A ship trajectory identification method and system based on VTS radar

Abstract

This invention discloses a ship trajectory recognition method and system based on VTS radar, belonging to the field of ship traffic monitoring technology. The method includes constructing a continuity equation, marking divergence anomaly regions, generating a preliminary trajectory point set, extracting the complex signal from the preliminary trajectory point set, setting a dynamic threshold, and marking a set of core points with high interaction. Starting from each core point, the method tracks the trajectory along the dominant direction, sets a direction offset threshold, forms a trajectory set, constructs an Eulerian grid based on the trajectory set, marks non-physical trajectory segments, corrects the non-physical trajectory segments, and generates a trajectory point set. This invention improves the accuracy and robustness of target trajectory recognition by mapping complex signals to an energy density field and combining it with energy flow vector field analysis. It also improves the accuracy of target trajectory tracking by combining changes in energy flow with trajectory adjustment, and avoids retaining unreasonable trajectory segments through Eulerian grid time consistency analysis and trajectory correction.

Description

Technical Field

[0001] This invention relates to the field of ship traffic monitoring technology, and in particular to a ship trajectory identification method and system based on VTS radar. Background Technology

[0002] With the continuous development of port intelligence and shipping traffic management technology, the Vessel Traffic Service System (VTS) plays an increasingly important role in ensuring shipping safety and improving navigation efficiency. The VTS system relies on multi-source sensing equipment such as radar, AIS, and video surveillance to monitor ships in the sea area. Among them, radar, as the core detection means that can detect ships around the clock, can continuously track targets under conditions such as low visibility and complex weather. VTS radar has made significant progress in detection accuracy, anti-interference capability, and signal processing performance. It can output complex signal data containing in-phase and quadrature components, which provides a foundation for high-precision ship trajectory identification.

[0003] Existing ship trajectory recognition technologies still have shortcomings. Current methods mostly process radar echoes at the amplitude or distance information level, lacking the ability to map complex signals to energy density fields and combine them with electromagnetic field energy flow vector fields for analysis. This results in insufficient detail in characterizing the target's motion direction and energy change trend. The trajectory post-processing stage lacks a correction mechanism based on physical consistency constraints, which easily retains trajectory segments that do not conform to actual motion laws, affecting subsequent traffic situation analysis and command decisions. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a ship trajectory identification method and system based on VTS radar, which solves the problem that current methods mostly process radar echoes at the amplitude or distance information level, lacking the ability to map complex signals to an energy density field and combine them with electromagnetic field energy flow vector fields for analysis. This results in insufficient detail in the characterization of the target's motion direction and energy change trend. Furthermore, the trajectory post-processing stage lacks a correction mechanism based on physical consistency constraints, which easily retains trajectory segments that do not conform to actual motion laws, affecting subsequent traffic situation analysis and command decision-making.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a ship trajectory identification method based on VTS radar, which includes the following steps:

[0008] Collect complex signal data and preprocess it, map the normalized complex signal to a rectangular coordinate system, calculate the energy density field of the radar wave, construct the continuity equation, mark the divergence anomaly region, generate a preliminary trajectory point set, extract the complex signal of the preliminary trajectory point set, calculate the phase angle, perform a two-dimensional Fourier transform on the phase angle to extract the dominant direction, calculate the interaction quantity, set a dynamic threshold, and mark the kernel point set with high interaction quantity.

[0009] Starting from each core point, the trajectory is tracked along the dominant direction. A directional offset threshold is set to form a trajectory set. Based on the trajectory set, the tension vector between adjacent points of each trajectory is calculated. Based on the tension vector between adjacent points, the local chain energy is calculated. The total chain energy of each trajectory is summarized, and the trajectory point positions are updated to obtain the adjusted trajectory point set.

[0010] Construct an Eulerian mesh, calculate the time consistency deviation, set a time deviation threshold, mark non-physical trajectory segments, correct the non-physical trajectory segments, generate a trajectory point set, and construct a visualization interface to display the trajectory point set.

[0011] As a preferred embodiment of the ship trajectory identification method based on VTS radar described in this invention, the step of mapping the normalized complex signal to a Cartesian coordinate system, calculating the energy density field of the radar wave, constructing a continuity equation, and marking divergence anomaly regions includes:

[0012] The normalized complex signal is mapped to a rectangular coordinate system, and the energy density field of the radar wave is calculated. Based on the normalized complex signal and the energy density field, an energy flow vector field is constructed.

[0013] Based on the energy density field and energy flow vector field, a continuity equation is constructed, and the continuity equation is solved using the finite difference method. The divergence anomaly region is marked, and a preliminary trajectory point set is generated.

[0014] Extract the complex signal of the initial trajectory point set, calculate the phase angle, perform phase unwrapping, perform a two-dimensional Fourier transform on the phase angle to extract the dominant direction, calculate the time gradient of the energy density field, and combine the time gradient and the dominant direction to calculate the interaction quantity.

[0015] Set a dynamic threshold to mark the core point set with high interaction volume.

[0016] As a preferred embodiment of the ship trajectory identification method based on VTS radar described in this invention, the step of tracing the trajectory along the dominant direction, starting from each core point, includes:

[0017] Starting from each core point, trace the trajectory along the dominant direction and calculate the root mean square error of the phase direction offset.

[0018] A statistical analysis method is used to set a direction offset threshold. The direction offset threshold is compared with the mean square error of the phase direction offset. If the mean square error of the phase direction offset is greater than the direction offset threshold, it is determined to be a separated trajectory; otherwise, it is determined to be a same trajectory. All separated trajectories are summarized to form a trajectory set.

[0019] As a preferred embodiment of the ship trajectory identification method based on VTS radar described in this invention, the steps of calculating the tension vector between adjacent points of each trajectory, calculating the local chain energy based on the tension vector between adjacent points, summarizing the total chain energy of each trajectory, and updating the trajectory point positions include:

[0020] Based on the set of trajectories, calculate the tension vector between adjacent points of each trajectory, calculate the local chain energy based on the tension vector between adjacent points, and summarize the total chain energy of each trajectory;

[0021] Calculate the partial derivative of the total chain energy with respect to the trajectory points and the adaptive step size, update the trajectory point positions, and use the gradient descent method to set the number of iterations to obtain the adjusted trajectory point set.

[0022] As a preferred embodiment of the ship trajectory identification method based on VTS radar described in this invention, the step of correcting non-physical trajectory segments to generate a trajectory point set includes:

[0023] Based on the adjusted trajectory point set, an Eulerian mesh is constructed, the time consistency deviation is calculated, a time deviation threshold is set using statistical analysis, and trajectories with time consistency deviations greater than the time deviation threshold are selected and marked as non-physical trajectory segments; otherwise, they are marked as normal trajectory segments.

[0024] Correct non-physical trajectory segments;

[0025] The corrected non-physical trajectory segments and normal trajectory segments are spliced ​​together to generate a trajectory point set.

[0026] As a preferred embodiment of the ship trajectory identification method based on VTS radar described in this invention, the step of constructing a visual interface to display the trajectory point set includes:

[0027] Use the visualization tool Matplotlib to build a visualization interface to display the trajectory point set in real time;

[0028] Users who have passed real-name verification are allowed to view it.

[0029] As a preferred embodiment of the ship trajectory identification method based on VTS radar described in this invention, the step of collecting complex signal data and performing preprocessing includes:

[0030] The VTS radar system captures electromagnetic echo signals within the target sea area, collects complex signal data, and performs noise reduction and normalization processing.

[0031] Secondly, the present invention provides a ship trajectory identification system based on VTS radar, comprising:

[0032] The data collection and processing module is used to collect complex signal data and perform preprocessing.

[0033] The core point update module is used to calculate the phase angle, perform a two-dimensional Fourier transform on the phase angle to extract the dominant direction, calculate the interaction quantity, set a dynamic threshold, mark the core point set with high interaction quantity, trace the trajectory along the dominant direction with each core point as the starting point, set a direction offset threshold to form a trajectory set, calculate the tension vector between adjacent points of each trajectory based on the trajectory set, calculate the local chain energy based on the tension vector between adjacent points, summarize the total chain energy of each trajectory, update the trajectory point position, and obtain the adjusted trajectory point set;

[0034] The correction module is used to construct an Eulerian mesh, calculate the time consistency deviation, set the time deviation threshold, mark non-physical trajectory segments, correct the non-physical trajectory segments, and generate a trajectory point set.

[0035] The display module is used to build a visual interface to display the trajectory point set.

[0036] The beneficial effects of this invention are as follows:

[0037] This invention improves the accuracy and robustness of target trajectory recognition by mapping complex signals to an energy density field and combining it with the analysis of energy flow vector fields. It also improves the accuracy of target trajectory tracking by combining changes in energy flow with trajectory adjustment. Furthermore, it avoids the retention of unreasonable trajectory segments by using Eulerian grid time consistency analysis and trajectory correction. Attached Figure Description

[0038] Figure 1 This is a flowchart of the operation of the ship trajectory identification method based on VTS radar in Example 1.

[0039] Figure 2 This is a schematic diagram of the ship trajectory identification system based on VTS radar in Example 1. Detailed Implementation

[0040] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0041] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0042] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0043] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides a ship trajectory identification method based on VTS radar, including the following steps:

[0044] S1. Collect complex signal data and preprocess it, map the normalized complex signal to a rectangular coordinate system, calculate the energy density field of the radar wave, construct the continuity equation, mark the divergence anomaly region, generate a preliminary trajectory point set, extract the complex signal of the preliminary trajectory point set, calculate the phase angle, perform a two-dimensional Fourier transform on the phase angle to extract the dominant direction, calculate the interaction quantity, set a dynamic threshold, and mark the kernel point set with high interaction quantity.

[0045] Specifically, the process involves collecting complex signal data and preprocessing it, including:

[0046] The VTS radar system captures electromagnetic echo signals within the target sea area, collects complex signal data, and performs noise reduction and normalization processing, using the following formula:

[0047] E(R,θ,t)=I(R,θ,t)+jQ(R,θ,t),

[0048] Where E(R,θ,t) is a complex signal, representing the radar echo at distance R, azimuth angle θ, and time t; I(R,θ,t) is the in-phase component, representing the real part of the echo signal; Q(R,θ,t) is the quadrature component, representing the imaginary part of the echo signal; R is the distance of the radar to the target (ship); θ is the azimuth angle of the radar scan; t is the timestamp; and j is the imaginary unit.

[0049] By normalizing and denoising complex signal data, the system can obtain higher quality signal input, which helps to accurately identify the position and dynamics of ship targets. This can effectively avoid the error problems that occur in traditional signal processing and improve the stability and robustness of the radar system in complex environments.

[0050] Furthermore, the normalized complex signal is mapped to a Cartesian coordinate system, and the energy density field of the radar wave is calculated. A continuity equation is constructed, and divergence anomaly regions are marked, including:

[0051] The normalized complex signal is mapped to a Cartesian coordinate system, and the energy density field of the radar wave is calculated using the following formula:

[0052] x=Rcosθ, y=Rsinθ, W(x,y,t)=|E'(x,y,t)| 2 / Z eff ,

[0053] Where W(x,y,t) is the energy density field of the radar wave, representing the energy intensity at rectangular coordinates (x,y) and time t, where x and y are the positions in the rectangular coordinate system, E'(x,y,t) is the normalized complex signal, and Z... eff For effective impedance, a fixed-value method is used to set it, and W(x,y,t) is the energy density field of spacetime;

[0054] Based on the normalized complex signal and energy density field, an energy flow vector field is constructed, with the following formula:

[0055] ,

[0056] in Let W be the energy flow vector field, representing the direction and intensity of electromagnetic wave energy propagation. μ0 is the free permeability, defined based on electromagnetic theory. Re is the real part of the complex number, and × is the vector cross product, representing the directional propagation of the electromagnetic field energy flow. max (t) represents the maximum value of the energy density field at the current time, ρ eff Free-space wave impedance;

[0057] Based on the energy density field and the energy flow vector field, a continuity equation is constructed, as follows:

[0058] ,

[0059] in Let be the partial derivative of energy density with respect to time, representing the rate of change of energy over time. The gradient operator represents the operator for spatial partial derivatives. Q is the divergence of the energy flow vector field. env This is an environmental disturbance term, representing the disturbance of energy flow by external factors;

[0060] The continuity equation is solved using the finite difference method, divergence anomaly regions are marked, and a preliminary trajectory point set is generated. The formula is as follows:

[0061] ,

[0062] σth =μ div +k σ ·σ div ,

[0063] Where P init Let i be the index of a single trajectory point in the initial trajectory point set, and σ be the index of the single trajectory point in the initial trajectory point set. th The divergence threshold is set using statistical analysis, where N is the total number of trajectory points, and μ... div and σ div Let k be the mean and standard deviation of the divergence, respectively. σ This is the dynamic adjustment coefficient for the divergence threshold;

[0064] Extract the complex signal from the initial trajectory point set, calculate the phase angle, and perform phase unwrapping. The formula is as follows:

[0065] ,

[0066] Where Φ(x,y,t) is the phase angle, representing the phase angle at rectangular coordinates (x,y) and time t, unwrap is the phase unwrapping operation, and Q'(x,y,t) and I'(x,y,t) are the orthogonal component and in-phase component of the normalized complex signal in the initial trajectory point set, respectively;

[0067] The dominant direction is extracted by performing a two-dimensional Fourier transform on the phase angle, as shown in the formula:

[0068] ,

[0069] ,

[0070] in The result is the two-dimensional Fourier transform of the phase angle, where U and V are the frequency coordinates in the Fourier domain, and N' is the size of the Fourier transform window. The dominant direction vector represents the direction of local motion. To obtain the frequency coordinates corresponding to the maximum value;

[0071] The formula for calculating the time gradient of the energy density field is:

[0072] ,

[0073] in Δt represents the time gradient of the energy density field, and Δt is the radar scanning period.

[0074] Combining the time gradient and the dominant direction, the interaction quantity is calculated using the following formula:

[0075] ,

[0076] in Let v be the interaction quantity, representing the dot product of the direction field and the energy gradient. max The maximum speed of the ship is obtained from sensors;

[0077] A dynamic threshold is set to mark the set of kernel points with high interaction volume, representing the position of the target ship. The formula is as follows:

[0078] ,

[0079] ,

[0080] in The core point set contains the coordinates and time of the target point. The dynamic threshold for time t is set using statistical analysis. and These are the mean and standard deviation of the interaction, respectively, k' σ This is the dynamic adjustment coefficient for the dynamic threshold.

[0081] By calculating the energy density field, the propagation characteristics of the signal can be intuitively presented from a spatial perspective, helping to further improve the target recognition capability of radar signals in complex maritime environments. By marking divergence anomaly regions, the reliability and accuracy of the system for ship trajectories can be significantly improved, the direction of ship movement can be extracted, and the instability of target recognition caused by factors such as sea surface disturbance and changes in ship maneuverability can be avoided. The combination of interaction quantity and dynamic threshold enables the system to flexibly respond to different maritime traffic conditions and has high adaptability. By marking the core point set with high interaction quantity, not only is the accuracy of ship trajectory recognition improved, but the sensitivity to ship interaction is also significantly enhanced. Especially in complex environments, such as densely populated port areas or severe weather conditions, it can ensure timely updates of target information, thereby achieving dynamic monitoring of ships.

[0082] S2. Starting from each core point, track the trajectory along the dominant direction, set a direction offset threshold, form a trajectory set, calculate the tension vector between adjacent points of each trajectory based on the trajectory set, calculate the local chain energy based on the tension vector between adjacent points, summarize the total chain energy of each trajectory, update the trajectory point position, and obtain the adjusted trajectory point set.

[0083] Specifically, starting from each core point, the trajectory is traced along the dominant direction, including:

[0084] Starting from each core point, the trajectory is traced along the dominant direction using the following formula:

[0085] ,

[0086] Where Γ ο (t) represents the position of the o-th trajectory at time t, v oLet be the speed of the ship on the o-th trajectory. is the direction vector of the trajectory point at the previous moment, and o is the index of a single trajectory;

[0087] The formula for calculating the root mean square error of the phase direction offset is:

[0088] ,

[0089] Where Δ Φ (o,u) represents the mean square error of the phase direction offset between the o-th and u-th trajectories. and Let be the direction vectors of the o-th and u-th trajectories at time t, respectively, where T is the length of the time window;

[0090] A statistical analysis method is used to set a direction offset threshold. The direction offset threshold is compared with the mean square error of the phase direction offset. If the mean square error of the phase direction offset is greater than the direction offset threshold, it is determined to be a separated trajectory; otherwise, it is determined to be a same trajectory. All separated trajectories are summarized to form a trajectory set.

[0091] By tracking the dominant direction, the system can accurately predict the trajectory of the target ship when the ship's direction changes, avoiding the delayed response or deviation of trajectory changes in traditional methods. Through intelligent trajectory separation, it can improve the efficiency of target recognition and tracking in multi-target scenarios, especially in complex navigation areas (such as ports or waterway intersections), and can more accurately identify the movement path of each ship, preventing misidentification.

[0092] Furthermore, the tension vector between adjacent points of each trajectory is calculated. Based on the tension vector between adjacent points, the local chain energy is calculated. The total chain energy of each trajectory is summarized, and the trajectory point positions are updated, including:

[0093] Based on the set of trajectories, the tension vector between adjacent points of each trajectory is calculated using the following formula:

[0094] ,

[0095] in Let u be the tension vector of the u-th segment of the trajectory, u=(x u ,y u ,t u () represents the position and time of the u-th trajectory point;

[0096] Based on the tension vector between adjacent points, the local chain energy is calculated, and the total chain energy of each trajectory is summarized using the following formula:

[0097] ,

[0098] ,

[0099] ,

[0100] Where E u Let t be the local chain energy of the u-th segment of the trajectory. u Let v be the timestamp of the u-th trajectory point. u Let σ be the instantaneous velocity of the u-th segment of the trajectory. u Let E' be the standard deviation of the velocity, and E' be the total chain energy.

[0101] The partial derivative of the total chain energy with respect to the trajectory points and the adaptive step size are calculated using the following formula:

[0102] ,

[0103] ,

[0104] in Let α be the partial derivative of the total chain energy with respect to the trajectory points, γ be the gradient weight coefficient (set using a linear search method), η be the adjustment step size (set using a linear weighting method), and α be the gradient weight coefficient. η and β η These are the step size scaling factor and the environmental disturbance adjustment factor, respectively, optimized using a grid search. env The intensity of environmental disturbance is set using rules of thumb;

[0105] Update the positions of the new trajectory points, use gradient descent to set the number of iterations, and obtain the adjusted trajectory point set. The formula is:

[0106] ,

[0107] Where P u new Let be the updated u-th trajectory point.

[0108] The introduction of tension vectors enhances the description of the relationships between trajectory points, helping the system accurately calculate the instantaneous velocity changes of the ship. By calculating the local chain energy, the system can effectively evaluate whether each trajectory point conforms to the physical motion laws of the ship. Furthermore, during trajectory update, it can avoid overfitting or spurious trajectory changes, thereby improving the stability and accuracy of trajectory prediction. By optimizing the partial derivative of the total chain energy with respect to the trajectory points, the position and trajectory of the trajectory points can be finely adjusted. The introduction of gradient descent allows the system to obtain accurate trajectory point positions through stepwise optimization, ensuring the dynamic updating and optimization of the trajectory point set. In a multi-target environment, iterative optimization ensures that the system accurately tracks the changes of each target, especially in cases of high-speed movement or complex trajectory changes, enabling rapid adjustment and reduction of errors, thus improving the accuracy of target recognition.

[0109] S3. Construct an Eulerian mesh, calculate the time consistency deviation, set a time deviation threshold, mark non-physical trajectory segments, correct the non-physical trajectory segments, generate a trajectory point set, and construct a visualization interface to display the trajectory point set.

[0110] Specifically, non-physical trajectory segments are corrected to generate a set of trajectory points, including:

[0111] Based on the adjusted trajectory point set, an Eulerian mesh is constructed, and the time consistency deviation is calculated using the following formula:

[0112] ,

[0113] ,

[0114] Where δ s Let M be the time consistency deviation of the s-th grid point, and M be the neighborhood of the grid point. Number of trajectory points within, The neighborhood of the s-th grid point is defined by a spatial neighborhood partitioning method, μ. flow P is the mean of the global time rate of change. ' u and P ' u+1 For trajectory point pairs within the neighborhood;

[0115] Using statistical analysis, a time deviation threshold is set, and trajectories with time consistency deviations greater than the time deviation threshold are filtered out and marked as non-physical trajectory segments; otherwise, they are marked as normal trajectory segments.

[0116] The formula for correcting non-physical trajectory segments is as follows:

[0117] ,

[0118] ,

[0119] in Let β' be the correction direction vector for segment u, and β' be the historical velocity weight, set using a linear search method. P is the historical average speed. * u These are the corrected trajectory points;

[0120] The corrected non-physical trajectory segments and normal trajectory segments are spliced ​​together to generate a trajectory point set.

[0121] By constructing an Eulerian grid, the system can uniformly map the spatial distribution and temporal variations of trajectory points onto the grid, providing more accurate trajectory analysis. The calculation of time consistency deviation can promptly identify non-physical parts in the trajectory, ensuring that the system only uses valid data that conforms to physical laws, thereby improving the reliability of trajectory prediction and analysis. The time deviation threshold set by statistical analysis can be dynamically adjusted according to different environments and application scenarios, providing high flexibility. By eliminating or correcting non-physical trajectory segments, the system can eliminate erroneous trajectories caused by sensor errors, data loss, or interference, improving the authenticity and reliability of trajectory data, and ultimately enhancing the accuracy of target recognition and tracking. Through a correction algorithm based on historical speed weights, the true motion path of non-physical trajectory segments can be more accurately recovered. The combination of linear search and historical speed averages enables intelligent trajectory correction, automatically adapting to the motion characteristics of different ships. Through correction and splicing, the system can ensure that the generated trajectory point set is uninterrupted and can reasonably reflect the true motion path of the ship. By splicing the corrected trajectory segments, the system can effectively integrate trajectory data from different time periods, thereby providing comprehensive target trajectory information.

[0122] Furthermore, a visual interface is constructed to display the trajectory point set, including:

[0123] Use the visualization tool Matplotlib to build a visualization interface to display the trajectory point set in real time;

[0124] Users who have passed real-name verification are allowed to view it.

[0125] Through a visual interface, users can intuitively view the trajectory point set and its changes, providing a user-friendly interface that improves data readability and ease of use. It allows verified users to access trajectory data, enabling them to not only view ship trajectories in real time but also perform data queries and analysis, providing personalized data display and analysis services for different users.

[0126] Example 2, refer to Figure 2 As a second embodiment of the present invention, a ship trajectory identification system based on VTS radar includes:

[0127] The data collection and processing module is used to collect complex signal data and perform preprocessing.

[0128] The core point update module is used to calculate the phase angle, perform a two-dimensional Fourier transform on the phase angle to extract the dominant direction, calculate the interaction quantity, set a dynamic threshold, mark the core point set with high interaction quantity, trace the trajectory along the dominant direction with each core point as the starting point, set a direction offset threshold to form a trajectory set, calculate the tension vector between adjacent points of each trajectory based on the trajectory set, calculate the local chain energy based on the tension vector between adjacent points, summarize the total chain energy of each trajectory, update the trajectory point position, and obtain the adjusted trajectory point set;

[0129] The correction module is used to construct an Eulerian mesh, calculate the time consistency deviation, set the time deviation threshold, mark non-physical trajectory segments, correct the non-physical trajectory segments, and generate a trajectory point set.

[0130] The display module is used to build a visual interface to display the trajectory point set.

[0131] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for ship trajectory identification based on VTS radar, characterized in that: Includes the following steps: Collect complex signal data and preprocess it, map the normalized complex signal to a rectangular coordinate system, calculate the energy density field of the radar wave, construct the continuity equation, mark the divergence anomaly region, generate a preliminary trajectory point set, extract the complex signal of the preliminary trajectory point set, calculate the phase angle, perform a two-dimensional Fourier transform on the phase angle to extract the dominant direction, calculate the interaction quantity, set a dynamic threshold, and mark the kernel point set with high interaction quantity. Starting from each core point, the trajectory is tracked along the dominant direction. A directional offset threshold is set to form a trajectory set. Based on the trajectory set, the tension vector between adjacent points of each trajectory is calculated. Based on the tension vector between adjacent points, the local chain energy is calculated. The total chain energy of each trajectory is summarized, and the trajectory point positions are updated to obtain the adjusted trajectory point set. Construct an Eulerian mesh, calculate the time consistency deviation, set a time deviation threshold, mark non-physical trajectory segments, correct the non-physical trajectory segments, generate a trajectory point set, and construct a visualization interface to display the trajectory point set.

2. The ship trajectory identification method based on VTS radar as described in claim 1, characterized in that: The process of mapping the normalized complex signal to a Cartesian coordinate system, calculating the energy density field of the radar wave, constructing a continuity equation, and marking divergence anomaly regions includes: The normalized complex signal is mapped to a rectangular coordinate system, and the energy density field of the radar wave is calculated. Based on the normalized complex signal and the energy density field, an energy flow vector field is constructed. Based on the energy density field and energy flow vector field, a continuity equation is constructed, and the continuity equation is solved using the finite difference method. The divergence anomaly region is marked, and a preliminary trajectory point set is generated. Extract the complex signal of the initial trajectory point set, calculate the phase angle, perform phase unwrapping, perform a two-dimensional Fourier transform on the phase angle to extract the dominant direction, calculate the time gradient of the energy density field, and combine the time gradient and the dominant direction to calculate the interaction quantity. Set a dynamic threshold to mark the core point set with high interaction volume.

3. The ship trajectory identification method based on VTS radar as described in claim 2, characterized in that: The process of tracing the trajectory along the dominant direction, starting from each core point, includes: Starting from each core point, trace the trajectory along the dominant direction and calculate the root mean square error of the phase direction offset. A statistical analysis method is used to set a direction offset threshold. The direction offset threshold is compared with the mean square error of the phase direction offset. If the mean square error of the phase direction offset is greater than the direction offset threshold, it is determined to be a separated trajectory; otherwise, it is determined to be a same trajectory. All separated trajectories are summarized to form a trajectory set.

4. The ship trajectory identification method based on VTS radar as described in claim 3, characterized in that: The process of calculating the tension vector between adjacent points of each trajectory, calculating the local chain energy based on the tension vector between adjacent points, summarizing the total chain energy of each trajectory, and updating the trajectory point positions includes: Based on the set of trajectories, calculate the tension vector between adjacent points of each trajectory, calculate the local chain energy based on the tension vector between adjacent points, and summarize the total chain energy of each trajectory; Calculate the partial derivative of the total chain energy with respect to the trajectory points and the adaptive step size, update the trajectory point positions, and use the gradient descent method to set the number of iterations to obtain the adjusted trajectory point set.

5. The ship trajectory identification method based on VTS radar as described in claim 4, characterized in that: The process of correcting non-physical trajectory segments to generate a trajectory point set includes: Based on the adjusted trajectory point set, an Eulerian mesh is constructed, the time consistency deviation is calculated, a time deviation threshold is set using statistical analysis, and trajectories with time consistency deviations greater than the time deviation threshold are selected and marked as non-physical trajectory segments; otherwise, they are marked as normal trajectory segments. Correct non-physical trajectory segments; The corrected non-physical trajectory segments and normal trajectory segments are spliced ​​together to generate a trajectory point set.

6. The ship trajectory identification method based on VTS radar as described in claim 5, characterized in that: The construction of the visualization interface to display the trajectory point set includes: Use the visualization tool Matplotlib to build a visualization interface to display the trajectory point set in real time; Users who have passed real-name verification are allowed to view it.

7. The ship trajectory identification method based on VTS radar as described in claim 6, characterized in that: The collection and preprocessing of complex signal data includes: The VTS radar system captures electromagnetic echo signals within the target sea area, collects complex signal data, and performs noise reduction and normalization processing.

8. A ship trajectory identification system based on VTS radar, used to implement the method described in any one of claims 1 to 7, characterized in that: include: The data collection and processing module is used to collect complex signal data and perform preprocessing. The core point update module is used to calculate the phase angle, perform a two-dimensional Fourier transform on the phase angle to extract the dominant direction, calculate the interaction quantity, set a dynamic threshold, mark the core point set with high interaction quantity, trace the trajectory along the dominant direction with each core point as the starting point, set a direction offset threshold to form a trajectory set, calculate the tension vector between adjacent points of each trajectory based on the trajectory set, calculate the local chain energy based on the tension vector between adjacent points, summarize the total chain energy of each trajectory, update the trajectory point position, and obtain the adjusted trajectory point set; The correction module is used to construct an Eulerian mesh, calculate the time consistency deviation, set the time deviation threshold, mark non-physical trajectory segments, correct the non-physical trajectory segments, and generate a trajectory point set. The display module is used to build a visual interface to display the trajectory point set.

Images