CN105390029B - Ship collision prevention aid decision-making method and system based on Track Fusion and Trajectory Prediction - Google Patents
Ship collision prevention aid decision-making method and system based on Track Fusion and Trajectory Prediction Download PDFInfo
- Publication number
- CN105390029B CN105390029B CN201510755138.7A CN201510755138A CN105390029B CN 105390029 B CN105390029 B CN 105390029B CN 201510755138 A CN201510755138 A CN 201510755138A CN 105390029 B CN105390029 B CN 105390029B
- Authority
- CN
- China
- Prior art keywords
- ship
- information
- track
- collision
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses a kind of ship collision prevention aid decision-making method and system based on Track Fusion and Trajectory Prediction, method includes the following steps: the ship information of S1, acquisition ship automatic identification system and radar transmissions, and it is pre-processed to obtain position, speed and the azimuth information of ship；S2, the position to ship, speed and azimuth information carry out track association and Track Fusion；S3, Trajectory Prediction is carried out to object ship according to the result of Track Fusion, and makes ship collision Risk Assessments, evacuation decision and the monitoring of object ship situation.The present invention can be improved the reliability and stability of ship's navigation data source, it real-time, intelligence can monitor security information when ship's navigation, it avoids ship from colliding, and facilitates the intelligence and miniaturization of ship-borne equipment, there is good practical application value.
Description
Technical field
The present invention relates to ship collision prevention technical fields more particularly to a kind of ship based on Track Fusion and Trajectory Prediction to keep away
Touch aid decision-making method and system.
Background technique
Ship collision is always major accident type in navigation safety, and 80% or more collision accident is by people
It is caused directly or indirectly for factor.Currently, mostly Collision Avoidance of Ships be by operator's empirically subjective decision,
The accuracy and normalization of operation cannot be guaranteed.As it can be seen that in order to reduce the generation of Collision Accidents of Ships, emphasis is to reduce operation
The nonstandard or invalid measures to keep clear of personnel.Therefore, there is an urgent need to it is a kind of can allow marine navigator in real time, pellucidly
Understand the navigation environment of ship, and the ship collision prevention system of anti-collision warning and avoidingcollis ionscheme can be provided for it, it is artificial for reducing
Collision accident caused by factor.But show following several there are also many deficiencies in existing ship collision prevention systematic research achievement
A aspect:
1, commonly using boat-carrying navigational aid has marine radar and ship automatic identification system (AIS), can obtain target information,
But the two respectively has advantage and disadvantage, so being difficult to ensure the accuracy of information and comprehensive using triangular web.
2, AIS equipment is likely to occur information and sends failure in actual operation, and radar may have blind area, this can all cause
Up-to-date information can not be timely received on this ship.On the other hand, Yao Shixian ship collision prevention warning function, not only will be to currently making
Risk-Degree of Collision analysis, also wants that analysis can be made between positional relationship new subsequent time ship, this could be in advance to dangerous feelings
Condition makes measures to keep clear.
3, at present in ship collision prevention analysis and this technical field of aid decision there are no accurate quantitative model, do not have
The positional relationship of detection target and this ship can be comprehensively considered, and analyze current risk of collision, the system of early warning scheme is provided.
4, current embedding assembly and computer, which calculate, rapidly develops, and ship collision prevention field can combine these skills not yet
The system of intelligence, the automation of art.
Summary of the invention
The technical problem to be solved in the present invention is that it is poor for single boat-carrying navigational aid reliability in the prior art, and
And the defect of ship collision early warning cannot be automatically provided, provide one kind can automate, Intelligent Calculation ship navigation state
The ship collision prevention aid decision-making method and system based on Track Fusion and Trajectory Prediction.
The technical solution adopted by the present invention to solve the technical problems is:
The present invention provides a kind of ship collision prevention aid decision-making method based on Track Fusion and Trajectory Prediction, including following step
It is rapid:
S1, the ship information for obtaining ship automatic identification system and radar transmissions, and it is pre-processed to obtain ship
Position, speed and azimuth information；
S2, the position to ship, speed and azimuth information carry out track association and Track Fusion, specific steps are as follows:
S21, the position to ship, speed and azimuth information carry out coordinate conversion and temporal registration, and longitude and latitude form is believed
Breath is converted to polar form information, using piecewise linear interpolation method by nonsynchronous information unification to synchronization；
S22, to treated, position, speed and azimuth information carry out track association, with object ship ship automatic identification system
On the basis of track information of uniting, time, range difference are first excluded compared with ship automatic identification system information away from biggish radar track
Information；The correlation degree for passing through Ship ' automatic recognition system track information and radar track information again, until more options one
This ship automatic identification system track information and radar information are chosen to be object ship by the biggish radar track information of correlation degree
The object of Track Fusion；
S23, the ship automatic identification system and radar track information of the selected biggish object ship of correlation degree are carried out
Track Fusion using being completed the Track Fusion process of object ship based on the Weighted estimation method of statistics, and is stored fusion results and is
Trajectory Prediction provides data；
S3, Trajectory Prediction is carried out to object ship according to the result of Track Fusion, and makes ship collision Risk Assessments, evacuation
Decision and the monitoring of object ship situation.
Pretreated method is carried out to ship information in step S1 specifically:
It is parsed respectively according to ship automatic identification system and radar message format, and extracts effective information storage to number
According in library.
The calculating of the ship automatic identification system track information of object ship and radar track information association degree in step S2
Method specifically:
The Euclidean distance of distance, orientation, the speed of a ship or plane, course this 4 factors is obtained by the subordinating degree function of normal distribution
Association and it is not associated with degree of membership value, then is weighted and averaged with each factor weight size and composite factor can be obtained is associated with and is not associated with
Degree of membership；
It finally carries out double threshold to be carefully associated with, that is, judges that composite factor association degree of membership maximum value is with thin degree of incidence is met
The no threshold value for meeting setting stops association judgement if all meeting, and stores and binds the ship for determining thin associated object ship
Automatic recognition system and radar label, the object as the biggish object ship Track Fusion of correlation degree.
The method of ship collision Risk Assessments in step S3 specifically:
Time, two ships distance, object ship and this bearing angle, this ship can be met by comprehensively considering least meeting distance, minimum
It is used as factor of evaluation than this 5 with the speed of object ship, obtains corresponding weighted value after respective degree of membership and weight to be integrated
Factor Risk-Degree of Collision.
The method of decision is avoided in step S3 specifically:
First determine Anti-collision Actions opportunity, using risk of collision topology degree method calculate Risk-Degree of Collision, and by its with
The danger level threshold value of setting is compared, and if more than the threshold value, is met situation according to the meeting of this ship and object ship and is judged evacuation mode,
It determines that this ship is stand-on vessel or evacuation ship, and still avoids to the right to the left；Finally determine turning avoidance amplitude.
The method that object ship situation monitors in step S3 specifically:
Using this ship as rectangular coordinate system center origin, real-time rendering simultaneously shows the monitoring mesh around this ship within the scope of 8 nautical miles
Cursor position, course information and track, and different risk of collision level states, point can intuitively be reflected by different colours drafting target
Hitting corresponding target can show that corresponding information and evacuation are suggested.
The present invention provides a kind of ship collision prevention aid decision-making system based on Track Fusion and Trajectory Prediction, including serial ports connects
Receive module and database, and the message processing module, algoritic module and the human-computer interaction module that connect with the database, institute
Serial ports receiving module is stated to be connected with the message processing module；
The message processing module, including ship automatic identification system message processing module, radar information processing module and
Other information processing module is located in advance for receiving the shipping information sent from serial ports receiving module, and to it
Reason obtains position, the speed, azimuth information of ship, and finally processing result is saved in database；
The algoritic module, including data anastomosing algorithm module, Trajectory Prediction algoritic module, evacuation decision making algorithm module,
Risk of collision algoritic module and other algoritic modules, for reading position, the speed, orientation letter of ship from data memory module
Breath, and Track Fusion and Trajectory Prediction are carried out to it, anti-collision warning and evacuation decision are carried out according to calculated result；
The human-computer interaction module, including target situation monitoring module, information inquiry module, anti-collision warning module, system
Configuration module and other function module, for show in real time ship sail information and various warning information.
The system uses linux embedded system for development platform, and database uses SQLite3, and Interface Development Tools is adopted
With QT, hardware ARM plate is using S3C6410 chip as processor.
The system further includes GPRS communication module, and is communicated by the GPRS communication module with monitoring center.
The human-computer interaction module carries out human-computer interaction using touch screen.
The beneficial effect comprise that: it is of the invention to be determined based on the ship collision prevention of Track Fusion and Trajectory Prediction auxiliary
Plan method still can touch ship in the case where ensure that triangular web failure by combining shipborne radar and AIS system
It hits danger level to be analyzed, improves the reliability and stability of data source；On the other hand, pre- by Track Fusion and track
Method of determining and calculating, risk of collision when to ship's navigation are analyzed, and make evacuation decision and the monitoring of target situation, can be real-time
, intelligent monitoring ship's navigation when security information, avoid ship from colliding；And in conjunction with embedded technology and computer
Technology, improves reliability, the scalability of system, and facilitates the intelligence and miniaturization of ship-borne equipment, has good
Practical application value.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the process of the ship collision prevention aid decision-making method based on Track Fusion and Trajectory Prediction of the embodiment of the present invention
Figure；
Fig. 2 is the work of the ship collision prevention aid decision-making method based on Track Fusion and Trajectory Prediction of the embodiment of the present invention
Flow chart；
Fig. 3 is the structure of the ship collision prevention aid decision-making system based on Track Fusion and Trajectory Prediction of the embodiment of the present invention
Block diagram；
Fig. 4 is the hardware of the ship collision prevention aid decision-making system based on Track Fusion and Trajectory Prediction of the embodiment of the present invention
Structural schematic diagram；
Fig. 5 be the embodiment of the present invention the ship collision prevention aid decision-making method based on Track Fusion and Trajectory Prediction in predict
Algorithm flow chart；
Fig. 6 is the ship of the ship collision prevention aid decision-making method based on Track Fusion and Trajectory Prediction of the embodiment of the present invention
Motion vector figure.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
As shown in Figure 1, the ship collision prevention aid decision-making method based on Track Fusion and Trajectory Prediction of the embodiment of the present invention,
The following steps are included:
S1, the ship information for obtaining ship automatic identification system and radar transmissions, and it is pre-processed to obtain ship
Position, speed and azimuth information；It is parsed respectively according to ship automatic identification system and radar message format, and extraction has
Information storage is imitated into database.
S2, the position to ship, speed and azimuth information carry out track association and Track Fusion, specific steps are as follows:
S21, the position to ship, speed and azimuth information carry out coordinate conversion and temporal registration, and longitude and latitude form is believed
Breath is converted to polar form information, using piecewise linear interpolation method by nonsynchronous information unification to synchronization；
S22, to treated, position, speed and azimuth information carry out track association, with object ship ship automatic identification system
On the basis of track information of uniting, time, range difference are first excluded compared with ship automatic identification system information away from biggish radar track
Information；The correlation degree for passing through Ship ' automatic recognition system track information and radar track information again, until more options one
This ship automatic identification system track information and radar information are chosen to be object ship by the biggish radar track information of correlation degree
The object of Track Fusion；
The calculation method of correlation degree specifically:
The Euclidean distance of distance, orientation, the speed of a ship or plane, course this 4 factors is obtained by the subordinating degree function of normal distribution
Association and it is not associated with degree of membership value, then is weighted and averaged with each factor weight size and composite factor can be obtained is associated with and is not associated with
Degree of membership；
It finally carries out double threshold to be carefully associated with, that is, judges that composite factor association degree of membership maximum value is with thin degree of incidence is met
The no threshold value for meeting setting stops association judgement if all meeting, and stores and binds the ship for determining thin associated object ship
Automatic recognition system and radar label, the object as the biggish object ship Track Fusion of correlation degree.
S23, the ship automatic identification system and radar track information of the selected biggish object ship of correlation degree are carried out
Track Fusion using being completed the Track Fusion process of object ship based on the Weighted estimation method of statistics, and is stored fusion results and is
Trajectory Prediction provides data；
S3, Trajectory Prediction is carried out to object ship according to the result of Track Fusion, and makes ship collision Risk Assessments, evacuation
Decision and the monitoring of object ship situation.
The method of ship collision Risk Assessments specifically:
Time, two ships distance, object ship and this bearing angle, this ship can be met by comprehensively considering least meeting distance, minimum
It is used as factor of evaluation than this 5 with the speed of object ship, obtains corresponding weighted value after respective degree of membership and weight to be integrated
Factor Risk-Degree of Collision.
The method for avoiding decision specifically:
First determine Anti-collision Actions opportunity, using risk of collision topology degree method calculate Risk-Degree of Collision, and by its with
The danger level threshold value of setting is compared, and if more than the threshold value, is met situation according to the meeting of this ship and object ship and is judged evacuation mode,
It determines that this ship is stand-on vessel or evacuation ship, and still avoids to the right to the left；Finally determine turning avoidance amplitude.
The method of object ship situation monitoring specifically:
Using this ship as rectangular coordinate system center origin, real-time rendering simultaneously shows the monitoring mesh around this ship within the scope of 8 nautical miles
Cursor position, course information and track, and different risk of collision level states, point can intuitively be reflected by different colours drafting target
Hitting corresponding target can show that corresponding information and evacuation are suggested.
As shown in Fig. 2, in another embodiment of the invention, for primary complete auxiliary collision prevention process, according to data
Processing and pass order, workflow specifically:
(1) message that AIS module, radar module transmission are received by serial ports, obtains target information；
(2) it parses, extract information needed and is stored into database according to the message information format of AIS and radar；
(3) from static, a variety of data of dynamic, position needed for merging, speed and azimuth information are taken out, data is carried out and melts
Close, display fusion track, be in this way in order to ensure quantitative analysis source correctness with it is comprehensive；
(4) according to fusion track, prediction next step target position, speed and azimuth information provide collision prevention analysis and collision
The data source of early warning, and ensure that the timeliness of subsequent analysis judgement；
(5) according to predictive information, judge that situation can be met, and be shown in a certain range of all mesh centered on this ship
Mark, allows operator intuitively to grasp surrounding navigation environment integral status；
(6) risk of collision has been assessed whether, this is the core of ship collision prevention system, and evaluation method there should be validity and fast
Speed；
(7) if judgement is dangerous, anti-collision warning is provided；
(8) according to situation can be met, evacuation scheme is provided.
As shown in figure 3, the ship collision prevention aid decision-making system based on Track Fusion and Trajectory Prediction of the embodiment of the present invention
It is connect for realizing the ship collision prevention aid decision-making method based on Track Fusion and Trajectory Prediction of the embodiment of the present invention, including serial ports
Receive module and database, and the message processing module, algoritic module and the human-computer interaction module that connect with the database, institute
Serial ports receiving module is stated to be connected with the message processing module；
The message processing module, including ship automatic identification system message processing module, radar information processing module and
Other information processing module is located in advance for receiving the shipping information sent from serial ports receiving module, and to it
Reason obtains position, speed and the azimuth information of ship, and finally processing result is saved in database；
The algoritic module, including data anastomosing algorithm module, Trajectory Prediction algoritic module, evacuation decision making algorithm module,
Risk of collision algoritic module and other algoritic modules, for reading position, speed and the orientation of ship from data memory module
Information, and Track Fusion and Trajectory Prediction are carried out to it, anti-collision warning and evacuation decision are carried out according to calculated result；
The human-computer interaction module, including target situation monitoring module, information inquiry module, anti-collision warning module, system
Configuration module and other function module, for show in real time ship sail information and various warning information.
In another embodiment of the invention, the ship collision prevention provided by the invention based on Track Fusion and Trajectory Prediction is auxiliary
Decision system is helped, is specifically included:
1. serial ports receiving module
The corresponding device realized of the present invention is connected by serial ports with AIS and radar module, hardware structural diagram such as Fig. 4
It is shown, the message information for obtaining AIS and radar transmissions is recycled by serial ports receiving module program.
2. message processing module
Including AIS and radar information processing module, i.e., information serial ports receiving module obtained, respectively according to AIS and thunder
It is parsed up to message format, and extracts effective information storage into database.
4. data anastomosing algorithm module
Data fusion is carried out to the position of AIS and radar target, speed and azimuth information, is specifically included:
(1) coordinate is converted: since the distance and bearing form of polar coordinate system is in radar target position, AIS is longitude and latitude shape
Formula information.In order to which unified coordinate system is convenient for follow-up data processing, earth ellipsoid face approximation is handled location information as circle,
AIS latitude and longitude information is converted into polar coordinates.
(2) temporal registration: nonsynchronous metric data to same target is unified to synchronization, this is often as
Multiple sensor sample periods are different, and system receives at the time of is also different.It is inserted using relatively simple feasible piecewise linearity
Value method, principle is to connect interpolation point with broken line, to more approach original function.
3) track association: progress time gap first is slightly associated with, and can exclude time, range difference away from bigger target,
It such as a few houres or more than ten nautical miles, drastically reduces need subsequent judgement affiliated partner in this way, improve computational efficiency；Then it carries out
Fuzzy comprehensive evoluation plot-track Association Algorithm obtains distance, orientation, the speed of a ship or plane, this 4, course by the subordinating degree function of normal distribution
The association of the Euclidean distance of factor be not associated with degree of membership value, then with each factor weight size be weighted and averaged and can be integrated
Correlate be not associated with degree of membership；Finally carry out double threshold be carefully associated with, i.e., judge composite factor association degree of membership maximum value and
Meet the threshold value whether thin degree of incidence meets setting, stop association judgement if all meeting, store and binds the thin pass of judgement
The AIS and radar target label of connection, determine the ship object of Track Fusion.
(4) Track Fusion: completing targetpath fusion process using the Weighted estimation method based on statistics, is overall equal
In the square the smallest situation of error, optimal weighted factor is determined, thus guarantee that fused estimated value reaches most accurate, this method letter
Single Yi Shixian.Last fusion results are stored in database, provide fusion track data for Trajectory Prediction.
5. Trajectory Prediction algoritic module
Using improved Sage-Husa Adaptive Kalman Filtering Algorithm, joined on the basis of Kalman filter pair
The statistical property estimation of noise is measured, and filtering divergence is prevented using the filtering convergence criterion based on covariances-matching techniques,
According to information using sequence, time update (estimating process) can be divided into and measure update (correction course), the two processes
Interleaved computation then completes recursive filtering process.Specific algorithm process is as shown in figure 5, prediction result is to calculate state vector in Fig. 5It is deposited into database.
6. risk of collision algoritic module
Including motion vector analysis, situation division, ship collision Risk Assessments algorithm can be met, mesh detailed process: will be studied
Mark is as particle, and that this ship and target are analyzed in rectangular coordinate system can specifically meet situation, as shown in Figure 6.
Ship collision Risk Assessments model, choose least meeting distance DCPA, minimum can meet time TCPA, two ship distance D,
Speed ratio K (the K=V of object ship and this bearing angle Δ B, this ship and object shipT/VO) this 5 be used as factor of evaluation.It can be with
Obtain the parameter that subsequent analysis needs, in which:
DCPA=D × sin (COT-BT)
Then according to BOTWith Δ C, can meet situation quantitatively be divided into end-on, starboard intersection meet, larboard intersection meet,
It overtakes, overtaken this 5 kinds of situation；Eventually by ship collision Risk Assessments model obtain specifically quantify Risk-Degree of Collision
Value, and it is deposited into database.
And pass through f (UDCPA,UTCPA,UD,UΔB,UK)=aDCPAUDCPA+aTCPAUTCPA+aDUD+aΔBUΔB+aKUK, obtain final
Composite factor Risk-Degree of Collision.aDCPA、aTCPA、aD、aΔB、aKFor the respective weights of object ship parameter, belong to [0,1], whole
Be 1, and corresponding subordinating degree function are as follows:
Wherein, d1Indicate the minimum range that two ships cross safely, d2Indicate that safety can meet range, r1Indicate ship collision away from
From；r2Indicate that ship pays attention to distance, t1Indicate ship collision time, t2Indicating that ship pays attention to the time, C is to touch angle, and W is constant, this
System takes 2.0.
7. avoiding decision making algorithm module
Anti-collision Actions opportunity is determined first, is the method using risk of collision topology degree, that is, the danger level threshold value set.If
Risk-Degree of Collision CRI is greater than the value and then starts to avoid；Then evacuation mode is judged according to currently situation can be met, determine that this ship is straight
Boat still avoids ship, and still avoids to the right to the left；It finally determines turning avoidance amplitude, seeks turning to using step length is increased
Angle, θC, it is stepped up satisfaction | DCPA ' | >=SDA ', at this time θCAs steering angle size considers that ship turns in actual conditions
To having certain delay, and take Anti-collision Actions that can " early ", to keep result safer, reasonable should calculate DCPA
Distance D in formula is suitably reduced.
8. target situation monitoring modular
Using this ship as rectangular coordinate system center origin, real-time rendering simultaneously shows the monitoring mesh around this ship within the scope of 8 nautical miles
Cursor position, course information and track, and different risk of collision level states can intuitively be reflected by different colours drafting target, this
System is to indicate that Risk-Degree of Collision higher (CRI >=0.5) suggests avoiding at once by red, and yellow indicates potential risk of collision
(0≤CRI≤0.5) should pay close attention to target, and green expression is safe from danger, and (CRI=0, two ships do not meet or have already passed through nearest meeting
Meet point).
9. information inquiry module
Including the inquiry to this ship and target Ship dynamic situation, static information, and other historical datas are inquired at any time, especially
It is after accident occurs, in this way it will be seen that cause of accident, personnel operate not after e.g. monitoring not in place or monitoring, alarming
In place.Also be able to can operate every time whether correctly effectively provide evidence to analysis to finding out who is responsible for an accident in this way.
10. anti-collision warning module
Risk of collision degree is divided into multiple warning levels, the Risk-Degree of Collision obtained according to intellectual analysis and is made
Threshold range, the different hazard types that can meet ship are shown with different colours, to driver carry out early warning, danger can met
When dangerous degree is very high, alarmed with sound.
11. system configuration module.
The static essential information of ship information configuration, mainly name of vessel, ship launching time etc.；Alarm is matched with threshold value of warning
It sets, is exactly warning value needed for (difference of such as cargo) setting according to actual needs；Algorithm parameter configuration, can be according to practical boat
Row environment is adjusted.
Further, the embedded ship collision prevention aid decision-making system based on Track Fusion and Trajectory Prediction is with embedded
System Linux, Interface Development Tools QT, database SQLite 3 are Software Development Platform, using S3C6410 chip as processor
ARM plate realizes corresponding intrument as hardware development platform.The device includes embedded platform, AIS module, radar module, GPRS
Communication module and touch screen, embedded platform are connected with radar information module, AIS information module, GPRS communication module, touch screen
It connects, and the device accesses Internet by GPRS communication module, to be communicated with monitoring center.
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (2)
1. a kind of ship collision prevention aid decision-making method based on Track Fusion and Trajectory Prediction, which is characterized in that including following step
It is rapid:
S1, the ship information for obtaining ship automatic identification system and radar transmissions, and it is pre-processed to obtain the position of ship
It sets, speed and azimuth information；
S2, the position to ship, speed and azimuth information carry out track association and Track Fusion, specific steps are as follows:
S21, the position to ship, speed and azimuth information carry out coordinate conversion and temporal registration, and longitude and latitude form information is turned
It is changed to polar form information, using piecewise linear interpolation method by nonsynchronous information unification to synchronization；
S22, to treated, position, speed and azimuth information carry out track association, with object ship ship automatic identification system boat
On the basis of mark information, time, range difference are first excluded compared with ship automatic identification system information away from biggish radar track information；
The correlation degree for passing through Ship ' automatic recognition system track information and radar track information again, until one association journey of more options
Biggish radar track information is spent, by fuzzy comprehensive evoluation plot-track Association Algorithm, is obtained by the subordinating degree function of normal distribution
To distance, orientation, the speed of a ship or plane, this 4 factors of course Euclidean distance association be not associated with degree of membership value, then with each factor weight
Size be weighted and averaged can be obtained composite factor association and be not associated with degree of membership；It finally carries out double threshold to be carefully associated with, that is, judges
Composite factor is associated with degree of membership maximum value and meets the threshold value whether thin degree of incidence meets setting, stops closing if all meeting
Connection judgement stores and binds the thin associated AIS of judgement and radar target label, determines the ship object of Track Fusion；By this ship
Oceangoing ship automatic recognition system track information and radar information are chosen to be the object of object ship Track Fusion；
S23, track is carried out to the ship automatic identification system and radar track information of the selected biggish object ship of correlation degree
Fusion, using completing the Track Fusion process of object ship based on the Weighted estimation method of statistics, and storing fusion results is track
Prediction provides data；
S3, Trajectory Prediction is carried out to object ship according to the result of Track Fusion, and makes ship collision Risk Assessments, evacuation decision
And object ship situation monitoring；
The method of ship collision Risk Assessments specifically:
Time, two ships distance, object ship and this bearing angle, this ship and mesh can be met by comprehensively considering least meeting distance, minimum
The speed for marking ship is used as factor of evaluation than this 5, and corresponding weighted value weights to obtain composite factor after obtaining respective degree of membership
Risk-Degree of Collision；
By ship collision Risk Assessments model, choose least meeting distance DCPA, minimum can meet time TCPA, two ship distance D,
The speed ratio K, K=V of object ship and this bearing angle Δ B, this ship and object shipT/VO, Vt is target ship's speed, and Vo is this ship ship
Speed, this 5 are used as factor of evaluation, obtain the parameter of subsequent analysis, in which:
DCPA=D × sin (COT-BT)
Then according to BOTWith Δ C, wherein COTFor two ship course angles, Δ C is COTSupplementary angle；It is quantitatively divided into situation can be met
End-on, starboard intersection are met, larboard intersection meets, overtakes, being overtaken this 5 kinds of situation；Eventually by ship collision Risk Assessments
Model obtains the value for specifically quantifying Risk-Degree of Collision, and is deposited into database；
Pass through f (UDCPA, UTCPA, UD, UΔB, UK)=aDCPAUDCPA+aTCPAUTCPA+aDUD+aΔBUΔB+aKUKObtain final composite factor
Risk-Degree of Collision；
Wherein, aDCPA、aTCPA、aD、aΔB、aKFor the respective weights of object ship parameter, belong to [0,1], the sum of whole is 1, and
Corresponding subordinating degree function are as follows:
Wherein, d1Indicate the minimum range that two ships cross safely, d2Indicate that safety can meet range, r1Indicate ship collision distance；r2
Indicate that ship pays attention to distance, t1Indicate ship collision time, t2Indicate that ship pays attention to the time, C is to touch angle, and W is constant；
The method for avoiding decision specifically:
Anti-collision Actions opportunity is determined first, Risk-Degree of Collision is calculated using the method for risk of collision topology degree, and by itself and setting
Danger level threshold value be compared, if more than the threshold value, situation is met according to the meeting of this ship and object ship and judge evacuation mode, determination
This ship is stand-on vessel or evacuation ship, and is still avoided to the right to the left；Finally determine turning avoidance amplitude；
The method of object ship situation monitoring specifically:
Using this ship as rectangular coordinate system center origin, real-time rendering simultaneously shows the monitoring objective position around this ship within the scope of 8 nautical miles
It sets, course information and track, and draw target by different colours can intuitively reflect different risk of collision level states, clicks pair
Answer target that can show that corresponding information and evacuation are suggested.
2. the ship collision prevention aid decision-making method according to claim 1 based on Track Fusion and Trajectory Prediction, feature
It is, pretreated method is carried out to ship information in step S1 specifically:
It is parsed respectively according to ship automatic identification system and radar message format, and extracts effective information storage to database
In.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510755138.7A CN105390029B (en) | 2015-11-06 | 2015-11-06 | Ship collision prevention aid decision-making method and system based on Track Fusion and Trajectory Prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510755138.7A CN105390029B (en) | 2015-11-06 | 2015-11-06 | Ship collision prevention aid decision-making method and system based on Track Fusion and Trajectory Prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105390029A CN105390029A (en) | 2016-03-09 |
| CN105390029B true CN105390029B (en) | 2019-04-26 |
Family
ID=55422265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510755138.7A Active CN105390029B (en) | 2015-11-06 | 2015-11-06 | Ship collision prevention aid decision-making method and system based on Track Fusion and Trajectory Prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105390029B (en) |
Families Citing this family (70)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105589464B (en) * | 2016-03-28 | 2019-02-26 | 哈尔滨工程大学 | A kind of UUV dynamic obstacle avoidance method based on Speed Obstacles method |
| CN106021675B (en) * | 2016-05-13 | 2020-04-24 | 自然资源部第三海洋研究所 | Data fusion method based on data of multi-source ship automatic identification system |
| CN106094606A (en) * | 2016-05-19 | 2016-11-09 | 南通航运职业技术学院 | A kind of unmanned surface vehicle navigation and control remote-controlled operation platform |
| CN106101590B (en) * | 2016-06-23 | 2019-07-19 | 上海无线电设备研究所 | The detection of radar video complex data and processing system and detection and processing method |
| CN106017475B (en) * | 2016-07-04 | 2019-03-08 | 四川九洲防控科技有限责任公司 | A kind of track update method and device |
| CN106446519B (en) * | 2016-08-31 | 2019-04-05 | 成都中星世通电子科技有限公司 | A kind of Marine Electronics data correlation method |
| CN108470491A (en) * | 2017-02-23 | 2018-08-31 | 中国人民解放军63891部队 | Radar detection aircraft color demonstration method |
| CN106816038B (en) * | 2017-03-17 | 2019-06-11 | 武汉理工大学 | A kind of inland waters abnormal behaviour ship automatic identification system and method |
| CN107577230B (en) * | 2017-08-16 | 2020-01-14 | 武汉理工大学 | Intelligent collision avoidance system for unmanned ship |
| CN107886773B (en) * | 2017-10-19 | 2020-12-11 | 天津大学 | Information quantity-based quantitative analysis method for urgency of meeting situation of ship |
| CN107908925A (en) * | 2017-11-17 | 2018-04-13 | 中国电子科技集团公司第十四研究所 | A kind of increment of rotation occupy-place formula moving-target label automatic avoiding method |
| CN108538088B (en) * | 2018-02-11 | 2020-06-05 | 江苏金海星导航科技有限公司 | Ship collision prediction method and device based on positioning |
| CN108917767B (en) * | 2018-06-28 | 2021-01-26 | 中国船舶重工集团公司第七0七研究所 | Electronic chart-based navigation motion plotting calculation method |
| CN108897272A (en) * | 2018-06-29 | 2018-11-27 | 南京海联智能科技有限公司 | Bank end intelligent monitoring system |
| CN109166355B (en) * | 2018-07-20 | 2021-08-03 | 大连海事大学 | Variable speed avoiding system during navigation of ship channel |
| CN109190170A (en) * | 2018-08-02 | 2019-01-11 | 哈尔滨工程大学 | A kind of Collision Risk Index modeling method based on cloud models theory |
| CN108828550A (en) * | 2018-08-03 | 2018-11-16 | 国网福建省电力有限公司 | A kind of sea cable regional boundary ship target method for detecting position |
| CN109191916A (en) * | 2018-10-11 | 2019-01-11 | 苏州大学 | A kind of ship collision early warning system based on image |
| CN109708638B (en) * | 2018-12-03 | 2022-10-25 | 江苏科技大学 | Ship track point extraction method |
| CN109360450A (en) * | 2018-12-05 | 2019-02-19 | 福州大学 | A kind of vessel traffic service method and system of wisdom navigation mark |
| CN109856624B (en) * | 2019-01-03 | 2021-03-16 | 中国人民解放军空军研究院战略预警研究所 | Target state estimation method for single-radar linear flight path line |
| CN109856625A (en) * | 2019-03-06 | 2019-06-07 | 国网福建省电力有限公司莆田供电公司 | A kind of vessel position recognition methods based on multisource data fusion |
| CN110009936B (en) * | 2019-03-15 | 2021-01-05 | 北京海兰信数据科技股份有限公司 | Ship auxiliary collision prevention method for busy water area |
| CN109887339B (en) * | 2019-03-20 | 2020-09-15 | 集美大学 | Ship collision danger and danger degree evaluation method for associating avoidance behavior |
| CN110009937B (en) * | 2019-03-21 | 2022-04-01 | 武汉理工大学 | Ship collision risk analysis method based on AIS data |
| CN109976342B (en) * | 2019-03-22 | 2020-07-31 | 智慧航海（青岛）科技有限公司 | Dynamic search intelligent ship multi-ship meeting collision avoidance method |
| CN110060281B (en) * | 2019-03-25 | 2023-02-28 | 同济大学 | Ship and water floater track tracking system |
| CN110083155B (en) * | 2019-04-19 | 2022-05-13 | 集美大学 | Machine learning method for realizing ship anthropomorphic intelligent collision avoidance decision |
| CN109996176B (en) * | 2019-05-20 | 2021-08-10 | 北京百度网讯科技有限公司 | Road side perception and vehicle terminal vehicle road cooperative fusion processing method and device |
| CN110208803B (en) * | 2019-05-24 | 2021-04-06 | 中铁大桥科学研究院有限公司 | Method for monitoring and identifying ship anti-collision radar at bridge |
| CN110164185A (en) * | 2019-06-05 | 2019-08-23 | 大连海事大学 | A kind of ship collision prevention system based on AIS |
| CN110203325A (en) * | 2019-06-14 | 2019-09-06 | 上海外高桥造船有限公司 | The test method and system of the collision prevention function of ship autonomous navigation system |
| CN110164186A (en) * | 2019-06-18 | 2019-08-23 | 武汉理工大学 | Ship passes through confluence waters auxiliary collision avoidance system and method |
| CN110322731B (en) * | 2019-06-20 | 2021-08-10 | 武汉理工大学 | Ship meeting navigation aid early warning method |
| CN111063218A (en) * | 2019-06-24 | 2020-04-24 | 武汉理工大学 | Ship collision avoidance decision method |
| CN110491171A (en) * | 2019-09-17 | 2019-11-22 | 南京莱斯网信技术研究院有限公司 | A kind of water transportation supervision early warning system and method based on machine learning techniques |
| CN110749321B (en) * | 2019-10-22 | 2021-05-04 | 中国人民解放军海军潜艇学院 | Navigation drawing electronic auxiliary method, device and system |
| CN111028546B (en) * | 2019-11-20 | 2021-09-03 | 智慧航海（青岛）科技有限公司 | Multi-ship cooperative collision prevention system and method for intelligent ship based on shore-based radar |
| CN111176271B (en) * | 2019-11-21 | 2023-05-02 | 智慧航海（青岛）科技有限公司 | Intelligent ship collision avoidance auxiliary decision-making system based on shore radar and implementation method thereof |
| CN110889221B (en) * | 2019-11-22 | 2022-06-17 | 武汉理工大学 | Method for establishing ship collision avoidance model based on non-Europe-preserving transformation |
| CN110987068B (en) * | 2019-11-28 | 2021-11-30 | 中国人民解放军陆军炮兵防空兵学院郑州校区 | Data fusion method for multi-sensor integrated control system |
| CN110910337A (en) * | 2019-11-29 | 2020-03-24 | 珠海云航智能技术有限公司 | Ship track fusion method and device and terminal equipment |
| TWI725677B (en) * | 2019-12-20 | 2021-04-21 | 財團法人船舶暨海洋產業研發中心 | Autonomous vessel simulation system and operating method thereof |
| JP7371907B2 (en) * | 2019-12-25 | 2023-10-31 | 知洋 下川部 | Management server in ship navigation support system, ship navigation support method, and ship navigation support program |
| CN111337027B (en) * | 2019-12-27 | 2022-03-01 | 北京海兰信数据科技股份有限公司 | Ship follow-up operation auxiliary driving method and system |
| CN111243339A (en) * | 2020-01-14 | 2020-06-05 | 武汉理工大学 | AIS system and method special for ferry with collision avoidance early warning function |
| CN111309201A (en) * | 2020-01-19 | 2020-06-19 | 青岛海狮网络科技有限公司 | Multi-window display method for autonomous collision avoidance of autonomously driven ship |
| CN111221336B (en) * | 2020-01-19 | 2023-06-30 | 智慧航海（青岛）科技有限公司 | Ship end auxiliary leaning and off-berthing system |
| CN111272171B (en) * | 2020-04-07 | 2023-05-30 | 上海船舶研究设计院（中国船舶工业集团公司第六0四研究院） | Ship track prediction method and device |
| CN111915928B (en) * | 2020-06-28 | 2022-04-26 | 大连海事大学 | Ship collision accident rate prediction method |
| CN111932944B (en) * | 2020-07-07 | 2021-09-03 | 智慧航海(青岛)智能系统工程有限公司 | Method for carrying out data processing at ship end based on regional ship data |
| CN111951606B (en) * | 2020-07-29 | 2021-07-30 | 武汉理工大学 | Ship collision risk assessment and early warning method and system |
| CN111968406B (en) * | 2020-08-18 | 2021-06-25 | 江苏航运职业技术学院 | Chaos theory-based fuzzy prediction method for short-term traffic flow of ship |
| KR20220049407A (en) | 2020-10-14 | 2022-04-21 | 삼성전자주식회사 | Display apparatus and control method thereof |
| CN112362042B (en) * | 2020-10-30 | 2023-03-10 | 智慧航海（青岛）科技有限公司 | Track correlation judgment method based on intelligent ship multi-sensing equipment |
| CN112364795B (en) * | 2020-11-18 | 2024-01-30 | 大连海事大学 | Automatic identification method for number lamps and situation awareness method for two ships meeting |
| CN113009470B (en) * | 2021-02-09 | 2023-04-21 | 北京理工大学 | Processing method, system, device and medium for target situation characteristic data |
| CN113380072B (en) * | 2021-05-21 | 2022-04-26 | 山东交通学院 | Ship safety protection method |
| CN113470435B (en) * | 2021-07-09 | 2022-10-25 | 上海海事大学 | Method and terminal for generating intelligent ship test scene of natural anti-marine environment |
| CN113744569B (en) * | 2021-11-03 | 2022-02-18 | 武汉理工大学 | Autonomous collision avoidance method, system, equipment and storage medium for ships in open water |
| CN113744570B (en) * | 2021-11-03 | 2022-03-25 | 武汉理工大学 | Anti-collision early warning method and device for ships in water area of bridge area |
| CN114495583A (en) * | 2021-12-24 | 2022-05-13 | 福建新继船舶服务有限公司 | Anti-collision method based on DQN-BP model |
| CN114464014A (en) * | 2022-01-05 | 2022-05-10 | 集美大学 | Fuzzy logic based regional ship collision risk processing method, system and medium |
| CN114415168A (en) * | 2022-01-18 | 2022-04-29 | 舟山市质量技术监督检测研究院 | Unmanned surface vessel track fusion method and device |
| CN114464015B (en) * | 2022-02-08 | 2023-05-02 | 北京百度网讯科技有限公司 | Data processing method, device, electronic equipment and storage medium |
| CN114664118B (en) * | 2022-03-18 | 2023-04-07 | 陕西正整数科技有限公司 | Intelligent ship collision avoidance automatic test scene generation method and system |
| CN115273556A (en) * | 2022-06-24 | 2022-11-01 | 大连海事大学 | Ship collision avoidance decision method and system based on interoperation technology |
| CN115410420B (en) * | 2022-10-31 | 2023-01-20 | 河北东来工程技术服务有限公司 | Ship safe navigation management method and system |
| CN115472041B (en) * | 2022-11-14 | 2023-03-24 | 福建飞通通讯科技股份有限公司 | Novel marine boats and ships meet early warning reminder system |
| CN117292583A (en) * | 2023-10-11 | 2023-12-26 | 绒智海试科技(河北)有限公司 | Target object situation display system based on comprehensive situation display and plotting |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714718A (en) * | 2013-12-31 | 2014-04-09 | 武汉理工大学 | Inland river bridge area ship safe navigation precontrol system |
| CN104391281A (en) * | 2014-11-21 | 2015-03-04 | 武汉大学 | Method for improving sky-wave radar sea surface ship target tracking and positioning precision |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9334030B2 (en) * | 2012-10-22 | 2016-05-10 | Electronics And Telecommunications Research Institute | Method and system for managing traffic considering GPS jamming |
-
2015
- 2015-11-06 CN CN201510755138.7A patent/CN105390029B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714718A (en) * | 2013-12-31 | 2014-04-09 | 武汉理工大学 | Inland river bridge area ship safe navigation precontrol system |
| CN104391281A (en) * | 2014-11-21 | 2015-03-04 | 武汉大学 | Method for improving sky-wave radar sea surface ship target tracking and positioning precision |
Non-Patent Citations (1)
| Title |
|---|
| 《基于AIS/雷达融合信息的船舶避碰终端设计与实现》;吴红双;《CNKI中国优秀硕士论文全文数据库》;20130310;2-60 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105390029A (en) | 2016-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105390029B (en) | Ship collision prevention aid decision-making method and system based on Track Fusion and Trajectory Prediction | |
| Zhang et al. | A systematic approach for collision risk analysis based on AIS data | |
| CN108873799A (en) | Boat-carrying intelligent driving assists terminal | |
| Emmens et al. | The promises and perils of Automatic Identification System data | |
| CN110083155B (en) | Machine learning method for realizing ship anthropomorphic intelligent collision avoidance decision | |
| Zhang et al. | Towards a model of regional vessel near-miss collision risk assessment for open waters based on AIS data | |
| CN112966332B (en) | Conflict detection method based on multi-ship motion uncertainty, memory and processor | |
| CN113536544B (en) | Ship probability conflict detection method based on minimum safe distance model | |
| Liu et al. | A quantitative method for the analysis of ship collision risk using AIS data | |
| Shi et al. | Fuzzy logic-based modeling method for regional multi-ship collision risk assessment considering impacts of ship crossing angle and navigational environment | |
| Silveira et al. | Assessment of ship collision estimation methods using AIS data | |
| Tang et al. | Detection of abnormal vessel behaviour based on probabilistic directed graph model | |
| Ma et al. | A data-driven approach for collision risk early warning in vessel encounter situations using attention-BiLSTM | |
| CN111815120A (en) | Water traffic risk assessment method, device, computer equipment and storage medium | |
| CN203094401U (en) | Shipborne automatic identification system (AIS) automatic intelligent collision prevention system adopting sonar detection | |
| Liu et al. | Modelling dynamic maritime traffic complexity with radial distribution functions | |
| Wu et al. | A new multi-sensor fusion approach for integrated ship motion perception in inland waterways | |
| Wang et al. | A real-time ship collision risk perception model derived from domain-based approach parameters | |
| Xu et al. | A novel ship speed and heading estimation approach using radar sequential images | |
| Vagale et al. | Evaluation of path planning algorithms of autonomous surface vehicles based on safety and collision risk assessment | |
| CN113110474A (en) | Offshore sea area small ship behavior decision method | |
| Liu et al. | A conflict cluster-based method for collision avoidance decision-making in multi-ship encounter situations | |
| CN117232520A (en) | Ship intelligent navigation system and navigation method suitable for offshore navigation | |
| CN115723919A (en) | Auxiliary navigation method and device for ship yaw | |
| Lamm et al. | Detecting maneuvers in maritime observation data with CUSUM |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |