A cyanobacteria region extraction method, system and product in an optical remote sensing image

Abstract

This invention relates to a method, system, and product for extracting cyanobacteria regions from optical remote sensing images. The method includes: acquiring optical remote sensing images; constructing different types of background noise extraction index algorithms; the types of background noise include terrestrial green vegetation, water bodies, exposed land from roads and buildings, and remaining vegetation in water other than cyanobacteria; normalizing the background noise extraction index algorithms to generate normalized background noise extraction index algorithms; constructing a noise suppression and separation function based on the normalized background noise extraction index algorithms, and suppressing the background noise according to the noise suppression and separation function to separate cyanobacteria and the background noise, generating suppression and separation results; and extracting cyanobacteria regions from the optical remote sensing images based on the suppression and separation results. This invention can improve the accuracy of cyanobacteria region identification.

Description

Technical Field

[0001] This invention relates to the field of low-altitude remote sensing, and in particular to a method, system, and product for extracting cyanobacteria regions from optical remote sensing images. Background Technology

[0002] With the development of society and industry, water pollution has intensified, with varying degrees of pollution occurring throughout the country. Eutrophication, in particular, is a major problem facing China. Eutrophication is mainly manifested in the massive proliferation of algae, leading to water quality deterioration, damage to aquatic ecosystems, and threats to the drinking water safety of surrounding areas. Therefore, rapidly and comprehensively understanding the areas and distribution ranges of cyanobacterial blooms is of great significance for maintaining the ecological balance of aquatic bodies.

[0003] In recent years, with the rapid development of UAV technology, UAV low-altitude remote sensing monitoring technology has gradually matured and has become an important means of rapidly acquiring low-altitude remote sensing data. UAV low-altitude remote sensing systems have unique advantages such as mobility, speed, and economy, and are increasingly being widely used in the field of cyanobacteria monitoring using low-altitude optical remote sensing images. Extracting cyanobacteria from low-altitude remote sensing data can quickly locate information such as the timing and distribution of cyanobacterial blooms, providing a rapid, intuitive, and accurate data foundation for cyanobacterial bloom monitoring.

[0004] Currently, the extraction of cyanobacteria from low-altitude optical remote sensing imagery mainly employs a method of combining various bands to preprocess the acquired data for dimensionality reduction before analysis and extraction. This combination method uses the reflectance of ground objects within two or more band ranges to perform calculations, thereby enhancing a specific characteristic or detail. Current cyanobacteria extraction based on low-altitude optical remote sensing imagery primarily utilizes the transformation of red-green-blue color images. By calculating and comparing different combinations of vegetation indices based on the reflectance of ground objects within two or more band ranges, the most suitable vegetation index is selected to achieve cyanobacteria extraction. Vegetation indices based on optical remote sensing imagery mainly include the excess green (EXG), normalized green-red difference index (NGRDI), red-green ratio index (RGRI), visible-band different vegetation index (VDVI), normalized green-blue difference index (NGBDI), and improved indices based on these indices. These index algorithms can all achieve extraction of cyanobacteria data to a certain extent.

[0005] Currently, when directly using these indices or improved indices to identify and extract cyanobacteria, it is impossible to achieve complete separation of cyanobacteria from other objects (vegetation, water bodies, and other aquatic vegetation besides cyanobacteria). Regardless of the range of the extraction threshold, it can only be approximately distinguished and extracted, and cannot achieve complete separation of cyanobacteria from background noise (areas other than cyanobacteria targets in the image).

[0006] To extract cyanobacteria information from low-altitude remote sensing images, it is necessary to first analyze the spectral characteristics between cyanobacteria and non-cyanobacteria, calculate and observe the differences in reflectance between different bands, and then construct vegetation indices to extract cyanobacteria data.

[0007] Currently, vegetation indices based on visible light remote sensing images mainly include the green index EXG, the normalized red-green difference index NGRDI, the red-green ratio index, the visible light band difference vegetation index, the normalized blue-green difference index, and other index algorithms that are improved based on these indices. These index algorithms can all extract cyanobacteria data from low-altitude optical remote sensing images to a certain extent.

[0008] For the extraction of cyanobacteria from low-altitude remote sensing images, the main approach is to process the remote sensing images using a constructed exponential algorithm. Then, based on the image processing results, a threshold range selection test is conducted (the specific selection test method varies among different researchers). Finally, a more suitable threshold range is selected to achieve the extraction and identification of cyanobacteria.

[0009] Each index algorithm and band has its own advantages and disadvantages in cyanobacteria identification and extraction. Some can effectively distinguish cyanobacteria from vegetation, some can distinguish cyanobacteria from water bodies, and some can distinguish cyanobacteria from roads and buildings. However, none of the algorithms can effectively distinguish cyanobacteria from all other noise, and cannot effectively balance the completeness and accuracy of identification.

[0010] Currently, relying solely on these index algorithms and threshold range adjustments to extract cyanobacteria from low-altitude remote sensing images often generates significant background noise, impacting the accuracy and reliability of cyanobacteria identification and extraction. While narrowing the selected threshold range can suppress background noise to some extent, making cyanobacteria identification clearer and more accurate, it can lead to incomplete identification, particularly in areas with low cyanobacteria density, resulting in missed areas and reduced extraction completeness. Increasing the selected threshold range improves the completeness of cyanobacteria identification to some extent, but simultaneously amplifies background noise, sometimes leading to the erroneous extraction of large areas of background noise as cyanobacteria, or even indistinguishability between background noise and cyanobacteria, thus compromising the accuracy of cyanobacteria identification and extraction. Summary of the Invention

[0011] The purpose of this invention is to provide a method, system, and product for extracting cyanobacteria regions from optical remote sensing images, in order to solve the problems of being unable to distinguish between background noise and cyanobacteria, and the low accuracy of identifying extracted cyanobacteria.

[0012] To achieve the above objectives, the present invention provides the following solution:

[0013] A method for extracting cyanobacteria regions from optical remote sensing images, comprising:

[0014] Acquire optical remote sensing images;

[0015] Construct different types of background noise extraction index algorithms; the types of background noise include terrestrial green vegetation, water bodies, exposed land of roads and buildings, and remaining vegetation in water except for blue-green algae;

[0016] The background noise extraction index algorithm is normalized to generate a normalized background noise extraction index algorithm.

[0017] A noise suppression and separation function is constructed based on the normalized background noise extraction index algorithm, and the background noise is suppressed according to the noise suppression and separation function to separate the cyanobacteria and the background noise, generating suppression and separation results.

[0018] Based on the suppression and separation results, the cyanobacteria region in the optical remote sensing image is extracted.

[0019] Optionally, the algorithm for extracting the index of terrestrial green vegetation is as follows:

[0020]

[0021] in, The extraction index for terrestrial green vegetation; This represents the reflectivity of the blue band.

[0022] Optionally, the extraction index algorithm for the water body is as follows:

[0023]

[0024] in, The extraction index of water bodies; The reflectivity is for the green band; This represents the reflectivity of the red band.

[0025] Optionally, the algorithm for extracting the index of exposed land for road construction is as follows:

[0026]

[0027] in, Extraction index for exposed land due to road construction; The green index.

[0028] Optionally, the algorithm for extracting the index of the remaining vegetation in the water, excluding cyanobacteria, is as follows:

[0029]

[0030] in, The extraction index is the remaining vegetation in the water excluding cyanobacteria. This is the red-green ratio index.

[0031] Optionally, the algorithm for extracting the background noise index after normalization is as follows:

[0032]

[0033] in, The index S is extracted from the normalized background noise. n Extraction index of different types of background noise; It is the first normalized variable; b n The second normalized variable is n, which takes values ​​from 1 to 4.

[0034] Optionally, the noise suppression separation function is:

[0035]

[0036] Among them, among them, The noise separation index is calculated after noise suppression. n The suppression and separation factors for different types of background noise; n K is the distinguishing variable for different types of background noise; K is a constant.

[0037] A system for extracting cyanobacteria regions from optical remote sensing images includes:

[0038] Optical remote sensing image acquisition module, used to acquire optical remote sensing images;

[0039] The background noise extraction index algorithm construction module is used to construct different types of background noise extraction index algorithms; the types of background noise include terrestrial green vegetation, water bodies, exposed land of roads and buildings, and remaining vegetation in water except for blue-green algae;

[0040] The normalization processing module is used to normalize the background noise extraction index algorithm to generate a normalized background noise extraction index algorithm.

[0041] The noise suppression and separation function construction module is used to construct a noise suppression and separation function based on the normalized background noise extraction index algorithm, and to suppress the background noise based on the noise suppression and separation function, separate the cyanobacteria and the background noise, and generate suppression and separation results.

[0042] The cyanobacteria region extraction module is used to extract cyanobacteria regions from the optical remote sensing image based on the suppression and separation results.

[0043] An electronic device includes a memory and a processor, the memory storing a computer program, and the processor running the computer program to enable the electronic device to perform the above-described method for extracting cyanobacteria regions from optical remote sensing images.

[0044] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for extracting cyanobacteria regions from optical remote sensing images.

[0045] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects: The present invention provides a method, system, and product for extracting cyanobacteria regions from optical remote sensing images. Taking cyanobacteria as the target, other content in the image is regarded as background noise. By constructing different types of background noise extraction index algorithms and using background noise suppression technology, the background noise is effectively suppressed, so that cyanobacteria in optical remote sensing images are completely separated from other background noise, ensuring the effective extraction of cyanobacteria in low-altitude remote sensing images. Compared with traditional calculation methods, it can not only guarantee the integrity of cyanobacteria extraction, but also greatly improve the accuracy of cyanobacteria identification. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a flowchart of the method for extracting cyanobacteria regions from optical remote sensing images provided by the present invention.

[0048] Figure 2 A schematic diagram of the noise suppression separation function;

[0049] Figure 3 This is an optical orthophoto image of the study area of ​​a reservoir in 2018.

[0050] Figure 4 This is a RGB three-channel separation index map of a reservoir in a study area in 2018; among which, Figure 4(a) is the separation index chart of the red channel. Figure 4 (b) is a graph showing the separation index of the green channel. Figure 4 (c) is the blue channel separation index chart;

[0051] Figure 5 This is a graph showing the results of vegetation index calculations, where... Figure 5 (a) is a graph showing the EXG calculation results. Figure 5 (b) is a graph showing the NGRDI calculation results. Figure 5 (c) is a graph showing the RGRI calculation results. Figure 5 (d) is a graph showing the VDVI calculation results. Figure 5 (e) is a graph showing the BVN calculation results;

[0052] Figure 6 The image shows the effect of cyanobacteria identification. Figure 6 (a) is a map of the cyanobacteria region. Figure 6 (b) is a diagram showing the effect of cyanobacteria identification based on red band reflectance. Figure 6 (c) is a diagram showing the effect of cyanobacteria identification based on green band reflectance. Figure 6 (d) shows the effect of cyanobacteria identification based on blue band reflectance. Figure 6 (e) is a diagram showing the results of EXG-based cyanobacteria recognition. Figure 6 (f) shows the effect of cyanobacteria recognition based on NGRDI. Figure 6 (g) shows the effect of cyanobacteria recognition based on RGRI. Figure 6 (h) shows the effect of VDVI-based cyanobacteria identification. Figure 6 (i) is a diagram showing the effect of cyanobacteria identification based on BVN;

[0053] Figure 7 This is an image showing the effect of suppressing background noise on green vegetation on land.

[0054] Figure 8 Map showing the road and building interference index;

[0055] Figure 9 To remove the water disturbance index map;

[0056] Figure 10 To remove the interference index of aquatic plants such as water chestnuts;

[0057] Figure 11 Index map for cyanobacteria identification to remove background noise interference;

[0058] Figure 12 This diagram illustrates the verification of the accuracy and completeness of cyanobacteria identification. Detailed Implementation

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] The purpose of this invention is to provide a method, system, and product for extracting cyanobacteria regions from optical remote sensing images, so as to improve the accuracy of cyanobacteria region identification.

[0061] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0062] Example 1

[0063] Figure 1 The flowchart of the method for extracting cyanobacteria regions from optical remote sensing images provided by the present invention is as follows: Figure 1 As shown, a method for extracting cyanobacteria regions from optical remote sensing images includes:

[0064] Step 101: Acquire optical remote sensing images.

[0065] In practical applications, UAV low-altitude remote sensing imagery technology is used to acquire image data, obtain optical remote sensing images, and process these images to achieve image stitching and synthesis. This processing includes the separation and calculation of the RGB three channels of the image (i.e., calculating the reflectance values ​​of ground objects in the red, green, and blue bands). Later, the different spectral characteristics of different objects are utilized to facilitate the segmentation and calculation of background noise.

[0066] Step 102: Construct different types of background noise extraction index algorithms; the types of background noise include terrestrial green vegetation, water bodies, exposed land of roads and buildings, and remaining vegetation in water except for blue-green algae.

[0067] In practical applications, the construction requirements for different types of background noise extraction index algorithms are as follows:

[0068] Requirement 1: After calculation using this index algorithm, by selecting an appropriate threshold range, background noise (such as water bodies) can be completely and accurately extracted (whether other noises are extracted in whole or in part at the same time is not required; for example, when extracting water bodies, roads and other noises are also extracted, which is also allowed).

[0069] Requirement 2: This index algorithm cannot extract cyanobacteria simultaneously when extracting background noise (such as water bodies). That is, after the application of this index algorithm, the threshold ranges of background noise (such as water bodies) and cyanobacteria must be clearly distinguishable and cannot overlap (for example, after the calculation by this algorithm, the threshold range of water bodies is 0.5-0.7, and the threshold of cyanobacteria should be >0.7 or <0.5).

[0070] Requirement 3: If a certain exponent algorithm does not meet requirements 1 and 2, modify the exponent algorithm until requirements 1 and 2 are met.

[0071] Background noise classification is achieved during the construction of different types of background noise extraction index algorithms. For example, when extracting roads, buildings and bare soil are also fully extracted, while water bodies are partially extracted. In this case, roads, buildings, and bare soil can be classified into one category, and water bodies into another. This process continues until all background noise in the low-altitude remote sensing image is effectively extracted and statistically classified. This invention classifies background noise into four main categories: terrestrial green vegetation, water bodies, roads, buildings, and exposed land, and remaining vegetation in water except for cyanobacteria; remaining vegetation in water except for cyanobacteria includes water chestnuts and lotus leaves.

[0072] The formulas for the exponential algorithms for extracting, optimizing, or constructing four main categories of background noise are summarized as follows:

[0073] Background noise and green vegetation extraction on land were performed using the BLUE band, and the exponential algorithm formula is as follows:

[0074] (1)

[0075] Background noise in water bodies is extracted using a constructed exponential algorithm, the formula of which is as follows:

[0076] (2)

[0077] Background noise, road and building bare soil extraction uses the green index EXG (excess green), and the index algorithm formula is as follows:

[0078] (3)

[0079] Background noise was extracted from other vegetation in the water besides cyanobacteria, such as water chestnuts and lotus leaves, using the Green Ratio Index (RGRI). The index algorithm formula is as follows:

[0080] (4)

[0081] in, The extraction index for terrestrial green vegetation; The extraction index of water bodies; Extraction index for exposed land due to road construction; ρ represents the extraction index of the remaining vegetation in the water excluding cyanobacteria. red ρ green ρ blue These represent the reflectance of the red, green, and blue bands, respectively (i.e., the RGB three-channel separation results in step 101).

[0082] Step 103: Normalize the background noise extraction index algorithm to generate a normalized background noise extraction index algorithm.

[0083] In practical applications, by adjusting the value of the normalization variable according to the threshold range of the noise, the extracted background noise value after normalization is controlled below 0, generally concentrated around -1, while the cyanobacteria value is above 0. The normalization formula is as follows:

[0084] (5)

[0085] in, The index S is extracted from the normalized background noise. n Extraction index of different types of background noise; It is the first normalized variable; b n The second normalized variable is n, which takes values ​​from 1 to 4.

[0086] Step 104: Construct a noise suppression and separation function based on the normalized background noise extraction index algorithm, and suppress the background noise according to the noise suppression and separation function to separate the cyanobacteria and the background noise, generating suppression and separation results.

[0087] In practical applications, to ensure more thorough suppression of certain noises and highlight the cyanobacteria target data, a noise suppression separation function is used to separate and suppress background noise from cyanobacteria. The calculation formula is as follows:

[0088] (6)

[0089] In the formula: A n Normalized values The noise separation index value obtained after noise suppression calculation (n takes 1~4). n The suppression and separation factor for different types of background noise is set based on the non-overlapping portion of the normalized noise and cyanobacteria threshold ranges (e.g., if the normalized noise range is (-1 to -0.2) and the cyanobacteria threshold range is (0.3 to 1), then... It can take any constant from -0.2 to 0.3. n To distinguish different types of background noise, based on The range size can be set, and generally, the larger the value (greater than 30), the better, as a larger value is more conducive to separating noise from cyanobacteria. However, an excessively large value will greatly increase the amount of computation. It is generally advisable to set it between 30 and 60. K is a constant with a value of 1.57.

[0090] The value is 1. When the value of K is 51 and the value of K is 1.57:

[0091] (7)

[0092] Figure 2 A schematic diagram of the noise suppression separation function, as shown below. Figure 2 As shown, background noise in An is assigned a value of 0 by noise suppression, and other values ​​are assigned between 0 and 1. According to the characteristics of the noise suppression function, the amount of data between 0 and 1 is very small, basically around 0 and 1, and the cyanobacteria data is assigned an approximate value of 1.

[0093] Step 105: Extract the cyanobacteria region from the optical remote sensing image based on the suppression and separation results.

[0094] In practical applications, By superimposing and averaging, the value of cyanobacteria is approximately 1, while other noise areas are reduced to 75% or less of their original value, thus achieving separation between cyanobacteria and background noise and enabling precise extraction of the cyanobacteria region.

[0095] The specific formula is as follows:

[0096] Algorithm for suppressing background noise in cyanobacteria extraction:

[0097] (8)

[0098] In the formula: The blue-green algae extraction index, S i An exponential algorithm is used to extract the exponent for each type of background noise. W i Weights are assigned to each type of noise (adjusted based on the actual proportion of noise). a i , b i Let i be the normalization variable, and let i be the loop variable, with a value range of (1-n). Different types of noise suppression separation factors. The variable distinguishes different types of noise, where n is the number of noise categories (in this invention, the number of noise categories is 4).

[0099] By applying the cyanobacteria extraction background noise suppression algorithm invented in this study, background noise in low-altitude remote sensing images can be effectively suppressed, thereby enabling the extraction of cyanobacteria data from the images. For example, the weight W... i If all values ​​are set to 1, the threshold range for cyanobacteria identification is (0.76-1), with the majority of values ​​distributed around 1 (more than 95% of values ​​fall within the range (0.95-1)); the threshold range for the sum of all background noise should be (0-0.75). This algorithm can completely separate cyanobacteria from other background noise in imagery. Compared to traditional low-altitude remote sensing cyanobacteria identification and extraction, this algorithm ensures the accuracy of cyanobacteria extraction while improving the completeness of cyanobacteria identification.

[0100] Example 2

[0101] Taking a certain reservoir as an example, Figure 3 The following is an optical orthophoto image of a reservoir in 2018. The process for extracting the cyanobacteria region is as follows:

[0102] 1. Research area:

[0103] In July 2018, a fixed-wing UAV was used to collect aerial images of a reservoir, totaling 189 optical aerial images covering an area of ​​2.088 square kilometers. All 189 images were used for image synthesis and index calculation, and low-altitude optical remote sensing orthophotos were obtained after data processing. Figure 2 0.088 square kilometers ( Figure 3 ) and the RGB three-channel separation index diagram of the image, Figure 4 This is a RGB three-channel separation index map of a reservoir in a study area in 2018; among which, Figure 4 (a) is the separation index chart of the red channel. Figure 4 (b) is a graph showing the separation index of the green channel. Figure 4 (c) is the blue channel separation index chart.

[0104] 2. Optimization or construction of background noise suppression algorithm:

[0105] Figure 5 This is a graph showing the results of vegetation index calculations, where... Figure 5 (a) is a graph showing the EXG calculation results. Figure 5 (b) is a graph showing the NGRDI calculation results. Figure 5 (c) is a graph showing the RGRI calculation results. Figure 5 (d) is a graph showing the VDVI calculation results. Figure 5 (e) shows the BVN calculation result. The total background value is processed using an algorithm based on five vegetation indices (EXG, NGRDI, RGRI, VDVI, and BVN) and three bands (RED, GREEN, and BLUE). Figure 5 (a) ~ Figure 5 (e).

[0106] The calculation formulas for the five vegetation indices are as follows:

[0107] (9)

[0108] (10)

[0109] (11)

[0110] (12)

[0111] (13)

[0112] Where, ρ red ρ green ρ blue These represent the reflectivity of the red, green, and blue bands, respectively.

[0113] Figure 6 The image shows the effect of cyanobacteria identification. Figure 6 (a) is a map of the cyanobacteria region. Figure 6 (b) is a diagram showing the effect of cyanobacteria identification based on red band reflectance. Figure 6 (c) is a diagram showing the effect of cyanobacteria identification based on green band reflectance. Figure 6 (d) shows the effect of cyanobacteria identification based on blue band reflectance. Figure 6 (e) is a diagram showing the results of EXG-based cyanobacteria recognition. Figure 6 (f) shows the effect of cyanobacteria recognition based on NGRDI. Figure 6 (g) shows the effect of cyanobacteria recognition based on RGRI. Figure 6 (h) shows the effect of VDVI-based cyanobacteria identification. Figure 6 (i) is a diagram showing the effect of cyanobacteria identification based on BVN. The effect of cyanobacteria region and the above 5 vegetation indices and three bands on cyanobacteria identification is as follows: Figure 6 (b) ~ Figure 6 As shown in (i), Figure 6 (a) The area enclosed in the box is the cyanobacteria region.

[0114] Among the above algorithms and bands, each index algorithm and band has its own advantages in cyanobacteria identification. Some can effectively distinguish cyanobacteria from vegetation, some can distinguish cyanobacteria from water bodies, and some can distinguish cyanobacteria from roads and buildings. However, relying on only one algorithm cannot effectively distinguish cyanobacteria from all other types of background noise.

[0115] To identify and extract cyanobacteria and distinguish them from other non-target elements, existing and newly constructed index algorithms were tested, compared, and optimized. Based on this, background noise was categorized into four main types: terrestrial vegetation, water bodies, exposed land from roads and buildings, and aquatic plants other than cyanobacteria.

[0116] Through comprehensive testing, the exponential algorithms S1-S4 were selected, and their formulas are shown in formulas (1)-(4). The exponential algorithm formulas can all meet the extraction requirements of the four types of background noise.

[0117] 3. Data normalization:

[0118] Data normalization uses a normalization function, the specific formula of which is shown in formula (5).

[0119] 4. Background noise suppression and separation:

[0120] The suppression separation function is adopted, and the specific formula and parameters are shown in formula (7).

[0121] Background noise includes terrestrial green vegetation, water bodies, bare soil from roads and buildings, and other vegetation in water besides cyanobacteria, such as water chestnuts and lotus leaves. The suppression and separation effect is as follows: Figures 7-10 As shown, Figure 7 This is an image showing the effect of suppressing background noise and green vegetation on land. Figure 8 To remove the road and building interference index map. Figure 9 To remove the water disturbance index map, Figure 10 To remove the disturbance index map of aquatic plants such as water chestnuts, by Figures 7-10 As can be seen, each type of noise in the figure is well suppressed under the corresponding exponential algorithm, achieving the expected results.

[0122] 5. Implementation of background noise suppression:

[0123] The final algorithm for extracting cyanobacteria from low-altitude remote sensing images is shown in Equation 8. This is achieved through the application of background noise suppression algorithms. Figure 11 To remove background noise interference, an index map for cyanobacteria identification was extracted, which suppressed all background noise in the image except for cyanobacteria, with the following effect: Figure 11 As shown, the target value of the cyanobacteria region is approximately 1, while other noise regions are reduced to 0.75 or below, achieving complete separation between cyanobacteria and background noise, thereby enabling accurate extraction of the cyanobacteria region.

[0124] Depend on Figure 11As can be seen, the noise from vegetation, exposed land of roads and buildings, water bodies, and aquatic plants such as water chestnuts in the image is well suppressed. Although sporadic interference still occurs, it is negligible compared to the cyanobacteria area, achieving the expected results. The identification results show that the cyanobacteria occurrence area (the black part in the image) is continuous, with its boundaries basically being river or pond boundaries, showing a high degree of consistency and clearly distinguishing its distribution range.

[0125] The accuracy and completeness of the background noise suppression algorithm are verified as follows:

[0126] To verify the accuracy of the cyanobacteria identification region, the identification results were superimposed onto the orthophoto image, and a portion of it was selected to see if the identification results completely overlapped with the cyanobacteria region in the optical image. Figure 12 This is a schematic diagram illustrating the verification of the accuracy and completeness of cyanobacteria identification, as shown below. Figure 12 As shown.

[0127] from Figure 12 It can be seen that the cyanobacteria identification area completely overlaps with the cyanobacteria area in the original optical remote sensing image, with high accuracy. It basically achieves complete identification of the cyanobacteria area and removes all other background noise. It realizes the goal of extracting cyanobacteria from optical remote sensing images by using background noise suppression technology, achieving a breakthrough and excellent result.

[0128] Example 3

[0129] In order to perform the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, a system for extracting cyanobacteria regions from optical remote sensing images is provided below.

[0130] A system for extracting cyanobacteria regions from optical remote sensing images includes:

[0131] The optical remote sensing image acquisition module is used to acquire optical remote sensing images.

[0132] The background noise extraction index algorithm construction module is used to construct different types of background noise extraction index algorithms; the types of background noise include terrestrial green vegetation, water bodies, exposed land of roads and buildings, and remaining vegetation in water except for blue-green algae.

[0133] The normalization processing module is used to normalize the background noise extraction index algorithm to generate a normalized background noise extraction index algorithm.

[0134] The noise suppression and separation function construction module is used to construct a noise suppression and separation function based on the normalized background noise extraction index algorithm, and to suppress the background noise and separate the cyanobacteria and the background noise according to the noise suppression and separation function, thereby generating suppression and separation results.

[0135] The cyanobacteria region extraction module is used to extract cyanobacteria regions from the optical remote sensing image based on the suppression and separation results.

[0136] Example 4

[0137] This invention provides an electronic device including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to perform the method for extracting cyanobacteria regions from optical remote sensing images provided in Embodiment 1.

[0138] In practical applications, the aforementioned electronic devices can be servers.

[0139] In practical applications, electronic devices include: at least one processor, memory, bus, and communication interface.

[0140] The processor, communication interface, and memory communicate with each other via a communication bus.

[0141] A communication interface is used to communicate with other devices.

[0142] The processor is used to execute programs, specifically the methods described in the above embodiments.

[0143] Specifically, the program may include program code, which includes computer operation instructions.

[0144] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The electronic device may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.

[0145] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0146] Based on the description of the above embodiments, this application provides a storage medium storing computer program instructions thereon, which can be executed by a processor to implement the methods described in any embodiment.

[0147] The cyanobacteria region extraction system in optical remote sensing images provided in this application exists in various forms, including but not limited to:

[0148] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and are primarily designed to provide voice and data communication. These terminals include smartphones (e.g., iPhones), multimedia phones, feature phones, and low-end phones.

[0149] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers, have computing and processing functions, and generally also have mobile internet access capabilities. These terminals include: PDAs, MIDs, and UMPCs, such as iPads.

[0150] (3) Portable entertainment devices: These devices can display and play multimedia content. This category includes: audio and video players (such as iPods), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.

[0151] (4) Other electronic devices with data interaction functions.

[0152] Specific embodiments of the subject matter have now been described. Other embodiments are within the scope of the appended claims. In some cases, the actions described in the claims can be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing can be advantageous.

[0153] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0154] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware components. Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0155] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0156] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0157] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0158] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0159] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0160] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, and CD-ROM.

[0161] Digital multifunction optical disc (DVD) or other optical storage, magnetic cassette tape, magnetic tape, disk storage or other magnetic storage devices

[0162] Or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transient media, such as modulated data signals and carrier waves.

[0163] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0164] This application can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific transactions or implement specific abstract data types. This application can also be practiced in distributed computing environments where transactions are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0165] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0166] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for extracting cyanobacteria regions from optical remote sensing images, characterized in that, include: Acquire optical remote sensing images; Construct different types of background noise extraction index algorithms; the types of background noise include terrestrial green vegetation, water bodies, exposed land of roads and buildings, and remaining vegetation in water except for blue-green algae; The algorithm for extracting the index of the terrestrial green vegetation is as follows: wherein, is an extraction index of terrestrial green vegetation; is the reflectance of the blue band; The algorithm for the water body extraction index is as follows: wherein, is an extraction index of the water body; is a reflectance of the green band; is a reflectance of the red band; The algorithm for extracting the index of exposed land in road construction is as follows: wherein, is the extraction index for road construction bare land; is the green index; The extraction index algorithm for the remaining vegetation in the water, excluding cyanobacteria, is as follows: wherein, is an extraction index for the remaining vegetation in the water other than blue algae; is a red-green ratio index; The background noise extraction index algorithm is normalized to generate a normalized background noise extraction index algorithm; wherein, by adjusting the value of the normalization variable according to the threshold range of the noise, the value of the background noise extraction after normalization is -1, and the value of the blue-green algae is above 0. A noise suppression and separation function is constructed based on the normalized background noise extraction index algorithm, and the background noise is suppressed and separated from the cyanobacteria and the background noise according to the noise suppression and separation function to generate suppression and separation results; the value range of the distinguishing variable in the noise suppression and separation function is 30-60; Based on the suppression and separation results, the cyanobacteria region in the optical remote sensing image is extracted.

2. The method according to claim 1, wherein the cyanobacterial region is extracted from the optical remote sensing image. The algorithm for extracting the background noise index after normalization is as follows: in, The index S is extracted from the normalized background noise. n Extraction index of different types of background noise; It is the first normalized variable; b n The second normalized variable is n, which takes values ​​from 1 to 4.

3. The cyanobacteria region extraction method in optical remote sensing imagery according to claim 2, characterized in that, The noise suppression separation function is: wherein, is the noise separation index calculated after noise suppression; n is the suppression separation factor for different kinds of background noise; n is the discrimination variable for different kinds of background noise; K is a constant.

4. A system for extracting cyanobacteria regions from optical remote sensing images, characterized in that, The extraction of cyanobacteria regions from optical remote sensing images is performed using the method for extracting cyanobacteria regions from optical remote sensing images according to any one of claims 1-3, wherein the cyanobacteria region extraction system for optical remote sensing images comprises: Optical remote sensing image acquisition module, used to acquire optical remote sensing images; The background noise extraction index algorithm construction module is used to construct different types of background noise extraction index algorithms; the types of background noise include terrestrial green vegetation, water bodies, exposed land of roads and buildings, and remaining vegetation in water except for blue-green algae; The normalization processing module is used to normalize the background noise extraction index algorithm to generate a normalized background noise extraction index algorithm. The noise suppression and separation function construction module is used to construct a noise suppression and separation function based on the normalized background noise extraction index algorithm, and to suppress the background noise based on the noise suppression and separation function, separate the cyanobacteria and the background noise, and generate suppression and separation results. The cyanobacteria region extraction module is used to extract cyanobacteria regions from the optical remote sensing image based on the suppression and separation results.

5. An electronic device, comprising: The device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to enable the electronic device to perform the method for extracting cyanobacteria regions from optical remote sensing images as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method for extracting cyanobacteria regions from optical remote sensing images as described in any one of claims 1-3.

Images