrast, the better the gain effect, and its mathematical expression is: .

[0099] In step S2.4 of this embodiment, the multispectral remote sensing image is enhanced. Enhance multispectral remote sensing images by performing multi-scale decomposition and fusion to enhance multispectral spatial detail information It can be expressed as:

[0100] ,

[0101] ,

[0102] ,

[0103] Enhanced multispectral remote sensing image For the Image detail layer after layer decomposition and image base layer The superposition composition can be based on which multi-scale decomposition and fusion can be performed to enhance the spatial detail information of the multi-spectrum. Specifically, step S2.4 in this embodiment includes:

[0104] S2.4.1, Initialization Iterations is 1, feature No. Layer Features Value is a feature ,feature No. Layer Features The value is the original feature , the features No. Layer Features Value is a feature , the features No. Layer Features Value is a feature ;

[0105] S2.4.2, calculate the Image detail layer after layer decomposition and image base layer :

[0106] ,

[0107] ,

[0108] In the above formula, Indicates summation, The kernel size is The mean filter, Represents element-wise multiplication operation, feature This is the result obtained by aggregating the original structural blocks and performing mean filtering;

[0109] S2.4.3, the number of iterations Add 1 to determine the number of iterations Equal to the preset decomposition level threshold Is it true? If not, then the feature No. Layer Features ,feature No. Layer Features ,feature No. Layer Features ,feature No. Layer Features After downsampling by a specified multiple, they are used as new features No. Layer Features ,feature No. Layer Features ,feature No. Layer Features ,feature No. Layer Features , jump to step S2.4.2; otherwise jump to step S2.4.4; where the decomposition level threshold The calculation function expression is:

[0110] ,

[0111] In the above formula, Indicates rounding down. To get the minimum value, and Multispectral images width and height;

[0112] S2.4.4, the final enhanced multispectral remote sensing image is obtained according to the following formula: :

[0113] + ,

[0114] ,

[0115] In the above formula, For the The image base layer after layer decomposition, is the upsampling (the inverse of the downsampling multiple), For the Image detail layer after layer decomposition, For the The image base layer after layer decomposition, For the Image detail layer after layer decomposition, For multispectral images The original size of the base layer image, For multispectral images The original size of the image detail layer, In this embodiment, the final enhanced multispectral remote sensing image is obtained like Figure 4 shown.

[0116] In this embodiment, step S3 includes:

[0117] S3.1, based on a reference image with the same viewpoint, scene, and satellite, without cloud or fog interference As a reference object, dark target subtraction is used to enhance the multispectral remote sensing image. Estimation of fog intensity and fog abundance to obtain enhanced multispectral remote sensing images Fog intensity map and fog abundance map :

[0118] ,

[0119] ,

[0120] In the above formula, Represents the reference image The bands that do not contain information on the red tide of Enteromorpha and Represents the reference image The number of bands that do not contain information on Enteromorpha red tides, Represents multispectral remote sensing images The bands that do not contain information on the red tide of Enteromorpha and Represents multispectral remote sensing images The number of bands that do not contain information on Enteromorpha red tide; To enhance multispectral remote sensing images Water body normalization index The average value of the pixels in the cloud area with a specified percentage before Fog intensity map Water body normalization index The average value of the pixels in the cloud area with a specified percentage before To enhance multispectral remote sensing images Water body normalization index The average value of the pixels in the cloud-free area before the specified percentage, Fog intensity map Water body normalization index The average value of pixels in the cloud-free area with a specified percentage;

[0121] S3.2, calculate the multispectral image after removing cloud and fog interference according to the following formula :

[0122] ，

[0123] In the above formula, To enhance multispectral remote sensing images, is the fog abundance map, The multispectral image obtained in this embodiment after removing the cloud and fog interference is like Figure 5 shown.

[0124] In step S3.1, input the enhanced multispectral remote sensing image And reference images with the same viewpoint, scene, satellite, and no cloud or fog interference , to obtain enhanced multispectral remote sensing images The average image of the band that does not contain the red tide information of Enteromorpha is used to obtain the reference image The average image of the corresponding band. In particular, the reflectivity of the enteromorpha red tide usually gradually increases in the red light band (700-750 nm), which is quite different from the seawater. Therefore, the spectrum less than 700 nm can be regarded as a band that does not contain information about the enteromorpha red tide, and the spectrum greater than 700 nm can be regarded as a band that contains information about the enteromorpha red tide. In the multispectral image used in the example, there are a total of 8 bands, namely 412 nm, 443 nm, 490 nm, 555 nm, 660 nm, 680 nm, 745 nm and 865 nm. Therefore, the first 6 bands can be regarded as bands that do not contain information about the enteromorpha red tide, and the last 2 bands can be regarded as bands that contain information about the enteromorpha red tide. Subsequently, the reference image is used The average image of the corresponding band minus the enhanced multispectral remote sensing image The enhanced multispectral remote sensing image can be obtained by averaging the image without the red tide information band of Enteromorpha. Fog intensity map , its function expression is as follows:

[0125] ,

[0126] In the above formula, Represents the reference image The bands that do not contain information on the red tide of Enteromorpha and Represents the reference image The number of bands that do not contain information on Enteromorpha red tides, Represents multispectral remote sensing images The bands that do not contain information on the red tide of Enteromorpha and Represents multispectral remote sensing images The number of bands that do not contain information on Enteromorpha blooms.

[0127] According to the dark channel method, the enhanced multispectral remote sensing image is obtained The minimum value of each pixel in the multispectral image across all bands is calculated using the following formula: Pixels with larger pixel values ​​represent areas with higher cloud concentrations, and pixels with a specified percentage (1% in this embodiment, or other specified percentages as needed) are selected to represent pixels in the cloud area; pixels with a specified percentage (1% in this embodiment, or other specified percentages as needed) in the water body normalization index of the multispectral image represent areas without cloud and fog, and the water body normalization index is calculated. The calculation function expression is as follows:

[0128] ,

[0129] In the above formula, Indicates the green band, The fog abundance map The calculation function expression is as follows:

[0130] ,

[0131] In the above formula, ,

[0132] In the above formula, To enhance multispectral remote sensing images Water body normalization index The average value of the pixels in the cloud area with a specified percentage before Fog intensity map Water body normalization index The average value of the pixels in the cloud area with a specified percentage before To enhance multispectral remote sensing images Water body normalization index The average value of the pixels in the cloud-free area before the specified percentage, Fog intensity map Water body normalization index The mean value of the pixels in the cloud-free area before the specified percentage.

[0133] In step S4, the multispectral image after removing the cloud and fog interference is The pre-trained classifier is used as the input image to classify the distribution map of Enteromorpha red tide. The required classifier and its training method can be used as needed. For example, the multispectral image after removing the cloud interference As the input image, the Enteromorpha red tide is marked and divided into training set and test set according to the ratio of 1:100. The support vector machine is used to classify it. The distribution map of the Enteromorpha red tide is as follows Figure 6(a) is the result of classification using a support vector machine before image enhancement, i.e., the distribution map of Enteromorpha red tide obtained by classification using only step S4 of the method of this embodiment, and (b) is the result of classification using a support vector machine after image enhancement, i.e., the distribution map of Enteromorpha red tide obtained by classification using steps S1 to S4 of the method of this embodiment. Figure 6 As can be seen, before image enhancement in steps S1-S3 of this embodiment, the classified Enteromorpha red tide distribution map (a) misidentifies some noise or thin cloud boundary areas as Enteromorpha red tide. However, after image enhancement in steps S1-S3 of this embodiment, the classified Enteromorpha red tide distribution map (b) effectively increases the separability between classes (background, seawater, and Enteromorpha), reducing instances of misclassification. Alternatively, classification methods or classifiers such as random forests can also be used to achieve a similarly classified Enteromorpha red tide distribution map.

[0134] In order to verify the multispectral remote sensing enteromorpha red tide detection system of this embodiment, three indicators are selected in this embodiment to quantitatively evaluate the target segmentation method proposed in this example. TP represents true positive, that is, the number of samples that are actually positive and correctly predicted as positive; FN represents false negative, that is, the number of samples that are actually positive but incorrectly predicted as negative; FP represents false positive, that is, the number of samples that are actually negative but incorrectly predicted as positive; TN represents true negative, that is, the number of samples that are actually negative and correctly predicted as negative. The following three indicators can be calculated based on the confusion matrix:

[0135] Accuracy AA (Accuracy): refers to the proportion of samples whose model predictions match the actual labels. The calculation formula is as follows:

[0136] AA=1 / 2×(TP / (TP+FN)+TN / (TN+FP)) ,

[0137] Prediction accuracy OA (Overal Accuracy): refers to the proportion of samples in the model prediction results that match the actual labels. The calculation formula is as follows:

[0138] OA=((TP+TN)) / (TP+TN+FP+FN),

[0139] Kappa coefficient (Cohen's Kappa): takes into account the difference between expected accuracy and actual accuracy and is used to measure the consistency of model classification. The calculation formula is as follows:

[0140] Kappa=((OA-AA)) / (1-AA).

[0141] The results obtained by using two classification methods, support vector machine or random forest, are shown in Table 1.

[0142] Table 1: Quantitative evaluation results of three indicators of two classification methods

[0143]

[0144] As shown in Table 1, the multispectral remote sensing enteromorpha red tide detection system of this embodiment, based on the two classification methods of support vector machine or random forest, achieved good results in the three indicators of prediction accuracy OA, accuracy AA and Kappa coefficient.

[0145] In summary, the multispectral remote sensing Enteromorpha red tide detection system of this embodiment processes low-resolution, large-scale multispectral remote sensing images, including image enhancement, image declouding, and Enteromorpha red tide segmentation. A pseudo-exposure sequence is generated for the current multispectral remote sensing image, and the image is fused and reconstructed based on the three components of signal structure, signal intensity, and average intensity. The reconstructed enhanced image is referenced to a cloud-free remote sensing image of the same scene, and dark target subtraction is performed to decloud the image, removing the influence of thin clouds and fog, thereby enhancing the spectral information of the Enteromorpha red tide. The declouded image is classified using classification methods such as random forests and support vector machines to effectively detect the distribution area of ​​the Enteromorpha red tide. The multispectral remote sensing Enteromorpha red tide detection system of this embodiment combines image enhancement and declouding technologies to enhance the separability of Enteromorpha red tide from seawater, land, clouds, and other areas. This allows for effective long-term monitoring of the distribution of Enteromorpha red tide in the ocean, providing support for research and application in related fields.

[0146] In addition, this embodiment also provides a multispectral remote sensing enteromorpha red tide detection system, including a microprocessor and a memory connected to each other, and the microprocessor is programmed or configured to execute the multispectral remote sensing enteromorpha red tide detection method.

[0147] In addition, this embodiment also provides a computer-readable storage medium, which stores a computer program or instruction. The computer program or instruction is programmed or configured to execute the multi-spectral remote sensing enteromorpha red tide detection method through a processor.

[0148] In addition, this embodiment also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the multi-spectral remote sensing enteromorpha red tide detection method through a processor.

[0149] Those skilled in the art should understand that the technical solutions provided by the embodiments of the present application may be in the form of methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including the instruction device, which implements the function specified in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0150] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the concept of the present invention are within the scope of protection of the present invention. It should be noted that for those skilled in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A multispectral remote sensing method for detecting red tides of Enteromorpha, characterized in that: The steps include: S1, the multispectral image of the ocean color remote sensing satellite is input Normalization is performed, and then pseudo-exposure image processing is performed to generate pseudo-exposure multispectral image sequences with different exposure levels , and there are ,in ~ is a pseudo-exposure multispectral image sequence No. 1~ pseudo-exposure multispectral images; S2, the pseudo-exposure multispectral image sequence The pseudo-exposure multispectral image in the image is decomposed into structural blocks, and the signal intensity, average intensity and signal structure components of each structural block are decomposed and fused to reconstruct the enhanced multispectral remote sensing image. ; S3, based on a reference image with the same viewpoint, scene, and satellite, without cloud or fog interference As a reference object, dark target subtraction is used to enhance the multispectral remote sensing image. Estimating fog intensity and fog abundance and removing the interference of thin clouds and fog in multispectral remote sensing images to obtain multispectral images after removing cloud and fog interference ; S4, remove the multispectral image after cloud and fog interference The input image is classified by the pre-trained classifier to obtain the distribution map of Enteromorpha red tide; Step S2 includes: S2.1, pseudo-exposure multispectral image sequence The pseudo-exposure multispectral image in is decomposed into structural blocks, and the signal intensity of each structural block is decomposed , average intensity , signal structure Three components; S2.2: The signal intensity, average intensity, and signal structure components of each pseudo-exposure multispectral image are fused to generate the fused signal intensity according to the following formula: , signal structure and average intensity ; ， ， ， In the above formula, Indicates taking the maximum value, and is an intermediate variable, and there are: ， ， in, and is a constant, is the standard deviation of the building blocks, Indicates summation, is the inverse tangent function; Solve the intermediate variables according to the following formula : ， in, is the signal strength; S2.3, intermediate variables of all pseudo-exposure multispectral images The stitching is restored to the original image size and represented as a feature , intermediate variables The stitching is restored to the original image size and represented as a feature , intermediate variables The stitching is restored to the original image size and represented as a feature , the enhanced multispectral remote sensing image is reconstructed according to the following formula ; ， In the above formula, Indicates summation, The kernel size is The mean filter, Represents element-wise multiplication operation, feature This is the result obtained by aggregating the original structural blocks and performing mean filtering; S2.4, will enhance multispectral remote sensing images Perform multi-scale decomposition and fusion to enhance the spatial detail information of multispectral images, thereby obtaining the final enhanced multispectral remote sensing image. ; Step S2.1 includes: based on a given structural block size parameter , the pseudo-exposure multispectral image sequence The pseudo-exposure multispectral image in is decomposed into The structural blocks, where For multispectral images The number of bands; for each structural block, the signal strength, average strength, and signal structure components are decomposed according to the following formula: ， ， ， In the above formula, 、 and Respectively Pseudo-exposure multispectral images The signal strength, average strength and signal structure are the three components. For the Pseudo-exposure multispectral images A collection of structural blocks, is equal to The intermediate variable, express norm, Indicates finding the mean of the structural blocks.

2. The multispectral remote sensing enteromorpha red tide detection method according to claim 1, characterized in that: The normalized function expression in step S1 is: ， In the above formula, is the normalized multispectral image, For multispectral images Matrix data obtained after matrix transformation The Rank List, Representing matrix data Middle The minimum value of the column, Representing matrix data Middle The maximum value of the column.

3. The multispectral remote sensing enteromorpha red tide detection method according to claim 1, characterized in that: In step S1, pseudo-exposure image processing is performed to generate pseudo-exposure multispectral image sequences with different exposure levels. Time, before The generating function expression of the pseudo-exposure multispectral image is: ， In the above formula, For the pseudo-exposure multispectral images, is the logarithmic coefficient of variation, is the normalized multispectral image, The pseudo-exposure multispectral image is a normalized multispectral image. It is obtained by using adaptive histogram equalization.

4. The multispectral remote sensing enteromorpha red tide detection method according to claim 1, characterized in that: Step S2.4 includes: S2.4.1, Initialization Iterations is 1, feature No. Layer Features Value is a feature ,feature No. Layer Features The value is the original feature , the features No. Layer Features Value is a feature , the features No. Layer Features Value is a feature ; S2.4.2, calculate the Image detail layer after layer decomposition and image base layer : ， ， In the above formula, Indicates summation, The kernel size is The mean filter, Represents element-wise multiplication operation, feature This is the result obtained by aggregating the original structural blocks and performing mean filtering; S2.4.3, the number of iterations Add 1 to determine the number of iterations Equal to the preset decomposition level threshold Is it true? If not, then the feature No. Layer Features ,feature No. Layer Features ,feature No. Layer Features ,feature No. Layer Features After downsampling by a specified multiple, they are used as new features No. Layer Features ,feature No. Layer Features ,feature No. Layer Features ,feature No. Layer Features , jump to step S2.4.2; otherwise jump to step S2.4.4; where the decomposition level threshold The calculation function expression is: ， In the above formula, Indicates rounding down. To get the minimum value, and Multispectral images width and height; S2.4.4, the final enhanced multispectral remote sensing image is obtained according to the following formula: : + ， ， In the above formula, For the The image base layer after layer decomposition, For upsampling, For the Image detail layer after layer decomposition, For the The image base layer after layer decomposition, For the Image detail layer after layer decomposition, For multispectral images The original size of the base layer image, For multispectral images The original size of the image detail layer, .

5. The multispectral remote sensing enteromorpha red tide detection method according to claim 1, characterized in that: Step S3 includes: S3.1, based on a reference image with the same viewpoint, scene, and satellite, without cloud or fog interference As a reference object, dark target subtraction is used to enhance the multispectral remote sensing image. Estimation of fog intensity and fog abundance to obtain enhanced multispectral remote sensing images Fog intensity map and fog abundance map : ， ， In the above formula, Represents the reference image The bands that do not contain information on the red tide of Enteromorpha and Represents the reference image The number of bands that do not contain information on Enteromorpha red tides, Represents multispectral remote sensing images The bands that do not contain information on the red tide of Enteromorpha and Represents multispectral remote sensing images The number of bands that do not contain information on Enteromorpha red tide; To enhance multispectral remote sensing images Water body normalization index The average value of the pixels in the cloud area with a specified percentage before Fog intensity map Water body normalization index The average value of the pixels in the cloud area with a specified percentage before To enhance multispectral remote sensing images Water body normalization index The average value of the pixels in the cloud-free area before the specified percentage, Fog intensity map Water body normalization index The average value of pixels in the cloud-free area with a specified percentage; S3.2, calculate the multispectral image after removing cloud and fog interference according to the following formula : ， In the above formula, To enhance multispectral remote sensing images, is the fog abundance map, This is the fog intensity map.

6. A multispectral remote sensing enteromorpha red tide detection system, comprising a microprocessor and a memory connected to each other, characterized in that: The microprocessor is programmed or configured to execute the multispectral remote sensing enteromorpha red tide detection method according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program or instruction stored therein, characterized in that: The computer program or instruction is programmed or configured to execute the multi-spectral remote sensing enteromorpha red tide detection method according to any one of claims 1 to 5 through a processor.

8. A computer program product comprising a computer program or instructions, characterized in that The computer program or instruction is programmed or configured to execute the multi-spectral remote sensing enteromorpha red tide detection method according to any one of claims 1 to 5 through a processor.

Images