CN106205213A - A kind of boats and ships trajectory predictions method - Google Patents

A kind of boats and ships trajectory predictions method Download PDF

Info

Publication number
CN106205213A
CN106205213A CN201610620437.4A CN201610620437A CN106205213A CN 106205213 A CN106205213 A CN 106205213A CN 201610620437 A CN201610620437 A CN 201610620437A CN 106205213 A CN106205213 A CN 106205213A
Authority
CN
China
Prior art keywords
boats
ships
sampling instant
parameter
track data
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.)
Pending
Application number
CN201610620437.4A
Other languages
Chinese (zh)
Inventor
韩云祥
赵景波
李广军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu University of Technology
Original Assignee
Jiangsu University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu University of Technology filed Critical Jiangsu University of Technology
Priority to CN201610620437.4A priority Critical patent/CN106205213A/en
Publication of CN106205213A publication Critical patent/CN106205213A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G3/00Traffic control systems for marine craft
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G3/00Traffic control systems for marine craft
    • G08G3/02Anti-collision systems

Abstract

The present invention relates to a kind of boats and ships trajectory predictions method, including following several steps, first pass through sea radar and obtain the real-time of boats and ships and historical position information and do preliminary treatment;Then in each sampling instant to boats and ships track data pretreatment, then in each sampling instant, boats and ships track data is clustered, HMM is utilized to carry out parameter training boats and ships track data again and in each sampling instant, then in each sampling instant according to HMM parameter, Viterbi algorithm is used to obtain hidden state q corresponding to current time observation, finally in each sampling instant by setting prediction time domain W, hidden state q based on boats and ships current time, obtain position prediction value O of future time period boats and ships, thus roll in each sampling instant and speculate to the track of boats and ships in future time period.The present invention rolls and is predicted boats and ships track in real time, and accuracy is preferable, thus provides powerful guarantee for follow-up boats and ships conflict Resolution.

Description

A kind of boats and ships trajectory predictions method
The application is Application No.: 2014108415648, and invention and created name is " a kind of boats and ships track real-time estimate side Method ", filing date: the divisional application of in December, 2014 application for a patent for invention of 30 days.
Technical field
The present invention relates to a kind of marine site traffic control method, particularly relate to a kind of boats and ships track based on Rolling Planning strategy Forecasting Methodology.
Background technology
Along with the fast development of whole world shipping business, the traffic in the busy marine site of part is the most crowded.Close in vessel traffic flow The complicated marine site of collection, still uses sail plan to combine the regulation model of artificial interval allotment the most not for the collision scenario between boats and ships Adapt to the fast development of shipping business.For ensureing the personal distance between boats and ships, enforcement effective conflict allotment just becomes marine site and hands over The emphasis of siphunculus system work.Boats and ships conflict Resolution is a key technology in navigational field, frees scheme pair safely and efficiently In increasing marine site boats and ships flow and guaranteeing that sea-freight safety is significant.
In order to improve the efficiency of navigation of boats and ships, marine radar automatic plotter has been widely applied to ship monitor With in collision prevention, this equipment provides reference frame by extracting boats and ships relevant information for the judgement of collision scenario between boats and ships.Although this Kind equipment greatly reduces manual supervisory load, but it does not has boats and ships automatic conflict Resolution function.And boats and ships conflict solution De-be based on the prediction to boats and ships track on the basis of, in boats and ships real navigation, by meteorological condition, navigator and driving The impact of the various factors such as member's operation, its running status the most not exclusively belongs to a certain specific kinestate, at boats and ships rail Need to consider the impact of various random factor during mark prediction, by obtaining the up-to-date characteristic of all kinds of random factors to its future Track is implemented rolling forecast and strengthens the robustness of its trajectory predictions.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of robustness preferable boats and ships trajectory predictions method, the method Boats and ships trajectory predictions precision is higher.
The technical scheme realizing the object of the invention is to provide a kind of boats and ships trajectory predictions method, including following several steps:
1. obtaining the real-time of boats and ships and historical position information by sea radar, the positional information of each boats and ships is discrete two-dimensional Position sequence x'=[x1',x2',...,xn'] and y'=[y1',y2',...,yn'], by application wavelet transformation theory to original Discrete two-dimensional position sequence x'=[x1',x2',...,xn'] and y'=[y1',y2',...,yn'] carry out preliminary treatment, thus obtain Take the denoising discrete two-dimensional position sequence x=[x of boats and ships1,x2,...,xn] and y=[y1,y2,...,yn];
2. in each sampling instant to boats and ships track data pretreatment, according to acquired boats and ships original discrete two-dimensional position Sequence x=[x1,x2,...,xn] and y=[y1,y2,...,yn], use first-order difference method to carry out processing the ship that acquisition is new to it Oceangoing ship discrete location sequence Δ x=[Δ x1,Δx2,...,Δxn-1] and Δ y=[Δ y1,Δy2,...,Δyn-1], wherein Δ xi= xi+1-xi,Δyi=yi+1-yi(i=1,2 ..., n-1);
3. in each sampling instant, boats and ships track data is clustered, to boats and ships discrete two-dimensional position sequence Δ new after processing X and Δ y, by setting cluster number M', uses K-means clustering algorithm to cluster it respectively;
4. HMM is utilized to carry out parameter training boats and ships track data in each sampling instant, at inciting somebody to action Vessel motion track data Δ x and Δ y after reason is considered as the aobvious observation of hidden Markov models, by setting hidden state number N and parameter update period τ ', according to T' nearest position detection value and use B-W algorithm to roll the up-to-date Hidden Markov of acquisition Model parameter λ ';
5. in each sampling instant according to HMM parameter, use Viterbi algorithm to obtain current time and see Hidden state q corresponding to measured value;
6. in each sampling instant, by setting prediction time domain W, hidden state q based on boats and ships current time, future is obtained Position prediction value O of period boats and ships, thus roll in each sampling instant and speculate to the track of boats and ships in future time period.
Further, described step 1. in, by application wavelet transformation theory to original discrete two-dimensional position sequence x'= [x1',x2',...,xn'] and y'=[y1',y2',...,yn'] carry out preliminary treatment, thus obtain the denoising discrete two-dimensional of boats and ships Position sequence x=[x1,x2,...,xn] and y=[y1,y2,...,yn]: for given original two dimensional sequence data x'= [x1',x2',...,xn'], utilize the linear representation of following form respectively it to be approximated:
Wherein:
F'(x') represent that, to the function expression obtained after data smoothing processing, ψ (x') represents female ripple, and δ, J and K are little Wave conversion constant, ψJ,K(x') transition form of female ripple, c are representedJ,KRepresent the function coefficients obtained by wavelet transform procedure, its body Show wavelet ψJ,K(x') the weight size to whole approximation to function, if this coefficient is the least, then it means wavelet ψJ,K(x') Weight the least, thus can be on the premise of not influence function key property, by wavelet ψ during approximation to functionJ,K (x') remove;In real data processing procedure, implement " threshold transition " by setting threshold value χ, work as cJ,KDuring < χ, set cJ,K=0;The employing the following two kinds mode of choosing of threshold function table:
With
For y'=[y1',y2',...,yn'], it is also adopted by said method and carries out denoising.
Further, described step 4. in determine flight path HMM parameter lambda '=the process of (π, A, B) is as follows:
4.1) variable composes initial value: application is uniformly distributed to variable πi, aijAnd bj(ok) compose initial value πi 0,WithAnd make It meets constraints:WithThus obtain λ0=(π0,A0,B0), wherein okRepresent a certain aobvious observation, π0、A0And B0It is by element respectivelyWithThe matrix constituted, Make parameter l=0, o=(ot-T'+1,...,ot-1,ot) it is T' historical position observation before current time t;
4.2) E-M algorithm is performed:
4.2.1) E-step: by λlCalculate ξe(i, j) and γe(si);
VariableSo
Wherein s represents a certain hidden state;
4.2.2) M-step: useEstimate respectively Meter πi, aijAnd bj(ok) and thus obtain λl+1
4.2.3) circulation: l=l+1, repeats E-step and M-step, until πi、aijAnd bj(ok) convergence, i.e.
|P(o|λl+1)-P(o|λl) | < ε, wherein parameter ε=0.00001, return step 4.2.4);
4.2.4): make λ '=λl+1, algorithm terminates.
Further, described step 5. in determine that the iterative process of the optimal hidden status switch of ship track is as follows:
5.1) variable composes initial value: make g=2, βT'(si)=1 (si∈ S), δ1(si)=πibi(o1), ψ1(si)=0, wherein,
δ g ( s i ) = max q 1 , q 2 , . . . , q g - 1 P ( q 1 , q 2 , . . . , q g - 1 , q g = s i , o 1 , o 2 , . . . , o g | λ ′ )
, wherein variable ψg(sj) represent make variable δg-1(si)aijTake hidden state s of ship track of maximumi, parameter S represents The set of hidden state;
5.2) recursive process:
5.3) moment updates: make g=g+1, if g≤T', returns step 5.2), otherwise iteration ends forward step to 5.4);
5.4)Forward step 5.5 to);
5.5) optimum hidden status switch obtains:
5.5.1) variable composes initial value: make g=T'-1;
5.5.2) backward recursion:
5.5.3) moment updates: make g=g-1, if g >=1, returns step 5.5.2), otherwise terminate.
Further, described step 3. in, cluster number M' value be 4.
Further, described step 4. in, the value of state number N is 3, parameter update period τ ' be 30 seconds, T' is 10.
Further, described step 6. in, it was predicted that time domain W is 300 seconds.
The present invention has a positive effect: (1) present invention during boats and ships track real-time estimate, incorporated random because of The impact of element, the rolling track prediction scheme used can be extracted the changing condition of extraneous random factor in time, improve ship The accuracy of oceangoing ship trajectory predictions.
(2) present invention is based on different performance index, and its boats and ships track real-time estimate result can be the multiple of existence conflict Boats and ships provide frees trajectory planning scheme, improves economy and the utilization rate of sea area resources of vessel motion.
Accompanying drawing explanation
Fig. 1 is the vessel motion short-term Track Pick-up schematic flow sheet in the present invention.
Detailed description of the invention
(embodiment 1)
Seeing Fig. 1, a kind of boats and ships trajectory predictions method of the present embodiment includes following several step:
1. obtaining the real-time of boats and ships and historical position information by sea radar, the positional information of each boats and ships is discrete two-dimensional Position sequence x'=[x1',x2',...,xn'] and y'=[y1',y2',...,yn'], by application wavelet transformation theory to original Discrete two-dimensional position sequence x'=[x1',x2',...,xn'] and y'=[y1',y2',...,yn'] carry out preliminary treatment, thus obtain Take the denoising discrete two-dimensional position sequence x=[x of boats and ships1,x2,...,xn] and y=[y1,y2,...,yn]: y=[y1,y2,..., yn]: for given original two dimensional sequence data x'=[x1',x2',...,xn'], utilize the linear representation of following form to divide Other it is approximated:
Wherein:
F'(x') represent that, to the function expression obtained after data smoothing processing, ψ (x') represents female ripple, and δ, J and K are little Wave conversion constant, ψJ,K(x') transition form of female ripple, c are representedJ,KRepresent the function coefficients obtained by wavelet transform procedure, its body Show wavelet ψJ,K(x') the weight size to whole approximation to function, if this coefficient is the least, then it means wavelet ψJ,K(x') Weight the least, thus can be on the premise of not influence function key property, by wavelet ψ during approximation to functionJ,K (x') remove;In real data processing procedure, implement " threshold transition " by setting threshold value χ, work as cJ,KDuring < χ, set cJ,K=0;The employing the following two kinds mode of choosing of threshold function table:
With
For y'=[y1',y2',...,yn'], it is also adopted by said method and carries out denoising;
2. in each sampling instant to boats and ships track data pretreatment, according to acquired boats and ships original discrete two-dimensional position Sequence x=[x1,x2,...,xn] and y=[y1,y2,...,yn], use first-order difference method to carry out processing the ship that acquisition is new to it Oceangoing ship discrete location sequence Δ x=[Δ x1,Δx2,...,Δxn-1] and Δ y=[Δ y1,Δy2,...,Δyn-1], wherein Δ xi= xi+1-xi,Δyi=yi+1-yi(i=1,2 ..., n-1);
3. in each sampling instant, boats and ships track data is clustered, to boats and ships discrete two-dimensional position sequence Δ new after processing X and Δ y, by setting cluster number M', uses K-means clustering algorithm to cluster it respectively;
4. HMM is utilized to carry out parameter training boats and ships track data in each sampling instant, at inciting somebody to action Vessel motion track data Δ x and Δ y after reason is considered as the aobvious observation of hidden Markov models, by setting hidden state number N and parameter update period τ ', according to T' nearest position detection value and use B-W algorithm to roll the up-to-date Hidden Markov of acquisition Model parameter λ ';Determine flight path HMM parameter lambda '=the process of (π, A, B) is as follows:
4.1) variable composes initial value: application is uniformly distributed to variable πi, aijAnd bj(ok) compose initial valueWithAnd It is made to meet constraints:WithThus To λ0=(π0,A0,B0), wherein okRepresent a certain aobvious observation, π0、A0And B0It is by element respectivelyWithThe square constituted Battle array, makes parameter l=0, o=(ot-T'+1,...,ot-1,ot) it is T' historical position observation before current time t;
4.2) E-M algorithm is performed:
4.2.1) E-step: by λlCalculate ξe(i, j) and γe(si);
VariableSo
Wherein s represents a certain hidden state;
4.2.2) M-step: useEstimate respectively Meter πi, aijAnd bj(ok) and thus obtain λl+1
4.2.3) circulation: l=l+1, repeats E-step and M-step, until πi、aijAnd bj(ok) convergence, i.e.
|P(o|λl+1)-P(o|λl) | < ε, wherein parameter ε=0.00001, return step 4.2.4);
4.2.4): make λ '=λl+1, algorithm terminates.
5. in each sampling instant according to HMM parameter, use Viterbi algorithm to obtain current time and see Hidden state q corresponding to measured value:
5.1) variable composes initial value: make g=2, βT'(si)=1 (si∈ S), δ1(si)=πibi(o1), ψ1(si)=0, wherein,
δ g ( s i ) = max q 1 , q 2 , . . . , q g - 1 P ( q 1 , q 2 , . . . , q g - 1 , q g = s i , o 1 , o 2 , . . . , o g | λ ′ )
, wherein variable ψg(sj) represent make variable δg-1(si)aijTake hidden state s of ship track of maximumi, parameter S represents The set of hidden state;
5.2) recursive process:
5.3) moment updates: make g=g+1, if g≤T', returns step 5.2), otherwise iteration ends forward step to 5.4);
5.4)Forward step 5.5 to);
5.5) optimum hidden status switch obtains:
5.5.1) variable composes initial value: make g=T'-1;
5.5.2) backward recursion:
5.5.3) moment updates: make g=g-1, if g >=1, returns step 5.5.2), otherwise terminate..
6. in each sampling instant, by setting prediction time domain W, hidden state q based on boats and ships current time, future is obtained Position prediction value O of period boats and ships.
The value of above-mentioned cluster number M' is 4, the value of state number N is 3, and it is 30 seconds that parameter updates period τ ', and T' is 10, Prediction time domain W is 300 seconds.
(application examples, navigation traffic control method)
The navigation traffic control method of the present embodiment includes following several step:
Step A, the boats and ships trajectory predictions method obtained according to embodiment 1 obtain what boats and ships speculated in each sampling instant The track of boats and ships in future time period;
Step B, at each sampling instant, the running status current based on boats and ships and historical position observation sequence, obtain sea The numerical value of territory wind field variable, its detailed process is as follows:
B.1) stop position of boats and ships is set as track reference coordinate initial point;
B.2) when boats and ships are in straight running condition and at the uniform velocity turning running status, marine site wind field linear filtering mould is built Type;
B.3) numerical value of wind field variable is obtained according to constructed Filtering Model.
Step C, in each sampling instant, when the boats and ships of running statuses based on each boats and ships and setting run in marine site need The safety regulation collection met, when likely there is the situation violating safety regulation when between boats and ships, to its dynamic behaviour implementing monitoring And provide warning information timely for maritime traffic control centre;
Step D, when warning information occurs, on the premise of meeting boats and ships physical property and marine site traffic rules, pass through Set optimizing index function and incorporate wind field variable value, using Model Predictive Control Theory method that boats and ships collision avoidance track is entered Row Rolling Planning, and program results is transferred to the execution of each boats and ships, its detailed process is as follows:
D.1) termination reference point locations P of boats and ships collision avoidance trajectory planning, collision avoidance policy control time domain Θ, trajectory predictions are set Time domain γ;
D.2) on the premise of being set in given optimizing index function, based on cooperative collision avoidance trajectory planning thought, by giving Each boats and ships give different weights and incorporate real-time wind field variable filtering numerical value, obtain the collision avoidance track of each boats and ships and keep away Hit control strategy and program results is transferred to the execution of each boats and ships, and each boats and ships only implement its first in Rolling Planning is spaced Optimal Control Strategy;
D.3) in next sampling instant, step 5.2 is repeated) until each boats and ships all arrive it frees terminal.
Above-mentioned termination reference point locations P is set as the next navigation channel point of vessel position conflict point, during collision avoidance policy control Territory Θ is 300 seconds;Trajectory predictions time domain γ is 300 seconds.
Obviously, above-described embodiment is only for clearly demonstrating example of the present invention, and not to the present invention The restriction of embodiment.For those of ordinary skill in the field, can also be made it on the basis of the above description The change of its multi-form or variation.Here without also cannot all of embodiment be given exhaustive.And these belong to this What bright spirit was extended out obviously changes or changes among still in protection scope of the present invention.

Claims (1)

1. a boats and ships trajectory predictions method, it is characterised in that include following several step:
1. obtaining the real-time of boats and ships and historical position information by sea radar, the positional information of each boats and ships is discrete two-dimensional position Sequence x'=[x1',x2',...,xn'] and y'=[y1',y2',...,yn'], by application wavelet transformation theory to original discrete Two-dimensional position sequence x'=[x1',x2',...,xn'] and y'=[y1',y2',...,yn'] carry out preliminary treatment, thus obtain ship The denoising discrete two-dimensional position sequence x=[x of oceangoing ship1,x2,...,xn] and y=[y1,y2,...,yn];
2. in each sampling instant to boats and ships track data pretreatment, according to acquired boats and ships original discrete two-dimensional position sequence X=[x1,x2,...,xn] and y=[y1,y2,...,yn], use first-order difference method carry out processing to it obtain new boats and ships from Dissipate position sequence △ x=[△ x1,△x2,...,△xn-1] and △ y=[△ y1,△y2,...,△yn-1], wherein △ xi=xi+1- xi,△yi=yi+1-yi, i=1,2 ..., n-1;
3. in each sampling instant, boats and ships track data is clustered, to new boats and ships discrete two-dimensional position sequence △ x after processing and △ y, by setting cluster number M', uses K-means clustering algorithm to cluster it respectively;
4. HMM is utilized to carry out parameter training boats and ships track data in each sampling instant, after processing Vessel motion track data △ x and △ y be considered as the aobvious observation of hidden Markov models, by set hidden state number N and Parameter update period τ ', according to T' nearest position detection value and use B-W algorithm roll acquisition up-to-date Hidden Markov mould Shape parameter λ ';
5. in each sampling instant according to HMM parameter, Viterbi algorithm is used to obtain current time observation Corresponding hidden state q;
6. in each sampling instant, by setting prediction time domain W, hidden state q based on boats and ships current time, future time period is obtained Position prediction value O of boats and ships, thus roll in each sampling instant and speculate to the track of boats and ships in future time period;
Described step 4. in determine flight path HMM parameter lambda '=the process of (π, A, B) is as follows:
4.1) variable composes initial value: application is uniformly distributed to variable πi, aijAnd bj(ok) compose initial valueWithAnd make it full Foot constraints:WithThus obtain λ0= (π0,A0,B0), wherein okRepresent a certain aobvious observation, π0、A0And B0It is by element respectivelyWithThe matrix constituted, order Parameter l=0, o=(ot-T'+1,...,ot-1,ot) it is T' historical position observation before current time t;
4.2) E-M algorithm is performed:
4.2.1) E-step: by λlCalculate ξe(i, j) and γe(si);
VariableSo
Wherein s represents a certain hidden state;
4.2.2) M-step: useEstimate π respectivelyi, aijAnd bj(ok) and thus obtain λl+1
4.2.3) circulation: l=l+1, repeats E-step and M-step, until πi、aijAnd bj(ok) convergence, i.e. | P (o | λl+1)-P(o|λl) | < ε, wherein parameter ε=0.00001 return step 4.2.4);
4.2.4): make λ '=λl+1, algorithm terminates.
CN201610620437.4A 2014-12-30 2014-12-30 A kind of boats and ships trajectory predictions method Pending CN106205213A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610620437.4A CN106205213A (en) 2014-12-30 2014-12-30 A kind of boats and ships trajectory predictions method

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410841564.8A CN104537891B (en) 2014-12-30 2014-12-30 A kind of boats and ships track real-time predicting method
CN201610620437.4A CN106205213A (en) 2014-12-30 2014-12-30 A kind of boats and ships trajectory predictions method

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
CN201410841564.8A Division CN104537891B (en) 2014-12-30 2014-12-30 A kind of boats and ships track real-time predicting method

Publications (1)

Publication Number Publication Date
CN106205213A true CN106205213A (en) 2016-12-07

Family

ID=52853410

Family Applications (4)

Application Number Title Priority Date Filing Date
CN201610620526.9A Pending CN106251704A (en) 2014-12-30 2014-12-30 Boats and ships trajectory predictions method
CN201610620437.4A Pending CN106205213A (en) 2014-12-30 2014-12-30 A kind of boats and ships trajectory predictions method
CN201610624893.6A Pending CN106228850A (en) 2014-12-30 2014-12-30 Boats and ships track real-time predicting method based on Rolling Planning strategy
CN201410841564.8A Active CN104537891B (en) 2014-12-30 2014-12-30 A kind of boats and ships track real-time predicting method

Family Applications Before (1)

Application Number Title Priority Date Filing Date
CN201610620526.9A Pending CN106251704A (en) 2014-12-30 2014-12-30 Boats and ships trajectory predictions method

Family Applications After (2)

Application Number Title Priority Date Filing Date
CN201610624893.6A Pending CN106228850A (en) 2014-12-30 2014-12-30 Boats and ships track real-time predicting method based on Rolling Planning strategy
CN201410841564.8A Active CN104537891B (en) 2014-12-30 2014-12-30 A kind of boats and ships track real-time predicting method

Country Status (1)

Country Link
CN (4) CN106251704A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110009936A (en) * 2019-03-15 2019-07-12 北京海兰信数据科技股份有限公司 A kind of ship auxiliary collision prevention method for crowded waters

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106251704A (en) * 2014-12-30 2016-12-21 江苏理工学院 Boats and ships trajectory predictions method
CN106154296A (en) * 2015-06-26 2016-11-23 安徽华米信息科技有限公司 The method of adjustment of a kind of path locus and device
CN106595665B (en) * 2016-11-30 2019-10-11 耿生玲 The prediction technique of mobile object space-time trajectory in a kind of space with obstacle
US10780968B2 (en) * 2017-11-27 2020-09-22 Applied Physical Sciences Corp. Systems and methods for wave sensing and ship motion forecasting with operational period indicators
CN110706518B (en) * 2019-08-19 2022-04-22 浙江海洋大学 Ship port-hanging and berthing prediction technology
CN111929715A (en) * 2020-06-28 2020-11-13 杭州云起智慧校园科技有限公司 Positioning method, device and equipment for school badge and storage medium
CN112070312B (en) * 2020-09-10 2021-11-02 龙马智芯(珠海横琴)科技有限公司 Flight path prediction method, flight path prediction device, and computer-readable storage medium
CN113093735B (en) * 2021-03-18 2022-07-26 华南理工大学 Cross-section function control method, system and medium of under-actuated unmanned ship with limited output under random disturbance
CN113627104B (en) * 2021-08-12 2024-02-06 北京中安智能信息科技有限公司 Underwater submarine track simulation method, device and equipment under multiple constraint conditions

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1693826A1 (en) * 2003-08-29 2006-08-23 Microsoft Corporation Vocal tract resonance tracking using a nonlinear predictor and a target-guided temporal constraint
JP2010033352A (en) * 2008-07-29 2010-02-12 Toyota Central R&D Labs Inc Lane change alarm and program
US20110273568A1 (en) * 2004-11-03 2011-11-10 Lagassey Paul J Modular intelligent transportation system
WO2012012550A2 (en) * 2010-07-20 2012-01-26 The University Of Memphis Research Foundation Theft detection nodes and servers, methods of estimating an angle of a turn, methods of estimating a distance traveled between successive stops, and methods and servers for determining a path traveled by a node
US20120053944A1 (en) * 2010-08-31 2012-03-01 Cuneyt Oncel Tuzel Method for Determining Compressed State Sequences
CN102568200A (en) * 2011-12-21 2012-07-11 辽宁师范大学 Method for judging vehicle driving states in real time
US20120215735A1 (en) * 2011-02-18 2012-08-23 Larus Technologies Corporation System and Method for Data Fusion with Adaptive Learning
US20130080068A1 (en) * 2011-04-13 2013-03-28 The Board Of Trustees Of The Leland Stanford Junior University Phased Whole Genome Genetic Risk In A Family Quartet
CN103152253A (en) * 2013-01-17 2013-06-12 王少夫 Mining path prediction algorithm based on complex communication network channel data
CN103235933A (en) * 2013-04-15 2013-08-07 东南大学 Vehicle abnormal behavior detection method based on Hidden Markov Model
CN103336863A (en) * 2013-06-24 2013-10-02 北京航空航天大学 Radar flight path observation data-based flight intention recognition method
CN103413443A (en) * 2013-07-03 2013-11-27 太原理工大学 Short-term traffic flow forecasting method based on hidden Markov model
CN103473540A (en) * 2013-09-11 2013-12-25 天津工业大学 Vehicle track incremental modeling and on-line abnormity detection method of intelligent traffic system
CN103471589A (en) * 2013-09-25 2013-12-25 武汉大学 Method for identifying walking mode and tracing track of pedestrian in room

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3725918A (en) * 1970-11-18 1973-04-03 Sperry Rand Corp Collision avoidance display apparatus for maneuverable craft
WO1995003598A1 (en) * 1993-07-20 1995-02-02 Philip Bernard Wesby Locating/map dissemination system
JP2002312900A (en) * 2001-04-13 2002-10-25 Original Engineering Consultants Co Ltd Three-dimensional position confirmation system
JP4461450B2 (en) * 2001-04-24 2010-05-12 日本無線株式会社 Weather information provision system
JP2005181077A (en) * 2003-12-18 2005-07-07 Tokimec Inc Navigation supporting system for vessel
JP4709684B2 (en) * 2006-04-13 2011-06-22 隼馬 今津 Counterpart movement monitoring device
CN101639988B (en) * 2009-05-15 2011-06-22 天津七一二通信广播有限公司 Method for preventing boats from colliding
CN102147981B (en) * 2010-12-20 2014-01-15 成都天奥信息科技有限公司 Method for warning of warning region of shipborne automatic identification system
CN102831787A (en) * 2012-07-30 2012-12-19 广东省公安边防总队 Quay berth-based intelligent supervision method and system
CN102890875B (en) * 2012-10-15 2015-04-15 浙江大学 Method for acquiring system collision risk of maritime intelligent transportation network
KR20150064909A (en) * 2013-12-04 2015-06-12 한국전자통신연구원 Apparatus and method for tracking vessel using ais target information
CN103714718B (en) * 2013-12-31 2016-01-13 武汉理工大学 A kind of inland river bridge area ship safe navigation precontrol system
CN104010167B (en) * 2014-06-16 2017-04-26 交通运输部天津水运工程科学研究所 Real-time virtual ship video displaying method for AIS data
CN104021700A (en) * 2014-06-16 2014-09-03 交通运输部天津水运工程科学研究所 Ship safety alarm device and method based on TETRA digital trunking system
CN104091470B (en) * 2014-07-15 2016-05-11 南京大学 A kind of navigation channel traffic information predicting method and application based on multi-data fusion
CN106251704A (en) * 2014-12-30 2016-12-21 江苏理工学院 Boats and ships trajectory predictions method

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1693826A1 (en) * 2003-08-29 2006-08-23 Microsoft Corporation Vocal tract resonance tracking using a nonlinear predictor and a target-guided temporal constraint
US20110273568A1 (en) * 2004-11-03 2011-11-10 Lagassey Paul J Modular intelligent transportation system
JP2010033352A (en) * 2008-07-29 2010-02-12 Toyota Central R&D Labs Inc Lane change alarm and program
WO2012012550A2 (en) * 2010-07-20 2012-01-26 The University Of Memphis Research Foundation Theft detection nodes and servers, methods of estimating an angle of a turn, methods of estimating a distance traveled between successive stops, and methods and servers for determining a path traveled by a node
US20120053944A1 (en) * 2010-08-31 2012-03-01 Cuneyt Oncel Tuzel Method for Determining Compressed State Sequences
US20120215735A1 (en) * 2011-02-18 2012-08-23 Larus Technologies Corporation System and Method for Data Fusion with Adaptive Learning
US20130080068A1 (en) * 2011-04-13 2013-03-28 The Board Of Trustees Of The Leland Stanford Junior University Phased Whole Genome Genetic Risk In A Family Quartet
CN102568200A (en) * 2011-12-21 2012-07-11 辽宁师范大学 Method for judging vehicle driving states in real time
CN103152253A (en) * 2013-01-17 2013-06-12 王少夫 Mining path prediction algorithm based on complex communication network channel data
CN103235933A (en) * 2013-04-15 2013-08-07 东南大学 Vehicle abnormal behavior detection method based on Hidden Markov Model
CN103336863A (en) * 2013-06-24 2013-10-02 北京航空航天大学 Radar flight path observation data-based flight intention recognition method
CN103413443A (en) * 2013-07-03 2013-11-27 太原理工大学 Short-term traffic flow forecasting method based on hidden Markov model
CN103473540A (en) * 2013-09-11 2013-12-25 天津工业大学 Vehicle track incremental modeling and on-line abnormity detection method of intelligent traffic system
CN103471589A (en) * 2013-09-25 2013-12-25 武汉大学 Method for identifying walking mode and tracing track of pedestrian in room

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
张彩虹: "隐马氏模型的建模及其应用", 《中国优秀博硕士学位论文全文数据库(硕士)基础科学辑》 *
李立言等: "一种基于小波降噪的GNSS轨迹平滑算法", 《电子技术应用》 *
柳长昕: "基于二维隐马尔科夫模型的离心泵故障诊断方法研究", 《中国优秀硕士学位论文全文数据库工程科技II辑》 *
桑凌志等: "基于航迹预测的实时船舶安全预警方法", 《中国安全科学学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110009936A (en) * 2019-03-15 2019-07-12 北京海兰信数据科技股份有限公司 A kind of ship auxiliary collision prevention method for crowded waters
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

Also Published As

Publication number Publication date
CN106228850A (en) 2016-12-14
CN104537891B (en) 2016-08-24
CN106251704A (en) 2016-12-21
CN104537891A (en) 2015-04-22

Similar Documents

Publication Publication Date Title
CN104537891B (en) A kind of boats and ships track real-time predicting method
CN104462856B (en) Ship conflict method for early warning
CN104484726B (en) Ship track real-time predicting method
CN104504277B (en) A kind of ship conflict method for early warning
CN107958269B (en) Driving risk degree prediction method based on hidden Markov model
CN105654139A (en) Real-time online multi-target tracking method adopting temporal dynamic appearance model
CN104504935A (en) Maritime traffic control method
CN103326903A (en) Hidden-Markov-based Internet network delay forecasting method
CN104504934B (en) A kind of navigation traffic control method
CN114022847A (en) Intelligent agent trajectory prediction method, system, equipment and storage medium
CN104050506A (en) Aircraft conflict detection method based on Spiking neural network
CN104049639A (en) Unmanned surface vehicle anti-surge control device and method based on support vector regression
CN106096324A (en) The power transmission and transformation main equipment load data disappearance returned based on k neighbour fills up algorithm
CN104485023B (en) Planning method for ship conflict release
CN108226887A (en) A kind of waterborne target rescue method for estimating state in the case of observed quantity transient loss
Liu et al. Ship route planning in the pirate area via hybrid probabilistic roadmap algorithm within the context of the Maritime Silk Road
Wang et al. Complex encounter situation modeling and prediction method for unmanned ships based on bounded rational game
CN112328651B (en) Traffic target identification method based on millimeter wave radar data statistical characteristics
CN116118772A (en) Uncertainty-considered automatic driving reinforcement learning movement planning method and system
CN109002860B (en) Intelligent adaptive matching prediction method for sudden change wind speed along high-speed railway
CN107545573A (en) A kind of underwater Forward-looking Sonar image partition method based on mode MRF random fields
CN117131940A (en) Situation reasoning method for unmanned surface vehicle
Luo et al. DYNAMIC COLLISION DETECTION OF UNMANNED SHIP BASED ON WIRELESS COMMUNICATION
Wang et al. Distributed model predictive control of inland ship platoon considering internal collision avoidance constraints
Xu et al. A hidden Markov model method for traffic incident detection using multiple features

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: No. 1801 Zhong Wu Avenue, Changzhou, Jiangsu Province, Jiangsu

Applicant after: Jiangsu University of Technology

Address before: 213001 1801 Zhong Wu Avenue, Zhong Lou District, Changzhou, Jiangsu

Applicant before: Jiangsu University of Technology

CB02 Change of applicant information
RJ01 Rejection of invention patent application after publication

Application publication date: 20161207

RJ01 Rejection of invention patent application after publication