Buoy platform wave element observation device

Abstract

The invention relates to the technical field of wave observation, and discloses a buoy platform wave element observation device, which realizes comprehensive monitoring on a large-range ocean surface by controlling a camera arranged at the bottom of a buoy upper platform to rotate around a buoy platform in all directions. Furthermore, through a priority processing method and a resource allocation method, the image data processing efficiency can be ensured. Furthermore, the wave height cycle data is determined in the wave height calculation module through an image recognition technology, so that the measurement precision is improved, and the wave change can be monitored in real time. Furthermore, wave element form modeling is carried out in the form modeling module through a Riemannian geometry method, wave peaks and wave troughs of wave elements are identified in the feature analysis module by utilizing a wave geometric model obtained through modeling, and wave feature data are obtained; and the regularity and the change trend of the wave behavior are identified and evaluated in the form analysis module in combination with a preset prediction model, so that the regularity and the change trend of the wave behavior can be obtained.

Description

Technical Field

[0001] The invention relates to the technical field of wave observation, and in particular to a buoy platform wave element observation device. Background Art

[0002] The field of wave observation technology focuses on monitoring and analyzing the dynamics of waves on the ocean surface. By combining physical oceanography, meteorology, hydrology and modern sensing technology, it can be used to obtain key parameters of ocean waves, such as wave height, period, wave direction, etc. Furthermore, using buoys, radars, satellites and sensor equipment, wave observation technology can provide real-time data to support marine navigation safety, coastline management, climate change research and marine energy development. It also plays a key role in disaster prevention and emergency response, such as predicting the potential impact of storm surges and tsunamis by analyzing wave data.

[0003] However, existing wave observation technology mainly relies on buoys, radars, satellites and sensor equipment. Although the equipment can provide real-time data to support marine navigation safety, coastline management, climate change research and marine energy development, it is insufficient in terms of data accuracy and comprehensiveness. Equipment such as buoys and radars can only monitor wave data at specific locations and lack the ability to comprehensively monitor a large range of ocean surfaces. Although satellites have a wide coverage range, they are limited by resolution and observation frequency and are difficult to capture subtle changes and short-term fluctuations in sea surface waves. When dealing with complex sea conditions, sensor equipment will be disturbed, resulting in reduced data accuracy. Existing technologies are relatively simple in data processing and fail to make full use of modern image recognition and machine learning technologies, resulting in insufficient analysis of wave shape and surface texture, lack of comprehensive analysis of wave behavior and trend prediction capabilities, and limited early warning capabilities in response to sudden marine disasters, resulting in inaccurate predictions of disasters such as storm surges and tsunamis, increasing the risks of marine operations and coastal residents. Summary of the invention

[0004] In view of this, the present invention provides a buoy platform wave element observation device to solve the problems existing in the existing wave observation technology, such as the lack of comprehensive monitoring capability of a large area of ​​the ocean surface, the difficulty in capturing subtle changes and short-term fluctuations of sea surface waves, and the lack of comprehensive monitoring capability of a large area of ​​the ocean surface.

[0005] In a first aspect, the present invention provides a buoy platform wave element observation device, wherein a camera is arranged at the bottom of the buoy upper platform, and the buoy upper platform is located above the buoy platform, and the device comprises: an image capture module, a resource adjustment module, a wave height calculation module, a morphology modeling module, a feature analysis module and a morphology analysis module;

[0006] The image capture module is used to control the camera to rotate around the buoy platform in all directions and obtain the target sea surface image set, and send the target sea surface image set to the resource adjustment module, the wave height calculation module and the feature analysis module respectively; the resource adjustment module is used to obtain the optimized resource allocation result based on the target sea surface image set through the priority processing method and the resource allocation method, and send the optimized resource allocation result to the wave height calculation module, and the optimized resource allocation result is used to reflect the response speed and processing efficiency of the image processing task after optimization; the wave height calculation module is used to identify and process the target sea surface image set using image recognition technology based on the optimized resource allocation result, and obtain the wave height calculation result. The wave height period data is sent to the morphological modeling module; the morphological modeling module is used to model the morphology of the wave elements based on the wave height period data using the Riemann geometry method to obtain the wave geometry model, and send the wave geometry model to the feature analysis module; the feature analysis module is used to use the wave geometry model to identify the crests and troughs of the wave elements in the target sea surface image set to obtain wave feature data, and send the wave feature data to the morphological analysis module; the morphological analysis module is used to identify and evaluate the regularity and change trend of the wave behavior based on the wave feature data using a preset prediction model to obtain the wave behavior analysis result.

[0007] The buoy platform wave element observation device provided by the present invention can capture the real-time changes of sea surface wave elements in real time by controlling the camera arranged at the bottom of the upper platform of the buoy to rotate around the buoy platform in all directions, check the image integrity of the wave elements and obtain the corresponding target sea surface image set, thereby realizing comprehensive monitoring of a large range of ocean surfaces. Further, the efficiency of image data processing can be ensured by the priority processing method and the resource allocation method. Further, the wave height period data is determined by the image recognition technology in the wave height calculation module, which not only improves the measurement accuracy, but also can monitor the wave changes in real time. Further, the wave element morphology is modeled by the Riemann geometry method in the morphology modeling module, and the wave geometry model obtained by modeling is used in the feature analysis module to identify the crest and trough of the wave element and obtain the wave feature data. Finally, the regularity and change trend of the wave behavior are identified and evaluated in the morphology analysis module in combination with the preset prediction model, so that the regularity and change trend of the wave behavior can be obtained, which provides strong data support for the monitoring of marine environmental changes, the safety of offshore operations, the optimal design and operation of marine energy facilities, and the accuracy improvement of meteorological forecasts. Therefore, by implementing the present invention, image recognition and machine learning techniques can be fully utilized to improve the ability to analyze wave shape and surface texture, thereby improving the ability to comprehensively analyze and predict the trend of wave behavior.

[0008] In an optional embodiment, the image capture module includes: an angle adjustment submodule, a capture submodule and an image review submodule;

[0009] The angle adjustment submodule is used to adjust the rotation state of the camera and obtain the position adjustment data set of the camera, and send the position adjustment data set to the capture submodule; the capture submodule is used to control the rotation of the camera to obtain the initial sponge image set based on the position adjustment data set, and timestamp the initial sponge image set to obtain a time stamp table, and send the time stamp table to the image review submodule; the image review submodule is used to analyze and process the time stamp table to obtain the target sea surface image set.

[0010] The buoy platform wave element observation device provided by the present invention can firstly adjust the rotation state of the camera through the angle adjustment submodule so that the camera can rotate in all directions around the buoy platform. Secondly, based on the obtained camera position adjustment data set, the camera rotation can be controlled by the capture submodule and the corresponding initial sponge image set can be obtained, thereby ensuring the real-time and continuity of the image data. Furthermore, the initial sponge image set is timestamped to reflect the specific moment of image capture in real time. Finally, the image review submodule is used to analyze and process the obtained time stamp table to obtain the final target sea surface image set, thereby improving the accuracy of the image. Therefore, by implementing the present invention, the real-time changes of sea surface wave elements can be captured in real time, the image integrity of the wave elements can be checked, and the corresponding target sea surface image set can be obtained, thereby achieving comprehensive monitoring of a large range of ocean surfaces.

[0011] In an optional implementation, the resource adjustment module includes: a performance evaluation submodule, a priority configuration submodule and a resource allocation submodule;

[0012] The performance evaluation submodule is used to process and analyze the target sea surface image set to obtain a performance parameter set, and send the performance parameter set to the priority configuration submodule, the performance parameter set is used to reflect the processing speed and storage capacity of the target sea surface image; the priority configuration submodule is used to adjust the image processing priority of the target sea surface image set based on the performance parameter set to obtain the target image processing priority, and send the target image processing priority to the resource allocation submodule; the resource allocation submodule is used to optimize resource allocation using the target image processing priority to obtain an optimized resource configuration result.

[0013] The buoy platform wave element observation device provided by the present invention first determines the performance parameter set for reflecting the processing speed and storage capacity of the target sea surface image through the performance evaluation submodule. Secondly, the image processing priority is adjusted by the priority configuration submodule to ensure the efficiency and accuracy of image data processing. Finally, based on the adjusted target image processing priority, the resource allocation submodule is used to optimize the resource allocation, which provides support for the subsequent improvement of the comprehensive analysis and trend prediction capabilities of wave behavior.

[0014] In an optional implementation, the priority configuration submodule includes: a determination unit and a configuration unit;

[0015] The determination unit is used to determine the image processing requirements based on the performance parameter set and send the image processing requirements to the configuration unit; the configuration unit is used to adjust the image processing priority of the target sea surface image set using the image processing requirements to obtain the target image processing priority.

[0016] The buoy platform wave element observation device provided by the present invention can more accurately ensure the efficiency and accuracy of image data processing by adjusting the image processing priority in combination with image processing requirements.

[0017] In an optional implementation, the resource allocation submodule includes: a calculation unit and an allocation unit;

[0018] The calculation unit is used to calculate the first resource requirement and the second resource requirement by using the target image processing priority, and send the first resource requirement and the second resource requirement to the allocation unit, wherein the first resource requirement is used to reflect the resource requirement of the image processing task, and the second resource requirement is used to reflect the resource requirement of the image storage task; the allocation unit is used to obtain an optimized resource configuration result based on the first resource requirement and the second resource requirement through a resource allocation algorithm.

[0019] The buoy platform wave element observation device provided by the present invention optimizes resource allocation by combining resource requirements reflecting image processing tasks and image storage tasks, thereby improving the accuracy of optimized resource allocation results.

[0020] In an optional implementation, the wave height calculation module includes: an element measurement submodule, an image processing submodule and a wave height analysis submodule;

[0021] The element measurement submodule is used to load and analyze the target sea surface image set and generate wave element data by using image recognition technology based on the optimized resource allocation result, and send the wave element data to the image processing submodule; the image processing submodule is used to optimize the target sea surface image set by using the wave element data and identify the key features of the wave element changes, generate wave profile data, and send the wave profile data to the wave height analysis submodule; the wave height analysis submodule is used to evaluate the height and periodic characteristics of the waves by using the wave profile data to obtain the wave height period data.

[0022] In an optional implementation, the morphological modeling module includes: a data analysis submodule, a surface measurement submodule and a modeling submodule;

[0023] The data analysis submodule is used to obtain the wave height periodicity analysis results based on the wave height periodicity data through statistical analysis methods, and send the wave height periodicity analysis results to the surface measurement submodule; the surface measurement submodule is used to analyze the wave physical properties using the wave height periodicity analysis results to obtain wave surface characteristic data, and send the wave surface characteristic data to the modeling submodule; the modeling submodule is used to model the morphology of wave elements based on the wave surface characteristic data using the Riemann geometry method to obtain a wave geometry model.

[0024] The buoy platform wave element observation device provided by the present invention utilizes a data analysis submodule to perform statistical analysis and processing on wave height periodicity data, and utilizes a surface measurement submodule to analyze wave physical properties based on the obtained wave height periodicity analysis results. Finally, in a modeling submodule, a Riemann geometry method is used to perform wave element morphology modeling based on the wave surface characteristic data obtained by analysis, thereby improving the robustness of the model and providing support for subsequent improvement of the comprehensive analysis and trend prediction capabilities of wave behavior.

[0025] In an optional implementation, the data analysis submodule includes: a data processing unit and an analysis unit;

[0026] The data processing unit is used to filter the wave height period data and send the filtered wave height period data to the analysis unit; the analysis unit is used to identify the filtered wave height period data using a statistical analysis method to obtain a wave height periodicity analysis result.

[0027] The buoy platform wave element observation device provided by the present invention screens wave height period data through a data processing unit, thereby improving the accuracy of the data.

[0028] In an optional implementation, the feature analysis module includes: a model application submodule, a positioning calculation submodule and a fluctuation trend analysis submodule;

[0029] The model application submodule is used to load and parse the model data of the wave geometry model, obtain the geometry model parsing results, and send the geometry model parsing results to the positioning calculation submodule; the positioning calculation submodule is used to use the geometry model parsing results to identify the crests and troughs in the wave elements in the target sea surface image set and generate crest and trough positioning data, and send the crest and trough positioning data to the wave trend analysis submodule; the wave trend analysis submodule is used to analyze the wave fluctuation trend and amplitude change based on the crest and trough positioning data and generate wave characteristic data.

[0030] The buoy platform wave element observation device provided by the present invention can identify and locate the crests and troughs in the wave elements through the model analysis results of the wave geometric model. Furthermore, the wave fluctuation trend and amplitude change of the waves can be analyzed through the crest and trough positioning data to generate wave characteristic data, thereby improving the accuracy of the wave characteristic data.

[0031] In an optional embodiment, the morphological analysis module includes: a data processing submodule, a behavior pattern comparison submodule and a behavior evaluation submodule;

[0032] The data processing submodule is used to use the wave characteristic data to identify the wave shape, obtain the wave shape data, and send the wave shape data to the behavior pattern comparison submodule; the behavior pattern comparison submodule is used to analyze the consistency and difference of the wave behavior based on the wave shape data, generate the wave pattern difference analysis result, and send the wave pattern difference analysis result to the behavior evaluation submodule; the behavior evaluation submodule is used to identify and evaluate the regularity and change trend of the wave behavior based on the wave pattern difference analysis result using a preset prediction model to obtain the wave behavior analysis result.

[0033] The buoy platform wave element observation device provided by the present invention recognizes wave morphology through wave characteristic data and uses the obtained wave morphology data to analyze the consistency and difference of wave behavior, and then uses a preset prediction model to identify and evaluate the regularity and change trend of wave behavior, thereby improving the accuracy of wave behavior analysis results, and providing strong data support for marine environmental change monitoring, offshore operation safety, optimal design and operation of marine energy facilities, and improving the accuracy of weather forecasts. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 is a structural block diagram of a buoy platform wave element observation device according to an embodiment of the present invention;

[0036] Figure 2 is a structural block diagram of an image capture module according to an embodiment of the present invention;

[0037] Figure 3 is a structural block diagram of a resource adjustment module according to an embodiment of the present invention;

[0038] Figure 4 is a structural block diagram of a wave height calculation module according to an embodiment of the present invention;

[0039] Figure 5 is a structural block diagram of a morphological modeling module according to an embodiment of the present invention;

[0040] Figure 6 is a structural block diagram of a feature analysis module according to an embodiment of the present invention;

[0041] Figure 7 is a structural block diagram of a morphological analysis module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0043] The buoy platform wave element observation equipment with image recognition technology is an innovation that applies advanced image processing technology to wave observation. By deploying high-resolution cameras on the buoy platform to capture real-time images of sea surface waves, image recognition and machine learning algorithms are used to automatically identify and analyze wave features. It can provide more accurate and comprehensive wave data and has unique advantages in wave shape and surface texture analysis. The main uses include accurately monitoring changes in the marine environment, supporting offshore operation safety, optimizing the design and operation of marine energy facilities, and improving the accuracy of weather forecasts. The development will help strengthen the combination of marine scientific research and practical applications and provide technical support for sustainable development of the ocean. However, the existing buoy platform wave element observation equipment with image recognition technology has problems such as lack of comprehensive monitoring capabilities for a large range of ocean surfaces, difficulty in capturing subtle changes and short-term fluctuations in sea surface waves, and lack of comprehensive monitoring capabilities for a large range of ocean surfaces.

[0044] In this embodiment, a buoy platform wave element observation device is provided, such as Figure 1 As shown, the buoy platform wave element observation device 1 includes: an image capture module 11, a resource adjustment module 12, a wave height calculation module 13, a morphological modeling module 14, a feature analysis module 15 and a morphological analysis module 16.

[0045] For example, Figure 2 As shown, the image capturing module 11 includes: an angle adjusting submodule 111 , a capturing submodule 112 and an image reviewing submodule 113 .

[0046] In an optional embodiment, the image capture module 11 is used to control the camera to rotate around the buoy platform in all directions and obtain a target sea surface image set, and send the target sea surface image set to the resource adjustment module 12, the wave height calculation module 13 and the feature analysis module 15 respectively.

[0047] The camera is deployed on a rotatable bracket at the bottom of the upper platform of the buoy, and can rotate around the buoy platform to capture the real-time changes of sea surface wave elements. Furthermore, the upper platform of the buoy is located above the buoy platform and usually has specific functions and structures.

[0048] Furthermore, the target sea surface image set may include wave dynamic images in different time periods, sea surface state images under illumination changes, and environmental feature images of the sea area around the buoy.

[0049] First, the angle adjustment submodule 111 is used to adjust the rotation state of the camera and obtain a position adjustment data set of the camera, and the position adjustment data set is sent to the capture submodule 112 .

[0050] Specifically, the camera is mounted on a rotatable bracket, so the angle adjustment submodule 111 controls a precise stepping motor on the rotatable bracket to adjust the angle, thereby ensuring that the camera can rotate 360 ​​degrees without blind spots.

[0051] Furthermore, for the position and angle adjustment of the camera, an angle adjustment parameter is first set, and then the angle adjustment parameter can be automatically adjusted according to the dynamic changes of the sea surface waves, and the field of view coverage of the image can be optimized by continuously adjusting the angle adjustment parameter.

[0052] When adjusting the angle, the best camera orientation at each time point can be calculated first according to the movement trend and speed of the waves on the sea surface. Further, the adjustment is achieved through a feedback device. For example, the device dynamically adjusts the parameter value according to the image quality captured at the previous moment, so that the camera can capture the best sea surface viewing angle and generate position adjustment data, as shown in the following relationship:

[0053] θ opt =θ 0 +k·Δθ

[0054] Where: θ opt Indicates the optimal angle adjustment value; θ 0 represents the initial angle; k represents the adjustment coefficient; Δθ represents the angle step of each adjustment.

[0055] Furthermore, the rotation state of the camera is continuously adjusted through the above-mentioned angle adjustment algorithm and the corresponding position adjustment data is obtained in real time to form a position adjustment data set and sent to the capture sub-module 112. Therefore, through the angle adjustment sub-module 111, the camera can be adjusted to an all-round rotatable state, thereby verifying the ability to capture the panoramic view of the sea surface. Furthermore, the image capture capability is optimized by rotating the angle and further generating position adjustment data.

[0056] Further, the obtained position-adjusted data set is sent to the capture submodule 112 .

[0057] Secondly, in the capture submodule 112, based on the position adjustment data set, the camera is controlled to rotate to obtain an initial sponge image set, and the initial sponge image set is timestamped to obtain a time stamp table, and the time stamp is sent to the image review submodule 113.

[0058] Specifically, after the capturing submodule 112 receives the position adjustment data set sent by the angle adjustment submodule 111 , it can control and start the real-time video capturing function of the camera.

[0059] Furthermore, when the real-time video capture function of the camera is activated, the specific adjustment parameters of the camera can be calculated according to the real-time received position adjustment data. Each adjustment parameter can represent a specific angle to which the camera should be adjusted. Furthermore, the specific angle can be determined according to the real-time analyzed sea surface wave dynamic data to ensure that each angle can capture the key visual information of the sea surface waves to the maximum extent.

[0060] Furthermore, the capture submodule 112 can accurately adjust the camera position according to the received position adjustment data set to optimize the field of view. At the same time, the camera adjustment action is synchronized with the camera video capture device to ensure the real-time and continuity of the image data.

[0061] Specifically, the camera starts capturing video immediately after adjusting to each new position, that is, when the capture submodule 112 receives the corresponding position adjustment data, and during the capture process, the video is automatically timestamped. The timestamp can reflect the specific moment of image capture.

[0062] Furthermore, the final time stamp table can be obtained through the timestamp marking, as shown in the following relationship:

[0063] T s =t 0 +n·Δt

[0064] Where: T s Indicates the timestamp of real-time video capture; t 0represents the initial time when video capture starts; n represents the number of frames since the start of the video; Δt represents the time interval between each frame.

[0065] Further, the obtained time stamp table is sent to the image review submodule 113.

[0066] Finally, the image review submodule 113 is used to analyze and process the time stamp to obtain a target sea surface image set.

[0067] When the image review submodule 113 receives the time stamp table sent by the capture submodule 112, it analyzes and processes the received time stamp table, removes the interference of the buoy itself and the flying of seabirds in the image, and further verifies the integrity and clarity of the sea surface image to obtain the final target sea surface image set.

[0068] Specifically, when the image review submodule 113 analyzes and processes the received time stamp table, in order to ensure that the image mainly displays the sea surface wave elements, a set of image analysis programs can be used to analyze the content of each frame of the image to identify and eliminate the interference of the buoy itself and non-wave elements such as seabirds. For example, first, a specific algorithm is used to identify the interference of the buoy itself, for example, according to the shape, color, texture and other characteristics of the buoy. Once the buoy is identified, the program can adopt the method of blocking, blurring or directly eliminating the buoy from the image to reduce its impact on the display of wave elements. Secondly, for non-wave elements such as seabirds, the program can use object detection technology. According to the appearance characteristics, movement patterns and the like of seabirds, they are identified. After the seabirds are identified, the elimination method can also be used to make the image mainly focus on the sea surface wave elements. Among them, during the implementation process, it is necessary to continuously adjust and optimize the parameters of the image analysis program to improve the accuracy and efficiency of recognition. At the same time, the image processed by the program can also be reviewed in combination with manual inspection to ensure that the wave elements are best displayed.

[0069] Furthermore, a customized image processing parameter can be pre-set, and the sensitivity of the objects to be identified and removed in the image can be controlled by using the image processing parameter. Thus, the accuracy of image review can be improved by adjusting the image processing parameter. The customized image processing parameter can be determined based on the objects to be identified and removed in the image, such as image contrast, brightness, color saturation, etc.

[0070] Specifically, during the adjustment of image processing parameters, the image processing parameters can be changed slightly to observe the impact on the objects to be identified and rejected. The audit results under different parameter combinations can be recorded to find the best parameter settings to improve the accuracy of image audit. Furthermore, multiple sets of images can be used for comparative testing to ensure that the parameters can maintain a high audit accuracy in different scenarios.

[0071] Furthermore, by using advanced image recognition technology, each non-wave element can be accurately marked and classified so that it can be eliminated before generating a set of sea surface images.

[0072] Furthermore, the integrity and clarity of the sea surface image are verified and the final target sea surface image set is generated, as shown in the following relationship:

[0073] β eff =β 0 ·(1-e -λ·x )

[0074] Where: β eff represents the effective image processing parameters; β 0 represents the baseline image processing parameters; λ represents the adjustment factor; x represents the proportion of non-wave elements that need to be removed.

[0075] Finally, the obtained target sea surface image set is sent to the resource adjustment module 12, the wave height calculation module 13 and the feature analysis module 15 respectively.

[0076] For example, Figure 3 As shown, the resource adjustment module 12 includes: a performance evaluation submodule 121 , a priority configuration submodule 122 and a resource allocation submodule 123 .

[0077] Optionally, the priority configuration submodule 122 includes: a determination unit 1221 and a configuration unit 1222 ; the resource allocation submodule 123 includes: a calculation unit 1231 and an allocation unit 1232 .

[0078] In an optional implementation, the resource adjustment module 12 is used to obtain an optimized resource configuration result based on the target sea surface image set through a priority processing method and a resource allocation method, and send the optimized resource configuration result to the wave height calculation module 13.

[0079] Among them, the optimization resource configuration results may include priority adjustment of data processing speed, priority allocation of key data storage space and temporary data caching strategy.

[0080] First, the target sea surface image set is processed and analyzed by the performance evaluation submodule 121 to obtain a performance parameter set, and the performance parameter set is sent to the priority configuration submodule 122 .

[0081] Among them, the performance parameter set is used to reflect the processing speed and storage capacity of the target sea surface image, that is, to reflect the processing speed and storage capacity of the buoy platform wave element observation device 1 for processing images, which can be obtained by analyzing the processing and storage requirements of the sea surface image set.

[0082] Furthermore, the target sea surface image set contains a batch of sea surface wave information. Therefore, when performing performance evaluation, it is necessary to calculate the speed at which the buoy platform wave element observation device 1 processes images and the space required to store images.

[0083] Specifically, when processing resource consumption at different image resolutions and complexities, the actual performance can be compared with the expected target to identify bottlenecks in processing power and storage limitations, automatically record bottlenecks, and adjust internal parameters to try to optimize performance, generating performance evaluation results, namely performance parameters, as shown in the following relationship:

[0084]

[0085] Where: R represents the performance evaluation result; v represents the image processing speed; c represents the image storage capacity; b represents the bottleneck of processing power; l represents the storage limitation.

[0086] Further, the obtained performance parameter set is sent to the priority configuration submodule 122 .

[0087] Secondly, in the priority configuration submodule 122 , the image processing priority of the target sea surface image set is adjusted according to the performance parameter set to obtain the target image processing priority, and the target image processing priority is sent to the resource allocation submodule 123 .

[0088] Specifically, when the priority configuration submodule 122 receives the performance parameter set, in the determination unit 1221, by analyzing the performance parameter set, key image processing requirements in the buoy platform wave element observation device 1, such as real-time image processing speed and data storage speed, can be identified.

[0089] Furthermore, in the configuration unit 1222, the execution priority of the processing and storage tasks can be set, and the priority parameters can be adjusted through a set of algorithms to ensure that the key tasks are executed first and the key data are processed and saved in time. The specific process involves the resource consumption and importance evaluation of each task to ensure the optimal resource allocation, and the adjusted priority setting, i.e., the target image processing priority, is obtained, as shown in the following relationship:

[0090]

[0091] Where: P represents the task execution priority; p img Indicates the initial priority of image processing; p data Indicates the initial priority of data storage; ω img and ω dataIt represents the weight coefficient, which can be determined based on experience and business needs. For example, if image processing tasks are usually more important than data storage tasks, a larger weight coefficient can be given to the initial priority of image processing. At the same time, the resource consumption of different tasks should also be considered to avoid giving too high a priority to tasks that consume too much resources.

[0092] Among them, a set of algorithms for adjusting priority parameters can be a simple weighted average method, an algorithm based on queuing theory, an algorithm based on machine learning, etc. The priority of the task is adjusted by a determined priority adjustment algorithm. The priority adjustment function can be implemented in the task scheduler to ensure that key tasks are executed first. At the same time, during the adjustment process, attention should be paid to the dependencies between tasks to avoid deadlock or other problems between tasks caused by priority adjustment.

[0093] Further, the obtained target image processing priority is sent to the resource allocation submodule 123 .

[0094] Finally, in the resource allocation submodule 123, the target image processing priority is used to optimize resource allocation to obtain an optimized resource configuration result.

[0095] Specifically, when the resource allocation submodule 123 receives the adjusted target image processing priority, it can use the target image processing priority to calculate the first resource requirement reflecting the resource requirement of the image processing task and the second resource requirement reflecting the resource requirement of the image storage task in the calculation unit 1231. Further, the obtained first resource requirement and second resource requirement are sent to the allocation unit 1232.

[0096] Furthermore, after the allocation unit 1232 receives the first resource requirement and the second resource requirement, it can use the resource allocation algorithm to optimize the execution of the task, and by adjusting the resource allocation ratio, improve the response speed and processing efficiency of key tasks and obtain the final optimized resource configuration result.

[0097] Specifically, the resource allocation algorithm can be dynamically adjusted based on the current resource usage to ensure that high-priority tasks obtain the necessary processing power and storage space, improve the performance of the overall device, and generate an optimized resource configuration result U, as shown in the following relationship:

[0098]

[0099] Where: U represents the optimized resource utilization rate; T proc represents the first resource demand; T store represents the second resource demand; r proc Indicates the resource allocation ratio allocated to image processing tasks; r storeIndicates the resource allocation ratio allocated to the image storage task.

[0100] Finally, the obtained optimized resource allocation result is sent to the wave height calculation module 13.

[0101] For example, Figure 4 As shown, the wave height calculation module 13 includes: an element measurement submodule 131 , an image processing submodule 132 and a wave height analysis submodule 133 .

[0102] In an optional embodiment, the wave height calculation module 13 is used to identify and process the target sea surface image set based on the optimized resource allocation result using image recognition technology to obtain wave height period data, and send the wave height period data to the morphological modeling module 14.

[0103] The wave height cycle data may include the average wave height within the wave cycle, the wave duration, and the interval time between the wave peaks and wave troughs within the cycle.

[0104] First, in the element measurement submodule 131 , based on the result of optimizing resource allocation, the target sea surface image set is loaded and analyzed using image recognition technology to generate wave element data, and the wave element data is sent to the image processing submodule 132 .

[0105] Specifically, after the wave height calculation module 13 receives the optimized resource configuration result, based on the optimized resource configuration result, the image recognition technology is used in the element measurement submodule 131 to load the wave element image and process it to improve the accuracy of the analysis.

[0106] Among them, image recognition technology is used to locate and measure the length fluctuations of the rubber band in the image. The process involves continuous tracking of the length changes of the rubber band in each frame of the image.

[0107] Specifically, after receiving the image data, the edge and width of the rubber band in the image are analyzed to accurately capture the ups and downs of the rubber band. By comparing the changes between consecutive frames, the highest and lowest points of the rubber band are identified and the real-time length of the rubber band is calculated. The length data is analyzed in time series to identify the periodic fluctuations of the length and calculate the height and period of the wave.

[0108] During the recognition process, errors caused by camera angle and light changes are automatically corrected to ensure the accuracy of the measurement data. At the same time, by setting the reference point and calibration length standards, the parameters can be automatically adjusted to adapt to the measurement requirements under different environmental conditions.

[0109] Furthermore, after each measurement is completed, the measurement results are automatically stored, and the wave height is calculated to be an average of 1.2 meters and the period is about 5.8 seconds, which can help evaluate the physical impact of the marine environment on the rubber belt and generate wave element data.

[0110] Furthermore, the image recognition technology is shown in the following relationship:

[0111]

[0112] Where: d represents the length fluctuation of the wave element; x 1 and x 2 They represent the x coordinates of the starting point and the end point of the wave element in the image; y 1 and 2 They represent the y coordinates of the starting point and the end point of the wave element in the image; c 1 and c 2 Represents the color intensity at the starting point and the end point respectively; l 1 and l 2 They represent the brightness at the starting point and the end point respectively; α and β represent the weight coefficients.

[0113] Furthermore, the calculation process of the above relationship may specifically include: measuring and recording the coordinates x of the starting point and the end point of the wave element in the image 1 、x 2 ,y 1 and 2 , calculate the basic length fluctuation of the wave element, measure the color intensity c at the start and end points 1 and c 2 , and calculate the square difference to measure the brightness l at the starting point and the end point 1 and l 2 , and calculate the square difference, determine the weight coefficients α and β, and use historical data analysis and model optimization methods, use regression analysis or optimization algorithm to determine the optimal value of the coefficient, substitute all parameters into the improved formula for calculation, and get the length fluctuation d of the wave element.

[0114] Further, the obtained wave element data is sent to the image processing submodule 132 .

[0115] Secondly, in the image processing submodule 132 , the wave element data is used to optimize the target sea surface image set and identify the key features of the wave element changes, generate wave profile data, and send the wave profile data to the wave height analysis submodule 133 .

[0116] Specifically, the clarity of the image can be optimized through advanced image processing technology, as shown in the following relationship:

[0117]

[0118] Where: C represents the optimized image clarity; p i represents the initial clarity value of each pixel in the wave element image, where the wave element image can be determined based on the target sea surface image after optimization processing; q i It represents the quality improvement coefficient of each pixel during the processing; T represents the total number of pixels in the image.

[0119] Furthermore, the visualization quality of the wave elements can be optimized by optimizing the clarity of the image. The image optimization process may include sharpening, contrast adjustment, and noise removal of the image to highlight the key features of the wave elements.

[0120] Further, the changes of wave elements in the image, such as changes in wave shape and size, are identified and recorded to generate wave profile data.

[0121] Among them, wave shape recognition can detect the edges of waves in the image through edge detection algorithms, such as Canny edge detection, Sobel operator, etc., and then perform shape analysis on the detected edges, such as calculating the curvature, bending and other parameters of the waves to describe the shape characteristics of the waves. Furthermore, mathematical morphological methods, such as expansion, corrosion, opening and closing operations, can be used to further process edge images, remove noise and small interference, and make the wave shape clearer.

[0122] Furthermore, the contour data of the wave can be extracted based on the results of edge detection and shape analysis. For example, the contour can be represented as a series of coordinate points or a curve equation.

[0123] Further, the obtained wave profile data is sent to the wave height analysis submodule 133 .

[0124] Finally, the wave height analysis submodule 133 uses the received wave profile data to evaluate the height and periodicity characteristics of the waves to obtain wave height period data.

[0125] Specifically, when the wave height analysis submodule 133 receives the wave profile data, it can use advanced algorithms to analyze the vertical distance between the peaks and troughs identified in the image. The analysis process can not only measure a single wave, but also involve distance measurements for multiple wave cycles, so that the trend of distance changes over time can be observed and evaluated.

[0126] Furthermore, wave profile data can reflect the height and periodicity characteristics of waves, which helps to understand the dynamic changes of the ocean environment. Therefore, wave height period data can be generated by calculating the average vertical distance between the crest and the trough, as shown in the following relationship:

[0127]

[0128] Where: H represents the average wave height period data; h peak Indicates the peak height in each cycle; h valley represents the trough height in each cycle; M represents the number of peak and trough pairs.

[0129] Finally, the obtained wave height period data is sent to the morphological modeling module 14 .

[0130] For example, Figure 5 As shown, the morphological modeling module 14 includes: a data analysis submodule 141 , a surface measurement submodule 142 and a modeling submodule 143 .

[0131] Optionally, the data analysis submodule 141 includes: a data processing unit 1411 and an analysis unit 1412 .

[0132] In an optional embodiment, the morphological modeling module 14 is used to model the morphology of wave elements based on wave height period data using a Riemann geometry method to obtain a wave geometry model, and send the wave geometry model to the feature analysis module 15 .

[0133] The wave geometry model may include a geometric description of the wave surface, a three-dimensional model of the wave shape, and a numerical value of the wave curvature.

[0134] Firstly, in the data analysis submodule 141 , based on the wave height periodicity data, a statistical analysis method is used to obtain a wave height periodicity analysis result, and the wave height periodicity analysis result is sent to the surface measurement submodule 142 .

[0135] Specifically, after receiving the wave height period data, the data processing unit 1411 is used to filter and sort the wave height period data to remove any abnormal or invalid data points to ensure the accuracy of the analysis.

[0136] Further, the filtered wave height period data is sent to the analysis unit 1412.

[0137] Furthermore, statistical analysis techniques such as time series analysis and pattern recognition may be used in the analysis unit 1412 to identify key patterns and trends from the wave height period data.

[0138] In an optional embodiment, a clustering algorithm, such as K-Means clustering, hierarchical clustering, etc., can be used to divide the wave height data into different modes or categories. Clustering is performed according to the size, change trend and other characteristics of the wave height to identify different wave behavior patterns.

[0139] Further, the following methods can be used to identify trends:

[0140] 1. Trend analysis

[0141] (1) Use linear regression, moving average and other methods to analyze the trend of wave height over time. Determine whether there is a long-term upward or downward trend, as well as the strength and stability of the trend.

[0142] (2) Draw a time series graph of wave height to visually observe the trend changes. You can use drawing tools in statistical software or programming languages, such as Python's Matplotlib library or R's ggplot2 package.

[0143] 2. Periodic analysis

[0144] (1) Use Fourier transform, spectrum analysis and other techniques to identify periodic components in wave height data and determine the main period lengths, such as seasonal periods, daily periods, etc.

[0145] (2) Display the energy distribution of different frequency components by drawing a spectrum or power spectrum density diagram. This can help determine which periods contribute more to the wave height variation.

[0146] 3. Autocorrelation analysis

[0147] (1) Calculate the autocorrelation function of the wave height time series and analyze the autocorrelation of the data. The autocorrelation function can reveal the similarities of the data at different time lags and help discover potential periodicity and trends.

[0148] (2) Based on the results of the autocorrelation function, determine the appropriate time lag range for further analysis. For example, if the autocorrelation function shows a clear peak at a certain time lag, it may indicate that there is a periodic change of the corresponding period.

[0149] Through analysis, periodic changes can be identified, such as seasonal changes in wave height with seasons or weather conditions. Furthermore, the key patterns and trends identified can be used to predict future ocean wave behavior and generate corresponding periodic analysis results.

[0150] Secondly, in the surface measurement submodule 142 , the wave height periodicity analysis result is used to analyze the wave physical properties to obtain wave surface characteristic data, and the wave surface characteristic data is sent to the modeling submodule 143 .

[0151] Specifically, after receiving the wave height periodicity analysis result, the surface measurement submodule 142 can use advanced image processing and geometric analysis technology to measure the geometric properties of the wave image, especially the principal curvature and Gaussian curvature. Among them, the geometric properties can reflect the complexity and variability of the wave surface, which is helpful to analyze the physical properties of the wave, as shown in the following relationship:

[0152]

[0153] Where: K represents the Gaussian curvature of the wave surface; r 1 and r 2 Represents the principal radius of curvature at any point on the wavy surface.

[0154] Furthermore, the curvature of each wave can be accurately calculated, the surface characteristics of the wave can be classified, and the data can be associated with environmental factors to explore the changes in wave morphology under different weather conditions and obtain wave surface characteristic data. Among them, the classification method can adopt cluster analysis, principal component analysis and other methods. Through cluster analysis, waves with similar characteristics can be classified into one category, and through principal component analysis, the main characteristic dimensions can be extracted to reduce the complexity of the data.

[0155] Furthermore, the wave data and the environmental factor data may be associated with each other using timestamp or geographic location information.

[0156] Furthermore, statistical analysis methods, such as correlation analysis and regression analysis, can be used to explore the relationship between wave surface characteristics and environmental factors, to determine which environmental factors have the greatest impact on the change of wave morphology, and the quantitative relationship between them.

[0157] Further, the obtained wave surface characteristic data is sent to the modeling submodule 143.

[0158] Finally, in the modeling submodule 143, based on the wave surface feature data, the morphology of the wave elements is modeled using the Riemann geometry method to obtain a wave geometry model.

[0159] Specifically, when the modeling submodule 143 receives the wave surface feature data, it can use the Riemann geometry method to model the wave shape in detail. At the same time, during the modeling process, not only the local geometric characteristics of the wave are considered, but also the overall shape and structure are modeled as a continuously changing geometric body.

[0160] Exemplarily, an imaging device is used to continuously perform high-precision three-dimensional scanning of waves to capture detailed geometric data of the wave surface. Further, the data points are reconstructed in three dimensions to form a geometric model of the wave, and surface analysis technology is applied to the model to calculate in detail the principal curvature of each wave surface point, that is, the curvature in the direction of maximum and minimum curvature of the surface at the wave surface point, and the second-order derivative of the local fitting surface of the wave surface is accurately calculated. At the same time, the calculation parameters can be automatically adjusted according to the complexity of the wave geometric model to ensure the accuracy of the calculation results and the optimization of the processing speed.

[0161] Furthermore, the model is able to describe the dynamic changes in wave morphology and accurately analyze the geometric characteristics of waves through a mathematical framework, which can be used to analyze and predict the behavior and dynamics of waves, helping marine scientists and engineers to better understand and predict the behavior of ocean waves and generate wave geometry models.

[0162] Among them, the Riemann geometry method is shown in the following relationship:

[0163]

[0164] Where: K represents Gaussian curvature; R 1212 represents the components of the Riemann curvature tensor; g represents the determinant of the metric tensor; H represents the height of the wave; S represents the slope of the wave; D represents the density of the wave; α, β and γ represent weight coefficients.

[0165] Furthermore, the calculation process of the above relationship may specifically include: measuring and recording the Riemann curvature tensor component R of the wave surface 1212 , calculate the metric tensor determinant g of the wave surface and record it, measure the wave height H, the wave slope S and the wave density D, determine the actual values ​​of the parameters, determine the weight coefficients α, β and γ, and use historical data analysis and model optimization methods, using regression analysis or optimization algorithms to determine the optimal values ​​of the coefficients. Substitute all parameters into the improved formula for calculation to obtain the Gaussian curvature value K of the wave surface.

[0166] Finally, the obtained wave geometry model is sent to the feature analysis module 15 .

[0167] For example, Figure 6 As shown, the feature analysis module 15 includes: a model application submodule 151, a positioning calculation submodule 152 and a fluctuation trend analysis submodule 153.

[0168] In an optional embodiment, the feature analysis module 15 is used to use a wave geometry model to identify the crests and troughs of wave elements in the target sea surface image set, obtain wave feature data, and send the wave feature data to the morphological analysis module 16.

[0169] Among them, wave characteristic data may include classification and identification of wave forms, summary of wave characteristic parameters and marking data of key wave events.

[0170] First, the model data of the wave geometry model is loaded and analyzed by the model application submodule 151 to obtain the geometry model analysis result, and the geometry model analysis result is sent to the positioning calculation submodule 152 .

[0171] Specifically, after receiving the wave geometry model, loading the wave geometry model data may include extracting the three-dimensional coordinates and time series data of the wave model. Further, the extracted data is preliminarily screened and records with unclear physical meaning or damaged data are excluded.

[0172] Furthermore, the key geometric features in the screened model data are analyzed in detail, which may include the calculation of wavelength, wave height and wave speed.

[0173] Among them, an improved geometric feature extraction algorithm can be used in the analysis process. This algorithm can accurately identify the positions of peaks and troughs by quantitatively analyzing the curvature and gradient changes of the model, as shown in the following relationship:

[0174]

[0175] Where: L represents wavelength; x i and x i+1 They represent the position coordinates of two consecutive peaks respectively; n represents the number of peaks.

[0176] Furthermore, relevant wave elements can be matched according to the observation requirements of the buoy platform, such as waves that meet specific heights and periods, and the corresponding geometric model analysis results can be generated.

[0177] Furthermore, the generated geometric model analysis result is sent to the positioning calculation submodule 152 .

[0178] Secondly, in the positioning calculation submodule 152, the geometric model analysis results are used to identify the crests and troughs in the wave elements in the target sea surface image set and generate crest and trough positioning data, and the crest and trough positioning data are sent to the wave trend analysis submodule 153.

[0179] Specifically, after receiving the geometric model analysis results, the crest and trough data contained in the geometric model analysis results can be used to conduct a detailed analysis of the observation data, i.e., the target sea surface image set, and identified through the set geometric matching algorithm. Not only can the crests and troughs in each wave element be identified, but the specific coordinates of the key points can also be located.

[0180] Furthermore, the accuracy of the data can be verified by comparing the similarity between the observed data and the geometric model. If the deviation between the observed data and the model analysis result exceeds the preset threshold, the device will mark the source of the error and generate peak and valley positioning data, as shown in the following relationship:

[0181]

[0182] Where: S represents the average deviation between the observed data and the model data; p iIndicates the peak or trough position in the observation; m i represents the corresponding position in the model analysis result; n represents the total number of observation points.

[0183] Finally, in the wave trend analysis submodule 153, the wave peak and trough positioning data are used to analyze the wave wave trend and amplitude change and generate wave characteristic data.

[0184] Specifically, when the wave trend analysis submodule 153 receives the peak and trough positioning data, it performs calculation and comparison of the wave element positions according to the peak and trough positioning data, calculates the height of each wave, that is, the maximum vertical distance from the trough to the peak, and analyzes the time difference between two consecutive peaks as an estimated value of the wave period.

[0185] Furthermore, by analyzing the fluctuation trend and amplitude change of the waves, the vertical distance between the crest and the trough and its change over time can be calculated, and the change can provide a detailed description of the wave motion.

[0186] Specifically, the linear regression model can be used to estimate the changing trend of wave height and period, analyze the regularity and changes of wave behavior in different time periods, help researchers and engineers understand wave dynamics, and predict future changes, and explore the growth trend of wave height and period during the observation period, providing important information for ocean observation and research, and generating wave characteristic data, as shown in the following relationship:

[0187]

[0188] Where: V represents the average moving speed of the wave; P peak,i represents the position of the i-th peak; P trough,i represents the position of the i-th trough; t i and t i+1 represents the time points of two consecutive observations; w i Represents the weight coefficient.

[0189] For example, Figure 7 As shown, the morphological analysis module 16 includes: a data processing submodule 161 , a behavior pattern comparison submodule 162 and a behavior evaluation submodule 163 .

[0190] In an optional embodiment, the morphological analysis module 16 is used to identify and evaluate the regularity and change trend of wave behavior based on wave characteristic data using a preset prediction model to obtain a wave behavior analysis result.

[0191] The wave behavior analysis results may include time series analysis of wave changes, comparative analysis of wave behavior under differentiated sea conditions, and trend data for predicting wave patterns in future time periods.

[0192] First, in the data processing submodule 161 , the wave characteristic data is used to perform wave form recognition to obtain wave form data, and the wave form data is sent to the behavior pattern comparison submodule 162 .

[0193] Specifically, after receiving the wave characteristic data, the data processing submodule 161 performs preliminary classification processing on the received wave characteristic data, and sorts the processed wave characteristic data according to its geometric characteristics such as wavelength and wave height. Further, after sorting, a specific morphology recognition algorithm can be used to extract the basic morphology of each wave, such as a sine waveform, a sawtooth waveform, etc.

[0194] Furthermore, in order to accurately match the requirements of the buoy platform wave element observation device 1, the scope of data analysis can also be adjusted according to the technical specifications of the buoy to ensure the accuracy and practicality of data processing.

[0195] In an optional embodiment, the technical specifications of the buoy may include:

[0196] (1) Measurement range: Determine the range of wave elements that the buoy can accurately measure, such as wave height, period, direction, etc.

[0197] (2) Accuracy requirements: Understand the accuracy requirements of the buoy for wave element measurement, which will affect the accuracy target of data analysis.

[0198] (3) Sampling frequency: Determine the frequency with which the buoy collects data so that the time scale can be appropriately selected in data analysis.

[0199] (4) Data storage capacity: Consider the amount of data that the buoy can store in order to determine the time span of data analysis and the scale of data processing.

[0200] (5) Communication method: Understand the communication method and data transmission rate between the buoy and the data receiver in order to optimize the data processing and transmission process.

[0201] Furthermore, the scope of data analysis can be adjusted according to the technical specifications of the buoy, and can specifically include the following:

[0202] 1. Data screening

[0203] (1) According to the measurement range and accuracy requirements of the buoy, the collected wave element data are screened. Data points that are beyond the measurement range of the buoy or have unreliable accuracy are removed to ensure the accuracy of the analysis results.

[0204] (2) Data filtering algorithms or statistical methods, such as outlier detection and removal, can be used to screen the data.

[0205] 2. Time scale adjustment

[0206] (1) Consider the sampling frequency and data storage capacity of the buoy and determine the appropriate time scale for data analysis. If the buoy sampling frequency is high, a shorter time interval can be selected for analysis to capture the rapid changes in waves. If the data storage capacity is limited, a longer time span can be selected for analysis to obtain more representative wave characteristics.

[0207] (2) The time scale can be adjusted by adjusting the time window size of the data analysis or by using different time steps in the time series analysis method.

[0208] 3. Spatial range adjustment

[0209] (1) If the buoy platform is deployed in a specific sea area or region, the spatial scope of data analysis can be adjusted according to the oceanographic characteristics of the region and the purpose of the research. For example, you can choose to focus on a specific sea area, water depth area, or area related to a specific ocean phenomenon.

[0210] (2) Geographic Information System (GIS) technology or spatial data analysis methods can be used to spatially screen and aggregate data to meet specific spatial range requirements.

[0211] 4. Variable Selection

[0212] (1) According to the measurement capability of the buoy and the research requirements, appropriate wave element variables are selected for analysis. In addition to the basic wave height, period and direction, other relevant variables can also be considered, such as wave steepness, wavelength, energy spectrum, etc.

[0213] (2) Through correlation analysis, principal component analysis and other methods, the variables that have a greater impact on wave characteristics can be determined and included in the scope of data analysis.

[0214] Furthermore, by analyzing the performance of wave data in different time periods, the setting parameters of the buoy platform wave element observation device 1 can be adjusted and optimized to meet the observation requirements of different wave behaviors and generate corresponding wave shape data.

[0215] Further, the obtained wave shape data is sent to the behavior pattern comparison submodule 162 .

[0216] Secondly, in the behavior pattern comparison submodule 162 , the wave morphology data is used to analyze the consistency and difference of the wave behavior, generate the wave pattern difference analysis result, and send the wave pattern difference analysis result to the behavior evaluation submodule 163 .

[0217] Specifically, the performance of waves in different time periods can be analyzed based on the geometric characteristics of waves contained in the wave morphology data, such as wavelength and wave height, and the data can be analyzed in time series to further identify the statistical characteristics of the wave morphology in each time period, such as the average wavelength and maximum wave height.

[0218] Furthermore, statistical analysis can be used to further identify special patterns of wave behavior in differentiated time periods, such as unusual wave activity during a particular storm. The identification process may involve calculating the coefficient of variation and correlation coefficient of wave characteristics in different time periods, as shown in the following relationship:

[0219]

[0220] Where: R represents the degree of differentiation of wave behavior; P t Represents the wave shape data at time t; std(P t ) represents the standard deviation of the wave data; μ(P t ) represents the average value; T 1 Represents the total number of observation time periods.

[0221] Furthermore, the consistency and difference of wave behavior can be determined through the coefficient of variation and correlation coefficient.

[0222] Furthermore, corresponding wave pattern difference analysis results can be generated through calculation.

[0223] Further, the obtained wave pattern difference analysis results are sent to the behavior evaluation submodule 163 .

[0224] Finally, in the behavior evaluation submodule 163, based on the wave pattern difference analysis results, the regularity and change trend of the wave behavior are identified and evaluated using a preset prediction model to obtain the wave behavior analysis results.

[0225] Specifically, after receiving the wave pattern difference analysis results, the wave pattern difference analysis results are used to conduct an in-depth assessment of the wave behavior, and key indicators in the difference analysis results, such as the frequency and amplitude change trends of wave activities, are analyzed. Further, the regularity and periodic changes of wave behavior can be identified by analyzing the key indicators.

[0226] Furthermore, the time series analysis method can be used to evaluate the past wave behavior data, and based on the data, the preset prediction model can be used to predict the wave behavior pattern in the future time period. Among them, the preset prediction model combines linear and nonlinear analysis, taking into account the seasonal changes and random fluctuations of historical data, and generates the wave behavior analysis results, as shown in the following relationship:

[0227]

[0228] Where: P future It means predicting the future wave behavior pattern; Represents the average mode of wave behavior in the current analysis period; σ(P current ) represents the standard deviation of the current wave behavior; α and β represent adjustment parameters.

[0229] The buoy platform wave element observation device provided in this embodiment can capture the real-time changes of sea surface wave elements by deploying a camera at the bottom of the buoy platform and rotating around the buoy platform to shoot, check the image integrity of the wave elements, and can fully capture the wave characteristics of the ocean surface. By detecting the processing capacity and storage space of the wave element observation equipment, the priority of image processing is adjusted to ensure the efficiency and accuracy of image data processing. When measuring the length fluctuation of the rubber belt in the wave element image, the image recognition technology is used to accurately calculate the height and period of the wave, which not only improves the measurement accuracy, but also monitors the wave changes in real time. According to the wave height period data, the Riemann geometry method is used to model the wave elements, and the crests and troughs of the wave elements observed by the buoy platform are identified by measuring the surface characteristics of the waves, including the principal curvature and Gaussian curvature. The continuous processing logic makes the entire device significantly improved in terms of accuracy, real-time and data integrity. By analyzing the wave feature data, comparing the behavior patterns of waves in different time periods, identifying and evaluating the regularity and change trend of wave behavior, it provides strong data support for monitoring marine environmental changes, offshore operation safety, optimal design and operation of marine energy facilities, and improving the accuracy of weather forecasts.

[0230] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A buoy platform wave element observation device, characterized in that: A camera is arranged at the bottom of the upper platform of the buoy, and the upper platform of the buoy is located above the buoy platform. The device comprises: an image capture module, a resource adjustment module, a wave height calculation module, a morphology modeling module, a feature analysis module and a morphology analysis module; The image capture module is used to control the camera to rotate around the buoy platform in all directions and obtain a target sea surface image set, and send the target sea surface image set to the resource adjustment module, the wave height calculation module and the feature analysis module respectively; The resource adjustment module is used to obtain an optimized resource configuration result based on the target sea surface image set through a priority processing method and a resource allocation method, and send the optimized resource configuration result to the wave height calculation module, wherein the optimized resource configuration result is used to reflect the response speed and processing efficiency of the image processing task after optimization; The wave height calculation module is used to identify and process the target sea surface image set based on the optimized resource allocation result using image recognition technology to obtain wave height period data, and send the wave height period data to the morphological modeling module; The morphology modeling module is used to model the morphology of wave elements based on the wave height period data using the Riemann geometry method to obtain a wave geometry model, and send the wave geometry model to the feature analysis module; The feature analysis module is used to identify the crests and troughs of the wave elements in the target sea surface image set by using the wave geometry model, obtain wave feature data, and send the wave feature data to the morphology analysis module; The morphological analysis module is used to identify and evaluate the regularity and change trend of wave behavior based on the wave characteristic data using a preset prediction model to obtain a wave behavior analysis result.

2. The device according to claim 1, characterized in that The image capture module includes: an angle adjustment submodule, a capture submodule and an image review submodule; The angle adjustment submodule is used to adjust the rotation state of the camera and obtain a position adjustment data set of the camera, and send the position adjustment data set to the capture submodule; The capture submodule is used to control the rotation of the camera to obtain an initial sponge image set based on the position adjustment data set, and to timestamp the initial sponge image set to obtain a time stamp table, and to send the time stamp table to the image review submodule; The image review submodule is used to analyze and process the time stamp table to obtain a target sea surface image set.

3. The device according to claim 1, characterized in that The resource adjustment module includes: a performance evaluation submodule, a priority configuration submodule and a resource allocation submodule; The performance evaluation submodule is used to process and analyze the target sea surface image set to obtain a performance parameter set, and send the performance parameter set to the priority configuration submodule, wherein the performance parameter set is used to reflect the processing speed and storage capacity of the target sea surface image; The priority configuration submodule is used to adjust the image processing priority of the target sea surface image set based on the performance parameter set to obtain the target image processing priority, and send the target image processing priority to the resource allocation submodule; The resource allocation submodule is used to optimize resource allocation by utilizing the target image processing priority to obtain the optimized resource configuration result.

4. The device according to claim 3, characterized in that The priority configuration submodule includes: a determination unit and a configuration unit; The determining unit is configured to determine an image processing requirement based on the performance parameter set, and send the image processing requirement to the configuring unit; The configuration unit is used to adjust the image processing priority of the target sea surface image set by using the image processing requirement to obtain the target image processing priority.

5. The device according to claim 3, characterized in that The resource allocation submodule includes: a calculation unit and an allocation unit; The calculation unit is used to calculate a first resource requirement and a second resource requirement by using the target image processing priority, and send the first resource requirement and the second resource requirement to the allocation unit, wherein the first resource requirement is used to reflect the resource requirement of the image processing task, and the second resource requirement is used to reflect the resource requirement of the image storage task; The allocation unit is used to obtain the optimized resource configuration result based on the first resource requirement and the second resource requirement through a resource allocation algorithm.

6. The device according to claim 1, characterized in that The wave height calculation module includes: an element measurement submodule, an image processing submodule and a wave height analysis submodule; The element measurement submodule is used to load and analyze the target sea surface image set based on the optimized resource configuration result using the image recognition technology and generate wave element data, and send the wave element data to the image processing submodule; The image processing submodule is used to optimize the target sea surface image set using the wave element data and identify key features of wave element changes, generate wave profile data, and send the wave profile data to the wave height analysis submodule; The wave height analysis submodule is used to evaluate the height and periodic characteristics of the waves using the wave profile data to obtain the wave height period data.

7. The device according to claim 1, characterized in that The morphological modeling module includes: a data analysis submodule, a surface measurement submodule and a modeling submodule; The data analysis submodule is used to obtain a wave height periodicity analysis result based on the wave height periodicity data through a statistical analysis method, and send the wave height periodicity analysis result to the curved surface measurement submodule; The surface measurement submodule is used to analyze the wave physical properties using the wave height periodicity analysis results to obtain wave surface characteristic data, and send the wave surface characteristic data to the modeling submodule; The modeling submodule is used to model the morphology of wave elements based on the wave surface feature data using the Riemann geometry method to obtain the wave geometry model.

8. The device according to claim 7, characterized in that The data analysis submodule includes: a data processing unit and an analysis unit; The data processing unit is used to filter the wave height period data and send the filtered wave height period data to the analysis unit; The analysis unit is used to identify the filtered wave height periodicity data using a statistical analysis method to obtain the wave height periodicity analysis result.

9. The device according to claim 1, characterized in that The feature analysis module includes: a model application submodule, a positioning calculation submodule and a fluctuation trend analysis submodule; The model application submodule is used to load and parse the model data of the wave geometric model to obtain a geometric model parsing result, and send the geometric model parsing result to the positioning calculation submodule; The positioning calculation submodule is used to identify the crests and troughs in the wave elements in the target sea surface image set by using the analysis results of the geometric model and generate crest and trough positioning data, and send the crest and trough positioning data to the wave trend analysis submodule; The fluctuation trend analysis submodule is used to analyze the fluctuation trend and amplitude change of the wave based on the peak and trough positioning data and generate the wave characteristic data.

10. The device according to claim 1, characterized in that The morphological analysis module includes: a data processing submodule, a behavior pattern comparison submodule and a behavior evaluation submodule; The data processing submodule is used to perform wave form recognition using the wave characteristic data to obtain wave form data, and send the wave form data to the behavior pattern comparison submodule; The behavior pattern comparison submodule is used to analyze the consistency and difference of wave behavior based on the wave form data, generate a wave pattern difference analysis result, and send the wave pattern difference analysis result to the behavior evaluation submodule; The behavior evaluation submodule is used to identify and evaluate the regularity and change trend of wave behavior based on the wave pattern difference analysis results using a preset prediction model to obtain a wave behavior analysis result.

Images