Wharf berth marine organism fouling degree detection method
By designing detection locations and depths at wharf berths and employing floating or fixed detection methods combined with image annotation and deep learning, the systematization problem of marine biofouling detection at wharf berths has been solved, achieving both accuracy and adaptability in the detection results.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-02-04
- Publication Date
- 2026-04-14
AI Technical Summary
Existing technologies are difficult to implement systematic and repeatable detection of marine biofouling in the environment of dock berths, and the detection results are difficult to standardize and compare horizontally. There is a lack of detection procedures applicable to complex hydrodynamic and variable environments.
A method for detecting the degree of marine biofouling at wharf berths is designed, including determining the detection location and depth, selecting floating or fixed detection methods, combining quantitative identification methods and database comparison, simulating the actual environment, and conducting detailed analysis through image annotation and deep learning.
It has improved the accuracy and reliability of marine biofouling detection results at wharf berths, adapted to different port environments, provided a systematic detection process and database support, and improved the standardization and precision of detection.
Smart Images
Figure CN121856280A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of marine engineering inspection and biofouling monitoring technology, and in particular to a method for detecting the degree of marine biofouling at wharf berths. Background Technology
[0002] Marine biofouling is a long-standing and significant issue in marine engineering, primarily referring to the attachment, growth, and reproduction of marine microorganisms, algae, barnacles, oysters, mussels, and other organisms on the surfaces of underwater structures or ship hulls. For port terminals, ship berthing areas, and related marine facilities, biofouling not only alters the surface properties of structures but also leads to a series of engineering and environmental problems. For instance, biofouling significantly increases ship drag, resulting in higher fuel consumption; biofilms formed on terminal structures can also cause accelerated localized corrosion, pipeline blockage, and difficulties in inspection. Furthermore, excessive biofouling reduces berth utilization efficiency, affects safe ship berthing, and may potentially disrupt the marine ecosystem.
[0003] Existing methods for detecting biofouling mainly include manual observation, traditional sample immersion methods, and some sensor-based monitoring systems. GB 5370-2007, "Test Method for Shallow Sea Immersion of Antifouling Paints," provides a procedure for detecting biofouling samples based on fixed structures or floating rafts. However, this method has a long testing cycle, high setup costs, and limited applicability to multi-site deployment and multi-cycle monitoring. Furthermore, traditional methods rely heavily on manual visual judgment, making it difficult to obtain precise quantitative parameters such as the area, type, quantity, thickness, and volume of biofouling coverage. Significant subjective differences among personnel also hinder the standardization and cross-sectional comparison of test results.
[0004] In recent years, with the improvement of port automation and the development of artificial intelligence technology, image recognition, deep learning, and other methods have been gradually applied to the automated identification of marine biofouling. However, existing research mostly focuses on the construction of image recognition models for single carriers, experimental pools, or experimental rafts. For actual terminal berths, which are characterized by complex hydrodynamics, frequent tidal changes, and diverse long-term exposure environments, there is still a lack of systematic, repeatable detection processes that integrate with engineering decision-making. In addition, the types and coverage of biofouling vary significantly across different regions and seasons, and there is currently a lack of a unified database and grading system to determine the level of biofouling development.
[0005] Therefore, there is an urgent need to propose a systematic biofouling detection method that can be applied to the actual environment of wharf berths. Summary of the Invention
[0006] The purpose of this invention is to provide a method for detecting the degree of marine biofouling at wharf berths, so as to solve the problems existing in the prior art.
[0007] The above-mentioned technical objective of the present invention is achieved through the following technical solution: A method for detecting the degree of marine biofouling at a wharf berth includes the following steps: Step S1: Determine the location and depth range for biofouling detection based on the wharf structure and ship berthing conditions; Step S2: Based on the spatial and hydrodynamic conditions of the detection location, design the on-site detection method, which includes floating detection, fixed detection, or a combination of both, and determine the size and substrate type of the detection carrier; Step S3: Set the detection cycle, carry out on-site detection according to the preset detection cycle, and record environmental information simultaneously during the detection process; Step S4: Acquire images of marine biofouling on the surface of the detection carrier, and analyze the characteristic parameters of marine biofouling using a quantitative identification method. The characteristic parameters include one or more of the following: biofouling coverage area, species, number of organisms, thickness of organisms, and volume of organisms. Step S5: Compare or match the feature parameters obtained by the quantitative identification method with the pre-established marine biofouling database to determine the marine biofouling level of the detection location within the corresponding detection period.
[0008] By adopting the above technical solution, step S1 makes the final detection result of the method of the present invention correspond to the area to be detected. Each different port situation faces different problems. By combining the role and function of the wharf, the method of acquiring the original data in the detection method has been adjusted to a certain extent, so that the original data is the data to be tested, thereby making the detection result of the method accurate and reliable. It should be noted that in step S2, the floating detection method suspends the detection carrier at a fixed depth below the sea level by a buoy. The fixed detection method fixes the detection carrier to a fixed height on the seabed by multiple ropes or ground piles, and the relative position is always fixed. The detection carrier of the fixed detection method does not drift with the waves like the detection carrier of the floating detection method. The detection carrier of the floating detection method will change its height and position with changes in the ocean such as wave height and swell.
[0009] In a further embodiment, in step S1, the detection location includes one or more of the following: the side wall area of the dock where the ship is berthed for a long time, the surface of the dock components, and structural parts that are prone to biological attachment.
[0010] It should be noted that the detection methods differ for different parts and structures when using the above technical solutions. By fixing the detection carrier, the detection carrier can simulate the actual location that needs to be detected. Then, the surface contamination degree of the detection carrier is judged according to the detection cycle.
[0011] In a further embodiment, in step S1, the detection depth range is between 0.2 meters and 5.0 meters from the average sea level. Depending on the water depth conditions of the wharf, the range of tidal changes, and the detection requirements, a single depth location or multiple depth locations may be selected for detection. When multiple depth locations are selected, the multiple depth locations are evenly distributed along the water depth direction.
[0012] In a further embodiment, in step S2, the detection carrier is a sample, the substrate of which is selected from one or more of metal materials, cement-based materials, polymer materials or composite materials to simulate the actual surface condition of dock facilities or ship components.
[0013] By adopting the above technical solution, different construction surfaces are simulated to be affected by marine biological pollution at different cycles using different substrates.
[0014] In a further embodiment, in step S3, the detection cycle is determined based on the average berthing time of ships at the wharf berth and the rate of biofouling development, including one of monthly, quarterly, or annual detection.
[0015] By adopting the above technical solutions and using detection methods, combined with data from multiple detection cycles, we can intelligently judge and detect whether the degree of biofouling is increasing year by year, thereby strengthening the monitoring of biofouling at wharf berths.
[0016] In a further embodiment, in step S4, the quantitative identification method includes one or more of the following: percentile scale method, image annotation method, and deep learning method.
[0017] In a further embodiment, when an image annotation method is used, step S4 specifically includes: Step S41: Acquire raw images of marine biofouling on the surface of the detection carrier; Step S42: Use image annotation software to manually annotate different types of marine biofouling in the original image to distinguish different types of biofouling organisms; Step S43: Based on the annotation results, generate binary mask images of the corresponding types of fouling organisms; Step S44: Based on the binary mask image, count the attachment area and / or number of various types of contaminating organisms on the surface of the detection carrier, as a feature parameter for quantitative identification.
[0018] In a further embodiment, in step S42, different types of fouling organisms are distinguished and labeled according to their morphological characteristics, color characteristics, and attachment patterns, and are represented by different colors.
[0019] In a further embodiment, in step S43, in the binary mask image, the pixel region belonging to the target contaminated organism is defined as the first color, and the remaining region is defined as the second color.
[0020] In a further embodiment, in step S5, the marine biofouling database includes characteristic parameter data of marine biofouling under different detection cycles, different detection depths and different environmental conditions. The characteristic parameter data includes at least one or more of the following: the proportion of fouled coverage area, the number of attached organism species, the biofouling density, and the biofouling thickness or volume.
[0021] In a further embodiment, the marine biofouling database forms a basic dataset by statistically analyzing historical detection data, and is dynamically updated and maintained as subsequent on-site detection results are added.
[0022] In a further embodiment, in step S5, the determination of the marine biofouling level is based on a comprehensive evaluation of one or more biofouling characteristic parameters, including the proportion of biofouling coverage area, the number of attached organisms, the number of biological species, and the average thickness or volume of the biofilm.
[0023] In a further embodiment, the determination of the fouling level is specifically as follows: the level is classified based on the proportion of biofouling coverage area on the surface of the detection carrier. When the coverage area proportion is less than a first threshold, it is determined to be lightly fouled; when the coverage area proportion is between the first threshold and a second threshold, it is determined to be moderately fouled; and when the coverage area proportion is greater than the second threshold, it is determined to be heavily fouled. The first threshold and the second threshold are set according to actual needs.
[0024] In a further embodiment, the first threshold is 10% and the second threshold is 30%.
[0025] In a further embodiment, the method further includes step S6: assessing the safety of ship berthing, analyzing the operational status of terminal facilities, and providing a basis for the formulation of terminal production and maintenance plans based on the determined marine biofouling level.
[0026] In a further embodiment, a detection system for implementing the detection method is included: The planning module is used to execute steps S1 and S2, and to plan the detection location, depth, method, and carrier. The on-site operation module is used to execute step S3, which involves deploying the detection carrier and collecting environmental information according to the detection cycle. The image acquisition module is used to acquire images of marine biofouling on the surface of the detection carrier; The data processing module is used to execute step S4, which performs quantitative identification and analysis on the acquired image to obtain the soiling characteristic parameters; The database module stores a pre-established database of marine biofouling. The evaluation module is used to perform step S5, which compares and matches the feature parameters obtained by the data processing module with the data in the database module to determine the level of contamination.
[0027] By adopting the above technical solution,
[0028] In a further embodiment, the data processing module integrates a percentile plate analysis unit, an image annotation analysis unit, and / or a deep learning recognition unit to achieve different quantitative recognition methods.
[0029] In a further embodiment, the image annotation and analysis unit includes an image annotation tool and a mask generation tool. The image annotation tool is used to manually annotate the smudged image, and the mask generation tool is used to convert the annotation results into a binary mask image and calculate feature parameters.
[0030] In summary, the present invention has the following beneficial effects: 1. Step S1 ensures that the final detection result of the method of the present invention corresponds to the area to be detected. Each port has different problems. By combining the role and function of the wharf, the method of acquiring the original data in the detection method has been adjusted to ensure that the original data is the data to be tested, thereby making the detection result of the method accurate and reliable. It should be noted that in step S2, the floating detection method suspends the detection carrier at a fixed depth below the sea level by a buoy. The fixed detection method fixes the detection carrier to a fixed height on the seabed by multiple ropes or piles, and the relative position is always fixed. The detection carrier of the fixed detection method does not drift with the waves like the detection carrier of the floating detection method. The detection carrier of the floating detection method will change in height and position with changes in the ocean such as wave height and swell. Attached Figure Description
[0031] Figure 1 This is an overall flowchart of a method for detecting the degree of marine biofouling at a wharf berth according to the present invention; Figure 2 This is a schematic diagram of the original image of step S41 of the present invention; Figure 3 This is a schematic diagram of the artificial region division in step S42 of the present invention; Figure 4 This is a schematic diagram of the binary mask image in step S43 of the present invention; Figure 5 This is a schematic diagram of the image used for quantitative identification in step S44 of the present invention. Detailed Implementation
[0032] The present invention will be further described in detail below with reference to the accompanying drawings.
[0033] It should be noted that in the description of this invention, any descriptions of orientation, such as up, down, front, back, left, right, etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings. They are only for the purpose of facilitating the description of this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed or operated in a specific orientation, and should not be construed as a limitation of this invention.
[0034] Example 1: like Figures 1-2 As shown, a method for detecting the degree of marine biofouling at a wharf berth involves, firstly, following step S1, determining the biofouling detection locations based on the wharf structure and vessel berthing methods. These locations include the sidewalls of the wharf berth where vessels are frequently berthed and the surfaces of wharf components prone to biofouling. Combining wharf water depth conditions, tidal range, and existing engineering experience, one or more depth locations within a range of 0.2–5.0 m above average sea level are determined. When the wharf water depth is shallow or the detection objective is rapid assessment, a single representative depth location can be selected. When the wharf water depth is greater or it is necessary to reflect differences in biofouling across different water depth ranges, multiple depth locations can be selected within the specified detection depth range for detection. These multiple depth locations can be evenly distributed along the water depth direction.
[0035] Subsequently, according to step S2, based on the spatial and hydrodynamic conditions of the detection location, an on-site detection method is designed. In this embodiment, a floating detection method is adopted to deploy a detection carrier at the front edge of the wharf berth. The detection carrier is a template, and its size is set according to the on-site operating conditions and detection requirements. The template substrate is selected from one or more of metal materials, cement-based materials, polymer materials or composite materials to simulate the actual surface conditions of wharf facilities or ship components.
[0036] According to step S3, on-site testing is carried out based on the preset testing cycle. In this embodiment, the monitoring cycle is determined based on the average berthing time of ships at the wharf berth and the approximate rate of biofouling development. In wharf berth areas where ships frequently berth and environmental conditions are relatively stable, quarterly testing is selected as the testing cycle, that is, testing is carried out once every three months at the same testing location. During the testing process, the marine biofouling status on the surface of the testing carrier is recorded, and environmental information such as water temperature, salinity, water flow velocity, water depth, and testing time are collected simultaneously.
[0037] In step S4, the obtained detection results are quantitatively identified. Specifically, firstly, images of marine biofouling on the surface of the detection carrier are acquired to obtain detection images containing the distribution characteristics of the biofouling organisms. Subsequently, the images of marine biofouling on the surface of the detection carrier are manually annotated using methods such as image annotation. In the specific implementation process, image annotation software is used to annotate different types of biofouling organisms in the detection images, and parameters such as the attachment area and quantity of various types of biofouling organisms on the surface of the detection carrier are calculated based on the annotation results as reference data for quantitative identification. In the specific implementation of step S4, such as Figures 2-5 As shown, firstly, the original image of marine biofouling on the surface of the detection carrier is acquired. Then, experienced professionals use image annotation software to manually annotate different types of marine biofouling in the original image, forming an annotation interface map. During the labeling process, different types of fouling organisms are distinguished and labeled according to their morphological characteristics, color characteristics, and attachment forms, and are represented by different colors. In this embodiment, green marking areas represent algal fouling, and red marking areas represent marine insect fouling. The boundaries of various fouling organisms are manually delineated and confirmed by professionals based on their actual attachment range to ensure the accuracy of the labeling results. After the annotation is completed, the annotation software exports the corresponding annotation file. Then, the annotation file is converted into a corresponding binary mask image through a binary mask generation program, in which the pixel area belonging to the target contaminated organism is defined as white and the remaining area is defined as black. Specifically, such as Figure 4 The image shows a binary mask image corresponding to algal contamination, where white areas represent the locations where algae adhere; for example... Figure 5 The binary mask image corresponding to marine worm fouling is shown. The white area represents the attachment location of the marine worm. Based on the binary mask image, the attachment area, quantity and spatial distribution characteristics of various fouling organisms can be further statistically analyzed, providing basic data for subsequent quantitative analysis of fouling degree.
[0038] Finally, in step S5, the quantitative identification results are compared or matched with a pre-established marine biofouling database to determine the level of marine biofouling at the detection location within the corresponding detection period.
[0039] The marine biofouling database can be established independently according to actual detection needs. Its content includes characteristic parameter data of marine biofouling under different detection cycles, different detection depths, and different environmental conditions. The characteristic parameters include at least one or more of the following: the proportion of biofouling coverage area, the number of attached organism species, the biofouling density, and the biofouling thickness or volume. During the database establishment process, a basic dataset can be formed by statistical analysis of historical detection data, and it can be continuously supplemented and updated in combination with subsequent field detection results. In long-term application, the database can be dynamically maintained according to newly added detection data to improve the accuracy and applicability of biofouling level determination.
[0040] In specific implementation, the determination of the marine biofouling level can be based on a comprehensive assessment of one or more biofouling characteristic parameters. These biofouling characteristic parameters include, but are not limited to, the proportion of biofouling coverage area, the number of attached organisms, the number of organism species, and the average thickness or volume of the biofouling layer. For example, in one embodiment, the degree of biofouling can be graded according to the proportion of biofouling coverage area on the surface of the detection carrier. When the coverage area proportion is less than 10%, it is determined to be light biofouling; when the coverage area proportion is 10% to 30%, it is determined to be moderate biofouling; and when the coverage area proportion is greater than 30%, it is determined to be heavy biofouling. The above thresholds can be adjusted according to actual needs.
[0041] The test results can be used to assess the safety of ship berthing, analyze the operating status of terminal facilities, and provide a basis for the formulation of subsequent production and maintenance plans. The specific embodiments of the present invention have been described above.
[0042] Example 2: The wharves requiring inspection are categorized into four levels based on their berthing capacity: 5,000 tons and below, 10,000 tons, 50,000 tons, and 100,000 tons and above. For wharves of 5,000 tons and below, the inspection depth range is one or more depths within 0.2–5.0 m above the mean sea level. For wharves of 10,000 tons, the inspection depth range is one or more depths within 5.0–9.0 m above the mean sea level. For wharves of 50,000 tons, the inspection depth range is one or more depths within 9.0–12.0 m above the mean sea level. For wharves of 100,000 tons and above, the inspection depth range is one or more depths within 12.0–16.0 m above the mean sea level.
[0043] Each level of the wharf corresponds to a detection depth containing two endpoints. The detection range for each level is divided into five equal parts, meaning each level has six detection points at different depths. The entire detection process is divided into two stages: raw data acquisition and precision detection. In the raw data acquisition stage, three months of raw data are collected on a monthly basis, combining floating and fixed detection methods. Specifically, the area to be inspected is divided into two zones, and six detection substrates are set from top to bottom at the center of each zone. The substrates in one zone are fixed using a floating detection method, while those in the other zone are fixed using a fixed detection method. At the end of the first month... Twelve biofouled test substrates were obtained. Two test substrates from the same depth in two different areas were compared. The test method for the test substrate with more severe surface fouling was selected at that depth. For example, when testing a 5,000-ton dock, at a depth of 0.2 meters, the fouling of the test substrate using the floating test method was more severe than that of the fixed test method. Therefore, the floating test method was used at this depth. A complete test cycle was set up annually. In the first month of each new year, this method was used to re-anchor the required test method for each depth. When re-anchoring the test method, the cycle of the original data acquisition phase was reduced to one month.
[0044] This solution can also use intelligent recognition to process and mark the original image. After the substrate is taken out, it is placed flat on the worktable. Then, the top of the substrate is quickly dried with a hot air gun. Then, the dried surface is irradiated with an incandescent lamp and the original image is taken with an industrial camera. Then, the top surface of the substrate is scanned along the length of the substrate using an infrared ranging grating. This will obtain a data on the height of the surface attachments of the substrate. The first step of the inspection is to detect the area of marine algae attached to the raw image acquired by the industrial camera. Since the top of the substrate was dried and the raw image was acquired under incandescent light, the color of the algae is very obvious. By locking the color saturation and color difference range, the area of marine algae attached to the substrate surface can be determined. The algae attachment rate can be obtained by the ratio of the area of marine algae attached to the total area of the top of the substrate.
[0045] The height of the algae attachment site can be determined by the algae attachment rate. By scanning the data of the infrared ranging grating, the data areas that are closer to the algae than the average distance detected by the infrared ranging grating are selected. These areas are the marine organism attachment areas. For example, if the average distance between the algae and the ranging grating is 20 centimeters, then all areas that are less than 20 centimeters away from the ranging grating are selected. This method can greatly reduce the amount of data processing and can also initially define the area as follows: Figure 3 The range shown is then masked to become Figure 4 The pattern shown is illustrated, with the biological attachment area being a white region. Each white region with unconnected boundaries is analyzed separately. Based on the height data, the height data within each white region is divided into five levels. For example, the height data within a certain white region is defined as the maximum distance to the ranging grating being 20.1 cm and the minimum distance being 19.6 cm. This means dividing the region into five intervals of 0.1 cm each, gradually decreasing from the maximum to the minimum distance. After each decrease, it is necessary to retrieve the number of point clouds in the region. In other words, after each decrease, the internal boundaries of the white region are redefined, and then masking is performed to determine how many new white regions the white region is divided into. The two minimum values are removed, and the average of the three maximum values is taken as the value defined as the number of marine organisms attached to the region.
[0046] By summing these values, the number of marine organisms attached to the tested substrate can be determined. The number indicates the degree of fouling within each depth range. If further analysis of the degree of fouling is required, each substrate can be divided into multiple equal parts along its elevation depth, and the values in each part can be summed to detect the distribution relationship between the degree of marine biofouling and ocean depth.
[0047] One side of the detection substrate is dried while the other side remains dry. After acquiring the raw data and images, before returning the detection substrate to its original position, the dried side can be polished clean. This allows you to choose whether to test data for multiple periods. For example, if you decide to test data for each month as a period, you also need to test data for each year to determine if it matches the prediction model. In this case, the other side will wait a year to dry and acquire the raw data and images. This means that a new detection substrate needs to be replaced every year, or both sides of the old detection substrate can be polished clean. The purpose of polishing is to remove marine attached organisms and algae.
[0048] This method saves on the amount of testing substrate used.
[0049] In the description of this invention, unless otherwise explicitly defined, terms such as "set up," "install," and "connect" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this invention in conjunction with the specific content of the technical solution.
[0050] This specific embodiment is merely an explanation of the present invention and is not intended to limit the invention. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they are within the scope of the claims of the present invention.
Claims
1. A method for detecting the degree of marine biofouling at a wharf berth, characterized in that: Includes the following steps: Step S1: Determine the location and depth range for biofouling detection based on the wharf structure and ship berthing conditions; Step S2: Based on the spatial and hydrodynamic conditions of the detection location, design the on-site detection method, which includes floating detection, fixed detection, or a combination of both, and determine the size and substrate type of the detection carrier; Step S3: Set the detection cycle, carry out on-site detection according to the preset detection cycle, and record environmental information simultaneously during the detection process; Step S4: Acquire images of marine biofouling on the surface of the detection carrier, and analyze the characteristic parameters of marine biofouling using a quantitative identification method. The characteristic parameters include one or more of the following: biofouling coverage area, species, number of organisms, thickness of organisms, and volume of organisms. Step S5: Compare or match the feature parameters obtained by the quantitative identification method with the pre-established marine biofouling database to determine the marine biofouling level of the detection location within the corresponding detection period.
2. The method for detecting the degree of marine biofouling at a wharf berth according to claim 1, characterized in that: In step S1, the detection location includes one or more of the following: the side wall area of the dock where the ship is berthed for a long time, the surface of the dock components, and structural parts that are prone to biological attachment.
3. The method for detecting the degree of marine biofouling at a wharf berth according to claim 1, characterized in that: In step S3, the detection cycle is determined based on the average berthing time of ships at the dock and the rate of biofouling development, including one of monthly, quarterly, or annual detection.
4. The method for detecting the degree of marine biofouling at a wharf berth according to claim 1, characterized in that: In step S4, the quantitative identification method includes one or more of the following: percentile scale method, image annotation method, and deep learning method.
5. The method for detecting the degree of marine biofouling at a wharf berth according to claim 4, characterized in that, When using image annotation, step S4 specifically includes: Step S41: Acquire raw images of marine biofouling on the surface of the detection carrier; Step S42: Use image annotation software to manually annotate different types of marine biofouling in the original image to distinguish different types of biofouling organisms; Step S43: Based on the annotation results, generate binary mask images of the corresponding types of fouling organisms; Step S44: Based on the binary mask image, count the attachment area and / or number of various types of contaminating organisms on the surface of the detection carrier, as a feature parameter for quantitative identification.
6. The method for detecting the degree of marine biofouling at a wharf berth according to claim 5, characterized in that: In step S42, different types of fouling organisms are distinguished and labeled according to their morphological characteristics, color characteristics, and attachment forms, and are represented by different colors.
7. The method for detecting the degree of marine biofouling at a wharf berth according to claim 5, characterized in that: In step S43, in the binary mask image, the pixel region belonging to the target contaminated organism is defined as the first color, and the remaining regions are defined as the second color.
8. The method for detecting the degree of marine biofouling at a wharf berth according to claim 1, characterized in that: In step S5, the marine biofouling database includes characteristic parameter data of marine biofouling under different detection cycles, different detection depths and different environmental conditions. The characteristic parameter data includes at least one or more of the following: the proportion of fouled coverage area, the number of attached organism species, the biofouling density, and the biofouling thickness or volume.