Method and system for recognizing large seaweed cultivation area based on otsu feature enhancement

Abstract

The application discloses a large-scale seaweed cultivation area recognition method and system based on Otsu feature enhancement. The method comprises the following steps: acquiring multispectral remote sensing image data of a target area and performing pretreatment; generating a spatial constraint binary mask by using an Otsu algorithm on the pretreated image; constructing a multi-dimensional feature space comprising spectral bands, normalized indexes and Otsu segmentation results; and inputting the multi-dimensional features into a classifier for classification. The Otsu binary result is reconstructed from terminal segmentation to spatial distribution features, which significantly improves the classification accuracy in multiple test scenarios, effectively reduces the area error of seaweed monitoring, overcomes the defects of feature solidification and noise sensitivity in traditional methods, and is suitable for near real-time monitoring requirements in various scale scenarios.

Description

Technical Field

[0001] This invention relates to the field of marine remote sensing information, specifically to a method for identifying large seaweed farming areas by fusing Otsu segmentation results with supervised classification. Background Technology

[0002] Accurate identification of large-scale seaweed farming areas is a core requirement for marine ecological monitoring and fisheries management. Existing remote sensing technologies generally face the bottleneck of insufficient feature representation capabilities in complex marine environments, mainly manifested in fluctuations in misclassification rates due to spectral confusion effects and spatial heterogeneity interference. Among traditional methods, binarization segmentation techniques based on the Otsu algorithm are widely used for coarse-grained separation of water bodies and land-based targets, but their application dimensions still have significant limitations:

[0003] Insufficient development of feature value: Current technology systems mostly use Otsu segmentation results as the terminal output, only for the division of land and sea boundaries, without deeply exploring its spatial distribution features and neighborhood correlation characteristics, resulting in the algorithm's potential in texture feature modeling and morphological optimization not being fully released.

[0004] Spatial information is missing: Existing feature construction methods often use a simple stacking of spectral indices and original bands, ignoring the topological properties such as gradient changes and spatial continuity implied in the Otsu segmentation results, making it difficult for classification models to capture the spatial distribution differences between algae and interference objects.

[0005] The core improvement of this invention lies in breaking through the traditional single application mode of the Otsu algorithm. By reconstructing the Otsu binarization result into a spatial feature input classification model, the synergistic enhancement of segmentation features and spectral features is achieved, thereby improving the recognition accuracy in complex scenes with lower computational cost. Summary of the Invention

[0006] The purpose of this invention is to provide a method for identifying large seaweed farming areas based on Otsu feature enhancement. By integrating Otsu segmentation results with multidimensional feature space collaborative modeling, this method solves the problems of insufficient spatial feature utilization and weak anti-interference ability in traditional methods, and achieves high-precision and high-efficiency dynamic monitoring of seaweed farming.

[0007] The specific technical solution adopted in this invention is as follows:

[0008] In a first aspect, the present invention provides a method for identifying large seaweed cultivation areas based on Otsu feature enhancement, which includes the following steps:

[0009] S1. Acquire multispectral remote sensing image data containing blue, green, red and near-infrared bands during the seaweed growth period in the target sea area, and perform image preprocessing operations to obtain preprocessed image data.

[0010] S2. Extract spectral features, exponential features, and spatial constraint features from the preprocessed image data to form multidimensional features; the spectral features consist of blue light band, green light band, red light band, and near-infrared band; the exponential features consist of at least one of normalized vegetation index and normalized water index; the spatial constraint features are a binary mask of the target sea area generated by the Otsu algorithm based on the green light band.

[0011] S3. Input the multidimensional features into the supervised training classification model. The classification model performs pattern recognition based on the multidimensional feature values ​​of each pixel location, predicts whether the pixel location belongs to the seaweed farming area, and finally outputs a spatial distribution map of the seaweed farming area.

[0012] As a preferred embodiment of the first aspect above, the spatial resolution of the multispectral remote sensing image data is not less than 10 meters, and it must include multispectral data in the blue, green, red and near-infrared bands.

[0013] As a preferred embodiment of the first aspect above, the image preprocessing operation includes one or more combinations of geometric correction, radiometric correction, atmospheric calibration, cloud masking, and land masking.

[0014] As a preferred embodiment of the first aspect above, the classification model employs a machine learning classifier, preferably a random forest classifier.

[0015] As a preferred embodiment of the first aspect, the classification model is pre-trained using labeled sample data before being used for actual identification; the labeled sample data is randomly collected from remote sensing images of seaweed farming areas that have been visually interpreted, and the visual interpretation results are used as ground truth labels.

[0016] As a preferred embodiment of the first aspect, the parameter settings of the classification model during supervised training are dynamically adjusted through a preset parameter combination. The adjusted parameters include a classifier type selection strategy, a model training iteration control method, and a precision optimization mechanism, selecting the optimal parameter combination that achieves the best classification performance.

[0017] Secondly, the present invention provides a large-scale seaweed cultivation area identification system based on Otsu feature enhancement, comprising:

[0018] The image preprocessing module is used to acquire multispectral remote sensing image data containing blue, green, red and near-infrared bands during the algae growth period of the target sea area, and to perform image preprocessing operations to obtain preprocessed image data.

[0019] The feature extraction module is used to extract spectral features, exponential features, and spatial constraint features from the preprocessed image data to form multidimensional features. The spectral features consist of blue light band, green light band, red light band, and near-infrared band. The exponential features consist of at least one of normalized vegetation index and normalized water index. The spatial constraint features are a binary mask of the target sea area generated by the Otsu algorithm based on the green light band.

[0020] The pattern recognition module is used to input the multidimensional features into a supervised training classification model. The classification model performs pattern recognition based on the multidimensional feature values ​​of each pixel location, predicts whether the pixel location belongs to the seaweed farming area, and finally outputs a spatial distribution map of the seaweed farming area.

[0021] Thirdly, the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, can realize the method for identifying large seaweed farming areas based on Otsu feature enhancement as described in any of the first aspects above.

[0022] Fourthly, the present invention provides a computer-readable storage medium, characterized in that the storage medium stores a computer program, which, when executed by a processor, enables the identification method for large seaweed farming areas based on Otsu feature enhancement as described in any of the first aspects above.

[0023] Fifthly, the present invention provides a computer electronic device, characterized in that it includes a memory and a processor;

[0024] The memory is used to store computer programs;

[0025] The processor is configured to, when executing the computer program, implement the method for identifying large seaweed farming areas based on Otsu feature enhancement as described in any of the first aspects above.

[0026] Compared with the prior art, the present invention has the following advantages:

[0027] 1. This invention overcomes the technical limitations of traditional methods that separate segmentation and classification by constructing a cascaded processing architecture of "Otsu spatial constraint generation → multidimensional feature classification". The Otsu segmentation result is dynamically reconstructed into a spatial constraint feature input classification model, effectively suppressing the spectral confusion effect of background interference (such as suspended matter and aquaculture facilities).

[0028] 2. This invention innovatively integrates Otsu binary masks with multispectral features and vegetation indices in a spatial-spectral dimension to form an environmentally adaptable feature expression system. This multi-source feature synergy mechanism has the following technical advantages:

[0029] Enhance the expression of algal morphological features by leveraging spatial constraint characteristics to reduce the false negative rate of fragmented small targets;

[0030] Dynamically balancing spectral sensitivity and spatial continuity improves classification stability in complex scenarios such as solar flares and thin cloud interference.

[0031] 3. This invention has the advantages of accurate results and good versatility. It supports multispectral image input with resolutions from 10 meters to sub-meters and is compatible with mainstream satellite data such as Sentinel-2 and Gaofen series. In addition to seaweed farming monitoring, after feature adaptation and adjustment, it can be transferred to monitoring scenarios of blue carbon ecosystems such as mangroves, salt marshes, and seagrass beds, providing core technical support for coastal environmental resource management. Attached Figure Description

[0032] Figure 1 A schematic diagram illustrating the steps of a method for identifying large seaweed farming areas based on Otsu feature enhancement;

[0033] Figure 2 This is a schematic diagram of the complete process of training and verification of the method of the present invention;

[0034] Figure 3 A schematic diagram of a module for a large-scale seaweed farming area identification system based on Otsu feature enhancement;

[0035] Figure 4 This is a schematic diagram of the structure of a computer electronic device;

[0036] Figure 5 This is a detailed flowchart illustrating an embodiment of the present invention;

[0037] Figure 6 The images show the visual interpretation results of the seaweed cultivation area, the classification results of the experimental group, and the classification results of the control group in an embodiment of the present invention. Detailed Implementation

[0038] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of the present invention. However, the present invention can be practiced in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below. Technical features in various embodiments of the present invention can be combined accordingly without mutual conflict.

[0039] like Figure 1 As shown, in a preferred embodiment of the present invention, a method for identifying large seaweed farming areas based on Otsu feature enhancement is provided, which includes the following steps:

[0040] S1. Acquire multispectral remote sensing image data containing blue, green, red and near-infrared bands during the algae growth period of the target sea area, and perform image preprocessing operations to obtain preprocessed image data.

[0041] It should be noted that due to the large amount of multispectral remote sensing imagery, it is necessary to pre-screen the data for remote sensing classification and interpretation. The image selection follows these principles: the imagery time should coincide with the algae growth period, i.e., from December to April of the following year. During this period, algae are growing vigorously, making them more identifiable and beneficial for subsequent remote sensing classification and interpretation.

[0042] In embodiments of the present invention, the spatial resolution of the aforementioned multispectral remote sensing image data is no less than 10 meters, and it must include multispectral data in the blue, green, red, and near-infrared bands. Therefore, the present invention supports multispectral image input with resolutions from 10 meters to sub-meters, and can be adapted to mainstream satellite data such as Sentinel-2 and Gaofen series.

[0043] Furthermore, the image preprocessing operations employed in this invention include one or more combinations of geometric correction, radiometric correction, atmospheric calibration, cloud masking, and land masking. Land masking is used to remove land areas from the image, reduce the influence of irrelevant features, and narrow the research scope; while cloud masking is used to remove cloud interference. The specific image preprocessing operation needs to be selected based on the actual remote sensing image quality.

[0044] S2. Extract spectral features, exponential features, and spatial constraint features from the preprocessed image data to form multidimensional features; the spectral features consist of blue light band, green light band, red light band, and near-infrared band; the exponential features consist of at least one of normalized vegetation index and normalized water index; the spatial constraint features are a binary mask of the target sea area generated by the Otsu algorithm based on the green light band.

[0045] The key to this invention lies in adaptive thresholding of preprocessed images based on the Otsu algorithm to generate a binary mask representing the potential distribution of algae. The Otsu algorithm, also known as the maximum inter-class variance method (Otsu algorithm), was proposed by Japanese scholar Nobuyuki Otsu in 1979. This algorithm is mainly used for automatic threshold selection in image processing, especially in image binarization. The core idea of ​​the Otsu algorithm is to segment the image into foreground and background parts by traversing all possible thresholds, maximizing the inter-class variance between these two parts. The specific implementation of the Otsu algorithm is prior art and will not be elaborated upon in this invention. This invention extracts the binary mask of the target region from the green light band using the Otsu algorithm, and can dynamically determine the boundary between algae-rich and non-algae-rich areas through grayscale statistics, providing a spatial constraint benchmark for subsequent feature space construction.

[0046] S3. Input the multidimensional features into a supervised training classification model. The classification model performs pattern recognition based on the multidimensional feature values ​​of each pixel location to predict whether the pixel location belongs to the seaweed farming area. Finally, it outputs a spatial distribution map of the seaweed farming area.

[0047] It should be noted that the classification model in this invention can theoretically be implemented using any model capable of pattern recognition and classification. Preferably, a machine learning classifier with high-dimensional data processing capabilities is used, such as logistic regression, support vector machines, random forests, etc. In the embodiments of this invention, a random forest algorithm is preferably used to construct the classifier. The parameter optimization mechanism can be set to dynamically adjust the model parameter combination through preset iterations and accuracy evaluation metrics.

[0048] It should be noted that steps S1 to S3 above describe the identification process of large-scale seaweed farming areas in practical applications. However, those skilled in the art should understand that this classification model undergoes supervised training using labeled sample data before being used for actual identification. The labeled sample data used in this invention can be randomly collected from remote sensing images of seaweed farming areas that have undergone visual interpretation, and each sample corresponds to one pixel. The visual interpretation result at that pixel location can be used as the ground truth label. After the model completes supervised training, it needs to undergo accuracy verification. Only after meeting the detection accuracy requirements can it be used for actual classification. Figure 2 As shown, the specific process of training and validating the above classification model is illustrated.

[0049] In addition, different classification models need to be supervised training according to their respective training requirements, and the parameter settings of the classification model during supervised training are dynamically adjusted through preset parameter combinations. The adjusted parameters include classifier type selection strategy, model training iteration control method and accuracy optimization mechanism, to select the best parameter combination that can achieve the best classification performance.

[0050] It should be noted that the method steps shown in S1 to S3 above can essentially be implemented in the form of computer programs or functional modules.

[0051] Therefore, based on the same inventive concept, such as Figure 3 As shown, the present invention also provides a large-scale seaweed farming area identification system based on Otsu feature enhancement, corresponding to the large-scale seaweed farming area identification method based on Otsu feature enhancement provided in the above embodiments, which includes the following functional modules:

[0052] The image preprocessing module is used to acquire multispectral remote sensing image data containing blue, green, red and near-infrared bands during the algae growth period of the target sea area, and to perform image preprocessing operations to obtain preprocessed image data.

[0053] The feature extraction module is used to extract spectral features, exponential features, and spatial constraint features from the preprocessed image data to form multidimensional features. The spectral features consist of blue light band, green light band, red light band, and near-infrared band. The exponential features consist of at least one of normalized vegetation index and normalized water index. The spatial constraint features are a binary mask of the target sea area generated by the Otsu algorithm based on the green light band.

[0054] The pattern recognition module is used to input the multidimensional features into a supervised training classification model. The classification model performs pattern recognition based on the multidimensional feature values ​​of each pixel location, predicts whether the pixel location belongs to the seaweed farming area, and finally outputs a spatial distribution map of the seaweed farming area.

[0055] Furthermore, based on the same inventive concept, such as Figure 4 As shown, the present invention also provides a computer electronic device corresponding to the Otsu feature-enhanced method for identifying large seaweed farming areas provided in the above embodiments, which includes a memory and a processor;

[0056] The memory is used to store computer programs;

[0057] The processor is configured to implement the large-scale seaweed farming area identification method based on Otsu feature enhancement as described above when executing the computer program;

[0058] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0059] Therefore, based on the same inventive concept, the present invention provides a computer-readable storage medium corresponding to the method for identifying large seaweed farming areas based on Otsu feature enhancement. The storage medium stores a computer program, which, when executed by a processor, can realize the method for identifying large seaweed farming areas based on Otsu feature enhancement as described above.

[0060] Therefore, based on the same inventive concept, the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, can realize the large-scale seaweed farming area identification method based on Otsu feature enhancement as described above.

[0061] Specifically, in the computer-readable storage medium of the above three embodiments, the stored computer program is executed by a processor, which can perform the aforementioned steps S1 to S3.

[0062] It is understood that the aforementioned storage media may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Furthermore, the storage media may also be various media capable of storing program code, such as USB flash drives, external hard drives, magnetic disks, or optical discs.

[0063] It is understood that the processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0064] It should also be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here. In the embodiments provided in this application, the division of steps or modules in the system and method is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple modules or steps may be combined or integrated together, and a module or step may also be split.

[0065] The present invention will further demonstrate the detailed implementation process and technical effects of the Otsu feature-enhanced method for identifying large seaweed farming areas shown in steps S1 to S3 on a specific dataset through a specific embodiment, so as to facilitate understanding of the essence of the present invention.

[0066] Example

[0067] like Figure 5As shown, this embodiment refers to the classification method for large-scale seaweed farming areas based on Otsu feature enhancement described in S1-S3 above, and specifically carried out the model construction, training, and verification process. To systematically verify the effect of Otsu feature enhancement on improving the classification accuracy of seaweed farming areas, this embodiment selected three typical experimental areas in large-scale seaweed farming areas to conduct experiments. Two experimental groups were set up: one with spatial constraint features (experimental group) and one without spatial constraint features (control group) to classify and identify large-scale seaweed farming areas. The technical implementation process is described in detail below with reference to the embodiment:

[0068] Step (1): Acquire and filter Sentinel-2 multispectral remote sensing image data during the algae growth period of the target sea area, and perform image cropping and cloud masking operations to obtain preprocessed image data.

[0069] This embodiment selects three typical experimental areas in the sea off Jeollanam-do, South Korea, as the target sea areas to be identified. Using Google Earth Engine, Sentinel-2MSI Level-2A data (containing blue, green, red, and near-infrared bands) is retrieved. Images meeting the criteria are selected based on boundaries, time (must be within the seaweed growth period, i.e., December to April of the following year), and cloud cover. The images are then cropped according to the three experimental areas. Since the images selected in this embodiment are free of cloud cover, cloud masking was not performed during image preprocessing. However, if thin cloud interference exists, cloud pixels are marked using the QA60 band and removed to obtain the preprocessed image data for each experimental area.

[0070] Step (2): Select green band images from the preprocessed image data of each experimental area, input them into the Otsu algorithm, dynamically calculate the optimal segmentation threshold, and generate a binary mask for each experimental area. In the binary mask, potential algae areas are marked as 1, and background areas are marked as 0.

[0071] Step (3): Construction of multidimensional features and design of comparative experiments

[0072] a) The experimental design is as follows:

[0073] The experimental group needs to construct a multidimensional feature space for the experimental region, including spectral features, exponential features, and spatial constraint features, where:

[0074] The spectral characteristics consist of blue light band, green light band, red light band, and near-infrared light band;

[0075] The index characteristics are a combination of the normalized vegetation index and the normalized water index;

[0076] The spatial constraint feature is the binary mask generated in step (2).

[0077] b) The control group was designed as follows:

[0078] The control group does not incorporate Otsu spatial constraint features, meaning it only includes spectral and exponential features.

[0079] All features in both the experimental and control groups were standardized before being input into the classification model.

[0080] S3. Input the multidimensional features into the supervised training classification model. The classification model performs pattern recognition based on the multidimensional feature values ​​of each pixel location, predicts whether the pixel location belongs to the seaweed farming area, and finally outputs a spatial distribution map of the seaweed farming area.

[0081] Step (4): Visually interpret the high-resolution reference image to determine the actual seaweed cultivation area in each experimental zone. Then, uniformly select sample points in the seaweed area and background area in each experimental zone to construct a sample dataset. Each sample point corresponds to one pixel. Note that since the feature spaces in the experimental group and the control group are different, corresponding sample inputs need to be constructed separately in this embodiment. The sample input for each sample in the experimental group is spectral features, exponential features, and spatial constraint features, while the sample input for each sample in the control group is spectral features and exponential features. Each sample is labeled with 0-1, where the seaweed area is labeled as 1 and the background area is labeled as 0. The sample dataset is divided into a training set and a validation set according to a preset ratio. Note that the collected sample distribution covers different growth stages and typical interference scenarios.

[0082] Different machine learning models were trained using supervised classification, and their pattern recognition performance was tested. In this embodiment, after comparison, a random forest classifier was ultimately selected to construct a model for recognizing large-scale seaweed farming areas. Random forest was used for supervised training and classification in both the experimental and control groups. Cross-validation was used to determine the order of magnitude of the decision trees, and parameter combinations were dynamically configured based on the criterion of optimal accuracy.

[0083] (5) After training, the trained random forest classifier was used on the validation set to output the identification results of the three regions corresponding to the large seaweed farming areas of the experimental group and the control group, respectively. The three farming areas were visually interpreted as a reference benchmark for visual comparison. The comparison results are as follows: Figure 6 As shown in the figure. When comparing the classification results of the experimental group and the control group, the validation metrics included the Kappa coefficient, overall accuracy, and consistency coefficient. The results showed that the experimental group exhibited a significant advantage in all experimental areas, with a classification accuracy improvement reaching the observable level. Simultaneously, in typical experimental areas, the experimental group effectively suppressed background misclassification through spatial constraint features, significantly reducing area error compared to the control group.

[0084] In summary, this invention reconstructs the Otsu binarization results from terminal segmentation into spatial distribution features, significantly improving classification accuracy in multiple experimental scenarios, effectively reducing area error in seaweed monitoring, overcoming the defects of feature solidification and noise sensitivity in traditional methods, and is suitable for near real-time monitoring needs in various scale scenarios.

[0085] The embodiments described above are merely some preferred implementations of the present invention and are not intended to limit the invention. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention. Therefore, all technical solutions obtained through equivalent substitution or transformation fall within the protection scope of the present invention.

Claims

1. A method for identifying large-scale seaweed cultivation areas based on Otsu feature enhancement, characterized in that, Includes the following steps: S1. Acquire multispectral remote sensing image data containing blue, green, red and near-infrared bands during the seaweed growth period in the target sea area, and perform image preprocessing operations to obtain preprocessed image data. S2. Extract spectral features, exponential features, and spatial constraint features from the preprocessed image data to form multidimensional features; the spectral features consist of blue light band, green light band, red light band, and near-infrared band; the exponential features consist of at least one of normalized vegetation index and normalized water index; the spatial constraint features are a binary mask of the target sea area generated by the Otsu algorithm based on the green light band. S3. Input the multidimensional features into a supervised training classification model. The classification model performs pattern recognition based on the multidimensional feature values ​​of each pixel location to predict whether the pixel location belongs to the seaweed farming area. Finally, it outputs a spatial distribution map of the seaweed farming area.

2. The method for identifying large seaweed farming areas based on Otsu feature enhancement according to claim 1, characterized in that, The spatial resolution of the multispectral remote sensing image data shall not be less than 10 meters, and it shall include multispectral data in the blue, green, red and near-infrared bands.

3. The method for identifying large seaweed farming areas based on Otsu feature enhancement according to claim 1, characterized in that, The image preprocessing operations include one or more combinations of geometric correction, radiometric correction, atmospheric calibration, cloud masking, and land masking.

4. The method for identifying large seaweed farming areas based on Otsu feature enhancement according to claim 1, characterized in that, The classification model employs a machine learning classifier, preferably a random forest classifier.

5. The method for identifying large seaweed farming areas based on Otsu feature enhancement according to claim 1, characterized in that, Before being used for actual identification, the classification model is trained in advance using labeled sample data. The labeled sample data is randomly collected from remote sensing images of seaweed farming areas that have been visually interpreted, and the visual interpretation results are used as ground truth labels.

6. The method for identifying large seaweed farming areas based on Otsu feature enhancement according to claim 1, characterized in that, The parameters of the classification model during supervised training are dynamically adjusted through preset parameter combinations. The adjusted parameters include classifier type selection strategy, model training iteration control method and accuracy optimization mechanism, to select the best parameter combination that can achieve the best classification performance.

7. A large-scale seaweed farming area identification system based on Otsu feature enhancement, characterized in that, include: The image preprocessing module is used to acquire multispectral remote sensing image data containing blue, green, red and near-infrared bands during the algae growth period of the target sea area, and to perform image preprocessing operations to obtain preprocessed image data. The feature extraction module is used to extract spectral features, exponential features, and spatial constraint features from the preprocessed image data to form multidimensional features. The spectral features consist of blue light band, green light band, red light band, and near-infrared band. The exponential features consist of at least one of normalized vegetation index and normalized water index. The spatial constraint features are a binary mask of the target sea area generated by the Otsu algorithm based on the green light band. The pattern recognition module is used to input the multidimensional features into a supervised training classification model. The classification model performs pattern recognition based on the multidimensional feature values ​​of each pixel location, predicts whether the pixel location belongs to the seaweed farming area, and finally outputs a spatial distribution map of the seaweed farming area.

8. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it can realize the method for identifying large seaweed farming areas based on Otsu feature enhancement as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method for identifying large seaweed farming areas based on Otsu feature enhancement as described in any one of claims 1 to 6.

10. A computer electronic device, characterized in that, Including memory and processor; The memory is used to store computer programs; The processor is configured to, when executing the computer program, implement the method for identifying large seaweed farming areas based on Otsu feature enhancement as described in any one of claims 1 to 6.

Images