A ship-shore cooperation-based maritime traffic scene reconstruction method
By constructing a three-dimensional nautical chart scene and integrating the location information of ship-shore collaboration, and using the Bayesian weighted average method to correct the ship's position, the problems of delayed and inaccurate maritime traffic scene information are solved, and a low-latency, high-precision display of maritime traffic situation is achieved.
Patent Information
- Application Number
- CN202410920612.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-10
- Publication Date
- 2025-10-17
- Estimated Expiration
- 2044-07-10
AI Technical Summary
In existing technologies, the lag and incompleteness of the AIS system result in delayed and inaccurate information on maritime navigation scenes, and nautical charts are unable to intuitively present maritime scenes. Existing solutions fail to effectively integrate ship and shore-based radar information to provide low-latency, highly reliable traffic status.
A three-dimensional scene is constructed through electronic nautical chart (ENC) data. Combined with information from shipborne GPS/DGPS, ship-side navigation radar, and shore-based ocean radar, the Bayesian weighted averaging method is used to fuse ship position information, correct absolute and relative positions, and form a low-latency, high-precision reconstruction of maritime traffic scenes.
It achieves low-latency, high-precision perception of maritime traffic scenes, provides a more intuitive display of maritime traffic situations, and solves the problems of information lag and inaccuracy in existing technologies.
Smart Images

Figure CN118896605B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of marine traffic scene construction, and particularly relates to a marine traffic scene reconstruction method based on ship-shore cooperation. BACKGROUND
[0002] The presentation of a marine traffic scene of a ship has always been a difficult problem. At present, the marine navigation scene is mainly recognized through an AIS (Automatic Identification System) system of a ship. The marine navigation scene constructed based on a chart and AIS data has been widely applied, such as a domestic "ship information network". However, due to the hysteresis and non-completeness of the AIS system, the marine scene information seen is of high latency and inaccuracy. The chart is only used as a base map, and the scene information of the sea cannot be more directly seen.
[0003] Chinese patent application No. CN201911145717.4 discloses an intelligent ship collision avoidance auxiliary decision-making system based on a shore-based radar, which comprises a transceiving module, a data processing module and a collision avoidance decision-making module. The transceiving module is used for receiving and storing the sensing information of an intelligent ship sensing system in a specified navigation area and the monitoring information of a chain-shaped shore-based radar system on the specified navigation area, and is used for delivering a ship collision avoidance scheme to an executing ship in the specified navigation area. The data processing module is used for analyzing and processing the sensing information and the monitoring information to obtain fusion data. The collision avoidance decision-making module is used for analyzing and processing the fusion data to obtain a ship collision avoidance scheme in the specified navigation area. The obtained information is comprehensive, accurate and stable, and can not only realize local collision avoidance of a ship, but also realize effective collision avoidance of multiple ships in danger of collision in cooperation. The scheme is used for assisting ship collision avoidance through information fusion of a navigation radar and a shore-based radar, and does not involve a specific fusion scheme and the presentation of a marine traffic condition.
[0004] Chinese patent application No. CN201911140774.3 discloses an intelligent ship-shore cooperative target tracking system and method based on shore-based radar, which is applied to the advanced technical field of intelligent ships and realizes accurate tracking of target ships in a specified sea area. The system includes shore-based radars arranged along the coastline, an intelligent ship monitoring system located on the intelligent ship, a data fusion system, a track prediction system, and a track optimization system. The track prediction system analyzes and processes the fusion monitoring data to obtain the predicted sailing trajectory of the target ship. The track optimization system optimizes the predicted sailing trajectory to obtain the optimized predicted trajectory of the target ship, so that the intelligent ship can track the target ship according to the optimized predicted trajectory. The target tracking system and method obtain the accurate trajectory of the target ship with the help of shore-based radars and the intelligent ship monitoring system. This scheme determines the sailing trajectory of the ship through shore-based radars and ship information, and does not involve specific fusion methods or present traffic situations.
[0005] Therefore, there is an urgent need to obtain low-latency and high-reliability maritime traffic scene information through new methods. SUMMARY
[0006] To solve the above technical problems, the present application provides a maritime traffic scene reconstruction method based on ship-shore cooperation.
[0007] To achieve the above purpose, the present application is implemented according to the following technical solutions:
[0008] A maritime traffic scene reconstruction method based on ship-shore cooperation, comprising the following steps:
[0009] S1. Constructing a three-dimensional chart scene through electronic chart ENC data;
[0010] S2. Collecting ship position information, i.e. absolute position, from shipborne GPS / DGPS of sea ships, target tracking information from ship end navigation radars of sea ships, and target tracking information from shore-based marine radars; and determining the relative position of surrounding ships through the target tracking information of ship end navigation radars;
[0011] S3. Correcting the absolute position of each moving ship through the target tracking information of shore-based marine radars;
[0012] S4. Displaying the corrected ship position in the three-dimensional chart scene to complete the scene perception and construction of ship-shore cooperation.
[0013] Further, the step S1 specifically comprises:
[0014] The ENC data of electronic sea chart is obtained by an electronic sea chart engine, including coastlines, isobaths, water depths, beacons, dangers and sea routes, and a three-dimensional digital elevation model is generated by means of coastlines, isobaths and water depth information by using OpenGL; models of beacons, dangers and sea routes in the model library are placed at positions corresponding to the positions marked by the ENC data, so as to generate a three-dimensional sea chart scene.
[0015] Further, in the step S2, the target tracking information of the shore-based marine radar is calculated by the following formula:
[0016]
[0017] In the formula, L is the distance of the target ship, n is the number of pulses, t is the flight time of the pulsed laser, c is the speed of light, and f is the pulse frequency.
[0018] Further, in the step S2, the relative position of the surrounding ship is determined by the target tracking information of the ship-end navigation radar in the following manner:
[0019] The target tracking information of the ship-end navigation radar is converted into coordinates in the coordinate system of the shore-based marine radar by coordinate conversion, and the relative coordinates are converted into absolute coordinates.
[0020] Further, the step S3 specifically includes:
[0021] S31, the target tracking information of the shore-based marine radar and the target tracking information of the ship-end navigation radar converted into absolute coordinates are compared and fused by the Bayesian weighted average method to give the absolute position information of each moving ship at sea after fusion:
[0022]
[0023] In the formula, is the fusion value of the horizontal coordinate or the vertical coordinate of the target absolute position, X0 is the target tracking information of the shore-based marine radar, and the weight is w0; X i is the target tracking information of the i-th ship-end navigation radar, and the weight is w i ;
[0024] The weight is estimated by the Bayesian model average:
[0025]
[0026] In the formula, l(θ i |X) is the log-likelihood function of the i-th sensor, X ij is the j-th measurement value of the i-th sensor, and m is the total number of measurements; and:
[0027]
[0028] S32, if there is no compared information, the target tracking information of the ship end navigation radar or the shore-based marine radar is used as the final absolute position information of the ship.
[0029] Compared with the prior art, the three-dimensional scene is constructed by the electronic chart ENC data, the absolute position of the information collecting ship is determined by the real-time reported position (GPS / DGPS information) of the ship, the relative positions of the surrounding ships are determined by the navigation radar, the target tracking information of the whole sea area is corrected by the information of the shore-based radar, the new target tracking information is formed by the correction of the absolute position of the information collecting ship and the relative positions of the surrounding ships, and all the information is drawn in the three-dimensional scene, so that the marine traffic scene perception and reconstruction are completed; the marine traffic situation of the ship can be effectively solved, and the method has the characteristics of low delay, high precision, more intuitive and the like. BRIEF DESCRIPTION OF DRAWINGS
[0030] Figure 1 It is a flow chart of the marine traffic scene reconstruction method based on ship-shore cooperation.
[0031] Figure 2 It is an information collecting mode.
[0032] Figure 3 It is a scene perception original information schematic diagram.
[0033] Figure 4 It is a scene perception correction information schematic diagram. DETAILED DESCRIPTION
[0034] In order to make the purpose, technical scheme and advantages of the present application clearer and more apparent, the present application will be further described in detail below with reference to the embodiments. The specific embodiments described herein are only used to explain the present application and do not limit the present application.
[0035] As shown in Figure 1 , Figure 2 , the present embodiment exemplarily shows a marine traffic scene reconstruction method based on ship-shore cooperation. Taking n ships as an example, a ship end navigation radar and a GPS / DGPS are arranged on each ship; the ship reporting the position of the ship obtains the relative positions of the surrounding ships and the target tracking information (denoted as TTMn, n is the number of the ship) of the surrounding ships through the ship end navigation radar, all the information is sent to the processor of the shore end through the ship communication system, and the ship communication system can be satellite communication or cellular network communication such as V-SAT, FBB, 4G / 5G. The shore-based marine radar directly obtains the relative positions of the ships in the effective range and the target tracking information (denoted as TTM) of the ships in the effective range through scanning, and transmits the information to the processor of the shore-based marine radar. The transmission mode can be through wired network or wireless network. The marine traffic scene reconstruction method based on ship-shore cooperation is as follows:
[0036] S1, constructing a three-dimensional sea chart scene by electronic sea chart ENC data: obtaining ENC data including coastline, contour line, water depth, beacon (lighthouse and buoy), danger and sea route data by an electronic sea chart engine. A three-dimensional DEM (digital elevation model) is generated by means of coastline, contour line and water depth information by using OpenGL (open graphics library) or other graphics software. Models of beacons, dangers and sea routes in a model library (generated by modeling software such as 3DMAX) are placed at positions corresponding to the positions marked by the ENC data, so as to generate a three-dimensional sea chart scene as a carrier of traffic information;
[0037] S2, collecting ship position information (absolute position) from a shipborne GPS / DGPS of a ship at sea, target tracking information from a ship end navigation radar of the ship at sea and target tracking information from a shore-based marine radar, and determining the relative position of surrounding ships by the target tracking information of the ship end navigation radar: collecting position information and radar target tracking information from the ship at sea by a ship communication system, the position information can be used for positioning of the ship in the three-dimensional sea chart scene, and the radar target tracking information can be used for positioning of surrounding ships; the marine radar obtains target tracking information at sea by the radar time flight principle, the absolute position of the shore-based marine radar is known, and the relative position of a tracked target within the range of action can also be determined by coordinate transformation:
[0038]
[0039] In the formula, L is the distance of the target ship, n is the number of pulses, t is the pulse laser flight time, c is the speed of light, and f is the pulse frequency; the absolute position (on the ground) of the ship at sea is positioned by GPS or DGPS, and the position, speed, heading and other information sent by the DGPS is fully trusted. The information is compared with the reported ship position detected by the marine radar, and the inaccuracy of the marine radar detection is corrected by the comparison deviation value. The target information of the ship end navigation radar is converted into coordinates in the coordinate system of the shore-based marine radar by coordinate conversion, and the relative coordinates are converted into absolute coordinates; the specific scene original information is shown in the accompanying drawings. Figure 3
[0040] S3, correcting the absolute position of each moving ship by the target tracking information of the shore-based marine radar: comparing the target tracking information of the shore-based marine radar and the converted navigation radar information, and fusing the absolute position information of the target at sea by the Bayesian weighted average method:
[0041]
[0042] In the formula, L is the distance of the target ship, n is the number of pulses, t is the pulse laser flight time, c is the speed of light, and f is the pulse frequency; the absolute position (on the ground) of the ship at sea is positioned by GPS or DGPS, and the position, speed, heading and other information sent by the DGPS is fully trusted. The information is compared with the reported ship position detected by the marine radar, and the inaccuracy of the marine radar detection is corrected by the comparison deviation value. The target information of the ship end navigation radar is converted into coordinates in the coordinate system of the shore-based marine radar by coordinate conversion, and the relative coordinates are converted into absolute coordinates; the specific scene original information is shown in the accompanying drawings. X0 is the target tracking information of the shore-based marine radar, and w0 is the weight of the target absolute position horizontal coordinate or vertical coordinate fusion value; X i X0 is the target tracking information of the shore-based marine radar, and w0 is the weight of the target absolute position horizontal coordinate or vertical coordinate fusion value; X i ;
[0043] The weight can be estimated by a Bayesian model average:
[0044]
[0045] Wherein, l (θ i |X) is the log maximum likelihood function of the i th sensor, X ij is the j th measurement value of the i th sensor, and m is the total number of measurements;
[0046]
[0047] The corrected scene information is fused by a Bayesian weighted average method, as shown in the accompanying drawings. Figure 4
[0048] If there is no compared information, the target tracking information of the ship end navigation radar or the shore-based marine radar is used as the final fusion result.
[0049] S4, display the corrected ship position in the three-dimensional sea chart scene, and complete the scene perception and construction of ship-shore cooperation.
[0050] The technical scheme of the present application is not limited to the above specific embodiments, and any technical modification made according to the technical scheme of the present application falls within the protection scope of the present application.
Claims
1. A method for reconstructing maritime traffic scenes based on ship-shore collaboration, characterized in that: The following steps are involved: S1. Construct a 3D chart scene using ENC data; S2. Collecting ship position information (i.e., absolute position) from onboard GPS / DGPS of maritime vessels, target tracking information from onboard navigation radars of maritime vessels, and target tracking information from shore-based oceanographic radars; and determining the relative positions of surrounding vessels using the target tracking information from the onboard navigation radars; S3. Correcting the absolute position of each mobile ship using target tracking information from shore-based oceanographic radar. Step S3 specifically includes: S31. Compare the target tracking information of the shore-based ocean radar and the target tracking information of the ship-side navigation radar after conversion into absolute coordinates, fuse them using the Bayesian weighted averaging method, and provide the absolute position information of each mobile ship at sea after fusion: ; Where, is the horizontal or vertical coordinate fusion value of the target absolute position, is the target tracking information of shore-based ocean radar, and the weight is ; For the The target tracking information of the ship-side navigation radar is weighted as follows: ; The weights are estimated by Bayesian model averaging: ; in, For the The logarithmic maximum likelihood function of the sensor, For the The first sensor The measured value, is the total number of measurements; and: ; S32. If there is no comparison information, the target tracking information of the ship's navigation radar or shore-based oceanographic radar is used as the final absolute position information of the ship; S4. Display the corrected ship position in the three-dimensional nautical chart scene to complete the scene perception and construction of ship-shore collaboration.
2. The method for reconstructing maritime traffic scenes based on ship-shore collaboration according to claim 1 is characterized in that: The step S1 specifically includes: The electronic chart engine obtains electronic chart ENC data, including coastlines, depth contours, water depths, beacons, hazards and sea routes. OpenGL is used to generate a three-dimensional digital elevation model based on the coastline, depth contours and water depth information. The beacon, hazard and sea route models in the model library are placed at the corresponding ENC data marked positions to generate a three-dimensional chart scene.
3. The method for reconstructing maritime traffic scenes based on ship-shore collaboration according to claim 1 is characterized in that: In step S2, the target tracking information of the shore-based ocean radar is calculated by the following formula: ; Where, is the target ship distance, x is the number of pulses, is the pulse laser flight time, is the speed of light, is the pulse frequency.
4. The method for reconstructing maritime traffic scenes based on ship-shore collaboration according to claim 3 is characterized in that: In step S2, the relative positions of the surrounding ships are determined by using the target tracking information of the ship-side navigation radar as follows: Through coordinate conversion, all target tracking information of the ship-side navigation radar is converted into coordinates in the shore-based ocean radar coordinate system, and relative coordinates are converted into absolute coordinates.
Citation Information
Patent Citations
Intelligent ship-shore cooperative target tracking system and method based on shore-based radar
CN111157982A
Intelligent ship collision avoidance auxiliary decision-making system based on shore-based radar and implementation method thereof
CN111176271A
Ship-shore collaborative simulation system for intelligent navigation and safety of ship
CN111913406A
Ship intelligent navigation virtual test scene generation method and system, and storage medium
CN116595049A