SAR (Synthetic Aperture Radar) and AIS (Automatic Identification System) data fused ship trajectory identification method, system and equipment and storage medium

Abstract

The embodiment of the invention provides a ship trajectory recognition method, system and device based on SAR and AI data fusion and a storage medium, and belongs to the technical field of data processing. The method comprises the following steps: acquiring satellite image data of a target area shot by a spaceborne synthetic aperture radar and trajectory data of ships passing through the target area from an automatic ship identification system, and performing ship target identification on the satellite image data to obtain a first target positioning point set; performing interpolation processing on each piece of ship trajectory data at a target moment to obtain a second target positioning point set, and then performing spatial density clustering based on distortion characteristics on the first target positioning point set to obtain a plurality of clustering areas, and matching the positioning points in the clustering region in the first target positioning point set and the second target positioning point set. According to the invention, the accuracy of marine ship trajectory identification can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, system, device and storage medium for ship trajectory identification by fusing SAR and AIS data. Background Art

[0002] Remote sensing equipment is widely used in marine target monitoring due to its stable data acquisition capabilities. Spaceborne SAR (Synthetic Aperture Radar) can periodically monitor ships over a large area, unaffected by weather. However, data collection frequency is low, often requiring hours or even days to collect position information for the same vessel. Automatic Identification System (AIS) equipment can acquire ship position data at a frequency of minutes, but relies on receiving active signals from the vessel. Therefore, for marine targets such as dynamic, invisible targets and fishing vessels not equipped with or activated AIS, SAR data can be actively collected from remote sensing systems and AIS data can be passively received. This active-passive collaborative sensing technology, combining SAR and AIS data for accurate and comprehensive perception and identification of vessel tracks, enables accurate and comprehensive perception and identification of vessel tracks. However, in addition to differences in data modalities, the revisit period of SAR satellites differs significantly from the reception time of AIS data. Furthermore, due to non-uniform geometric distortion in SAR images and AIS positioning errors, there are temporal and spatial differences between vessel targets in SAR images and those in AIS, leading to discrepancies in the identification of marine vessel tracks. Summary of the Invention

[0003] The main purpose of the embodiments of the present application is to propose a ship trajectory identification method, system, device and storage medium that fuses SAR and AIS data, aiming to improve the accuracy of maritime ship trajectory identification.

[0004] To achieve the above objectives, one aspect of an embodiment of the present application provides a method for identifying ship tracks by fusing SAR and AIS data, comprising the following steps:

[0005] Obtaining satellite image data of a target area captured by a spaceborne synthetic aperture radar, and obtaining trajectory data of each ship passing through the target area from an automatic ship identification system;

[0006] Performing ship target recognition on the satellite image data to obtain a first target positioning point set;

[0007] performing interpolation processing on the target time of each of the ship trajectory data to obtain a second target positioning point set, wherein the target time is the shooting time of the satellite image data;

[0008] Performing spatial density clustering on the first target positioning point set based on distortion characteristics to obtain a plurality of clustering regions;

[0009] Matching the first target positioning point set and the second target positioning point set that are located in the cluster area to obtain a fused target trajectory.

[0010] In some embodiments, before the step of performing spatial density clustering on the first target positioning point set based on distortion errors to obtain a plurality of clustering areas, the ship trajectory identification method using SAR and AIS data fusion further includes the following steps:

[0011] Constructing an objective function based on the Euclidean distance between the first target positioning point set and the second target positioning point set;

[0012] A rotation transformation matrix is ​​solved according to the objective function, and the positioning points in the second target positioning point set are transformed to coarse matching positions according to the rotation transformation matrix to update the second target positioning point set.

[0013] In some embodiments, performing ship target recognition on the satellite image data to obtain a first target positioning point set includes the following steps:

[0014] Inputting the satellite image data into a trained object detection model to obtain a ship detection result, wherein the ship detection result includes bounding box information for marking the ship;

[0015] Determining ship feature points of each target according to the ship detection result and the target area, wherein the ship feature points include first ship coordinates and ship size identification parameters;

[0016] The first target positioning point set is determined according to the ship characteristic points of each target.

[0017] In some embodiments, performing interpolation processing on each of the ship trajectory data at the target time to obtain a second target positioning point set includes the following steps:

[0018] determining a target time period including the target time according to the target time;

[0019] Extracting the ship trajectory data according to the target time period to obtain target trajectory data;

[0020] Determining a normalized time according to time nodes of the target trajectory data located before and after the target time, and interpolating the normalized time using the constructed polynomial to obtain a second ship coordinate at the target time;

[0021] A second target positioning point set is formed based on the second ship coordinates at the target time and the ship reported size parameters obtained from the respective ship trajectory data.

[0022] In some embodiments, the objective function is expressed as:

[0023]

[0024] Among them, A i represents the first target positioning point set, B i Represents the second target positioning point set, R represents the rotation transformation matrix, and t represents the translation vector.

[0025] In some embodiments, performing spatial density clustering on the first target positioning point set based on distortion characteristics to obtain multiple clustering areas includes the following steps:

[0026] Determining a range distortion error of each target in the first target positioning point set according to state parameters of the satellite image data captured by the spaceborne synthetic aperture radar;

[0027] With the goal of minimizing the average sum of the distortion errors under the clustering clusters, the K-means algorithm is used to cluster the distance distortion errors of each target to obtain the clustering results;

[0028] A clustering area is determined according to the first ship coordinates of the target included in each cluster in the clustering result.

[0029] In some embodiments, matching the first target positioning point set and the second target positioning point set in the cluster area to obtain a fused target trajectory includes the following steps:

[0030] Extracting positioning points located in the cluster area from the first target positioning point set and the second target positioning point set respectively, to obtain a first target positioning point subset and a second target positioning point subset respectively;

[0031] Fine matching of positioning points is performed based on the Euclidean distance between the first target positioning point subset and the second target positioning point subset to obtain a fused target trajectory.

[0032] To achieve the above objectives, another aspect of the present application provides a ship track identification system that integrates SAR and AIS data, including:

[0033] The first module is used to obtain satellite image data of the target area taken by a space-borne synthetic aperture radar, and obtain trajectory data of each ship passing through the target area from the automatic identification system of the ship;

[0034] The second module is used to perform ship target recognition on the satellite image data to obtain a first target positioning point set;

[0035] A third module is configured to perform interpolation processing on each of the ship trajectory data at a target time to obtain a second target positioning point set, wherein the target time is the shooting time of the satellite image data;

[0036] A fourth module is configured to perform spatial density clustering on the first target positioning point set based on distortion characteristics to obtain multiple clustering areas;

[0037] The fifth module is configured to match the first target positioning point set and the second target positioning point set that are located in the cluster area to obtain a fused target trajectory.

[0038] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes an electronic device, which includes a memory, a processor, a program stored on the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the method described in the above embodiment is implemented.

[0039] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method described in the above embodiment.

[0040] The ship trajectory identification method, system, device and storage medium for SAR and AIS data fusion proposed in the present application obtain satellite image data of a target area captured by a spaceborne synthetic aperture radar and trajectory data of each ship passing through the target area from an automatic ship identification system, perform ship target identification on the satellite image data to obtain a first target positioning point set, and perform target time interpolation processing on each ship trajectory data to obtain a second target positioning point set, where the target time is the shooting time of the satellite image data. The first target positioning point set is then subjected to spatial density clustering based on distortion characteristics to obtain multiple clustering areas. The positioning points located in the clustering areas of the first target positioning point set and the second target positioning point set are then matched. This method can reduce positioning errors caused by geometric distortion in SAR images and systematic errors in AIS positioning, achieve accurate matching and fusion of positioning data from the two data sources, and improve the accuracy of maritime ship trajectory identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flow chart of a method for identifying ship tracks by fusing SAR and AIS data provided in an embodiment of the present application;

[0042] Figure 2 This is a schematic diagram of the rough matching process of positioning points provided in an embodiment of the present application;

[0043] Figure 3 is a schematic diagram of the target incident angle provided in an embodiment of the present application;

[0044] Figure 4 This is a schematic diagram of the positioning point fine matching process provided by the embodiment of the present application;

[0045] Figure 5 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0047] It should be noted that although the system is divided into functional modules and the flowcharts illustrate a logical sequence, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowcharts. The terms "first," "second," and so on in the specification, claims, and drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0049] First, let’s analyze some of the terms used in this application:

[0050] Spaceborne SAR (Synthetic Aperture Radar) is an active microwave remote sensing system carried on a satellite platform. It generates high-resolution two-dimensional or three-dimensional images by transmitting microwave pulses and receiving echo signals reflected from the Earth's surface, using synthetic aperture technology. Spaceborne SAR, leveraging the characteristics of satellite orbits, offers continuous global scanning capabilities, and its data acquisition periodicity and stability surpass those of airborne systems.

[0051] AIS (Automatic Identification System) is a digital aid to navigation system standardized by the International Maritime Organization (IMO) and other organizations. Based on VHF communications, satellite positioning, and computer technology, it enables the automatic exchange and real-time monitoring of navigation data between ships and between ships and shores. The system's onboard terminal integrates GPS, a VHF transceiver, and a data processing unit to collect and report dynamic and static vessel information.

[0052] K-means clustering algorithm is an unsupervised learning partitioning clustering method that divides the data set into K mutually exclusive clusters through iterative optimization, so that the samples in the same cluster have high similarity and the differences between different clusters are significant.

[0053] The embodiments of the present application provide a ship track identification method, system, device and storage medium by fusing SAR and AIS data, aiming to improve the accuracy of ship track identification at sea.

[0054] The ship trajectory identification method, system, device and storage medium for SAR and AIS data fusion provided in the embodiments of the present application are specifically illustrated by the following embodiments. First, the ship trajectory identification method for SAR and AIS data fusion in the embodiments of the present application is described.

[0055] The ship trajectory identification method based on the fusion of SAR and AIS data provided in the embodiment of the present application relates to the field of data processing technology. The ship trajectory identification method based on the fusion of SAR and AIS data provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the ship trajectory identification method based on the fusion of SAR and AIS data, etc., but is not limited to the above forms.

[0056] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0057] Figure 1 This is an optional flowchart of the ship trajectory identification method based on SAR and AIS data fusion provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S105.

[0058] Step S101, obtaining satellite image data of a target area captured by a spaceborne synthetic aperture radar, and obtaining trajectory data of each ship passing through the target area from an automatic ship identification system;

[0059] Step S102, performing ship target recognition on the satellite image data to obtain a first target positioning point set;

[0060] Step S103, performing interpolation processing on the target time of each ship trajectory data to obtain a second target positioning point set, wherein the target time is the shooting time of the satellite image data;

[0061] Step S104: performing spatial density clustering on the first target positioning point set based on distortion characteristics to obtain multiple clustering areas;

[0062] Step S105 : Match the first target positioning point set and the second target positioning point set that are located in the cluster area to obtain a fused target trajectory.

[0063] In step S101 of some embodiments, SAR image data (i.e., satellite image data) of the target area to be identified and within the time period is obtained. The satellite image data carries the shooting time. AIS data is obtained, and AIS track data (ship track data) of each ship passing through the target area and within the corresponding time period is extracted from the AIS data.

[0064] In step S102 of some embodiments, the SAR image data is preprocessed and noise filtered, and then a ship detection result is obtained for each ship target based on a target detection algorithm. The ship detection result can be a detection frame that represents the pixel position, length, width, and rotation angle of the ship center point. Furthermore, the relative vertical and horizontal distances from the center point of each detection frame to the upper left corner can be calculated based on the geographic coordinates of the upper left corner of the SAR image data. Based on the image resolution, the geographic coordinates of the center point of the detection frame are calculated based on the above relative vertical and horizontal distances, and combined with the product of the length and width of the detection frame to generate a three-dimensional SAR target point set (i.e., a first target positioning point set). The first target positioning point set includes the positioning points of several ship targets located in the target area at the time of capture (i.e., the geographic coordinates corresponding to the center points of the detection frames). The first target positioning point set may also include ship size identification parameters for several ship targets.

[0065] In step S103 of some embodiments, each ship trajectory data is interpolated at the target time to obtain a second target positioning point set, where the target time is the shooting time of the satellite image data, and the second target positioning point set includes the interpolated trajectory points of the AIS trajectory data of each ship located in the target area at the target time. The embodiment of the present application does not impose any specific restrictions on the interpolation algorithm of the trajectory points. For example, the AIS trajectory data (i.e., ship trajectory data) is decoded and cleaned, and then the AIS trajectory is divided into several intervals according to the trajectory points. A multiple polynomial interpolation function is constructed in each interval, the boundary conditions of the interpolation function are determined, and the coefficients of the polynomial to be determined are calculated and solved. The interpolation interval where the target moment is located is determined, and the trajectory interpolation is calculated based on the normalized time according to the AIS positioning of the previous moment, and the positioning coordinates of the trajectory at the target moment are obtained. The coordinates are converted into geographic coordinates, and the product of the length and width of the ship is combined as a feature to generate an AIS target point set (i.e., the second target positioning point set).

[0066] In some embodiments, steps S104 and S105 process targets within different clusters separately based on the imaging distortion characteristics of the SAR image data. For positioning points from two different sets within different clusters, a specific AIS target matching object is determined for each SAR ship target based on an iterative registration transformation rule based on the Euclidean distance between the two point sets, and the target is fused. This implementation can reduce positioning errors caused by geometric distortion in SAR images and systematic errors in AIS positioning, achieving accurate matching and fusion of positioning data from the two data sources, thereby improving the accuracy of maritime vessel trajectory identification.

[0067] According to some embodiments of the present application, step S102 may include but is not limited to the following steps:

[0068] Step S210: inputting the satellite image data into the trained object detection model to obtain a ship detection result, wherein the ship detection result includes bounding box information for marking the ship;

[0069] Step S220, determining ship feature points of each target based on the ship detection results and the target area, where the ship feature points include first ship coordinates and ship size identification parameters;

[0070] Step S230: determining a first target positioning point set according to the ship feature points of each target.

[0071] In this embodiment, the target detection model can adopt the convolutional neural network structure of the YOLO series, and the target detection model is trained by samples of satellite image data to obtain a trained target detection model. In the process of target detection on SAR image data, the convolutional neural network of the target detection model is used to extract the pixel features of the ship target in the SAR image data, and the ship features are input into the prediction network of the target detection model to obtain the ship detection results. The ship detection results include the bounding box information and classification information of each ship target. Calculate the geometric center of the bounding box, which can be regarded as the ship coordinates, and record the length and width product of the bounding box at the same time. The length and width product of the bounding box is regarded as the ship size identification parameter. Convert the geometric center of the bounding box of all ship targets in the image into geographic coordinates, and based on the detection box height h and width w, record the single ship feature point as (x, y, h×w). The ship feature points of each target form the first target positioning point set.

[0072] According to some embodiments of the present application, step S103 may include but is not limited to the following steps:

[0073] Step S310, determining a target time period including the target time according to the target time;

[0074] Step S320, extracting the ship trajectory data according to the target time period to obtain target trajectory data;

[0075] Step S330, determining a normalized time based on the time nodes of the target trajectory data located before and after the target time, and interpolating the normalized time using the constructed polynomial to obtain the second ship coordinates at the target time;

[0076] Step S340: forming a second target positioning point set based on the second ship coordinates at the target time obtained from the trajectory data of each ship and the size parameters reported by the ship.

[0077] In this embodiment, the AIS latitude and longitude positioning coordinates (X lat ,X lon) is converted into geographic coordinates (X, Y) to unify the representation of the first target positioning point set and the second target positioning point set. The target time period before and after time t is determined based on the shooting time t of the SAR image data. For ships in the target area, n+1 AIS track nodes in their AIS track data are intercepted based on the target time period, that is, the track of each ship M = {(x0, y0), (x1, y1), (x2, y2)... (x n ,y n )}. For every two adjacent data points (x i ,y i ) and (x i+1 ,y i+1 ), construct a cubic polynomial as follows:

[0078] S i (x) = a1 + a2 (x i )+a3(xx i ) 2 +a4(xx i ) 3 ;

[0079] Among them, a1, a2, a3, and a4 are unknown coefficients.

[0080] Let S i (x i )=y i , S i (x i+1 )=y i+1 , S”0(x0)=S” n-1 (x n )=0, solve the system of equations to determine the unknown coefficients.

[0081] For each ship's track M, the AIS normalized time is determined based on the two track time nodes before and after the shooting time t. The AIS interpolation point coordinates of the normalized time are calculated based on the cubic polynomial with the unknown coefficients. The AIS interpolation point coordinates of the normalized time are considered to be the AIS interpolation point coordinates of the target time (i.e., the second ship coordinates). At the same time, combined with the length L and width W reported by the ship, the single ship feature point is recorded as (X, Y, L×W). The second target positioning point set is formed based on the ship feature points of all ships in the target area.

[0082] According to some embodiments of the present application, before step S104, the ship trajectory identification method using SAR and AIS data fusion in the embodiment of the present application may further include, but is not limited to, the following steps:

[0083] Step S410, constructing an objective function based on the Euclidean distance between the first target positioning point set and the second target positioning point set;

[0084] Step S420 , solving a rotation transformation matrix according to the objective function, and transforming the positioning points in the second target positioning point set to coarse matching positions according to the rotation transformation matrix, so as to update the second target positioning point set.

[0085] In this embodiment, after obtaining a first target positioning point set by processing SAR image data and obtaining a second target positioning point set by processing AIS track data of each ship in the target area, the positioning points in the first target positioning point set and the second target positioning point set can be roughly matched based on the entire range of the target area.

[0086] For details, please refer to Figure 2 Schematic diagram of the coarse matching process, where circles represent the positioning points of the second target positioning point set, and triangles represent the positioning points of the first target positioning point set.

[0087] Set the first target positioning point set as A, the second target positioning point set as B, and define the objective function based on the Euclidean distance as follows:

[0088]

[0089] Where R represents the rotation transformation matrix and e represents the translation vector.

[0090] Normalize the two point sets to solve R, solve e based on the obtained R, update the AIS ship positioning point position B'=RB+t, iterate the AAIS ship positioning points until the D value or its change degree is less than a certain threshold, thereby obtaining a new second target positioning point set.

[0091] By establishing a rotation transformation matrix based on the Euclidean distance between the two point sets, the positioning points in the second target positioning point set are transformed to a coarse matching position, narrowing the gap between the AIS positioning points and the SAR positioning points, allowing the AIS positioning points to be subsequently divided into corresponding cluster areas. The image area is then divided according to the clustering conditions, and the rotation matrix and translation vector of the secondary transformation are iteratively calculated in different areas. The AIS target point set and the SAR target point set are registered one by one based on the transformation method obtained from the two calculations. The different features of the two target data are combined to complete the fusion.

[0092] According to some embodiments of the present application, step S104 may include but is not limited to the following steps:

[0093] Step S510, determining the range distortion error of each target in the first target positioning point set according to the state parameters of the satellite image data captured by the spaceborne synthetic aperture radar;

[0094] Step S520: clustering the distance distortion errors of each target using the K-means algorithm with the goal of minimizing the average sum of the distortion errors under the clusters to obtain a clustering result;

[0095] Step S530: determining a clustering area according to the first ship coordinates of the target included in each cluster in the clustering result.

[0096] In this embodiment, the azimuth and range directions of SAR image data are acquired, and the SAR image data is extended in the range direction; the distortion error of each SAR target is calculated based on the state acquisition number such as satellite altitude and incident angle; the SAR targets are clustered using the K-means clustering algorithm, traversing the parameter K; the average sum of the distortion errors of all clusters under different parameters is calculated, and the number of cluster centers with the minimum average sum is found; and the SAR image data is divided into different cluster areas based on the coordinates of the cluster centers under the clustering result.

[0097] For details, please refer to Figure 3 The state parameters of satellite image data captured by spaceborne synthetic aperture radar include the satellite incident angle θ0, altitude h, and slant range R. The horizontal coordinate of each target (i.e., positioning point) in the first target positioning point set is x, and the pixel length of the image in the range direction is L. Then, the range incident angle of each target is:

[0098]

[0099] The range distortion error of a single target is:

[0100] Δd=RcosΔθ;

[0101] Use the K-means clustering algorithm to cluster the targets, traverse the parameter K, that is, the number of cluster centers, and calculate the average sum of distortion errors under each clustering result as follows:

[0102]

[0103] Find the K that minimizes the average sum of the distortion errors of all clusters in the clustering result, divide the targets of the first target positioning point set according to the clustering result with the minimum error, and obtain multiple first target positioning point subsets and corresponding clustering areas.

[0104] According to some embodiments of the present application, step S105 may include but is not limited to the following steps:

[0105] Step S610, extracting the positioning points located in the cluster area from the first target positioning point set and the second target positioning point set, respectively, to obtain a first target positioning point subset and a second target positioning point subset;

[0106] Step S620 , performing fine matching of positioning points based on the Euclidean distance between the first target positioning point subset and the second target positioning point subset to obtain a fused target trajectory.

[0107] In this embodiment, the positioning points located in the cluster area are extracted from the first target positioning point set and the second target positioning point set, respectively, to obtain the first target positioning point subset and the second target positioning point subset. Figure 4 For the positioning points in each cluster area, the positioning points are re-finely matched based on the Euclidean distance between the first target positioning point subset and the second target positioning point subset to fuse the SAR target and the AIS target to obtain a fused target trajectory. For details, please refer to the matching process of step S420 above, which will not be repeated here.

[0108] According to some embodiments of the present application, the method of the embodiment of the present application obtains the image features of ship targets in SAR image data through a target detection model in SAR data and AIS data of the same area and time period, further identifies the positioning information and size information of each ship target in the SAR image data, and generates a SAR target set. The target positioning information of each ship at the time of SAR image shooting is obtained by trajectory interpolation, and an AIS target set is generated. A clustering algorithm is used for the targets in the SAR image data, and the degree of distortion generated by the targets in different areas is determined according to the spatial density of the targets, and the targets are divided according to the distortion error. For targets with a certain type of distortion characteristics, the transformation matrix is ​​iteratively calculated based on the Euclidean distance of the target points between different data to unify the SAR image targets and the AIS trajectory targets into point coordinates on a two-dimensional plane at the same time, thereby solving the problem of different time and modalities between the two types of data. At the same time, adding the ship size as a matching feature enhances the characteristic correlation between the same targets, thereby improving the problem of difficulty in matching and fusing targets from the two types of data.

[0109] Among them, the distortion degree clustering can be performed by traversing to obtain the optimal number of cluster centers that minimizes the sum of the distortion errors, that is, the K-means algorithm parameter K. By obtaining the altitude and incident angle of the SAR satellite when shooting, the distortion error of the ship target at different positions can be calculated, which is usually related to the satellite distance. Each cluster target is regarded as a two-dimensional Gaussian distribution, and the variance is calculated. The error sum is the sum of the variances of all cluster distributions. The SAR target data is divided according to the position distortion characteristics, which reduces the positioning error caused by geometric distortion in the SAR image and the systematic error of AIS positioning, solves the problem that the spatial position of the same target at the same time in different data may be different, and further improves the problem of difficult target fusion from the two data sources.

[0110] The present application also proposes a ship track identification system that integrates SAR and AIS data, including:

[0111] The first module is used to obtain satellite image data of the target area taken by a space-borne synthetic aperture radar, and obtain trajectory data of each ship passing through the target area from the automatic identification system of the ship;

[0112] The second module is used to perform ship target recognition on the satellite image data to obtain a first target positioning point set;

[0113] The third module is used to perform interpolation processing on the target time of each ship trajectory data to obtain a second target positioning point set, wherein the target time is the shooting time of the satellite image data;

[0114] The fourth module is used to perform spatial density clustering on the first target positioning point set based on the distortion characteristics to obtain multiple clustering areas;

[0115] The fifth module is used to match the positioning points in the first target positioning point set and the second target positioning point set located in the cluster area to obtain a fused target trajectory.

[0116] It can be understood that the contents of the above-mentioned embodiments of the ship trajectory identification method for fusing SAR and AIS data are applicable to the embodiments of this system. The functions specifically implemented by this system embodiment are the same as those in the above-mentioned embodiments of the ship trajectory identification method for fusing SAR and AIS data, and the beneficial effects achieved are also the same as those achieved by the above-mentioned embodiments of the ship trajectory identification method for fusing SAR and AIS data.

[0117] The present application also provides an electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for enabling communication between the processor and the memory. When the program is executed by the processor, the aforementioned method for ship trajectory identification using SAR and AIS data fusion is implemented. The electronic device can be any intelligent terminal, including a tablet computer and a shipboard computer.

[0118] See also Figure 5 , Figure 5 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0119] The processor 901 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0120] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program codes are stored in the memory 902 and are called by the processor 901 to execute the ship trajectory identification method for SAR and AIS data fusion according to the embodiments of this application.

[0121] Input / output interface 903, used to implement information input and output;

[0122] Communication interface 904, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0123] Bus 905 , which transmits information between various components of the device (e.g., processor 901 , memory 902 , input / output interface 903 , and communication interface 904 );

[0124] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0125] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned ship trajectory identification method of SAR and AIS data fusion.

[0126] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0127] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0128] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0129] The system embodiment described above is merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0130] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0131] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0132] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0133] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the above units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0134] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0136] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0137] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A ship trajectory identification method based on SAR and AIS data fusion, characterized in that: The following steps are involved: Obtaining satellite image data of a target area captured by a spaceborne synthetic aperture radar, and obtaining trajectory data of each ship passing through the target area from an automatic ship identification system; Performing ship target recognition on the satellite image data to obtain a first target positioning point set; performing interpolation processing on the target time of each of the ship trajectory data to obtain a second target positioning point set, wherein the target time is the shooting time of the satellite image data; Performing spatial density clustering on the first target positioning point set based on distortion characteristics to obtain a plurality of clustering regions; Matching the first target positioning point set and the second target positioning point set that are located in the cluster area to obtain a fused target trajectory.

2. The ship trajectory identification method based on SAR and AIS data fusion according to claim 1, characterized in that: Before the step of performing spatial density clustering on the first target positioning point set based on distortion errors to obtain a plurality of clustering areas, the ship trajectory identification method using SAR and AIS data fusion further includes the following steps: Constructing an objective function based on the Euclidean distance between the first target positioning point set and the second target positioning point set; A rotation transformation matrix is ​​solved according to the objective function, and the positioning points in the second target positioning point set are transformed to coarse matching positions according to the rotation transformation matrix to update the second target positioning point set.

3. The ship trajectory identification method based on SAR and AIS data fusion according to claim 1, characterized in that: The performing ship target recognition on the satellite image data to obtain a first target positioning point set includes the following steps: Inputting the satellite image data into a trained object detection model to obtain a ship detection result, wherein the ship detection result includes bounding box information for marking the ship; Determining ship feature points of each target according to the ship detection result and the target area, wherein the ship feature points include first ship coordinates and ship size identification parameters; The first target positioning point set is determined according to the ship characteristic points of each target.

4. The ship trajectory identification method based on SAR and AIS data fusion according to claim 1, characterized in that: The interpolation processing of the target time of each of the ship trajectory data is performed to obtain a second target positioning point set, comprising the following steps: determining a target time period including the target time according to the target time; Extracting the ship trajectory data according to the target time period to obtain target trajectory data; Determining a normalized time according to time nodes of the target trajectory data located before and after the target time, and interpolating the normalized time using the constructed polynomial to obtain a second ship coordinate at the target time; A second target positioning point set is formed based on the second ship coordinates at the target time and the ship reported size parameters obtained from the respective ship trajectory data.

5. The ship trajectory identification method based on SAR and AIS data fusion according to claim 2, characterized in that: The objective function is expressed as: Among them, A i represents the first target positioning point set, B i Represents the second target positioning point set, R represents the rotation transformation matrix, and t represents the translation vector.

6. The ship trajectory identification method based on SAR and AIS data fusion according to claim 5, characterized in that: The performing spatial density clustering on the first target positioning point set based on distortion characteristics to obtain a plurality of clustering areas comprises the following steps: Determining a range distortion error of each target in the first target positioning point set according to state parameters of the satellite image data captured by the spaceborne synthetic aperture radar; With the goal of minimizing the average sum of the distortion errors under the clustering clusters, the K-means algorithm is used to cluster the distance distortion errors of each target to obtain the clustering results; A clustering area is determined according to the first ship coordinates of the target included in each cluster in the clustering result.

7. The ship trajectory identification method based on SAR and AIS data fusion according to claim 6, characterized in that: The matching of the first target positioning point set and the positioning points in the second target positioning point set located in the cluster area to obtain a fused target trajectory includes the following steps: Extracting positioning points located in the cluster area from the first target positioning point set and the second target positioning point set respectively, to obtain a first target positioning point subset and a second target positioning point subset respectively; Fine matching of positioning points is performed based on the Euclidean distance between the first target positioning point subset and the second target positioning point subset to obtain a fused target trajectory.

8. A ship track identification system based on SAR and AIS data fusion, characterized in that: include: The first module is used to obtain satellite image data of the target area taken by a space-borne synthetic aperture radar, and obtain trajectory data of each ship passing through the target area from the automatic identification system of the ship; The second module is used to perform ship target recognition on the satellite image data to obtain a first target positioning point set; A third module is configured to perform interpolation processing on each of the ship trajectory data at a target time to obtain a second target positioning point set, wherein the target time is the shooting time of the satellite image data; A fourth module is configured to perform spatial density clustering on the first target positioning point set based on distortion characteristics to obtain multiple clustering areas; The fifth module is configured to match the first target positioning point set and the second target positioning point set that are located in the cluster area to obtain a fused target trajectory.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for implementing connection and communication between the processor and the memory. When the program is executed by the processor, the steps of the method described in any one of claims 1 to 7 are implemented.

10. A storage medium, which is a computer-readable storage medium and is used for computer-readable storage, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any one of claims 1 to 7.

Images