A method, equipment, and medium for fishing vessel state analysis based on trajectory bounding boxes.
By using trajectory bounding box analysis, combined with speed and trajectory characteristics, the accuracy and real-time performance issues of fishing vessel operation status analysis are resolved, enabling efficient judgment of fishing vessel operation status and providing support for fisheries management and maritime safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANDONG TIANDITONG DIGITAL TECH
- Filing Date
- 2025-06-30
- Publication Date
- 2026-06-30
AI Technical Summary
Existing methods for analyzing the operational status of fishing vessels are inaccurate, lack real-time performance, and cannot fully extract trajectory features, making it difficult to meet the needs of tracing the source of catches and managing the total catch volume.
A bounding box-based analysis method is adopted, which combines speed and trajectory characteristics. The fishing vessel operation status is comprehensively judged by using a speed operation identification model, a bounding box grid occupancy method, and a fishing vessel trajectory monitoring model. Data processing is performed using a Beidou terminal and an edge computing box.
It improves the accuracy and reliability of judging the operational status of fishing vessels, is applicable to environments without network signals, supports fisheries management and maritime safety, and provides a basis for decision-making.
Smart Images
Figure CN120735919B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of marine fisheries monitoring technology, and in particular to a method, equipment and medium for analyzing the status of fishing vessels based on trajectory bounding boxes. Background Technology
[0002] Currently, methods for analyzing the operational status of fishing vessels have many limitations. Regarding accuracy, some methods rely solely on a single data indicator, such as judging operational status based solely on speed, ignoring the impact of the complex and variable marine fishing environment on speed, leading to misjudgments. Furthermore, some fishing vessels may be operating within the operational speed range when not in operation due to factors such as ocean currents and wind direction, causing further errors in judgment.
[0003] In terms of real-time performance, traditional methods suffer from slow data processing speeds and cannot provide timely feedback on changes in fishing vessel operational status. Faced with the rapidly changing marine operating environment, they struggle to provide timely and effective decision-making support for fisheries management departments and vessel owners. Furthermore, existing methods lack comprehensive trajectory feature analysis, failing to fully extract the operational information contained within the trajectories, and thus cannot meet future needs such as catch traceability and total catch management. Summary of the Invention
[0004] This application provides a method, device, and medium for analyzing the status of fishing vessels based on trajectory bounding boxes, which solves the following technical problems: the current fishing vessel operation status is easily affected by many factors, making it difficult to accurately monitor the operation status of fishing vessels, and is also not conducive to the management and monitoring of fishing vessel fishing operations.
[0005] The embodiments of this application adopt the following technical solutions:
[0006] On one hand, this application provides a method for analyzing the status of fishing vessels based on bounding boxes, including: using a preset speed operation identification model, partitioning and filtering the fishing vessel speed data in the target sea area according to the fishing vessel operation status to determine the fishing vessel speed data under the operation status to be determined; using the bounding box grid occupancy method, calculating the trajectory occupancy of the fishing vessel trajectory features corresponding to the fishing vessel speed data under a small area grid to determine the suspected fishing vessel trajectory data under a tortuous trajectory; judging the degree of trajectory tortuosity under straight navigation for the suspected fishing vessel trajectory data in a preset historical time period to obtain the fishing vessel trajectory data; performing trajectory interval backtracking processing on the fishing vessel trajectory data under the fishing vessel speed characteristics to determine the fishing vessel start time data corresponding to the fishing vessel trajectory data; using a fishing vessel trajectory monitoring model, performing trajectory tracking processing on the fishing vessel under the relevant speed interval to obtain the fishing vessel end time data; and based on the fishing vessel start time data and the fishing vessel end time data, obtaining the completed operation trajectory and the actual operation water area of the fishing vessel.
[0007] This application's embodiments only require positioning terminals used in daily navigation, avoiding additional investment and making it more suitable for situations at sea without network signals. It can comprehensively consider multiple key factors such as speed and trajectory characteristics for judgment, avoiding errors caused by single-indicator judgments, and further avoids omissions through forward and backward extension algorithms. Furthermore, the comprehensive analysis of multi-dimensional data and a secondary confirmation mechanism greatly improve the reliability of the judgment results. It also provides strong support for fishery companies to rationally arrange operational tasks, improve production efficiency, and reasonably calculate fuel consumption, and provides decision-making basis for government departments to trace catches and assess fishery resources. At the same time, it enhances the reliability of maritime safety assurance.
[0008] In one feasible implementation, a preset speed operation identification model is used to partition and filter the speed data of fishing vessels in the target sea area according to their operational status, thereby determining the speed data of fishing vessels in the operational status to be determined. Specifically, this includes: collecting historical trajectory features and speed features of fishing vessels during production operations; wherein both the trajectory features and speed features are collected through positioning via a BeiDou terminal; based on shipborne edge computing boxes deployed in densely populated fishing vessel areas in the target sea area, the trajectory features and speed features are used to determine the fishing vessel operational status type within the relevant speed range, obtaining a speed-operation type feature mapping relationship; wherein the fishing vessel operational status types include: anchored state, operational state, and non-operational navigation state; and multi-vessel collaborative identification clustering is performed on the corresponding trajectory features in the target sea area at a DBSCAN clustering density. The trajectory-operation type feature clustering relationship is obtained; based on the speed-operation type feature mapping relationship and the trajectory-operation type feature clustering relationship, the trajectory features and speed features under historical fishing vessel production operations are trained using a neural network multi-node model to generate the speed operation identification model; through the speed operation identification model, the current fishing vessel speed set data in the target sea area is subjected to speed partition threshold filtering processing for fishing vessel operation status to obtain fishing vessel speed data in different speed ranges; wherein, the different speed ranges include: operation range speeds between 1.5 knots and 6 knots, anchorage range speeds below 1.5 knots, and non-operation range speeds above 6 knots; the fishing vessel speed data in the operation range speeds are determined as the fishing vessel speed data in the operation status to be determined.
[0009] In one feasible implementation, the bounding box grid occupancy method is used to calculate the trajectory occupancy of the fishing vessel trajectory features corresponding to the fishing vessel speed data under small-area grids, thereby identifying the trajectory data of suspected fishing vessels operating under zigzag trajectories. Specifically, this includes: according to a preset historical time period, marking all points in the historical fishing vessel trajectory data corresponding to the fishing vessel speed data with marine positioning data to obtain a point distribution map; generating a vertex-covering rectangle map based on the latitude and longitude points with the largest values in the point distribution map; and dividing the vertex-covering rectangle map into rectangular blocks of regional grids according to the maximum and minimum latitude and longitude to obtain several small-area grids; Within the area encompassed by the small-area grid, the spatial occupancy of all points connected in the historical fishing vessel trajectory data is assessed based on the degree of tortuous trajectory, thus determining the occupied area grid. The higher the degree of tortuous trajectory, the greater the number of occupied area grids. The trajectory occupancy ratio is calculated by comparing the first number of occupied area grids with the second number of all the small-area grids. If the trajectory occupancy is less than a first preset threshold, the historical fishing vessel trajectory data is determined to be non-operating fishing vessel trajectory data. If the trajectory occupancy is greater than or equal to the first preset threshold, the historical fishing vessel trajectory data is determined to be suspected operating fishing vessel trajectory data.
[0010] In one feasible implementation, the trajectory data of suspected fishing vessels within a preset historical time period is analyzed to determine the degree of trajectory curvature under straight-line navigation, thereby obtaining the fishing vessel trajectory data. Specifically, this includes: determining the start and end points of the suspected fishing vessel trajectory data within the historical time period to obtain the trajectory start and end points; calculating the straight-line distance between the trajectory start and end points to obtain the straight-line distance between the start and end points; and calculating the distance between each pair of trajectory points in the suspected fishing vessel trajectory data according to the chronological order of each trajectory point within the historical time period to obtain the point-to-point line segment distance. The following steps are taken: First, the line segment distances of all points in the suspected fishing vessel trajectory data are summed to obtain a cumulative line segment distance. Then, the ratio between the straight-line distance between the starting and ending points and the cumulative line segment distance is calculated to obtain a distance ratio. Finally, a threshold judgment is made on the distance ratio: if the distance ratio is greater than a second preset threshold, the suspected fishing vessel trajectory data is determined to be non-operating fishing vessel trajectory data; if the distance ratio is less than or equal to the second preset threshold, the suspected fishing vessel trajectory data is determined to be operating fishing vessel trajectory data. The operating fishing vessel corresponding to the operating fishing vessel trajectory data is then marked with an operating status.
[0011] In one feasible implementation, the trajectory data of the fishing vessel is processed by backtracking the trajectory interval under the relevant vessel speed characteristics to determine the start time data of the fishing vessel corresponding to the trajectory data. Specifically, this includes: marking the trajectory start time of the fishing vessel trajectory data in a historical time period; based on the time mark, performing a second trajectory backtracking query on the fishing vessel corresponding to the trajectory data in a historical time period to obtain a historical trajectory interval; based on a preset continuous time period, performing a reverse query judgment on the historical vessel speed characteristics corresponding to the historical trajectory interval to obtain a non-operation time node under the first non-operation speed characteristic; determining the non-operation time node as the actual start time of the fishing vessel trajectory data, and defining and marking the actual start time of the fishing vessel trajectory as the start time data of the fishing vessel corresponding to the trajectory data.
[0012] In one feasible implementation, after determining the start time data of the fishing vessel corresponding to the fishing vessel trajectory data, the method further includes: dividing the historical trajectory interval based on the actual start time of the operation trajectory, and splicing the divided trajectory data with the fishing vessel trajectory data to obtain new fishing vessel operation data; uploading the fishing vessel-related element data in the new fishing vessel operation data to the cloud and storing it in the fisheries management database; wherein the fishing vessel-related element data includes at least: a unique identifier, fishing vessel name, terminal number, operation start time, and operation start fishing area.
[0013] In one feasible implementation, a fishing vessel trajectory monitoring model is used to perform trajectory tracking processing on the fishing vessel within a relevant speed range to obtain data on the fishing vessel's end-of-operation time. Specifically, this includes: configuring dynamic threshold monitoring for the fishing vessel's speed characteristics; generating a dynamic speed end-of-operation trigger mechanism for the fishing vessel based on the end-of-operation trigger speed characteristics corresponding to the non-operational speed and the anchoring speed; performing collaborative delay compensation processing on the fishing vessel's retrospective trajectory characteristics and the predicted trajectory characteristics from the shipboard end using a preset trajectory retrospective feature matching engine to generate a trajectory collaborative architecture for the fishing vessel; and based on the fishing vessel... The positioning and tracking model integrates the dynamic speed end triggering mechanism with the trajectory collaborative architecture to obtain the fishing vessel trajectory monitoring model. Using the fishing vessel trajectory monitoring model and based on a preset continuous time period, the model performs trajectory tracking processing on the speed range of the fishing vessel under relevant time-series extrapolation to obtain the non-operation time node under the first non-operation speed characteristic. The non-operation time node is determined as the fishing vessel's end-of-operation time data under the new fishing vessel operation data. The fishing vessel's end-of-operation time data and the corresponding end-of-operation fishing area are stored in the fisheries management database.
[0014] In one feasible implementation, based on the fishing vessel's start time data and end time data, the completed operation trajectory and actual operating water area of the fishing vessel are obtained. Specifically, this includes: acquiring actual fishing vessel operation trajectory data between the fishing vessel's end time data and start time data based on satellite positioning data; performing interval marking processing on the actual fishing vessel operation trajectory data to obtain the completed operation trajectory; and determining the corresponding actual operating water area by comparing the grid occupancy of the points connected in the completed operation trajectory using the bounding box grid occupancy method.
[0015] Secondly, embodiments of this application also provide a fishing vessel status analysis device based on trajectory bounding box, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, so that the at least one processor can execute a fishing vessel status analysis method based on trajectory bounding box as described in any of the above embodiments.
[0016] Thirdly, embodiments of this application also provide a non-volatile computer storage medium, which is a non-volatile computer-readable storage medium storing at least one program. Each program includes instructions, which, when executed by a terminal, cause the terminal to execute a fishing vessel state analysis method based on trajectory bounding boxes as described in any of the above embodiments.
[0017] This application provides a fishing vessel state analysis method based on trajectory bounding boxes. Compared with the prior art, the embodiments of this application have the following beneficial technical effects:
[0018] 1. This application embodiment only uses the marine positioning and navigation terminal already equipped on the fishing vessel, and then analyzes it in conjunction with trajectory features. There is no need to install other terminals (such as cameras) on the fishing vessel to sense the operation status. The operation status of the fishing vessel can be obtained through a simple algorithm even when the network conditions are poor or the bandwidth is insufficient. It has significant advantages in improving the simplicity, accuracy and reliability of operation status judgment.
[0019] 2. In terms of simplicity, fishing boats do not need to install additional terminals, but only need to rely on the positioning terminals used in daily navigation, which avoids additional investment and is more suitable for situations where there is no network signal at sea.
[0020] 3. Regarding accuracy, the system comprehensively considers multiple key factors, including speed and trajectory characteristics, to avoid errors caused by relying on a single indicator. Furthermore, it employs forward and backward extension algorithms to further prevent omissions. For example, previously, relying solely on speed often led to misjudgments due to sea conditions. However, by incorporating trajectory feature analysis, this application effectively reduces such misjudgments.
[0021] 4. In terms of reliability, the credibility of the judgment results is greatly improved through comprehensive analysis of multi-dimensional data and a secondary confirmation mechanism.
[0022] 5. It provides strong support for fishery companies to rationally arrange operational tasks, improve production efficiency, and reasonably calculate fuel consumption, and provides decision-making basis for government departments to trace catches and assess fishery resources. It also enhances the reliability of maritime safety assurance. Attached Figure Description
[0023] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:
[0024] Figure 1 A flowchart of a fishing vessel state analysis method based on trajectory bounding boxes is provided for an embodiment of this application;
[0025] Figure 2 A schematic flowchart illustrating the screening and determination of fishing vessels provided in this application embodiment;
[0026] Figure 3A grid map of the trajectory of a suspected fishing vessel is provided in this application embodiment;
[0027] Figure 4 A non-operational fishing vessel trajectory grid diagram provided in this application embodiment;
[0028] Figure 5 A schematic diagram illustrating the trajectory of a fishing vessel at the start and end of its fishing operation, provided as an embodiment of this application;
[0029] Figure 6 This is a schematic diagram of the structure of a fishing vessel status analysis device based on a trajectory bounding box, provided in an embodiment of this application. Detailed Implementation
[0030] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.
[0031] It should be noted that the proposed method for analyzing the status of fishing vessels in this application is of significant necessity and practical importance. Addressing the inaccuracy of existing methods, this method comprehensively considers speed and trajectory characteristics to assess operational status from multiple dimensions, greatly improving the accuracy of the assessment. Regarding real-time performance, the optimized data processing workflow enables rapid data analysis and results, meeting the real-time requirements of fisheries management. Marine fisheries production management requires accurate understanding of fishing vessel operational dynamics to rationally allocate resources and avoid overfishing. Maritime safety also relies on accurate operational status information to promptly detect anomalies. This method effectively solves existing problems, providing strong support for sustainable fisheries development and maritime safety, and is of irreplaceable importance.
[0032] This application aims to address the problems of low accuracy and poor real-time performance in existing methods for analyzing the operational status of fishing vessels. By comprehensively analyzing the characteristics of fishing vessel production and operation trajectories and speed information, it achieves accurate judgment of the operational status of fishing vessels. Specifically, it aims to accurately distinguish between different states of fishing vessels, such as stationary, drifting, operating, and sailing, providing fisheries resource management departments with precise dynamic data on fishing vessel operations to assist them in formulating scientific and reasonable fisheries management strategies. It also provides reliable operational status information for ship owners and relevant maritime safety agencies, contributing to the efficient implementation of maritime safety assurance work.
[0033] Meanwhile, this application is based on installing satellite positioning terminals such as Beidou or GPS on fishing vessels navigating at sea. These terminals can report the fishing vessel's position to a server in real time at intervals of 10 minutes or less, thereby obtaining a continuous fishing vessel trajectory. The following analysis is based on this.
[0034] In practical applications, a large fishing area is defined as every 0.5 degrees, and each large fishing area is then divided into nine smaller fishing areas of 3x3. The fishing area where the fishing boat is located can be determined directly by the latitude and longitude range of each fishing area and the location of the fishing boat.
[0035] This application provides a method for analyzing the state of fishing vessels based on trajectory bounding boxes, such as... Figure 1 As shown, the fishing vessel state analysis method based on trajectory bounding boxes specifically includes steps S101-S106:
[0036] S101. Using a preset speed operation identification model, the speed data of fishing vessels in the target sea area is partitioned and filtered according to the fishing vessel operation status to determine the speed data of fishing vessels in the operation status to be determined.
[0037] Specifically, the first step is to collect the trajectory and speed characteristics of fishing vessels during historical operations. Both trajectory and speed characteristics are collected through positioning via BeiDou terminals.
[0038] Furthermore, based on the shipborne edge computing boxes deployed in densely populated fishing areas within the target sea area, the trajectory features and speed features are used to determine the fishing vessel operation status type within the relevant speed range, thus obtaining the speed-operation type feature mapping relationship. The fishing vessel operation status types include: anchored state, operational state, and non-operational navigation state.
[0039] Furthermore, multi-ship collaborative identification clustering is performed on the corresponding trajectory features in the target sea area under the DBSCAN clustering density to obtain the trajectory-operation type feature clustering relationship.
[0040] Furthermore, based on the mapping relationship between speed and operation type features and the clustering relationship between trajectory and operation type features, the trajectory features and speed features under historical fishing vessel production operations are processed by a neural network multi-node model training process to generate a speed operation recognition model.
[0041] Furthermore, using a speed operation identification model, the current fishing vessel speed data in the target sea area is processed by speed zoning threshold filtering based on the fishing vessel's operational status, resulting in fishing vessel speed data in different speed ranges. These different speed ranges include: operational speeds between 1.5 knots and 6 knots, anchoring speeds below 1.5 knots, and non-operational speeds above 6 knots.
[0042] Furthermore, the speed data of fishing vessels operating within the operational zone is determined as the speed data of fishing vessels operating under the undetermined operational state.
[0043] In one embodiment, Figure 2 This application provides a schematic flowchart for screening and determining fishing vessels, as shown in the embodiments. Figure 2 As shown, the BeiDou Navigation Satellite System is first used to provide precise positioning services for fishing vessels. Then, historical trajectory and speed data of the fishing vessels are collected via BeiDou terminals. Next, shipborne edge computing boxes are deployed in densely populated fishing areas within the target sea zone to process the trajectory and speed data in real time. A neural network model with multiple nodes is designed using the speed-operation type feature mapping relationship established after feature mapping calculation, and the trajectory-operation type feature clustering relationship obtained from density analysis based on the DBSCAN algorithm. Finally, historical fishing vessel operation data is used to train the neural network, generating a speed-operation recognition model.
[0044] In one embodiment, the speed operation identification model is first applied to the fishing vessel speed data in the current sea area. Then, based on the model output, the speed data is filtered by partitioning thresholds. Next, the fishing vessel speed data in different speed ranges is determined, including speeds within the operation range, speeds within the anchorage range, and speeds outside the operation range. Finally, the fishing vessel speed data within the operation range is identified as the fishing vessel speed data for the operation state to be determined.
[0045] As a feasible implementation method, based on long-term summarization of the characteristics of fishing vessel production operation trajectories, different speed ranges correspond to different operational states. A speed-operation type feature mapping relationship derived from the deployed shipborne edge computing boxes is used, along with a trajectory-operation type feature clustering relationship obtained through multi-vessel collaborative identification and clustering, to generate a speed-operation identification model. This model enables the specific identification and analysis of the current fishing vessel speed data. After extensive experimental verification, when the speed is less than 1.5 knots, due to the extremely slow speed, it can be determined that the fishing vessel is stationary or drifting, and is not engaged in operation. This is because during normal operations, fishing vessels need to maintain a certain level of propulsion to complete tasks such as fishing, and the speed is usually higher than this value. When a fishing vessel is in operation, the speed is generally between 1.5 and 6 knots. Within this speed range, the fishing vessel can perform various operations such as trawls and purse seines at appropriate speeds, ensuring operational efficiency while meeting the power requirements of actual operations. When a fishing boat is in operation (releasing its nets into the water), it is difficult for it to reach a speed of more than 6 knots. Therefore, when a fishing boat is traveling at a speed greater than 6 knots, it indicates that the fishing boat is in a non-operational navigation state. At this time, the fishing boat may be on its way to or from the target fishing area, and it is traveling at a higher speed to reach its destination as quickly as possible.
[0046] As a feasible implementation method, by receiving the fishing vessel speed reported by the shipborne positioning terminal through software, fishing vessels that may be in operation are initially screened using model recognition. This method can quickly distinguish the dynamics of tens of thousands of fishing vessels at sea into anchored, sailing, and potentially operational states. The method is simple and direct, avoids invalid trajectories from entering subsequent complex analysis logic, and consumes relatively little computing power. Speeds below 1.5 knots indicate anchoring or drifting; speeds between 1.5 and 6 knots may indicate operation, but further judgment is needed; speeds above 6 knots may indicate non-operational sailing.
[0047] S102. Using the bounding box grid occupancy method, the trajectory occupancy of the fishing vessel trajectory features corresponding to the fishing vessel speed data is calculated under a small area grid to determine the trajectory data of suspected fishing vessels operating under a tortuous trajectory.
[0048] Specifically, by combining the preset historical time period, all points in the historical fishing vessel trajectory data corresponding to the fishing vessel speed data are processed by marine positioning data marking to obtain a point distribution map.
[0049] Furthermore, based on the latitude and longitude points with the largest values in the point distribution map, a vertex-covered rectangle map is generated.
[0050] Furthermore, based on the maximum and minimum latitude and longitude, the vertex-covered rectangle map is divided into rectangular blocks of regional grids to obtain several small regional grids.
[0051] Furthermore, it is necessary to determine the spatial occupancy of all points in the historical fishing vessel trajectory data based on the degree of zigzag trajectory by analyzing the area encompassed by the small-area grid, thus identifying the occupied area grids. The higher the degree of zigzag trajectory, the more occupied area grids there are.
[0052] Furthermore, the trajectory occupancy ratio is obtained by calculating the ratio of the first number of occupied area grids to the second number of all small area grids.
[0053] Furthermore, if the trajectory occupancy is less than a first preset threshold, the historical fishing vessel trajectory data is identified as non-operational fishing vessel trajectory data. If the trajectory occupancy is greater than or equal to the first preset threshold, the historical fishing vessel trajectory data is identified as suspected operational fishing vessel trajectory data.
[0054] As a feasible implementation method, the bounding box grid occupancy method is used to analyze the characteristics of fishing vessel tracks to reconfirm whether the tracks at operating speed in the first step are in an operational state. First, all points on the fishing vessel tracks within the last two hours are selected, and the maximum and minimum latitude and longitude of these points are identified. The maximum and minimum latitude and longitude are then recombine to form a rectangle with these as vertices. Next, this rectangle is divided into 5x2 or 2x5 smaller rectangles of the same size (the maximum and minimum latitude and longitude can be used to determine whether the rectangle is horizontal or vertical). Then, each smaller rectangle is used to check whether any point on the track is contained within it. If a smaller rectangle contains any track point, it is marked in red; otherwise, it is marked in black. The number of red smaller rectangles is counted. If there are 7 or more red smaller rectangles, it indicates that the fishing vessel track is relatively tortuous, suggesting that it is likely in an operational state.
[0055] In one embodiment, "the fishing vessel trajectory in the last 2 hours" and "5x2 or 2x5 small rectangles" are the selected quantities for verification in this application. Other durations and separation methods can also be used, but the duration should not be less than 2 hours, and the number of small rectangles marked in red should account for more than 60% of the total number of small rectangles. The longer the duration and the higher the proportion of small rectangles marked in red, the more accurate the judgment will be, but the more omissions will occur. When used in a real production environment, this threshold can be adjusted as needed. Figure 3 A grid map of the trajectory of a suspected fishing vessel is provided for an embodiment of this application, such as... Figure 3 As shown, there are 7 small rectangles marked in red, which match the analysis of suspected operations, that is, the trajectory data of suspected fishing vessels, which in the research experiment are the actual fishing vessels in operation.
[0056] In one embodiment, Figure 4 A non-operational fishing vessel trajectory grid map is provided as an embodiment of this application, such as... Figure 4 As shown, there are 6 small rectangles marked in red. If the trajectory is relatively straight, it will be analyzed as a non-operational state. That is, the trajectory data of non-operational fishing vessels. In the research experiment, it means that the actual fishing vessels have entered the net-hauling stage and are gradually leaving the operation state.
[0057] S103. The trajectory data of suspected fishing vessels in the preset historical time period are used to determine the degree of trajectory curvature under straight navigation to obtain the trajectory data of fishing vessels in operation.
[0058] Specifically, the starting and ending points of suspected fishing vessel trajectories within a historical time period are first determined. Then, the straight-line distance between the starting and ending points is calculated to obtain the straight-line distance between the starting and ending points.
[0059] Furthermore, based on the chronological order of each trajectory point in the historical time period, the distance between each pair of trajectory points in the suspected fishing vessel trajectory data is calculated sequentially to obtain the point-to-point line segment distance.
[0060] Furthermore, the line segment distances of all points in the suspected fishing vessel trajectory data are combined and added together to obtain the cumulative line segment distance.
[0061] Furthermore, the ratio between the straight-line distance from the starting point and the accumulated line segment distance is calculated to obtain the distance ratio, and a threshold judgment is applied to the distance ratio:
[0062] If the distance ratio is greater than the second preset threshold, the suspected fishing vessel trajectory data is determined to be non-operating fishing vessel trajectory data. If the distance ratio is less than or equal to the second preset threshold, the suspected fishing vessel trajectory data is determined to be operating fishing vessel trajectory data; and the operating fishing vessel corresponding to the operating fishing vessel trajectory data is marked with an operating status.
[0063] As a possible implementation method, such as Figure 2 As shown, if the fishing vessel's trajectory is determined to be suspected of being in operation (suspected operation fishing vessel trajectory data), the degree of curvature of the trajectory is further assessed. First, the straight-line distance from the starting point to the ending point of the trajectory is calculated to obtain DLine (straight-line distance between the starting and ending points). Then, the distances between all trajectory points are calculated pairwise in chronological order, and the sums are obtained to obtain DSum (cumulative line segment distance). DLine and DSum are then divided. If the former is less than 70% of the latter, it further indicates that the fishing vessel was not traveling in a straight line during that time period, but rather frequently turning. This suggests that the fishing vessel was in operation and its trajectory data is considered to be from an operation fishing vessel. If the former exceeds 70%, it indicates that the fishing vessel's trajectory is closer to a straight line, and the operation status is ruled out.
[0064] S104. Perform trajectory interval backtracking processing on the fishing vessel trajectory data under the relevant fishing vessel speed characteristics to determine the fishing vessel start time data corresponding to the fishing vessel trajectory data.
[0065] Specifically, the starting time of the fishing vessel's trajectory data within a historical time period is time-series marked. Then, based on the time-series markings, a second historical time period trajectory backtracking query is performed on the fishing vessel corresponding to the fishing vessel's trajectory data to obtain the historical trajectory interval.
[0066] Furthermore, based on a preset continuous time period, it is also necessary to perform a reverse query and judgment of the historical fishing vessel speed characteristics corresponding to the historical trajectory interval to obtain the non-operation time node under the first non-operation speed characteristic.
[0067] Furthermore, the non-operation time node is determined as the actual operation trajectory start time of the fishing vessel trajectory data, and the actual operation trajectory start time is defined and marked as the fishing vessel start time data corresponding to the fishing vessel trajectory data.
[0068] Furthermore, based on the starting time of the actual operation trajectory, the historical trajectory interval is divided, and the divided trajectory data is spliced with the operation vessel trajectory data to obtain new fishing vessel operation data.
[0069] Furthermore, the vessel-related element data from the new fishing vessel operation data will be uploaded to the cloud for processing and stored in the fisheries management database. This vessel-related element data will include at least: a unique identifier, vessel name, terminal number, operation start time, and the fishing area where the operation began.
[0070] In one embodiment, Figure 5 This application provides a schematic diagram of the trajectory of a fishing vessel during the start and end of its fishing operation, as shown in the embodiments of this application. Figure 5 As shown, after determining that the fishing vessel is in operation, the vessel's trajectory within the previous 24 hours is queried backwards from the starting time of the above trajectory (the starting point of the trajectory tracked within the previous 2 hours). The vessel's speed is then determined in reverse chronological order, starting from the trajectory starting point (the starting point of the trajectory tracked within the previous 2 hours). This process continues until a 20-minute interval with a speed below 1.5 knots or above 6 knots is found, which is considered the start time of the fishing operation. A new fishing operation data entry is then created, and relevant elements of the fishing operation (including unique identifier, vessel name, terminal number, operation start time, and starting fishing area) are stored in the database. It is necessary to re-include the non-operational trajectory intervals from the above two-hour monitoring data as part of the operation period. This is beneficial for analyzing situations where the fishing vessel has indeed been sailing in a straight line for more than two hours due to special circumstances. This is because a fishing vessel will inevitably turn during a single operation, but the trajectory within any consecutive 2-hour period may not necessarily involve a turn, so these instances may be missed. The start time of the entire operation interval is obtained based on the characteristic that fishing vessels must be operating continuously (at operating speed) during the net casting and hauling process. In other words, it is the start time data of the fishing vessel corresponding to the fishing vessel trajectory data after the second judgment.
[0071] S105. Using the fishing vessel trajectory monitoring model, track the trajectory of the fishing vessel in the relevant speed range to obtain the data on the time when the fishing vessel finishes its operation.
[0072] Specifically, it is necessary to first configure dynamic threshold monitoring of the speed characteristics of the fishing vessel, and then generate a dynamic speed termination trigger mechanism for the fishing vessel based on the termination trigger speed characteristics corresponding to the speed in the non-operation zone and the anchorage speed.
[0073] Furthermore, by combining the preset trajectory backtracking feature matching engine, the backtracking trajectory features of the fishing vessel and the predicted trajectory features of the shipboard terminal are processed for collaborative delay compensation to generate the trajectory collaborative architecture of the fishing vessel.
[0074] Furthermore, based on the fishing vessel positioning and tracking model, it is also necessary to perform data fusion processing between the dynamic speed termination trigger mechanism and the trajectory collaborative architecture to obtain the fishing vessel trajectory monitoring model.
[0075] Furthermore, by using a fishing vessel trajectory monitoring model and based on a preset continuous time period, trajectory tracking processing is performed on the speed range of the fishing vessel under relevant time-series extrapolation to obtain the non-operation time node under the first non-operation speed characteristic.
[0076] Furthermore, non-operational time nodes are defined as the fishing vessel's end-of-operation time data under the new fishing vessel operation data. This end-of-operation time data, along with the corresponding fishing area where the operation ended, is stored in the fisheries management database.
[0077] As a possible implementation method, such as Figure 2 As shown in the above calculations, it is known that the fishing vessel is currently in operation and the start time of the operation has been obtained. To obtain the end time of the operation, the vessel can be added to the list of fishing vessels in operation. Then, a timed task is set in the program to continuously analyze the speed of fishing vessels already in operation. When a trajectory range of less than 1.5 knots or more than 6 knots is detected for 20 consecutive minutes, the operation is considered to have ended. Then, the end time of the operation, the fishing area where the operation ended, and the operation duration (end time of operation minus start time of operation) are stored in a pre-created fisheries management database. In other words, using the pre-trained fishing vessel trajectory monitoring model, trajectory tracking processing under relevant time-series extrapolation can be performed on the speed range of the fishing vessel in operation to obtain the non-operation time node under the first non-operation speed characteristic. Thus, the subsequent extrapolated non-operation time nodes are determined as the end time data of the fishing vessel in the new fishing vessel operation data.
[0078] In one embodiment, the fishing vessel trajectory monitoring model needs to first perform data configuration and fusion under multiple architectures: (1) Configuration of dynamic speed termination trigger mechanism, the code configuration can be as follows:
[0079] (2) Using a trajectory backtracking feature matching engine, collaborative delay compensation is performed on the backtracking trajectory features of the fishing vessel and the predicted trajectory features from the shipboard end. The core architecture of the trajectory backtracking feature matching engine is as follows: A [Speed drops below threshold] --> B [Start trajectory backtracking]; B --> C {Extract trajectory from the previous 20 minutes}; C --> D [Calculate feature vector]; D --> E [Match operation end mode library]; E --> F {{Feature matching degree > 85%?}}; F --> |Yes|G [Mark predicted end time T_pre]; F --> |No|H [Continue tracking for 15 minutes]. Furthermore, the collaborative delay compensation can be implemented using the following code:
[0080]
[0081]
[0082] Then, based on the fishing vessel positioning and tracking model, the dynamic speed termination trigger mechanism and trajectory collaborative architecture are fused together. This means that the input layer of the fishing vessel positioning and tracking model is defined as the dynamic speed threshold configuration and the output of the collaborative architecture. Combined with a feature fusion engine, trajectory tracking is performed under time-series extrapolation for the fishing vessel's speed range, extrapolating and calculating the non-operational time node under the first non-operational speed characteristic. Simultaneously, the predicted time from the shipboard end, the compensation time from the cloud, and the secondary correction from the equipment data in the calibration layer are also incorporated to finally train and generate the fishing vessel trajectory monitoring model.
[0083] S106. Based on the data of the start time and end time of the fishing vessel, the completed operation trajectory and actual operating water area of the fishing vessel are obtained.
[0084] Specifically, based on satellite positioning data, the actual fishing vessel operation trajectory data between the fishing vessel's end time and start time is obtained. Then, the actual fishing vessel operation trajectory data is processed by marking intervals at data points to obtain the completed operation trajectory.
[0085] Furthermore, by using the bounding box grid occupancy method, the grid occupancy of the points connected in the completed operation trajectory is compared to determine the corresponding actual operation area.
[0086] In the verification phase of the embodiments, this application uses the real fishing vessel activity trajectory obtained by Beidou shipborne terminal positioning, which includes periods of operation and non-operation. The following will perform fishing vessel state calculation and analysis based on trajectory bounding boxes. For example, in the first trajectory segment, the departure trajectory is tortuous, but the speed is relatively high (above 6 knots), indicating that the vessel is heading to the target operating area and has begun operations in fishing zone 110-2. Further refining the fishing vessel activity trajectory in fishing zone 110-2, we can see that the fishing vessel speed has decreased to between 1.5 and 6 knots, and there are many turns. Continuing to track the fishing vessel trajectory to the right, as shown in the figure below, at the red arrow, the fishing vessel reaches 7.7 knots. At this point, the fishing vessel has completed hauling in the nets and begins to enter the non-operational navigation zone. Continuing to track the trajectory to the right, the fishing vessel continues to sail at high speed (above 6 knots) until reaching the next target operating area, during which the trajectory is relatively straight. At the red arrow in the trajectory diagram, the fishing vessel reduces its speed, casts the nets, and enters the operating state. After entering the operating state, the fishing vessel's activity trajectory will involve multiple turns and detours. Observations reveal that fishing vessels typically maintain speeds above 6 knots and follow relatively straight paths when not in operational mode. However, when fishing vessels are in operation, their paths generally fall between 1.5 and 6 knots and are more tortuous and circuitous. This is because after the nets are cast, the increased water resistance caused by the nets reduces speed. Depending on the net type, the length of the nets ranges from hundreds to thousands of meters. Due to fish movement, fishing vessels usually maneuver around the vicinity after spotting a school of fish, resulting in a more varied and winding path. The determined operational fishing vessel paths, along with their corresponding start and end times, closely correspond to the actual fishing vessel activity paths. Therefore, the accuracy of this application's judgment is high, providing strong support for fishery companies to rationally allocate operational tasks, improve production efficiency, and accurately calculate fuel consumption. It also provides a decision-making basis for government departments to trace catches and assess fishery resources.
[0087] In addition, embodiments of this application also provide a fishing vessel state analysis device based on trajectory bounding boxes, such as... Figure 6 As shown, the fishing vessel status analysis device 600 based on trajectory bounding boxes specifically includes:
[0088] At least one processor 601. And a memory 602 communicatively connected to the at least one processor 601. The memory 602 stores instructions executable by the at least one processor 601, enabling the at least one processor 601 to execute:
[0089] By using a preset speed operation identification model, the speed data of fishing vessels in the target sea area is partitioned and filtered according to the operation status of the fishing vessels, and the speed data of the fishing vessels in the operation status to be determined is identified.
[0090] By using the bounding box grid occupancy method, the trajectory occupancy of the fishing vessel trajectory features corresponding to the fishing vessel speed data is calculated under a small area grid, and the trajectory data of suspected fishing vessels operating under the tortuous trajectory is determined.
[0091] The trajectory data of suspected fishing vessels in a preset historical time period is obtained by judging the degree of trajectory curvature under straight navigation.
[0092] The trajectory data of the fishing vessels is backtracked under the relevant speed characteristics of the fishing vessels to determine the start time data of the fishing vessels corresponding to the trajectory data of the fishing vessels.
[0093] By using the fishing vessel trajectory monitoring model, the trajectory of the fishing vessel in operation is tracked within the relevant speed range to obtain the data on the time when the fishing vessel finishes its operation.
[0094] Based on the data of the start time and end time of fishing operations, the completed operation trajectory and actual operating waters of the fishing vessels are obtained.
[0095] This application's embodiments only require positioning terminals used in daily navigation, avoiding additional investment and making it more suitable for situations at sea without network signals. It can comprehensively consider multiple key factors such as speed and trajectory characteristics for judgment, avoiding errors caused by single-indicator judgments, and further avoids omissions through forward and backward extension algorithms. Furthermore, the comprehensive analysis of multi-dimensional data and a secondary confirmation mechanism greatly improve the reliability of the judgment results. It also provides strong support for fishery companies to rationally arrange operational tasks, improve production efficiency, and reasonably calculate fuel consumption, and provides decision-making basis for government departments to trace catches and assess fishery resources. At the same time, it enhances the reliability of maritime safety assurance.
[0096] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.
[0097] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.
[0098] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0099] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0100] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0101] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0102] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0103] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0104] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0105] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0106] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of this specification.
Claims
1. A method for analyzing the state of fishing vessels based on trajectory bounding boxes, characterized in that, The method includes: Using a pre-defined speed operation identification model, the speed data of fishing vessels in the target sea area is partitioned and filtered according to their operational status to determine the speed data of fishing vessels in the operational status to be determined, specifically including: The trajectory and speed characteristics of fishing vessels during historical fishing operations are collected; wherein, the trajectory and speed characteristics are collected through positioning via a Beidou terminal. Based on the shipborne edge computing boxes deployed in the densely populated fishing areas of the target sea area, the trajectory features and the speed features are used to determine the fishing vessel operation status type under the relevant speed range, and the speed-operation type feature mapping relationship is obtained; wherein, the fishing vessel operation status type includes: anchoring status, operation status and non-operation navigation status. Perform multi-ship collaborative identification clustering on the trajectory features corresponding to the target sea area under the DBSCAN clustering density to obtain the trajectory-operation type feature clustering relationship; Based on the speed-operation type feature mapping relationship and the trajectory-operation type feature clustering relationship, the trajectory features and speed features under historical fishing vessel production operations are trained using a neural network multi-node model to generate the speed operation recognition model. Using the speed operation identification model, the current fishing vessel speed data in the target sea area is processed by speed partition threshold filtering based on the fishing vessel's operational status to obtain fishing vessel speed data in different speed ranges; wherein, the different speed ranges include: operational speed range between 1.5 knots and 6 knots, anchorage speed range below 1.5 knots, and non-operational speed range above 6 knots; The speed data of fishing vessels in the operating range is determined as the speed data of fishing vessels in the operating state to be determined. Using the bounding box grid occupancy method, trajectory occupancy calculations are performed on the trajectory features of the fishing vessels corresponding to the vessel speed data under a small-area grid to determine the trajectory data of suspected fishing vessels operating under zigzag trajectories, specifically including: According to the preset historical time period, all points in the historical fishing vessel trajectory data corresponding to the fishing vessel speed data are processed by marine positioning data marking to obtain a point distribution map. Based on the latitude and longitude point with the largest value in the point distribution map, a vertex-covered rectangle map is generated; Based on the maximum and minimum latitude and longitude, the vertex covering rectangle is divided into rectangular blocks of regional grids to obtain several small regional grids; By analyzing the area encompassed by the small-area grid, the spatial occupancy of all points in the historical fishing vessel trajectory data is determined based on the degree of tortuous trajectory, thus identifying the occupied area grid; wherein, the higher the degree of tortuous trajectory, the more occupied area grids there are. The trajectory occupancy ratio is obtained by calculating the ratio of the first number of the occupied area grids to the second number of all the small area grids. If the trajectory occupancy is less than a first preset threshold, then the historical fishing vessel trajectory data is determined as non-operational fishing vessel trajectory data. If the trajectory occupancy is greater than or equal to the first preset threshold, then the historical fishing vessel trajectory data is determined as the suspected fishing vessel trajectory data. The trajectory data of the suspected fishing vessels in the preset historical time period is determined by judging the degree of trajectory curvature under straight navigation to obtain the trajectory data of the fishing vessels. The trajectory data of the fishing vessel is processed by backtracking the trajectory interval under the relevant speed characteristics of the fishing vessel to determine the start time data of the fishing vessel corresponding to the trajectory data of the fishing vessel. By using a fishing vessel trajectory monitoring model, the trajectory of the fishing vessel in the relevant speed range is tracked to obtain the fishing vessel's end time data. Based on the fishing vessel's start time and end time data, the completed operation trajectory and actual operating waters of the fishing vessel are obtained.
2. The method for analyzing the state of a fishing vessel based on a trajectory bounding box according to claim 1, characterized in that, The trajectory data of suspected fishing vessels in a preset historical time period is analyzed to determine the degree of trajectory curvature under straight-line navigation, resulting in the fishing vessel trajectory data, specifically including: By determining the start and end points of the trajectory data of suspected fishing vessels within a historical time period, the starting and ending points of the trajectory can be obtained. The straight-line distance between the starting point and the ending point of the trajectory is calculated to obtain the straight-line distance between the starting and ending points. Based on the chronological order of each trajectory point in the historical time period, the distance between each pair of trajectory points in the suspected fishing vessel trajectory data is calculated sequentially to obtain the point-to-point line segment distance. The cumulative line segment distances of all points in the suspected fishing vessel trajectory data are summed together to obtain the cumulative line segment distances. The distance ratio is calculated by comparing the straight-line distance between the starting and ending points with the accumulated line segment distances, and a threshold judgment is then applied to the distance ratio. If the distance ratio is greater than the second preset threshold, the suspected fishing vessel trajectory data will be determined as non-fishing vessel trajectory data. If the distance ratio is less than or equal to the second preset threshold, the suspected fishing vessel trajectory data is determined as the fishing vessel trajectory data; and the fishing vessel corresponding to the fishing vessel trajectory data is marked with its operational status.
3. The method for analyzing the state of fishing vessels based on trajectory bounding boxes according to claim 1, characterized in that, The trajectory data of the fishing vessels is processed by backtracking the trajectory intervals based on the vessel speed characteristics to determine the start time data of the fishing vessels corresponding to the trajectory data. Specifically, this includes: The trajectory start time of the fishing vessel's trajectory data in the historical time period is time-series marked; Based on the time sequence marker, a second historical time period trajectory backtracking query is performed on the fishing vessel corresponding to the fishing vessel trajectory data to obtain the historical trajectory interval. Based on a preset continuous time period, the historical fishing vessel speed characteristics corresponding to the historical trajectory interval are queried and judged in reverse order of time nodes to obtain the non-operation time node under the first non-operation speed characteristic. The non-operation time node is determined as the actual operation trajectory start time of the fishing vessel trajectory data, and the actual operation trajectory start time is defined and marked as the fishing vessel start operation time data corresponding to the fishing vessel trajectory data.
4. The method for analyzing the state of a fishing vessel based on a trajectory bounding box according to claim 3, characterized in that, After determining the start time data of the fishing vessel corresponding to the fishing vessel trajectory data, the method further includes: Based on the starting time of the actual operation trajectory, the historical trajectory interval is divided, and the divided trajectory data is spliced with the operation vessel trajectory data to obtain new fishing vessel operation data. The fishing vessel-related element data in the new fishing vessel operation data is uploaded to the cloud for processing and stored in the fisheries management database; wherein the fishing vessel-related element data includes at least: unique identifier, fishing vessel name, terminal number, operation start time and operation start fishing area.
5. The method for analyzing the state of a fishing vessel based on a trajectory bounding box according to claim 1, characterized in that, By using a fishing vessel trajectory monitoring model, the trajectory of the fishing vessel in operation is tracked within a certain speed range to obtain data on the time when the fishing vessel finishes its operation, specifically including: Dynamic threshold monitoring configuration is performed on the fishing vessel's speed characteristics, and a dynamic speed termination trigger mechanism is generated based on the termination trigger speed characteristics corresponding to the non-operational speed and the anchoring speed. Based on the preset trajectory backtracking feature matching engine, the backtracking trajectory features of the fishing vessel and the predicted trajectory features of the shipboard terminal are processed for collaborative delay compensation to generate the trajectory collaborative architecture of the fishing vessel. Based on the fishing vessel positioning and tracking model, the dynamic speed termination triggering mechanism and the trajectory collaborative architecture are fused together to obtain the fishing vessel trajectory monitoring model. Using the fishing vessel trajectory monitoring model and based on a preset continuous time period, the trajectory tracking processing of the speed range of the fishing vessel is performed under the relevant time series extrapolation to obtain the non-operation time node under the first non-operation speed characteristic. The non-operation time node is determined as the fishing vessel's end-of-operation time data under the new fishing vessel operation data; and the fishing vessel's end-of-operation time data and the corresponding fishing area where the operation ended are stored in the fisheries management database.
6. The method for analyzing the state of a fishing vessel based on a trajectory bounding box according to claim 1, characterized in that, Based on the fishing vessel's start and end time data, the completed operation trajectory and actual operating waters of the fishing vessel are obtained, specifically including: Based on satellite positioning data, the actual fishing vessel operation trajectory data between the fishing vessel's end time data and the fishing vessel's start time data is obtained. The actual fishing vessel operation trajectory data is processed by marking the data points at intervals to obtain the completed operation trajectory; By using the bounding box grid occupancy method, the grid occupancy of the points in the completed operation trajectory is compared to determine the corresponding actual operation water area.
7. A fishing vessel status analysis device based on trajectory bounding boxes, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, enabling the at least one processor to perform a fishing vessel state analysis method based on trajectory bounding boxes according to any one of claims 1-6.
8. A non-volatile computer storage medium, characterized in that, The storage medium is a non-volatile computer-readable storage medium that stores at least one program, each program including instructions that, when executed by a terminal, cause the terminal to perform a fishing vessel state analysis method based on a trajectory bounding box according to any one of claims 1-6.