A multi-source heterogeneous data fusion oceanographic survey ship dynamic tracking and identification method

Abstract

This invention provides a method for dynamic tracking and identification of oceanographic survey vessels based on multi-source heterogeneous data fusion, comprising: constructing a dedicated information database for oceanographic survey vessels, collecting and storing the MMSI (Missing Data Identity) of oceanographic survey vessels; accessing a multi-source AIS (Airborne Information System) data service network, and acquiring real-time and historical trajectory data of the target survey vessel from the AIS data service network based on the target survey vessel's MMSI in the database; performing spatiotemporal analysis on the acquired AIS trajectory data to identify the operational behavior characteristics of the target survey vessel and predict its future operational activity area; using the operational behavior characteristics and the predicted future operational activity area as input, generating satellite imaging control commands using satellite mission programmable control technology to observe and image the target sea area; acquiring the imaged remote sensing data, and fusing the remote sensing data with AIS data within the corresponding spatiotemporal range of the image; and outputting the operational status information of the target survey vessel based on the fusion result.

Description

Technical Field

[0001] This invention belongs to the field of data processing and information fusion technology, and specifically relates to a method, device and readable storage medium for dynamic tracking and identification of marine survey vessels based on multi-source heterogeneous data fusion. Background Technology

[0002] In existing technologies, marine environmental elements, including marine meteorological elements, marine hydrological elements, marine geographical elements, and marine acoustic elements, are important factors affecting weaponry and maritime military activities, significantly impacting combat operations, military exercises, weapons testing, and disaster relief. Marine observation refers to the continuous, long-term observation of these elements using scientific instruments, which is of great significance for naval operations.

[0003] Oceanographic survey vessels are indispensable core platforms in the ocean observation system. Leveraging their specialized equipment, flexible operational capabilities, and continuous endurance, they play an irreplaceable role in areas such as oceanographic data acquisition, resource exploration, environmental monitoring, and engineering support. While not primarily tasked with direct firepower, oceanographic survey vessels provide an "invisible cornerstone" for modern naval operations, weapon effectiveness, and strategic deterrence through the systematic collection, analysis, and application of oceanographic data. They are the navy's "behind-the-scenes intelligence," and the oceanographic data they collect serves as a crucial link between equipment performance and the battlefield environment. From single-ship maneuvers to fleet deployments, from weapon launches to strategic deterrence, almost all naval operations rely on the oceanographic intelligence they provide.

[0004] Monitoring the activities of oceanographic survey vessels is a crucial link in safeguarding national maritime rights and interests, ensuring national defense security, and gaining the initiative on the battlefield. Its role and significance are mainly reflected in immediate security defense, strategic situational awareness, analysis of strategic intentions, early warning of potential military movements, and ultimately, providing solid environmental and intelligence support for maritime military operations and defense decision-making. In routine monitoring of oceanographic survey vessels, AIS (Automatic Identification System) and satellite remote sensing are the two most widely used technologies. However, both have significant limitations in practical operation, making it difficult to achieve effective, all-weather, high-precision, and comprehensive monitoring of survey vessels.

[0005] As a crucial technology for monitoring oceanographic survey vessels, Aerospace Information System (AIS) offers significant advantages in near-shore real-time monitoring, information richness, low cost, and ease of integration. It is particularly suitable for dynamic tracking, identification, and collaborative monitoring of oceanographic survey vessels in dense coastal environments. While it has limitations in far-sea coverage and anti-evasion capabilities, it remains an indispensable and efficient tool for routine near-shore monitoring, often working in conjunction with satellite remote sensing and radar to form a complementary monitoring system. AIS can acquire dynamic information about survey vessels, including position, heading, and speed, with a high update frequency, and can track their navigation trajectories. However, its limitations cannot be ignored. AIS relies on very high frequency (VHF) radio signals for transmission, but VHF signals are easily affected by the curvature of the earth, terrain (such as islands and mountains), and distance. AIS is highly dependent on the target ship's equipment and is ineffective against ships that actively shut down or deliberately avoid AIS signals. The information transmitted by AIS is mainly digital data, including static information of the ship (ship name, call sign, length, etc.) and dynamic information (position, speed, heading, etc.), but it has obvious limitations. It cannot provide key information such as the physical details of the surveying ship (such as hull size, whether it is carrying surveying equipment, draft), operational status (such as whether it is towing sonar, whether it has deployed detection equipment), and surrounding environmental correlation (such as whether there are surveying traces nearby, whether there are abnormal water features in the sea area). In addition, the VHF band is susceptible to radio frequency interference (such as other radio equipment, areas with complex electromagnetic environments), which can easily lead to signal loss or mistransmission.

[0006] Compared to AIS, satellite remote sensing technology has disadvantages in monitoring survey vessels, including poor timeliness, significant lag in dynamic tracking, and a lack of direct identification and attribute data due to its limited information dimensions. However, its advantages are equally significant. Satellite constellations can achieve global coverage, unaffected by distance or terrain. Satellite remote sensing imagery does not rely on any equipment; as long as the survey vessel is physically present on the water, its position and shape can be directly captured through imaging. It can still effectively monitor survey vessels that deliberately disable AIS signals. Satellite remote sensing imagery can directly present the appearance of the survey vessel (length, width, deck equipment), operational scenarios (such as the trajectory of equipment towed by the vessel), and the surrounding marine environment (such as water disturbance caused by surveying), providing intuitive evidence for determining the nature of its operations (such as hydrological surveying and geological exploration). Furthermore, SAR remote sensing imagery is unaffected by cloudy, rainy, or foggy weather, allowing for timely and effective monitoring of survey vessels.

[0007] In summary, AIS and satellite remote sensing technologies each have their own advantages and disadvantages in marine target monitoring, and neither single method can achieve all-weather, high-precision, multi-dimensional continuous tracking and identification of marine survey vessels. Summary of the Invention

[0008] The purpose of this invention is to address the problems in existing technologies. On the one hand, while AIS signals can provide digital navigation data for ships, they are limited by the curvature of the Earth and the obstruction caused by complex terrain. Furthermore, this technology is highly dependent on the operational status of the target ship's equipment, which can easily lead to data loss or interruption. In addition, it cannot present the physical morphology details and real-time dynamic behavior of the ship. On the other hand, while satellite remote sensing imagery can intuitively capture the physical morphology and spatial distribution of ships, it is difficult to directly obtain continuous track data, resulting in relatively limited information dimensions. Moreover, due to the limitation of satellite revisit cycles, its data timeliness is significantly inferior to the real-time updated AIS signals. This invention proposes a multi-source heterogeneous data fusion method for dynamic tracking and identification of oceanographic survey vessels. The real-time performance of AIS and the accuracy of track data, combined with the physical morphology perception capabilities of satellite remote sensing, complement each other functionally. Deep fusion processing of satellite remote sensing images and AIS signals of oceanographic survey vessels is performed, achieving complementary advantages through technological synergy, breaking through the application bottleneck of single technologies, and improving the comprehensiveness and accuracy of target identification.

[0009] To achieve the above objectives, the present invention adopts the following technical solution.

[0010] The aforementioned method for dynamic tracking and identification of oceanographic survey vessels based on multi-source heterogeneous data fusion includes: Construct a dedicated information database for oceanographic survey vessels and collect and store the identification codes for maritime mobile communication services of oceanographic survey vessels; Access the multi-source AIS data service network, and obtain real-time and historical trajectory data of the target measurement vessel from the AIS data service network based on the target measurement vessel's maritime mobile communication service identifier code in the database; Spatiotemporal analysis of the acquired AIS trajectory data is performed to identify the operational behavior characteristics of the target measurement vessel and predict its future operational activity area. Using the operational behavior characteristics and the predicted future operational activity area as input, satellite mission programmable control technology is used to generate satellite imaging control commands to observe and image the target sea area. Acquire the remote sensing data after imaging, and then fuse the remote sensing data with the AIS data within the corresponding spatiotemporal range of the imaging. The operational status information of the target survey vessel is output based on the fusion results.

[0011] Furthermore, the construction of a dedicated information database for oceanographic survey vessels, and the collection and storage of maritime mobile communication service identification codes for oceanographic survey vessels, includes: Collect basic information on global oceanographic survey vessels through multiple open-source intelligence channels; A mapping table of survey vessel identity information is established, using the maritime mobile communication service identification code as the core identifier. The collected data is standardized, cleaned, classified, archived, verified, and updated to generate a structured information database.

[0012] Furthermore, the spatiotemporal analysis of the acquired AIS trajectory data to identify the operational behavior characteristics of the target measurement vessel and predict its future operational activity area includes: Trajectory clustering algorithm is used to identify hotspot areas of the survey vessel's operations; The duration and intensity of the vessel's operations in a specific area are analyzed using a dwell point detection algorithm. Distinguish between operational segments and transfer segments based on speed change patterns and trajectory morphology characteristics; A spatiotemporal prediction model is established based on historical behavior patterns to predict the target ship's future activity area and time window.

[0013] Furthermore, the step of using the operational behavior characteristics and the predicted future operational activity area as input, and employing satellite mission programmable control technology to generate satellite imaging control commands for observation and imaging of the target sea area includes: Based on the predicted future operational activity areas, a vector map layer of the operational area is generated using a geographic information system. Using the vector layer as a spatial constraint, the satellite platform database is docked to retrieve satellite transit orbit parameter information covering the vector layer of the operational area, and the available imaging time window is determined. Based on the maximum span parameters of the operating area in the east-west and north-south directions, and combined with the imaging characteristics of the satellite platform, an imaging swath width optimization calculation model is established. Through spatial coverage simulation calculations, the optimal combination of satellite imaging parameters is determined to ensure complete coverage of the operational area while maintaining imaging resolution. The determined satellite imaging area, time window, and swath width parameters are integrated into standardized satellite control commands.

[0014] Furthermore, the inputs to the imaging swath optimization calculation model include the spatial geometric features of the operating area, the maneuvering features of the satellite platform, and the imaging features of the sensor; The optimal combination of imaging swath width and resolution parameters for the imaging swath width optimization calculation model is solved using a multi-objective optimization algorithm. The imaging parameters are dynamically adjusted based on real-time AIS signals to dynamically track the target measurement vessel.

[0015] Furthermore, the process of acquiring the imaged remote sensing data and fusing the remote sensing data with AIS data within the corresponding spatiotemporal range includes: Data cleaning and spatiotemporal filtering are performed on the raw AIS trajectory data to generate a standardized list of AIS information for the survey vessel. Geocoding is used to convert the AIS coordinate data of the survey vessel into spatial vector data, forming a continuous digital track of the survey vessel's AIS. Select satellite remote sensing images that match the time range of AIS data, and ensure that the geographic reference benchmark of the images is consistent with the AIS data through coordinate correction; A feature matching algorithm was used to establish the correspondence between AIS signal points and target measurement vessels in remote sensing images; By associating multimodal data, identity attribute information and visual feature information are deeply integrated.

[0016] Furthermore, the feature matching algorithm includes: Based on the time difference between AIS position reporting time and satellite imaging time, a motion prediction model is used to interpolate the position of the survey vessel. A multi-feature matching and association algorithm is designed to establish the correspondence between AIS signals and image targets through spatial relationship analysis, trajectory morphology matching, and feature similarity calculation.

[0017] Furthermore, the operational status information of the target measurement vessel output based on the fusion results includes: Extract the physical characteristics, motion characteristics, and environmental correlation characteristics of the survey vessel from the fused data; A work pattern classification model is established based on multimodal features to identify work patterns, including mobile surveying, regional sweeping and fixed-point observation, and to summarize the activity cycle and regional preferences. By using spatial overlay analysis, the degree of agreement between the actual flight path and the planned survey area is compared; Integrate multi-dimensional analysis results to generate a comprehensive situation map and visualize it.

[0018] To achieve the above objectives, the present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a program that runs on the processor, and the processor executes the steps of the multi-source heterogeneous data fusion method for dynamic tracking and identification of oceanographic survey vessels as described above when running the program. To achieve the above objectives, the present invention also provides a computer-readable storage medium having computer instructions stored thereon, wherein the computer instructions, when executed, perform the steps of the oceanographic survey vessel dynamic tracking and identification method for multi-source heterogeneous data fusion as described above.

[0019] This invention proposes a method for dynamic tracking and identification of oceanographic survey vessels through multi-source heterogeneous data fusion, which has the following beneficial effects: First, this invention achieves comprehensive and three-dimensional precise perception of oceanographic survey vessels through the deep fusion of AIS data and satellite remote sensing imagery. This effectively overcomes the inherent limitations of single-technology approaches, compensating for the lack of visual information on the physical form and operational scenarios provided by the AIS system, and addressing the lack of vessel identification attributes and continuous track data in satellite remote sensing. The complementary advantages of these two technologies form a collaborative monitoring system of "dynamic tracking - static verification - identification - behavior analysis," significantly improving the accuracy and reliability of target identification.

[0020] Secondly, this invention innovatively establishes an intelligent satellite mission guidance mechanism based on AIS behavior prediction. By analyzing the historical activity patterns of the survey vessel, it accurately predicts its future operational area and time window, and dynamically plans satellite imaging parameters accordingly. Combined with the dynamic correction capability of real-time AIS signals, it significantly improves the acquisition probability and imaging quality of moving survey vessels, effectively solving the timeliness problem caused by satellite revisit cycle limitations.

[0021] This invention constructs a complete intelligent operational situation analysis system, realizing a deep transformation from raw data to decision support information. Through the fusion analysis of multi-source features, it can not only identify the real-time operational status of vessels but also quantitatively assess operational efficiency, coverage, and potential risks, generating an intuitive comprehensive situation map. This provides strong technical support for safeguarding maritime rights, managing maritime security, and military decision-making.

[0022] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. Attached Figure Description

[0023] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a method for dynamic tracking and identification of oceanographic survey vessels based on multi-source heterogeneous data fusion according to the present invention; Figure 2 This is a schematic diagram of the dynamic tracking and identification technology process for oceanographic survey vessels based on multi-source heterogeneous data fusion, according to Embodiment 1 of the present invention. Figure 3 This is a schematic diagram of the AIS trajectory according to Embodiment 1 of the present invention; Figure 4 This is a schematic diagram illustrating the fusion effect of satellite imagery and AIS signal according to Embodiment 1 of the present invention; Figure 5 A schematic diagram of the structure of the electronic device 300 in the embodiments of this application. Detailed Implementation

[0024] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0025] Example 1 Figure 1 The flowchart of the oceanographic survey vessel dynamic tracking and identification method based on multi-source heterogeneous data fusion according to the present invention will be referenced below. Figure 1 The present invention provides a detailed description of the method for dynamic tracking and identification of marine survey vessels based on multi-source heterogeneous data fusion.

[0026] In step 101, basic information on major global oceanographic survey vessels is obtained through multi-channel open-source intelligence gathering, and a structured database of basic ship information is established.

[0027] Optionally, basic information on various oceanographic survey vessels worldwide can be obtained through systematic, multi-channel, open-source intelligence gathering. This basic information includes, but is not limited to, the vessel's accurate Chinese or English name, affiliated organization, vessel type, main technical parameters, and typical operational characteristics. During this process, the focus is on accurately collecting the unique Maritime Mobile Service Identity (MMSI) code for each vessel. This code serves as the vessel's "digital ID card" in the global maritime communication network, possessing global uniqueness and traceability, and is the core identifier for achieving accurate vessel identification and dynamic tracking.

[0028] In this embodiment, a systematic open-source intelligence gathering network is established to acquire basic information on global oceanographic survey vessels through the following channels: Official registration databases: Accessing authoritative information sources such as the International Maritime Organization (IMO) vessel registration database and publicly available data from ship registration agencies in various countries to obtain legally registered vessel information. Maritime monitoring platforms: Integrating data interfaces from multiple Automatic Identification System (AIS) public service platforms to obtain real-time dynamic information of vessels and their associated static information. Professional intelligence sources: Collecting specialized information on survey vessels released by professional channels such as maritime research institutions, shipping databases, and shipyard construction records. Public intelligence sources: Systematically searching and analyzing publicly available information sources such as maritime news reports, academic publications, and industry forums to extract survey vessel-related intelligence.

[0029] In this embodiment, the core identification information of each survey vessel is collected. The Maritime Mobile Service Identifier (MMSI) code serves as the unique digital identity of the vessel. The collection method includes: verification through the MMSI coding segment allocated by the International Telecommunication Union (ITU); cross-comparison of MMSI information from multiple data sources to eliminate coding conflicts or errors; and establishment of an MMSI coding validity verification mechanism to regularly update the coding status.

[0030] Optionally, based on the above-mentioned collection results, the massive amount of data is standardized, classified, archived, verified, and updated to construct a comprehensive, accurate, and dynamically updated basic information database for marine survey vessels. This database supports queries based on multiple conditions such as vessel name, MMSI (Maritime Mobile Service Identity), nationality, and vessel type, providing a reliable data foundation and retrieval basis for subsequent monitoring, analysis, and management of marine survey vessels.

[0031] Optionally, building a professional-grade MMSI coding database for oceanographic survey vessels includes: establishing a professional data standardization processing pipeline based on the multi-source basic information of survey vessels collected in the early stage; building a professional-grade MMSI coding database for oceanographic survey vessels; establishing a sound data quality management mechanism to achieve continuous updates and maintenance of the database; and providing rich database search and service functions.

[0032] In this embodiment, based on the previously collected multi-source survey vessel basic information, a professional data standardization processing pipeline is established. Specifically, this includes: format unification: converting heterogeneous data from different sources into a standard structured format; coding standardization: adopting internationally accepted coding systems (such as UN / LOCODE, ISO standards); unit unification: standardizing measurement units and data accuracy standards; and time standardization: unifying all time information to the UTC time zone and adopting the ISO 8601 format. A multi-level classification architecture is established: by vessel type: hydrographic survey vessels, oceanographic survey vessels, geological exploration vessels, etc.; by affiliated institution: military, research institutions, commercial companies, etc.; by operational capabilities: shallow-sea surveying, deep-sea exploration, comprehensive surveying, etc.; and by regional characteristics: polar survey vessels, tropical waters vessels, etc. Data association and fusion: establishing a unique identifier mapping table for vessel entities; achieving entity alignment and association of multi-source information; constructing a vessel knowledge graph and establishing attribute association relationships.

[0033] In this embodiment, a professional-grade MMSI coding database for oceanographic survey vessels is constructed, which can be specifically implemented as follows: A distributed columnar storage architecture is adopted to support massive data storage; a hierarchical storage strategy for hot, warm, and cold data is designed; data compression and encrypted storage are implemented to improve storage efficiency and security. The data model design includes an entity relationship model: defining entity relationships such as ships, institutions, and equipment; a spatiotemporal data model: supporting spatiotemporal trajectory data storage and querying; and a version management model: enabling data change history and version tracking. The index optimization mechanism includes: establishing a multi-level composite index system; implementing spatial and time-series indexes; and supporting full-text search and fuzzy matching.

[0034] This embodiment provides rich database retrieval and service functions, specifically including: supporting precise and fuzzy searches, providing searches based on spatiotemporal ranges, enabling multi-condition combined searches, and supporting full-text and semantic searches; providing a standard RESTful API data service interface, supporting multiple data format outputs (JSON, XML, CSV), controlling data access permissions, and providing data subscription and push services; and providing a visual search interface with map-based visual search, enabling timeline search and display, supporting multi-dimensional analysis of search results, and providing search history and management functions.

[0035] In step 102, based on the key operational characteristics of the AIS trajectory of the measurement vessel when it is in operation, the professional AIS data service platform is used to analyze the future operational area and construct a dynamic tracking system for the target measurement vessel at all times.

[0036] Optionally, a full-time dynamic tracking system for the target survey vessel can be constructed by relying on professional network platforms that provide real-time AIS location information for ships, such as Shipxy.com, Port.com, and Marinetraffic. This includes continuously capturing real-time AIS track data of the vessel while it is in operation, using the target vessel's MMSI code as an index to achieve real-time monitoring of its current navigation status, and retrieving historical track information to obtain its historical and real-time AIS trajectory data. The raw AIS data undergoes quality control and outlier removal to extract structured information including timestamps, latitude and longitude coordinates, speed, heading, and navigation status. Spatiotemporal trajectory analysis methods are used to identify the vessel's operational pattern characteristics, including but not limited to: operational sea area range, typical speed range, route repetition patterns, hotspot areas, and operational time patterns. Based on historical patterns, a behavioral model is established to predict its possible future activity areas and operational periods.

[0037] Optionally, a professional-grade AIS data acquisition and processing platform can be built to achieve real-time dynamic monitoring of the target survey vessel; based on AIS trajectory data, the operational behavior characteristics of the survey vessel can be analyzed in depth; based on historical operational patterns, future operational areas and behavioral patterns can be predicted; a highly available professional analysis platform can be built; and rich application support capabilities can be provided.

[0038] In this embodiment, a professional-grade AIS data acquisition and processing platform is constructed to achieve real-time dynamic monitoring of the target measurement vessel. Specifically, this involves: integrating data sources from multiple AIS data service providers; establishing a unified data access interface; standardizing and adapting API interfaces to support access to mainstream AIS data platforms; establishing a data quality assessment mechanism to classify data from different sources based on quality; and designing load balancing strategies to ensure the stability and continuity of data acquisition. A real-time data pipeline processing architecture is constructed, employing a distributed stream processing framework to achieve real-time processing of massive amounts of AIS data. A data caching mechanism is established to address network fluctuations and data latency, enabling data deduplication and outlier filtering to guarantee data quality. A comprehensive historical data management system is established, designing a time-series database storage architecture to support rapid historical data retrieval; implementing data compression and hierarchical storage to optimize storage efficiency; and establishing a data lifecycle management strategy to automatically archive data.

[0039] In this embodiment, the steps for in-depth analysis of the operational behavior characteristics of the survey vessel based on AIS trajectory data can be specifically executed as follows: Developing a multi-dimensional operational status identification model; identifying the characteristic speed range of the measurement operation through time-series analysis of operational status changes in speed; distinguishing between measurement routes and transfer routes using trajectory clustering algorithms; identifying key measurement areas based on operational point analysis of dwelling behavior; establishing a complete operational characteristic index system; conducting path characteristic analysis based on operational path density, coverage uniformity, and repeated measurement areas; conducting behavioral characteristic analysis based on operational time period distribution, operational duration, and operational interval cycle time characteristics; conducting behavioral characteristic analysis based on speed change pattern turning characteristics and operational efficiency indicators; realizing the correlation analysis between operational behavior and environmental factors, including the relationship between environmental parameters such as water depth, ocean currents, and tides and operational behavior; analyzing the spatiotemporal patterns of operational mode differences in different seasons and sea areas; and evaluating operational efficiency based on operational coverage and time utilization.

[0040] In this embodiment, the steps of predicting future operation areas and behavior patterns based on historical operation patterns can be specifically executed as follows: identifying operation patterns using a time-series pattern mining algorithm based on historical trajectories; comprehensively considering variables such as marine environment, seasonal factors, and task type for collaborative prediction; providing confidence assessment and error range of the prediction results; and establishing a multi-variable collaborative spatiotemporal prediction model. The prediction results are displayed in multiple dimensions, including a heatmap showing the probability distribution of operation areas based on historical data, a visualized trajectory prediction of possible future operation paths, and a three-dimensional display of the spatiotemporal distribution characteristics of operation behavior. A prediction model evaluation mechanism is established to assess prediction accuracy, comparing prediction results with actual observation data, continuously optimizing model parameters based on prediction errors, and dynamically adjusting the prediction model based on new data.

[0041] In step 103, based on the work scope and the future planned work area, spatial analysis of the AIS trajectory data of the survey vessel is performed using Geographic Information System (GIS) tools to obtain the work scope and time dynamic characteristics information of the survey vessel.

[0042] Optionally, based on trajectory data, spatiotemporal trajectory analysis methods can be used to systematically analyze the patterns and characteristics of the survey vessel's operation time distribution, route preferences, and key operation sea areas, accurately delineate its routine activity range and operation coverage area, and form a comprehensive understanding of the survey vessel's operation intensity, operation mode, and activity trends.

[0043] In this embodiment, a spatiotemporal trajectory data analysis method is employed to deeply mine and identify patterns in the operational behavior of the survey vessel. First, a complete spatiotemporal database of vessel activities is constructed based on historical AIS trajectory data. This database integrates multi-dimensional attributes such as speed, heading, and timestamps, forming trajectory sequences with complete spatiotemporal characteristics. The trajectory data is preprocessed, including data cleaning, outlier removal, and trajectory reconstruction, to ensure that the data quality meets the requirements of subsequent analysis.

[0044] In this embodiment, density clustering algorithm is used to identify and extract vessel dwell points during the trajectory analysis phase. By setting time and spatial thresholds, the operational dwell points of the survey vessel in a specific sea area are accurately identified. Simultaneously, trajectory segmentation technology is used to divide the complete navigation trajectory into different segments, distinguishing between operational segments and transfer segments based on speed change patterns and trajectory morphology characteristics. This process combines spatial location information with temporal analysis, enabling accurate identification of the vessel's actual operational status.

[0045] Furthermore, this invention employs a spatiotemporal cube model for three-dimensional visualization analysis of ship activities. The geographic space is divided into regular grid cells, each recording the frequency and characteristic indicators of ship activities within a specific time period. This analytical method clearly demonstrates the temporal variation in the activity intensity of survey vessels in different sea areas. Combined with kernel density estimation, a ship activity heatmap is generated, visually displaying operational hotspots and their distribution characteristics. This analytical method not only identifies current key operational areas but also reveals the spatiotemporal evolution of operational patterns.

[0046] In terms of pattern recognition, machine learning algorithms are used to intelligently classify ship operation behaviors. By extracting geometric, statistical, and semantic features of trajectories, an operation pattern classification model is established. This model can automatically identify different types of operation patterns, such as area surveying, route measurement, and fixed-point observation. Simultaneously, by combining time series analysis methods, the periodic patterns of ship operations are mined, including daily, weekly, and seasonal cycle characteristics, providing important data for predicting future ship activities.

[0047] Based on the above analysis results, a knowledge base for the operational characteristics of survey vessels was established. This knowledge base system records the operational preferences, activity patterns, and performance indicators of each survey vessel, forming a complete profile of vessel operations. Vessel activity data is then integrated and analyzed with marine environmental data, seabed topography data, and other sources to gain a deeper understanding of the intrinsic relationship between operational behavior and environmental factors.

[0048] In this embodiment, an automatic spatial boundary generation algorithm is used to generate a probabilistic operational boundary by comprehensively considering factors such as the spatial distribution density of operational points and the frequency of operational duration, thus accurately delineating the routine operational range of the survey vessel. Simultaneously, an operational intensity assessment index system is established to quantitatively analyze the vessel's activity intensity and work efficiency in different sea areas.

[0049] In this embodiment, the system supports dynamic updates and visualization of analysis results, and can automatically adjust the analysis model and parameters based on new data to ensure the timeliness and accuracy of the analysis results. Through the system's analysis methods, a deep understanding and precise grasp of the operational behavior of the survey vessel are achieved, providing strong technical support for marine monitoring activities.

[0050] In step 104, based on AIS signal data, satellite mission programmable control technology is used to carry out precise observation and imaging of the marine survey area where the survey vessel is located.

[0051] In this embodiment, based on the multi-dimensional information of the survey vessel, including its operational area characteristics, historical activity patterns, and real-time AIS signal data, satellite mission programmable control technology is employed to perform precise observation and imaging of the marine survey area where the survey vessel is located. By establishing a dynamic feedback mechanism, the satellite imaging parameters are continuously optimized based on the real-time acquired AIS signals (including dynamic data such as vessel position, speed, and heading) as the core guidance source. This allows the satellite to dynamically adjust the imaging range and timing under the real-time guidance of the AIS signals, ensuring high-precision continuous tracking and imaging of the moving survey vessel.

[0052] Step 401: Based on the data of the survey vessel's operational range obtained from the previous analysis, the spatial data is processed in a refined manner using geographic information system tools, including vector data conversion and precise boundary delineation, to form a vector map layer of the operational area containing latitude and longitude coordinates, providing a spatial reference for the accurate delineation of the subsequent satellite imaging area.

[0053] In this embodiment, the convex hull algorithm is first used to generate the minimum boundary geometry, accurately defining the outer boundary of the operation area. Combined with the historical activity density distribution of the survey vessel, a vector layer of the operation area is generated. This layer is stored in a standard geographic data format, containing complete spatial reference information, boundary coordinate sequences, and time validity indicators, providing a reliable spatial benchmark for the subsequent accurate delineation of the satellite imaging area. During this process, the system also comprehensively considers auxiliary information such as marine environmental factors and seabed topographic features to ensure that the delineated operation area conforms to both the actual operational characteristics of the survey vessel and meets the engineering and technical requirements of satellite imaging.

[0054] Step 402: In the satellite transit opportunity analysis stage, using the operational range vector data as the core spatial retrieval condition, the system connects to the SAR satellite mission planning system database to retrieve and filter satellite transit orbit parameter information covering the vector area.

[0055] In this embodiment, an orbit matching algorithm automatically retrieves all satellite orbit resources that may cover the target area within a specific future time window. This algorithm comprehensively considers multiple parameters such as orbital altitude, inclination, and coverage band width, and evaluates candidate orbits from multiple dimensions, including coverage integrity, imaging geometric quality, and time matching degree. A detailed satellite transit opportunity analysis report is generated, including key parameters such as the specific time of each transit window, satellite attitude angle range, and illumination conditions, ensuring that the selected orbits effectively cover the target operational area and providing sufficient data support for subsequent imaging mission planning.

[0056] Step 403: Based on the analysis results of the time activity pattern of the measuring ship on a daily cycle, accurately match the available imaging time period of the satellite, and determine the optimal imaging time window of the satellite from three time dimensions: morning, afternoon and night.

[0057] In this embodiment, regarding the optimization of the imaging time window, the analysis results of the survey vessel's temporal activity patterns are deeply integrated, such as the operational density and navigation trajectory stability during specific time periods, to accurately match the available imaging time periods of the satellite. A time series prediction model based on machine learning is established to accurately predict the activity time distribution of the survey vessel on specific future dates. This prediction model comprehensively considers multiple influencing factors such as the survey vessel's historical operational patterns, marine environmental conditions, and seasonal factors, accurately predicting the vessel's operational peak periods and activity intensity changes on a daily basis. Based on this, an optimization algorithm under multiple constraints is employed to select the optimal imaging time window from three time dimensions: morning, afternoon, and night, maximizing the overlap between the imaging time and the survey vessel's active operational periods.

[0058] Step 404: In the imaging parameter optimization and configuration stage, a parameter calculation model is established based on the spatial characteristic parameters of the measurement vessel's activity range, combined with the imaging mode characteristics and swath width adjustment range.

[0059] In this embodiment, the parameter calculation model is based on the maximum width parameters of the survey vessel's operating range in the east-west and north-south directions. Combined with the satellite's imaging mode characteristics and swath width adjustment range, spatial coverage simulation calculations determine the optimal satellite imaging swath width parameters that can completely cover the survey vessel's operating area while ensuring imaging resolution. During this process, detailed spatial coverage simulation analysis is conducted. By establishing a digital earth model and a satellite imaging simulation environment, the imaging effects under different parameter combinations are pre-evaluated to ensure that the finally selected imaging parameters can both completely cover the target operating area and effectively identify the survey vessel's features. This avoids situations where insufficient swath width results in the survey vessel being unable to capture images, or excessive swath width makes it difficult to capture the survey vessel's dynamic features.

[0060] Step 405: In the mission instruction generation and uploading stage, all imaging parameters determined in the previous steps are integrated into a standardized satellite control instruction set and uploaded upwards through the ground station data transmission system to complete the deployment of the satellite's programmed imaging mission.

[0061] In this embodiment, the satellite control command set adopts a hierarchical and progressive structure, including three levels: mission-level commands, platform-level commands, and payload-level commands. Mission-level commands specify the basic requirements and quality indicators of the imaging mission; platform-level commands control the satellite platform's attitude adjustment and orbit maintenance; and payload-level commands detail the operating modes and parameter configurations of the imaging sensors. A secure and encrypted data transmission link transmits the complete command sequence to the satellite platform, and a command execution status monitoring mechanism is established to track mission execution in real time. In particular, a dynamic command update mechanism is designed, allowing for fine-tuning of imaging parameters based on real-time AIS data at the latest moment before the satellite's transit, ensuring accurate tracking of moving targets and achieving precise and efficient remote sensing observation of the survey vessel's operating area.

[0062] In step 105, the AIS signal data from the survey vessel is fused with satellite remote sensing data.

[0063] Step 501: Perform information processing based on the AIS signal trajectory of the survey vessel to generate a list of vessel AIS information with geographic coordinates for the time period of interest.

[0064] In this embodiment, during the data preprocessing stage, information processing is carried out based on the AIS signal trajectory of the survey vessel. This includes employing a multi-level data cleaning algorithm to clean and filter the raw AIS signal trajectory data, automatically identifying and removing abnormal data points caused by signal interference, transmission errors, etc. Simultaneously, based on the ship's kinematics model, missing important fields are appropriately interpolated to ensure data integrity and continuity. Data is then extracted according to a preset time interval to generate a ship AIS information list. This ship AIS information list not only includes basic information such as the ship's MMSI code, precise timestamp, and latitude and longitude coordinates, but also integrates dynamic parameters such as speed, heading, and navigation status, forming a ship activity dataset with complete spatiotemporal characteristics. To further improve data quality, the system also introduces a sliding window mechanism to smooth key parameters such as speed and heading, eliminating data jitter caused by measurement errors.

[0065] Step 502: The geographic coordinate information of the survey vessel is vectorized using GIS tools to form the AIS track of the survey vessel.

[0066] In this embodiment, during the spatial data vectorization process, a geographic information processing platform is used to convert the cleaned AIS coordinate data into spatial vector data with topological relationships. A spatial database is established to structurally store and manage discrete AIS point data. A trajectory reconstruction algorithm is employed to temporally connect continuous AIS points, generating a smooth ship navigation trajectory. During this process, considering the ship's motion characteristics, a Bayesian filtering method is used to optimize the trajectory, eliminating trajectory jitter caused by positioning errors. Simultaneously, feature parameters of the trajectory are automatically extracted, including average speed, rate of change of heading, and turning radius. These feature parameters provide important basis for subsequent behavioral analysis. The generated digital trajectory not only contains geometric information but also inherits complete attribute data, forming a spatiotemporal dataset with rich semantic information.

[0067] Step 503: Importing geographic information from satellite remote sensing imagery. Select satellite remote sensing imagery that matches the time range of the AIS data. Ensure that the geographic reference benchmark of the imagery is consistent with the AIS data through coordinate correction. Import the processed remote sensing imagery into the GIS system to construct a basic geographic environment layer, providing background reference for the activities of the survey vessel.

[0068] In this embodiment, regarding satellite remote sensing data processing, firstly, matching satellite remote sensing image data is selected based on the time range of the AIS data. The selected remote sensing images undergo geometric fine correction processing, employing a high-precision digital elevation model and ground control points to eliminate geometric distortions caused by factors such as sensor attitude and terrain undulations. Coordinate system unification ensures that all remote sensing images use the same geographic reference datum and projected coordinate system as the AIS data. Radiometric calibration and atmospheric correction are also performed on the images to eliminate the influence of environmental factors on image quality. The processed remote sensing images are imported into a spatial database to construct a basic environmental layer with accurate geographic coordinates. This layer not only provides background information on ship activities but also includes important geographic elements such as marine environmental characteristics and shoreline information, providing a complete contextual environment for subsequent spatial analysis.

[0069] Step 504: The AIS signal is superimposed on the satellite remote sensing image layer, and the AIS signal of the measuring vessel is fully integrated with the physical features in the satellite image to match the AIS signal one moment before and one moment after the satellite imaging.

[0070] In this embodiment, during the multi-source data layer overlay and fusion stage of AIS signals and satellite remote sensing images, an advanced spatiotemporal matching algorithm is employed to establish a unified spatiotemporal reference framework, registering the AIS vector layer with the remote sensing image layer. During this process, considering the time difference between the AIS data timestamp and the satellite imaging time, a motion prediction model is used to accurately interpolate the ship's position, ensuring a high degree of consistency between the two types of data in the spatiotemporal dimension. A feature matching algorithm is developed to automatically establish the correspondence between the AIS reported position and the spatial relationship between the ship target in the image. For successfully matched targets, a fused data record is generated, which simultaneously contains the identity attribute information provided by AIS and the visual feature information extracted from the remote sensing image.

[0071] As an example, a multi-level data association mechanism was established to further improve the fusion effect. At the spatial level, buffer analysis and spatial querying were used to determine the correspondence between AIS signals and ship targets in the imagery. At the temporal level, a dynamic time warping algorithm was employed to address the temporal alignment problem caused by different data acquisition frequencies. At the feature level, multimodal data feature extraction was used to achieve deep association between attribute information and visual information. A feedback optimization mechanism was also designed to automatically adjust matching parameters and algorithm thresholds through continuous evaluation of the fusion results, thereby continuously improving the accuracy and reliability of data fusion.

[0072] In this embodiment, a comprehensive dataset integrating multi-source information is finally generated. This dataset retains the real-time nature and accuracy of AIS data while incorporating the intuitiveness and richness of remote sensing imagery, providing a solid data foundation for subsequent ship behavior analysis, operational status identification, and situation assessment.

[0073] In step 106, a comprehensive analysis of the survey vessel's operational status is conducted.

[0074] Optionally, features of ships and their surrounding environment can be extracted from satellite images to establish spatial correlations between ships and their environment; speed, heading, and track density in AIS signals can be analyzed to quantify ship motion characteristics; combining the first two types of features, operational patterns can be identified, and activity cycles and regional preferences can be summarized. The degree of agreement between actual tracks and planned survey areas can be compared to generate a situation map that includes operational coverage, efficiency, and risk points.

[0075] In this embodiment, AIS time-series data is deeply mined at the motion feature analysis level. By establishing a ship kinematic model, not only are basic parameters such as speed and heading analyzed, but also higher-order motion features such as speed change rate, turning angular velocity, and trajectory curvature are extracted. Time series analysis methods are used to identify the periodicity and regularity of ship motion, including acceleration and deceleration patterns, turning preferences, and stationary behavior. By analyzing the spatial distribution of trackpoint density, the operational intensity of the ship in different areas is quantified. Combined with trajectory complexity and repeatability indicators, the precision and coverage of measurement operations are accurately determined. The analysis of these motion features provides behavioral data support for operational pattern recognition.

[0076] In the intelligent identification stage of operational patterns, visual and motion features are integrated to construct a multimodal feature vector. Machine learning classification algorithms are used to automatically identify different operational patterns of the survey vessel, including but not limited to typical operational types such as underway surveying, area scanning, fixed-point observation, and route surveying. By analyzing historical operational data, a spatiotemporal pattern model of operational patterns is established to summarize the vessel's activity cycle characteristics and regional preferences. For example, it identifies deeper characteristics such as seasonal operational patterns in specific sea areas, differences in operational patterns under different tidal conditions, and regional selection preferences based on task requirements. The discovery of these patterns provides an important knowledge foundation for predicting future vessel behavior.

[0077] Optionally, a comprehensive operational efficiency evaluation system can be established. Using spatial overlay analysis technology, the actual vessel trajectory is precisely compared with the planned survey area to calculate key indicators such as operational coverage, repeat measurement rate, and blank area ratio. A comprehensive operational efficiency evaluation model is constructed by comprehensively considering multiple dimensions, including operational time utilization efficiency, the optimization degree of the measurement path, and the impact of environmental factors. By establishing an efficiency indicator system, the completion quality and efficiency of measurement operations can be quantitatively evaluated, providing data support for operational optimization.

[0078] In terms of risk assessment, multi-source information is integrated to construct an intelligent early warning mechanism. By analyzing the spatiotemporal relationship between vessel operations and marine environmental factors, waterway traffic density, and the distribution of sensitive areas, potential operational risks are identified. For example, monitoring whether vessels are too close to restricted navigation areas, operating under complex hydrological conditions, or experiencing navigational conflicts with other vessels. A risk assessment model is established to classify and assess the impact of identified risks, providing a basis for safety management decisions.

[0079] In this embodiment, a comprehensive operational situation map is generated, integrating multi-dimensional information such as spatial distribution, time series, operational status, effectiveness assessment, and risk warning. Through visualization, the situation map presents the overall operational situation of the survey vessel in a hierarchical and focused manner. Users can gain a deeper understanding of the detailed operational situation in specific areas or time periods through an interactive interface. The system supports automatic updates and dynamic simulations of the situation map, enabling prediction of operational trends based on real-time data, providing comprehensive, accurate, and timely situational awareness support for maritime operational command and decision-making.

[0080] The comprehensive analysis method effectively improves the transparency and controllability of marine surveying operations through in-depth integration and intelligent analysis of multi-source data, providing important technical support for marine resource development and maritime safety assurance.

[0081] This invention provides a method for dynamic tracking and identification of oceanographic survey vessels based on multi-source heterogeneous data fusion, such as... Figure 2 As shown, using the MMSI code of the target survey vessel as the key identification identifier, the system first systematically collects its AIS signal data to deeply analyze the characteristics of the target vessel's survey operation area, including the core area of ​​operation, activity range boundaries, and operational time patterns. Based on the analysis results, it accurately guides remote sensing satellites to conduct targeted imaging of the target area, ensuring that the acquired remote sensing images are highly matched with the AIS signals in the spatiotemporal dimensions. By deeply fusing the AIS signals and satellite remote sensing images, dynamic tracking of the target survey vessel is achieved. This fusion not only integrates navigation parameters such as track, speed, and heading provided by AIS, but also combines physical characteristics such as hull size and appearance extracted from the images to form a multi-dimensional, three-dimensional set of target information. Compared with traditional single-technology methods, this invention achieves complementary advantages through technology fusion, overcoming the shortcomings of AIS signals in providing physical morphological details and compensating for the deficiencies of satellite remote sensing images in acquiring track data. Ultimately, it achieves effective tracking and rapid detection of survey vessels, providing more comprehensive and accurate technical support for the monitoring and management of marine survey vessels.

[0082] Example 2 This explanation will be based on an example of a survey vessel from country A conducting a survey mission in the Balabala Straits of the Philippines.

[0083] First, basic information about the survey vessel was obtained through open-source intelligence channels, as follows: Its hull designation is T-AGS-62, MMSI code is 367955000, and it is a member of the Pathfinder-class oceanographic survey vessels. The vessel is 100 meters long, 18 meters wide, has a draft of 5.8 meters, and a full-load displacement of 4700 tons. Its propulsion system uses diesel-electric propulsion, with a maximum speed of 16 knots and a range of 12,000 nautical miles at 12 knots. In terms of equipment, the survey vessel is equipped with 3 multi-functional cranes, 5 winches, and various oceanographic surveying equipment, including multibeam echo sounders, towed sonar, consumable sensors, seabed shallow profilers, Doppler acoustic current meters, and magnetometers. It also has a dedicated surveying workstation, giving it comprehensive marine environmental detection capabilities.

[0084] Subsequently, using the port network information platform, and with the MMSI code 367955000 as the search identifier, the historical navigation trajectory of the survey vessel was tracked. Analysis of the acquired trajectory data revealed that the survey vessel had continuous operational activities in the Balabac Strait of the Philippines during March 2025. The trajectory characteristics showed that during this period, the survey vessel exhibited a high-frequency travel pattern to and from specific areas in this sea area, with its navigation path forming a densely intersecting network in local waters. This characteristic highly aligns with the operational logic of marine surveying, which requires repeated exploration of key areas. To further precisely define its operational scope, spatial analysis was performed on the vessel's AIS (Automatic Identification System) trajectory data using Geographic Information System (GIS) tools: such as... Figure 3 As shown, a spatial database is established by extracting the latitude and longitude coordinates of the trajectory points. A buffer analysis tool is used to generate an influence area within a certain range around the trajectory. Then, topology checks are combined to remove interference from abnormal trajectory points. Finally, a vector layer that can accurately reflect the ship's operating area in March is constructed.

[0085] Next, relying on the constructed operational area vector layer, the transit orbit information of SAR satellites for the same period was simultaneously queried. System searches revealed a satellite transit window on March 5, 2025, occurring at night. To improve the targeting of observations, further retrospective analysis of the vessel's past activities on the same day revealed significant spatiotemporal distribution characteristics: during the day, it typically conducted measurement operations north of Barabác Island, and at night it moved to the Barabási area for continuous operations. Combining the timing characteristics of this satellite transit, the observation area was ultimately narrowed down to the waters west of Barabác Island.

[0086] Based on preliminary trajectory data calculations, the ship's operational area west of Barabác Island is a rectangular region spanning approximately 18 kilometers east to west and 40 kilometers north to south. Considering this spatial scale and comprehensively evaluating observation accuracy and coverage efficiency, a strip imaging mode was selected, and a resolution of 3 meters was set for observation and imaging. After the parameters were determined, the satellite control commands were compiled and uploaded to ensure that the satellite executes its observation mission according to the pre-set plan.

[0087] The satellite successfully completed its imaging mission at 22:33 on March 5, 2025. Following the acquisition of satellite images, a multi-source data fusion and analysis process was immediately initiated: such as... Figure 4 As shown, the AIS signal data of the survey vessel was first precisely matched with satellite imagery. Specifically, the latitude, longitude, timestamp, and other information contained in the AIS signal list were vectorized to generate a spatial point feature layer. Simultaneously, coordinate correction was performed on the satellite remote sensing imagery, and ground control point matching was used to ensure complete consistency between the geographic reference datum and the AIS vector layer. Layer overlay analysis revealed that eight AIS signal points fell within the satellite imagery coverage area. From the imagery features, the survey vessel's exterior texture was clearly discernible, with the grayscale differences between the deck equipment and the hull structure forming a distinct outline. Based on its wake length and diffusion pattern, the vessel's speed was determined to be below 5 knots, which is within the normal speed range for survey operations, with a heading of approximately 100 degrees. According to the signal record at 22:33 (within 3 minutes before the satellite imagery), its heading was 105 degrees and its speed was 3.8 knots. The specific location information of the AIS signals in the satellite imagery is as follows: Table 1: Navigation trajectory of a marine survey vessel from Country A

[0088] The above case demonstrates how deep fusion of SAR satellite remote sensing observations with AIS data from the same time period can accurately capture not only the external morphology and physical dynamics of the survey vessel, but also complete key navigation information such as its navigation trajectory and speed changes. The cross-validation and matching of these two types of data create a three-dimensional perception of the real-time status of the oceanographic survey vessel, ultimately achieving comprehensive, high-precision dynamic tracking and identification of the target vessel from static features to dynamic behavior, providing solid data support for subsequent monitoring and analysis.

[0089] Example 3 The following is for reference. Figure 5This document illustrates a structural diagram of an electronic device 300 suitable for implementing embodiments of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0090] like Figure 5 As shown, electronic device 300 may include processing device 310, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 320 or a program loaded from storage device 380 into random access memory (RAM) 330. Processing device 310 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processing device 310 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processing device 310 performs the various methods and processes described above.

[0091] The RAM 330 also stores various programs and data required for the operation of the electronic device 300. The processing device 310, ROM 320, and RAM 330 are interconnected via bus 340. The input / output (I / O) interface 350 is also connected to bus 340.

[0092] Typically, the following devices can be connected to I / O interface 350: input devices 360 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 370 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 380 including, for example, magnetic tapes, hard disks, etc.; and communication devices 390. Communication device 390 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0093] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 390, or installed from a storage device 380, or installed from a ROM 320. When the computer program is executed by the processing device 310, it performs the functions defined in the methods of the embodiments of this application. Alternatively, in other embodiments, the processing device 310 may be configured by any other suitable means (e.g., by means of firmware) to perform the following method: constructing a dedicated information database for oceanographic survey vessels, collecting and storing the MMSI of oceanographic survey vessels; accessing a multi-source AIS data service network, and acquiring real-time and historical trajectory data of the target survey vessel from the AIS data service network based on the target survey vessel MMSI in the database; performing spatiotemporal analysis on the acquired AIS trajectory data, identifying the operational behavior characteristics of the target survey vessel, and predicting its future operational activity area; using the operational behavior characteristics and the predicted future operational activity area as input, generating satellite imaging control commands using satellite mission programmable control technology, and performing observation imaging of the target sea area; acquiring the imaged remote sensing data, fusing the remote sensing data with the AIS data within the corresponding spatiotemporal range of the image; and outputting the operational status information of the target survey vessel based on the fusion result.

[0094] Example 4 The computer-readable medium described in this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0095] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0096] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0097] The aforementioned computer-readable medium carries one or more programs. When the electronic device executes one or more of these programs, the electronic device causes the following actions: It constructs a dedicated information database for oceanographic survey vessels, collects and stores the MMSI (Missing Data Identity) of the oceanographic survey vessels; it accesses a multi-source AIS data service network, and based on the target survey vessel's MMSI in the database, it acquires real-time and historical trajectory data of the target survey vessel from the AIS data service network; it performs spatiotemporal analysis on the acquired AIS trajectory data, identifies the operational behavior characteristics of the target survey vessel, and predicts its future operational activity area; using the operational behavior characteristics and the predicted future operational activity area as input, it generates satellite imaging control commands using satellite mission programmable control technology to observe and image the target sea area; it acquires the imaged remote sensing data, and fuses the remote sensing data with AIS data within the corresponding spatiotemporal range of the image; and it outputs the operational status information of the target survey vessel based on the fusion result.

[0098] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0099] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0100] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the modules themselves.

[0101] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof, etc.

[0102] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0103] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0104] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0105] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0106] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is established by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem that addresses the management difficulties and weak business scalability inherent in traditional physical hosting and VPS services. Servers can also be servers for distributed systems or servers integrated with blockchain technology.

[0107] Artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies mainly include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0108] Cloud computing refers to a technology system that enables access to a shared pool of physical or virtual resources via a network. These resources can include servers, operating systems, networks, software, applications, and storage devices, and can be deployed and managed on demand and in a self-service manner. Cloud computing technology can provide efficient and powerful data processing capabilities for applications such as artificial intelligence and blockchain, as well as for model training.

[0109] The embodiments described above are some, but not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0110] In the description of the embodiments of this application, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this application is in use. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the electric vehicle or component referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the present invention. In addition, the terms "first," "second," and "third," etc., are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0111] In the description of the embodiments of this application, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0112] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the technical scope disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for dynamic tracking and identification of oceanographic research vessels based on multi-source heterogeneous data fusion, characterized in that, include: Construct a dedicated information database for oceanographic survey vessels and collect and store the identification codes for maritime mobile communication services of oceanographic survey vessels; Access the multi-source AIS data service network, and obtain real-time and historical trajectory data of the target measurement vessel from the AIS data service network based on the target measurement vessel's maritime mobile communication service identifier code in the database; Spatiotemporal analysis of the acquired AIS trajectory data is performed to identify the operational behavior characteristics of the target measurement vessel and predict its future operational activity area. The process of performing spatiotemporal analysis on the acquired AIS trajectory data to identify the operational behavior characteristics of the target measurement vessel and predict its future operational activity area includes: Trajectory clustering algorithm is used to identify hotspot areas of the survey vessel's operations; The duration and intensity of the vessel's operations in a specific area are analyzed using a dwell point detection algorithm. Distinguish between operational segments and transfer segments based on speed change patterns and trajectory morphology characteristics; A spatiotemporal prediction model is established based on historical behavior patterns to predict the target ship's future activity area and time window. Using the operational behavior characteristics and the predicted future operational activity area as input, satellite mission programmable control technology is used to generate satellite imaging control commands to observe and image the target sea area. The step of generating satellite imaging control commands by using the operational behavior characteristics and the predicted future operational area as input, and employing satellite mission programmable control technology to conduct observation and imaging of the target sea area includes: Based on the predicted future operational activity areas, a vector map layer of the operational area is generated using a geographic information system. Using the vector layer as a spatial constraint, the satellite platform database is docked to retrieve satellite transit orbit parameter information covering the vector layer of the operational area, and the available imaging time window is determined. Based on the maximum span parameters of the operating area in the east-west and north-south directions, and combined with the imaging characteristics of the satellite platform, an imaging swath width optimization calculation model is established. Through spatial coverage simulation calculations, the optimal combination of satellite imaging parameters is determined to ensure complete coverage of the operational area while maintaining imaging resolution. The determined satellite imaging area, time window, and swath width parameters are integrated into standardized satellite control commands; Acquire the remote sensing data after imaging, and then fuse the remote sensing data with the AIS data within the corresponding spatiotemporal range of the imaging. The operational status information of the target survey vessel is output based on the fusion results.

2. The multi-source heterogeneous data fusion oceanographic survey vessel dynamic tracking and identification method of claim 1, wherein, The construction of a dedicated information database for oceanographic survey vessels, and the collection and storage of maritime mobile communication service identifiers for oceanographic survey vessels, include: Collect basic information on global oceanographic survey vessels through multiple open-source intelligence channels; A mapping table of survey vessel identity information is established, using the maritime mobile communication service identification code as the core identifier. The collected data is standardized, cleaned, classified, archived, verified, and updated to generate a structured information database.

3. The method for dynamic tracking and identification of oceanographic survey vessels based on multi-source heterogeneous data fusion according to claim 1, characterized in that, The inputs to the imaging swath optimization calculation model include the spatial geometric features of the operating area, the maneuvering features of the satellite platform, and the imaging features of the sensor. The optimal combination of imaging swath width and resolution parameters for the imaging swath width optimization calculation model is solved using a multi-objective optimization algorithm. The imaging parameters are dynamically adjusted based on real-time AIS signals to dynamically track the target measurement vessel.

4. The multi-source heterogeneous data fusion oceanographic survey vessel dynamic tracking and identification method of claim 1, wherein, The process of acquiring the imaged remote sensing data and fusing it with AIS data within the corresponding spatiotemporal range includes: Data cleaning and spatiotemporal filtering are performed on the raw AIS trajectory data to generate a standardized list of AIS information for the survey vessel. Geocoding is used to convert the AIS coordinate data of the survey vessel into spatial vector data, forming a continuous digital track of the survey vessel's AIS. Select satellite remote sensing images that match the time range of AIS data, and ensure that the geographic reference benchmark of the images is consistent with the AIS data through coordinate correction; A feature matching algorithm was used to establish the correspondence between AIS signal points and target measurement vessels in remote sensing images; By associating multimodal data, identity attribute information and visual feature information are deeply integrated.

5. The multi-source heterogeneous data fusion oceanographic survey vessel dynamic tracking and identification method of claim 4, wherein, The feature matching algorithm includes: Based on the time difference between AIS position reporting time and satellite imaging time, a motion prediction model is used to interpolate the position of the survey vessel. A multi-feature matching and association algorithm is designed to establish the correspondence between AIS signals and image targets through spatial relationship analysis, trajectory morphology matching, and feature similarity calculation.

6. The multi-source heterogeneous data fusion oceanographic survey vessel dynamic tracking and identification method of claim 1, wherein, The operational status information of the target measurement vessel output based on the fusion results includes: Extract the physical characteristics, motion characteristics, and environmental correlation characteristics of the survey vessel from the fused data; A work pattern classification model is established based on multimodal features to identify work patterns, including mobile surveying, regional sweeping and fixed-point observation, and to summarize the activity cycle and regional preferences. By using spatial overlay analysis, the degree of agreement between the actual flight path and the planned survey area is compared; Integrate multi-dimensional analysis results to generate a comprehensive situation map and display it visually.

7. An electronic device, comprising: The device includes a memory and a processor, wherein the memory stores a program that runs on the processor, and the processor executes the method for dynamic tracking and identification of oceanographic survey vessels based on multi-source heterogeneous data fusion as described in any one of claims 1-6 when running the program.

8. A computer readable storage medium having stored thereon computer instructions, wherein, When the computer instructions are executed, they perform a method for dynamic tracking and identification of oceanographic survey vessels based on multi-source heterogeneous data fusion as described in any one of claims 1-6.

Images