CN112164247A - Ship route prediction method based on ship track clustering - Google Patents
Ship route prediction method based on ship track clustering Download PDFInfo
- Publication number
- CN112164247A CN112164247A CN202010914709.8A CN202010914709A CN112164247A CN 112164247 A CN112164247 A CN 112164247A CN 202010914709 A CN202010914709 A CN 202010914709A CN 112164247 A CN112164247 A CN 112164247A
- Authority
- CN
- China
- Prior art keywords
- ship
- track
- historical
- clustering
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G3/00—Traffic control systems for marine craft
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Ocean & Marine Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of Yangtze river digital navigation channels, and provides a ship route prediction method based on ship track clustering, so that the accuracy of ship route prediction is improved, and the method comprises the following steps: acquiring ship track data of a target ship in the channel, and preprocessing missing values, abnormal values and data formats in the ship track data to obtain a high-quality historical course data set of the ship; clustering the historical routes of the predicted ship, extracting typical characteristic routes of the ship navigating in the control river reach, matching the current track of the ship with the characteristic routes, predicting the routes selected by the ship through the control river reach, and calculating the passing time of the ship based on the predicted routes.
Description
Technical Field
The invention relates to the technical field of Yangtze river digital navigation channels, in particular to a ship route prediction method.
Background
The main area influencing the passing safety and passing efficiency of ships is the river control section in the Yangtze river channel. Because the river reach beach is controlled to be in a high water emergency and to be bent and narrow, the current signal station is mainly used for commanding the ship to pass in sequence and automatically receiving AIS signals through a manual command or an intelligent auxiliary command system for controlling the river reach ship to pass, the ship navigation dynamics is known in real time, and the ship passing sequence can be judged based on a first-come first-serve principle. The accuracy of the prediction of the passing time can be improved by improving the accuracy of the prediction of the ship route, so that the safe, efficient and orderly passing of the ship through the controlled river reach is ensured, and the traffic capacity of the Yangtze river is improved.
At present, a command system assumes that all ships pass through a control river reach at a constant speed to the ground in real time by taking a fixed route as a starting point along a center line of a channel. In practice, however, when the ship passes through the controlled river reach, a proper route is selected according to the characteristics of the ship and the channel environment, and the ship cannot advance along the fixed route.
At present, two methods are mainly used for predicting and researching ship tracks: the first method is to predict the course of the ship based on the current trajectory of the ship. The basic research idea of the method is to realize the purpose of predicting the ship route by fitting the current track of the ship based on the current track of the ship. The prediction precision of the method at the next position point is very high, however, the prediction precision can be rapidly reduced along with the increase of the number of the predicted track points, and the requirement of controlling the great number of the track points predicted by the river course air route cannot be met.
The second method is to match the current track of the ship with the historical course of the ship. The method is characterized in that the research idea is to analyze the typical characteristics of the ship during historical navigation, the current navigation characteristics of the ship are matched with the historical navigation characteristics, and the matching schemes are two: the first solution is to build a database of historical routes for the vessel. The patent-ship point-to-point voyage time estimation method based on course matching screens out alternative courses to be matched according to current course characteristics of a target ship, matches current tracks of the ship with the alternative courses one by one, and selects a course most similar to a target predicted ship as a possible course selected by the target predicted ship. After the method is successfully matched, the prediction precision is high, however, if the number of the selected alternative routes is very large, a long matching time is needed. Therefore, the method generally requires higher time cost and has poorer real-time performance. The second scheme is that firstly, historical routes of the ship are divided into a plurality of categories by a track clustering method, and the possible selected routes of the ship are predicted by predicting the possible selected categories of the ship. The method has better prediction effect and better efficiency than the first scheme, but aims at the clustering of all ship historical tracks, and does not consider the actual conditions of the target ship speed and the like during clustering.
In conclusion, the accuracy of forecasting the ship route of the controlled river reach can be improved, and the selection of the method is particularly important. Therefore, it is practical and important to cluster the historical track of a specific selected ship or the historical tracks of ships similar to the specific selected ship and find the course of the ship by matching.
Disclosure of Invention
In view of the above, the invention provides a method for predicting a ship route of a controlled river reach based on ship track clustering, which can effectively improve the accuracy of predicting the ship route of the controlled river reach.
The invention adopts the following technical scheme to solve the technical problems:
the method for predicting the ship route of the controlled river reach based on the ship route track clustering comprises the following steps:
1) detecting whether a ship enters a matching area through AIS and/or radar;
2) when a ship is detected to enter a matching area, screening out a historical track of the ship on the channel, which is required by clustering, through processing track data points according to past historical data of the ship in a historical database;
3) dividing the selected historical track of the ship into a plurality of spaces;
4) automatically clustering the historical tracks of the ship in the interval, classifying and integrating the results to realize the clustering of the whole historical track of the ship, and extracting the characteristic track of each type of historical track in the matching area;
5) and matching the current sailing track of the ship in the matching area with the extracted characteristic track in the matching area to realize the prediction of the course of the target prediction ship.
Further, in the step 1), the channel is divided into two areas, namely a control river reach and a matching area.
Further, in the step 2), missing values, abnormal values and data formats in the ship track data are preprocessed to obtain a high-quality ship historical track data set, so that reliable data support is provided for ship track clustering. The historical data is the historical data of a specific ship passing through the control river reach.
Further, if the database does not have the ship historical data in the step 2), selecting a historical track similar to the type, the length, the width and the load characteristics of the target prediction ship.
Further, in the step 3), in the area dividing process, firstly, the obvious merging and separating point in the ship historical track is taken as a dividing point, and then the divided areas are divided averagely
Further, an improved Hausdorff (Hausdorff) distance is adopted for calculating the similarity distance during track clustering in the step 4), and a position distance factor between track points, an actual navigational speed information factor and a time period water level factor are considered.
Further, the step 5) comprises the matching of the current sailing track of the ship and the characteristic track in the matching area, and the similarity of the ship track is measured, so that the possible selected air route of the ship passing through the control river reach is selected.
According to the method for predicting the ship route of the controlled river reach based on the ship track clustering, the current route track of the appointed ship is matched with the characteristic route track which is clustered and extracted after the historical route is extracted, so that the problems of low prediction precision, long matching time and the like are effectively solved, and the prediction accuracy can be greatly improved compared with the existing scheme. The invention is applied to a certain control river reach, can improve the traffic command efficiency, more efficiently and accurately complete the traffic command, and has wide market space and application prospect.
Drawings
FIG. 1 shows a flow chart of a ship course prediction method based on ship track clustering;
FIG. 2 is a schematic diagram illustrating track matching in a ship course prediction method based on ship track clustering;
FIG. 3 shows a flowchart of a ship matching method in a ship route prediction method based on ship track clustering.
Detailed Description
The invention is described in detail below with reference to the accompanying drawings:
referring to fig. 1: the ship route prediction method based on ship track clustering comprises the following steps:
1) referring to fig. 2, a certain channel is divided into two areas, one area is a control river reach from an upper boundary marker to a lower boundary marker, and the other area is a matching area outside the upper boundary marker or the lower boundary marker. Whether a ship enters a matching area is detected through AIS and/or radar.
2) And when a certain searched ship enters the matching area, screening the control river reach required by clustering and the ship historical track of the matching area by processing track data points according to past historical data of the ship in a historical database. The method selects the historical track of the target prediction ship based on the MMSI or selects the historical track of the ship with the characteristics similar to the type, the length, the width and the load of the target prediction ship.
3) The invention divides the screened ship historical track into a plurality of intervals by adopting a region division method, thereby realizing the segmentation of the whole track. In the process of area division, the obvious merging and separating points in the ship historical track are used as dividing points, and then the divided areas are divided evenly.
4) And segmenting the screened historical track of the ship to obtain a plurality of intervals. Clustering the historical tracks of the ship in the interval: firstly, clustering the historical track of the ship in each interval by using an improved density-based clustering algorithm (DBSCAN), then obtaining an optimal parameter combination of the improved density-based clustering algorithm (DBSCAN) by using a wolf optimization algorithm (GWO), and finally storing the track clustering result of the ship route in each interval.
After classifying and integrating the clustering result of each interval, clustering the whole historical track of the ship: firstly, acquiring a track clustering label sequence of each track on each interval, then classifying the whole tracks with consistent track clustering sequences on each interval into one class, and finally adding a class label to each class of divided tracks.
If a certain target predicts that the ship history has m tracks through the control river reach. The historical track of the ship is divided into 3 intervals according to a ship track segmentation method. The ship tracks in the first interval are divided into 2 types through an improved DBSCAN clustering algorithm, and track type labels are 1 and 2. The ship tracks in the second interval are classified into 3 types, and the track type labels are 3, 4 and 5. The ship tracks in the third interval are classified into 3 types, and the track type labels are 6, 7 and 8. Each of the m ship history tracks has 3 categories, such as Tra1 ═ 2,3,6, which indicates that the track Tra1 belongs to the track cluster 2 in the first interval, belongs to the track cluster 3 in the second interval, and belongs to the track cluster 6 in the third interval. If Tra is {2,3,6}, Tra1 and Tra are considered to belong to the same type of route, and have relatively high similarity. The results of clustering the m ship historical tracks based on this rule are shown in table 1.
TABLE 1 clustering results of historical trajectories of m ships
Extracting the characteristic tracks of each type of historical tracks of the ship in the matching area: and respectively calculating the average value of the similarity distance from each track in each class to other tracks in the class, and selecting the track with the minimum similarity distance average value as a characteristic track capable of representing the navigation characteristic of the class of tracks to the maximum extent.
5) Referring to fig. 3, the current sailing track of the ship in the matching area is matched with the extracted characteristic track in the matching area to realize target prediction
Such as: the characteristic track extracted after clustering the historical track of a certain ship is shown in figure 2, and the characteristic track is divided into two areas, namely a control river reach and a matching area in figure 2. The matching area is used for realizing the matching of the current sailing track and the characteristic track of the ship, and the control river reach area is used for forecasting the passing time of the ship. Assuming that there are 3 extracted characteristic tracks of the target prediction ship, the ship track matching steps are as follows: firstly, acquiring a navigation track s1 of a target ship in a matching area; acquiring navigation tracks s2, s3 and s4 of the 3 characteristic tracks in the matching area; calculating s1 and s2 respectively; s 3; s4, similarity distance d 1; d2, d3, the distance is calculated by adopting an improved Hausdorff distance; finding out possible selected routes of the ship passing through the controlled river reach according to the calculated d1, d2 and d 3. The method for selecting the middle route comprises the following steps: a. firstly, finding out the minimum similarity distance among d1, d2 and d3, and then calculating the difference value x between the minimum distance and other similarity distances; b. extracting a characteristic track corresponding to the difference value of less than 0.2; c. if only one extracted characteristic track exists, the fact that only the characteristic track in the characteristic tracks has higher similarity with the current track of the target ship is shown, and the probability that the target ship selects the track as the air route passing through the control river reach is very high. And then directly determining the characteristic track as a route selected by the target ship through the control river reach. If the similarity distance between the current sailing track of the target ship and the characteristic track 3 in the map in the matching area is minimum, and the difference between d3 and d1 and d2 is large, determining the characteristic track 3 as a course of the target ship passing through the control river reach; d. if there are a plurality of extracted characteristic tracks, it is indicated that these characteristic tracks may become routes selected when the target ship passes through the control river reach, and then the probability that the target prediction ship selects different characteristic tracks should be calculated. Assuming that the calculated track similarity is the smallest d1, the target ship is considered to be possible to select the characteristic track 2 to pass through the control river reach due to the very small distance difference between d1 and d 2. The probability calculation method for selecting different characteristic tracks by the target ship comprises the following steps: assuming that m tracks exist in the category to which the characteristic track 1 belongs and n tracks exist in the category to which the characteristic track 2 belongs, the probability that the target selects the characteristic track 1 is m/m + n, and the probability that the ship selects the characteristic track 2 is n/m + n.
Finally, it should be noted that the above examples are intended to illustrate the method of the present invention and are not intended to limit the same, as will be understood by those skilled in the art. Any modification, equivalent replacement, etc. made within the spirit and principle of the present invention should be covered within the protection scope of the present invention.
Claims (6)
1. A ship route prediction method based on ship track clustering is characterized by comprising the following steps: the method comprises the following steps:
1) detecting whether a ship enters a matching area through AIS and/or radar;
2) when a ship entering a matching area is detected, screening out the control river reach required by clustering and the ship historical track of the matching area through processing track data points according to past historical data of the ship in a historical database;
3) dividing the selected historical track of the ship into a plurality of spaces;
4) classifying and integrating results after the historical tracks of the ship are clustered in the interval, realizing the clustering of the whole historical track of the ship, and extracting the characteristic track in a matching area in each type of historical track;
5) and matching the current sailing track of the ship in the matching area with the extracted characteristic track in the matching area to realize the prediction of the course of the target prediction ship.
2. The vessel course prediction method based on vessel trajectory clustering of claim 1, characterized in that: the step 1) divides the channel into two areas of a control river reach and a matching area.
3. The vessel course prediction method based on vessel trajectory clustering of claim 1, characterized in that: missing values, abnormal values and data formats in the ship track data contained in the step 2) are preprocessed to obtain a high-quality ship historical track data set, and reliable data support is provided for ship track clustering. The historical data is past historical data of a specific ship passing through the control river reach. And 2) if the database does not have the ship historical data, selecting a historical track similar to the type, the length, the width and the load characteristics of the target prediction ship.
4. The vessel course prediction method based on vessel trajectory clustering of claim 1, characterized in that: in the step 3), in the process of area division, firstly, the obvious merging and separating point in the ship historical track is taken as a dividing point, and then the divided areas are divided averagely.
5. The vessel course prediction method based on vessel trajectory clustering of claim 1, characterized in that: and 4) calculating the historical track similarity distance of the ship during track clustering in the step 4), and considering the position distance factor between track points, the actual navigational speed information factor and the time period water level factor.
6. The vessel course prediction method based on vessel trajectory clustering of claim 1, characterized in that: and step 5) comprises the matching of the current sailing track of the ship and the characteristic track in the matching area, and measuring the similarity of the ship tracks, thereby selecting the possible selected route of the ship passing through the channel.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010914709.8A CN112164247A (en) | 2020-09-03 | 2020-09-03 | Ship route prediction method based on ship track clustering |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010914709.8A CN112164247A (en) | 2020-09-03 | 2020-09-03 | Ship route prediction method based on ship track clustering |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112164247A true CN112164247A (en) | 2021-01-01 |
Family
ID=73859155
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010914709.8A Pending CN112164247A (en) | 2020-09-03 | 2020-09-03 | Ship route prediction method based on ship track clustering |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112164247A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112906858A (en) * | 2021-01-26 | 2021-06-04 | 武汉工程大学 | Real-time prediction method for ship motion trail |
CN113312438A (en) * | 2021-03-09 | 2021-08-27 | 中南大学 | Sea target position prediction method integrating airline extraction and trend judgment |
CN113534126A (en) * | 2021-07-07 | 2021-10-22 | 中船重工鹏力(南京)大气海洋信息系统有限公司 | Radar-based method for judging contra-movement violation of ship in intersection water area |
CN113689739A (en) * | 2021-08-24 | 2021-11-23 | 重庆大学 | Historical data-based judgment method for controlling river reach ship to enter or exit water |
CN114063126A (en) * | 2021-11-15 | 2022-02-18 | 广州一链通互联网科技有限公司 | Electronic fence system and method for establishing electronic fence accurate track model |
CN114117637A (en) * | 2021-11-26 | 2022-03-01 | 江苏科技大学 | Ship segmented coating process design method based on improved DBSCAN and decision tree |
CN115618251A (en) * | 2022-11-03 | 2023-01-17 | 中国科学院空天信息创新研究院 | Ship trajectory prediction method, ship trajectory prediction device, electronic equipment and storage medium |
WO2023150833A1 (en) * | 2022-02-11 | 2023-08-17 | Wisetech Global Limited | Vessel movement prediction |
CN116774710A (en) * | 2023-08-09 | 2023-09-19 | 山东经纬海通海洋科技有限公司 | Ship track optimization method based on artificial intelligence and marine environment |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103531043A (en) * | 2013-09-27 | 2014-01-22 | 重庆大学 | Point-to-point ship sailing time estimation method based on ship route matching |
CN104008674A (en) * | 2014-06-16 | 2014-08-27 | 中国民航大学 | Terminal area approach flight time forecasting method based on pattern matching |
CN104899263A (en) * | 2015-05-22 | 2015-09-09 | 华中师范大学 | Ship trajectory mining, analysis and monitoring method based on specific region |
CN109840358A (en) * | 2019-01-09 | 2019-06-04 | 上海海洋大学 | A kind of track segmentation method based on track time-domain difference |
CN110210352A (en) * | 2019-05-23 | 2019-09-06 | 中国人民解放军海军工程大学 | Ship track method for detecting abnormality based on navigation channel model |
CN111291149A (en) * | 2020-02-28 | 2020-06-16 | 中国人民解放军国防科技大学 | Ship AIS space-time trajectory segmentation and mode extraction method based on course deviation |
CN111401668A (en) * | 2020-06-05 | 2020-07-10 | 江苏海事职业技术学院 | Unmanned ship route planning method based on big data |
CN111582380A (en) * | 2020-05-09 | 2020-08-25 | 中国人民解放军92493部队试验训练总体研究所 | Ship track density clustering method and device based on space-time characteristics |
-
2020
- 2020-09-03 CN CN202010914709.8A patent/CN112164247A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103531043A (en) * | 2013-09-27 | 2014-01-22 | 重庆大学 | Point-to-point ship sailing time estimation method based on ship route matching |
CN104008674A (en) * | 2014-06-16 | 2014-08-27 | 中国民航大学 | Terminal area approach flight time forecasting method based on pattern matching |
CN104899263A (en) * | 2015-05-22 | 2015-09-09 | 华中师范大学 | Ship trajectory mining, analysis and monitoring method based on specific region |
CN109840358A (en) * | 2019-01-09 | 2019-06-04 | 上海海洋大学 | A kind of track segmentation method based on track time-domain difference |
CN110210352A (en) * | 2019-05-23 | 2019-09-06 | 中国人民解放军海军工程大学 | Ship track method for detecting abnormality based on navigation channel model |
CN111291149A (en) * | 2020-02-28 | 2020-06-16 | 中国人民解放军国防科技大学 | Ship AIS space-time trajectory segmentation and mode extraction method based on course deviation |
CN111582380A (en) * | 2020-05-09 | 2020-08-25 | 中国人民解放军92493部队试验训练总体研究所 | Ship track density clustering method and device based on space-time characteristics |
CN111401668A (en) * | 2020-06-05 | 2020-07-10 | 江苏海事职业技术学院 | Unmanned ship route planning method based on big data |
Non-Patent Citations (4)
Title |
---|
梁山: "基于改进卡尔曼滤波的控制河段船舶航迹预测", 《计算机应用》 * |
罗永豪: "基于AIS数据的船舶航行轨迹预测", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
靳晓雨: "船舶轨迹的分析与预测方法", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
高永胜: "基于数据挖掘的4D航迹预测方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112906858A (en) * | 2021-01-26 | 2021-06-04 | 武汉工程大学 | Real-time prediction method for ship motion trail |
CN113312438A (en) * | 2021-03-09 | 2021-08-27 | 中南大学 | Sea target position prediction method integrating airline extraction and trend judgment |
CN113312438B (en) * | 2021-03-09 | 2023-09-15 | 中南大学 | Marine target position prediction method integrating route extraction and trend judgment |
CN113534126B (en) * | 2021-07-07 | 2023-10-24 | 中船重工鹏力(南京)大气海洋信息系统有限公司 | Radar-based method for determining reverse traffic violation of ship in intersection water area |
CN113534126A (en) * | 2021-07-07 | 2021-10-22 | 中船重工鹏力(南京)大气海洋信息系统有限公司 | Radar-based method for judging contra-movement violation of ship in intersection water area |
CN113689739A (en) * | 2021-08-24 | 2021-11-23 | 重庆大学 | Historical data-based judgment method for controlling river reach ship to enter or exit water |
CN114063126A (en) * | 2021-11-15 | 2022-02-18 | 广州一链通互联网科技有限公司 | Electronic fence system and method for establishing electronic fence accurate track model |
CN114117637A (en) * | 2021-11-26 | 2022-03-01 | 江苏科技大学 | Ship segmented coating process design method based on improved DBSCAN and decision tree |
WO2023150833A1 (en) * | 2022-02-11 | 2023-08-17 | Wisetech Global Limited | Vessel movement prediction |
CN115618251A (en) * | 2022-11-03 | 2023-01-17 | 中国科学院空天信息创新研究院 | Ship trajectory prediction method, ship trajectory prediction device, electronic equipment and storage medium |
CN115618251B (en) * | 2022-11-03 | 2024-02-06 | 中国科学院空天信息创新研究院 | Ship track prediction method and device, electronic equipment and storage medium |
CN116774710A (en) * | 2023-08-09 | 2023-09-19 | 山东经纬海通海洋科技有限公司 | Ship track optimization method based on artificial intelligence and marine environment |
CN116774710B (en) * | 2023-08-09 | 2024-03-01 | 山东经纬海通海洋科技有限公司 | Ship track optimization method based on artificial intelligence and marine environment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112164247A (en) | Ship route prediction method based on ship track clustering | |
CN104899263B (en) | A kind of ship track mining analysis and monitoring method based on specific region | |
US11719543B2 (en) | Course guidance method for efficient sailing of ship | |
CN107766808B (en) | Method and system for clustering moving tracks of vehicle objects in road network space | |
EP2255347B1 (en) | Travel pattern information obtaining device, travel pattern information obtaining method, travel pattern information obtaining program and computer readable medium | |
CN111582380B (en) | Ship track density clustering method and device based on space-time characteristics | |
CN114066354B (en) | Intelligent route recommendation method and system based on global ship historical track | |
CN108961758B (en) | Road junction widening lane detection method based on gradient lifting decision tree | |
CN113537386B (en) | Ship typical motion trail self-adaptive mining method based on improved K-Medoids clustering | |
CN112862156B (en) | Ship path planning method based on ship track and ant colony algorithm | |
CN105788273A (en) | Urban intersection automatic identification method based on low precision space-time trajectory data | |
CN110196962A (en) | A kind of air speed abnormality recognition method based on Density Estimator | |
Virjonen et al. | Ship movement prediction using k-NN method | |
CN105893621B (en) | Goal behavior law mining method based on multidimensional track cluster | |
CN112487116A (en) | Ship track analysis method based on AIS big data | |
CN110598917B (en) | Destination prediction method, system and storage medium based on path track | |
CN111640304B (en) | Automatic quantitative extraction method for traffic jam propagation characteristics of continuous flow traffic facility | |
CN115050214A (en) | Ship collision risk prediction method based on AIS data | |
CN116978259B (en) | Ship navigation track prediction method, device and storage medium | |
CN113962283A (en) | Aircraft trajectory clustering method based on local self-adaptive dynamic time warping | |
Pu et al. | Road intersection detection based on direction ratio statistics analysis | |
CN113934803A (en) | Ship accompanying mode mining method based on space-time subdivision | |
CN117131394A (en) | Ship track clustering method and equipment based on AIS data and storage equipment | |
CN116524230A (en) | Ship type classification and identification method based on priori knowledge base | |
KR102429235B1 (en) | System and method for predicting maritime traffic congestion |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210101 |
|
WD01 | Invention patent application deemed withdrawn after publication |