CN112613677A - Method and device for generating airway network and computer storage medium - Google Patents

Method and device for generating airway network and computer storage medium Download PDF

Info

Publication number
CN112613677A
CN112613677A CN202011600738.3A CN202011600738A CN112613677A CN 112613677 A CN112613677 A CN 112613677A CN 202011600738 A CN202011600738 A CN 202011600738A CN 112613677 A CN112613677 A CN 112613677A
Authority
CN
China
Prior art keywords
track
points
ship
point
clustering
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
CN202011600738.3A
Other languages
Chinese (zh)
Inventor
周春辉
严钇
李成
谭林旭
张治豪
黄亮
文元桥
肖长诗
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.)
Wuhan University of Technology WUT
Original Assignee
Wuhan University of Technology WUT
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 Wuhan University of Technology WUT filed Critical Wuhan University of Technology WUT
Priority to CN202011600738.3A priority Critical patent/CN112613677A/en
Publication of CN112613677A publication Critical patent/CN112613677A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Evolutionary Biology (AREA)
  • Operations Research (AREA)
  • Evolutionary Computation (AREA)
  • Development Economics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Navigation (AREA)

Abstract

The invention relates to a method and a device for generating a marine route network and a computer storage medium, wherein the method comprises the following steps: acquiring ship tracks of all ships in a certain time period in an observation water area; extracting characteristic points in the ship track to generate a characteristic track; performing density clustering on each feature point to obtain a plurality of clustering clusters and corresponding clustering center points; replacing each characteristic point in the characteristic track with the waypoint of the corresponding clustering cluster by taking the clustering central point as the waypoint to generate the waypoint track; and sequentially connecting each route point in the route track to generate a route network. The invention constructs the airway network based on the ship track, and the construction precision is high.

Description

Method and device for generating airway network and computer storage medium
Technical Field
The present invention relates to the field of airway networks, and in particular, to a method and an apparatus for generating an offshore airway network, and a computer storage medium.
Background
The course is the main route of the ship, and usually, the track of the ship is gathered near the course. The airway network is a topological structure formed by each airway point and an airway, and the structural characteristics of the airway network are very concerned by practitioners.
The road network research is started in the road traffic field at the earliest and then expanded to the air traffic field and the water traffic field, and the basic logic of the road network research is to use traffic infrastructures such as stations, intersections, airports, ports and the like or special road sections as network nodes to construct a traffic network. The water traffic is greatly different from the road traffic and the air traffic, a navigation area of a ship in the water traffic has no boundary constraint, and besides ports, the water traffic has less infrastructure, so that a way of constructing a route network based on the infrastructure and a road section boundary is obviously not applicable, and a route network generation method is urgently needed.
Disclosure of Invention
In view of the above, it is desirable to provide a method, an apparatus and a computer storage medium for generating a marine route network, so as to solve the problems of few reference identifiers and difficult generation of the route network.
The invention provides a method for generating an offshore route network, which comprises the following steps:
acquiring ship tracks of all ships in a certain time period in an observation water area;
extracting characteristic points in the ship track to generate a characteristic track;
performing density clustering on each feature point to obtain a plurality of clustering clusters and corresponding clustering center points;
replacing each characteristic point in the characteristic track with the waypoint of the corresponding clustering cluster by taking the clustering central point as the waypoint to generate the waypoint track;
and sequentially connecting each route point in the route track to generate a route network.
Further, acquiring ship tracks of each ship in a certain time period of an observation water area specifically comprises:
acquiring AIS data of each ship in a certain time period in an observation water area, wherein the AIS data comprises static information and dynamic information, and the dynamic information comprises a ship position, a ship speed and a course;
and generating the ship track by combining the ship position, the ship speed and the course, and marking the ship tracks of different ships based on the static information.
Further, extracting feature points in the ship track to generate a feature track, specifically:
the feature points include three types: a start feature point, a dwell feature point, and a turning feature point;
extracting a track starting point and a track end point in the ship track as starting feature points;
extracting track points with the navigational speed smaller than a navigational speed threshold value in the ship track as stay characteristic points;
track points, of which the heading change value is greater than the change value threshold value and the heading change rate is greater than the change rate threshold value, in the ship track are extracted as steering characteristic points;
and (4) keeping the three types of characteristic points in the ship track, and deleting other track points to obtain the characteristic track.
Further, extracting track points in the ship track, of which the heading change value is greater than the change value threshold and the heading change rate is greater than the change rate threshold, as steering feature points, specifically:
calculating course change values and course change rates of all track points in the ship track:
Figure BDA0002869226800000021
Figure BDA0002869226800000022
wherein alpha isiIs the value of the change in the course direction,
Figure BDA0002869226800000023
representing points of track tri+1The value of the heading of (a) is,
Figure BDA0002869226800000024
representing points of track triThe value of the heading of (a) is,
Figure BDA0002869226800000025
representing points of track tri+1The time stamp of (a) is stored,
Figure BDA0002869226800000026
representing points of track triA timestamp of (d); beta is aiIndicating a heading rate of change;
and sequentially judging whether the course change value of each track point in the ship track is greater than the change value threshold value and the course change rate is greater than the change rate threshold value, and if so, setting the corresponding track point as a steering characteristic point.
Further, density clustering is performed on each feature point to obtain a plurality of cluster clusters and corresponding cluster center points, specifically:
and respectively carrying out density clustering on the three types of feature points to obtain a plurality of clustering clusters of each type of feature points and corresponding clustering center points.
Further, density clustering is performed on the three types of feature points respectively to obtain a plurality of cluster clusters and corresponding cluster center points of each type of feature points, specifically:
generating a corresponding feature point set by combining each type of feature points;
and performing density clustering on each type of feature point set by adopting a DBSCAN density clustering algorithm to obtain a plurality of clustering clusters of each type of feature point, and taking the average value point of all feature points in the clustering clusters as a clustering central point.
Further, taking the average value point of all the feature points in the cluster as a cluster center point specifically includes:
Figure BDA0002869226800000031
wherein, waypoint is the average value point, i.e. the cluster center point, LATjLongitude, LON, representing the jth feature point in a clusterjAnd representing the latitude of the jth characteristic point in the cluster, and N representing the number of the characteristic points in the cluster.
Further, the method also comprises the following steps:
and setting weights for corresponding route sections according to the connection times between two route points in the route network, and dividing route levels for each route section in the route network according to the weights to realize the classification of the route network.
The invention also provides a marine route network generation device, which comprises a processor and a memory, wherein the memory is stored with a computer program, and the computer program is executed by the processor to realize the marine route network generation method.
The present invention also provides a computer storage medium having stored thereon a computer program which, when executed by a processor, implements the marine route network generation method.
Has the advantages that: according to the method, the ship track in the observation water area is obtained, the characteristic points are extracted based on the ship track, the characteristic track is generated, the characteristic track describes the main characteristics of ship navigation, and compared with the ship track, the method is simplified, unnecessary track points are deleted, and the method is favorable for rapid and smooth implementation of a subsequent clustering process. And clustering the feature points after the feature points are extracted to obtain the route points, and generating a route network based on the route points. The invention excavates route points in the route network based on the analysis of the ship track, and the route network constructed based on the ship track can embody the main characteristics of observing the ship navigation in the water area.
Drawings
FIG. 1 is a flow chart of a method of a first embodiment of a method of generating a marine route network according to the present invention;
FIG. 2 is a schematic diagram of feature trajectory extraction of a first embodiment of a method for generating a marine route network according to the present invention;
FIG. 3 is a schematic diagram of a feature point clustering result of a first embodiment of a method for generating a marine route network according to the present invention;
fig. 4 is a schematic diagram of a route network classification result of the first embodiment of the method for generating the marine route network according to the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
Example 1
As shown in fig. 1, embodiment 1 of the present invention provides a method for generating a marine route network, including the steps of:
s1, acquiring ship tracks of each ship in a certain time period in an observation water area;
s2, extracting the characteristic points in the ship track to generate a characteristic track;
s3, performing density clustering on each feature point to obtain a plurality of clustering clusters and corresponding clustering center points;
s4, replacing each characteristic point in the characteristic track with the corresponding clustering waypoint by taking the clustering central point as the waypoint to generate the waypoint track;
and S5, sequentially connecting each route point in the route track to generate a route network.
The method for generating the marine route provided by the embodiment is different from a method for constructing a road network based on traffic facilities and road section boundaries in road traffic and air traffic, and is used for extracting route points based on characteristic points of ship tracks and constructing a marine route network based on a density clustering algorithm. Specifically, a ship track in an observation water area is obtained firstly, and a characteristic point is extracted based on the ship track to generate the characteristic track, wherein the characteristic track describes main characteristics of ship navigation, but is simpler compared with the ship track, unnecessary track points are deleted, and the method is favorable for quick and smooth implementation of a subsequent clustering process. And clustering the feature points after the feature points are extracted to obtain the route points, and generating a route network based on the route points.
The invention provides a ship track analysis method, which is used for mining route points in a route network based on ship track analysis.
Preferably, the method for acquiring the ship track of each ship in the observation water area within a certain time period specifically comprises the following steps:
acquiring AIS data of each ship in a certain time period in an observation water area, wherein the AIS data comprises static information and dynamic information, and the dynamic information comprises a ship position, a ship speed and a course;
and generating the ship track by combining the ship position, the ship speed and the course, and marking the ship tracks of different ships based on the static information.
An Automatic Identification System (AIS) for ships refers to a novel navigation aid System applied to marine safety and communication between ships and shore and between ships. The system is usually composed of a VHF communication machine, a GPS locator and a communication controller connected with a ship-borne display, a sensor and the like, and can automatically exchange important information such as ship position, navigational speed, course, ship name, call sign and the like. The AIS system on board receives the information of other ships in the coverage area of the VHF communicator while sending the information outwards, thereby realizing automatic response.
In this embodiment, the AIS data is provided by an AIS system on the ship, the AIS system may provide static information and dynamic information of the ship, the static information includes a ship name, an MMSI number, a ship type, a ship size, and the like, and the dynamic information of the ship includes a ship position, a ship speed, a course, and the like. According to the embodiment, the ship track is generated by utilizing the collected ship AIS data and is used for generating a subsequent airway network.
Preferably, the feature points in the ship track are extracted to generate a feature track, specifically:
the feature points include three types: a start feature point, a dwell feature point, and a turning feature point;
extracting a track starting point and a track end point in the ship track as starting feature points;
extracting track points with the navigational speed smaller than a navigational speed threshold value in the ship track as stay characteristic points;
track points, of which the heading change value is greater than the change value threshold value and the heading change rate is greater than the change rate threshold value, in the ship track are extracted as steering characteristic points;
and (4) keeping the three types of characteristic points in the ship track, and deleting other track points to obtain the characteristic track.
The purpose of extracting the characteristic points in the ship track is to simplify the ship track and form a simplified characteristic track. Therefore, the selection of the feature points requires the selection of the feature points capable of describing the ship track change features. In this embodiment, three types of feature points are selected to simplify the description of the ship track, which specifically includes:
initial characteristic points: a track starting point and a track ending point of each ship track;
the characteristic point of the stay: the stay characteristic points represent the behavior of the ship staying or stopping, generally occur at ports or anchor sites, and track points with low ship speed or stopping are set as the stay characteristic points;
turning characteristic points: and the steering points represent the behavior of changing the course of the ship, and when the ship course change value and the course change rate both exceed the corresponding threshold values, the corresponding ship track points are set as steering characteristic points.
And after the characteristic points are extracted, simplifying the ship track into the characteristic track only keeping the three types of characteristic points.
Specifically, in the present embodiment, the ship trajectory is denoted by TR ═ { TR ═ TR1,tr2,…,trM}，triRepresenting the ith track in the track of a shipAnd (3) tracing points, i is 1,2, …, and M is the number of the tracing points.
Starting point TR of ship track TR1And the track end point trMAnd adding the initial characteristic point set start _ end _ points { }.
Track points TR with navigational speed smaller than navigational speed threshold value in ship track TRstop＝{trstop1,trstop2,…,trstopAAdding the points into a stop feature point set stop _ points { }, trstopaThe number a of stay feature points is represented, where a is 1,2, …, and a is the number of stay feature points.
Calculating course change absolute values and course change rates of track points in the ship track TR, and simultaneously satisfying the condition that the course change absolute values are larger than a change value threshold value and the course change rates are larger than a change rate threshold value in the ship track TRturn＝{trturn1,trturn2,…,trturnBAdd to the set of turning feature points turn _ points { }, trturnbThe number B of the stopping feature points is represented, B is 1,2, …, and B is the number of turning feature points.
Three types of characteristic points are reserved according to the original sequence of the ship track, other track points are deleted, and a characteristic track TR is generatedfeature＝{tr1,trstop1,trstop2,…,trturn1,trturn2,…,trM}. The characteristic track TRfeatureAnd adding the middle feature points into the feature track set feature _ tr { } in sequence.
The characteristic track of a certain ship extracted in the embodiment is shown in fig. 2, black dots in fig. 2 represent track points, the track points are connected through a solid line to form a ship track, two initial characteristic points, a turning characteristic point and a stopping characteristic point are extracted from the track points, and the extracted characteristic points are connected to form a characteristic track shown by a dotted line in fig. 2.
Traversing each ship track, and sequentially extracting the characteristic points and the characteristic tracks of all the ship tracks by adopting the method. Adding the initial characteristic points of each ship track into an initial characteristic point set start _ end _ points { }; adding the stopping characteristic points of each ship track into a stopping characteristic point set stop _ points { }; and adding the steering characteristic points of each ship track into a steering characteristic point set turn _ points { }.
Preferably, the method for extracting the track points in the ship track, in which the heading change value is greater than the change value threshold and the heading change rate is greater than the change rate threshold, is as the steering feature points, and specifically comprises the following steps:
calculating course change values and course change rates of all track points in the ship track:
Figure BDA0002869226800000071
Figure BDA0002869226800000072
wherein alpha isiIs the value of the change in the course direction,
Figure BDA0002869226800000073
representing points of track tri+1The value of the heading of (a) is,
Figure BDA0002869226800000074
representing points of track triThe value of the heading of (a) is,
Figure BDA0002869226800000075
representing points of track tri+1The time stamp of (a) is stored,
Figure BDA0002869226800000076
representing points of track triA timestamp of (d); beta is aiIndicating a heading rate of change;
and sequentially judging whether the course change value of each track point in the ship track is greater than the change value threshold value and the course change rate is greater than the change rate threshold value, and if so, setting the corresponding track point as a steering characteristic point.
Preferably, density clustering is performed on each feature point to obtain a plurality of cluster clusters and corresponding cluster center points, specifically:
and respectively carrying out density clustering on the three types of feature points to obtain a plurality of clustering clusters of each type of feature point and corresponding clustering center points.
In this embodiment, three types of feature points are extracted, and thus density clustering of the three types of feature points is required. Density clustering is respectively carried out on an initial feature point set start _ end _ points { }, a stopping feature point set stop _ points { }, and a turning feature point set turn _ points { }, so as to obtain a plurality of clustering clusters of each type of feature points and corresponding clustering center points.
Preferably, density clustering is performed on the three types of feature points respectively to obtain a plurality of cluster clusters and corresponding cluster center points of each type of feature points, specifically:
generating a corresponding feature point set by combining each type of feature points;
and performing density clustering on each type of feature point set by adopting a DBSCAN density clustering algorithm to obtain a plurality of clustering clusters of each type of feature point, and taking the average value point of all feature points in the clustering clusters as a clustering central point.
In this embodiment, a DBSCAN density clustering algorithm is used to cluster feature points, and a clustering of an initial feature point set start _ end _ points { }istaken as an example to describe: firstly, setting clustering parameters: parameter radius of the neighborhood and minimum limiting density of the track points in the neighborhood, and manually selecting clustering parameters according to an observed water area; sequentially traversing initial feature points in an initial feature point set, calculating the point density in the neighborhood of each initial feature point, judging whether the point density is greater than the minimum limit density, if so, judging that the corresponding feature point is a core point, adding the core point into a core set, marking all feature points in the neighborhood of the core point as a cluster where the core point is located, and otherwise, judging that the corresponding feature point is a noise point; traversing other feature points except the core point in the clustering cluster, judging whether the feature point density in the neighborhood of the other feature points is greater than the minimum limit density, if so, judging that the corresponding feature point is the core point, updating the core point to the core set, and otherwise, judging that the corresponding feature point is a noise point; and judging whether all the characteristic points in the initial characteristic point set are marked or not, if so, deleting all the characteristic points marked as noise points to obtain a plurality of clustering clusters, and otherwise, judging and marking the next characteristic point. And obtaining a plurality of clustering clusters according to the clustering result, wherein the clustering center is the average value of all the characteristic points in the corresponding clustering cluster.
And clustering the stop feature point set stop _ points { } and the turning feature point set turn _ points { } in the same clustering mode as the start feature point set start _ end _ points { } to obtain a plurality of clustering clusters and clustering centers of the stop feature points and a plurality of clustering clusters and clustering centers of the turning feature points.
Preferably, the average value point of all the feature points in the cluster is used as a cluster center point, and specifically:
Figure BDA0002869226800000091
wherein, waypoint is the average value point, i.e. the cluster center point, LATjLongitude, LON, representing the jth feature point in a clusterjAnd representing the latitude of the jth characteristic point in the cluster, and N representing the number of the characteristic points in the cluster.
After the clustering process of the three types of feature points is finished, replacing each feature point in the clustering cluster with a corresponding clustering center point (namely, a waypoint), setting the clustering center point obtained by clustering as the waypoint, and finding out the waypoints corresponding to all the feature points according to the calculated corresponding relation between each clustering cluster and the clustering center point.
As shown in fig. 3, fig. 3 shows the clustering result of a class of feature points, and n clusters are obtained by clustering: cluster _1, Cluster _2, … and Cluster _ n, wherein each Cluster comprises a plurality of feature points, and the feature points in each Cluster are replaced by corresponding Cluster center points, for example: the characteristic point Cluster _1 in the Cluster Cluster _1 is set as { tr }1,tr2,…,trn1Replacing the Cluster center point waypoint _1 with n1 to represent the number of characteristic points in the Cluster _ 1; the characteristic point Cluster _ n in the Cluster _ n is set as { tr1,tr2,…,trnnIn the clusteringThe center point waypoint _ n is replaced.
And replacing the feature points in the feature track set feature _ tr { } with corresponding waypoints to generate a waypoint track waypoint _ tr { }.
Traversing each route track, connecting route points according to each route track sequence, and generating a route network, as shown in fig. 4, a hollow circle in fig. 4 represents a route point, and route points are connected through a solid line to form the route network.
Preferably, the method further comprises the following steps:
and setting weights for corresponding route sections according to the connection times between two route points in the route network, and dividing route levels for each route section in the route network according to the weights to realize the classification of the route network.
In order to distinguish and identify the ship navigation frequency of each route segment in the route network, the present embodiment classifies each route segment in the route network after the route network is generated, so as to form a more comprehensive and more accurate classified route network.
Specifically, the connection times between any two waypoints are calculated, if no waypoint is connected between the two waypoints, the connection times are marked as 0, the connection times are marked as 1 once, the connection times are marked as 2 twice, and the like; traversing all the waypoints, calculating the connection times between each waypoint and all other waypoints, and generating a connection matrix, which is shown in table 1:
TABLE 1 connection matrix
Figure BDA0002869226800000101
A connection matrix of 10 waypoints is shown in table 1, with the number of connections between each waypoint and itself being noted directly as 0.
The route section connecting the route points can be regarded as a main route for the ship to navigate between the two points, the times between the two route points are obtained according to the connection matrix, and the times are used as the weight of the route section connecting the two route points.
And dividing the airway into three levels of a main airway, a secondary airway and a branch, dividing each airway section into airways of different levels according to the weight, and finishing the classification of the airway network. For example: dividing the route section with the weight between 0 and 10 into branch roads, dividing the route section with the weight between 10 and 20 into secondary routes, and dividing the route with the weight above 20 into primary routes. The result of the ranking of the network of routes in this embodiment is shown in fig. 4, and as shown in fig. 4, the thickest solid line identifies the primary route, the second thickest solid line identifies the secondary route, and the finest implementation identifies the branch.
Example 2
Embodiment 2 of the present invention provides a marine route network generation device, including a processor and a memory, where the memory stores a computer program, and the computer program is executed by the processor to implement the marine route network generation method provided in embodiment 1.
The marine route network generation device provided by the embodiment of the invention is used for realizing the marine route network generation method, so that the marine route network generation method has the technical effects, and the marine route network generation device also has the technical effects, and the details are not repeated herein.
Example 3
Embodiment 3 of the present invention provides a computer storage medium having stored thereon a computer program that, when executed by a processor, implements the marine route network generation method provided in embodiment 1.
The computer storage medium provided by the embodiment of the invention is used for realizing the marine route network generation method, so that the technical effects of the marine route network generation method are also achieved by the computer storage medium, and the details are not repeated herein.
According to the ship track analysis method, the ship track analysis device and the computer storage medium, when the airway network is established, the ship track in a certain time period is acquired without the aid of infrastructure or special road sections in the airway, airway points in the airway network are analyzed and excavated based on the ship track, and then the airway network is established. The construction of the route network is based on ship estimation, so that the main characteristics of observing ship navigation in a water area can be reflected, and compared with the prior art, the method has the advantages of being dynamic, rapid and accurate.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.

Claims (10)

1. A method for generating a maritime route network is characterized by comprising the following steps:
acquiring ship tracks of all ships in a certain time period in an observation water area;
extracting characteristic points in the ship track to generate a characteristic track;
performing density clustering on each feature point to obtain a plurality of clustering clusters and corresponding clustering center points;
replacing each characteristic point in the characteristic track with the waypoint of the corresponding clustering cluster by taking the clustering central point as the waypoint to generate the waypoint track;
and sequentially connecting each route point in the route track to generate a route network.
2. The marine route network generation method of claim 1, wherein the acquiring of the ship track of each ship in a certain time period in an observation water area specifically comprises:
acquiring AIS data of each ship in a certain time period in an observation water area, wherein the AIS data comprises static information and dynamic information, and the dynamic information comprises a ship position, a ship speed and a course;
and generating the ship track by combining the ship position, the ship speed and the course, and marking the ship tracks of different ships based on the static information.
3. The marine route network generation method of claim 1, wherein the feature points in the ship trajectory are extracted to generate a feature trajectory, specifically:
the feature points include three types: a start feature point, a dwell feature point, and a turning feature point;
extracting a track starting point and a track end point in the ship track as starting feature points;
extracting track points with the navigational speed smaller than a navigational speed threshold value in the ship track as stay characteristic points;
track points, of which the heading change value is greater than the change value threshold value and the heading change rate is greater than the change rate threshold value, in the ship track are extracted as steering characteristic points;
and (4) keeping the three types of characteristic points in the ship track, and deleting other track points to obtain the characteristic track.
4. The marine route network generation method of claim 3, wherein track points in the ship track having a course change value greater than a change value threshold and a course change rate greater than a change rate threshold are extracted as turning feature points, specifically:
calculating course change values and course change rates of all track points in the ship track:
Figure FDA0002869226790000021
Figure FDA0002869226790000022
wherein alpha isiIs the value of the change in the course direction,
Figure FDA0002869226790000023
representing points of track tri+1The value of the heading of (a) is,
Figure FDA0002869226790000024
representing points of track triThe value of the heading of (a) is,
Figure FDA0002869226790000025
representing points of track tri+1The time stamp of (a) is stored,
Figure FDA0002869226790000026
representing points of track triA timestamp of (d); beta is aiIndicating a heading rate of change;
and sequentially judging whether the course change value of each track point in the ship track is greater than the change value threshold value and the course change rate is greater than the change rate threshold value, and if so, setting the corresponding track point as a steering characteristic point.
5. The maritime route network generation method according to claim 3, wherein density clustering is performed on each feature point to obtain a plurality of cluster clusters and corresponding cluster center points, specifically:
and respectively carrying out density clustering on the three types of feature points to obtain a plurality of clustering clusters of each type of feature points and corresponding clustering center points.
6. The maritime route network generation method according to claim 5, wherein density clustering is performed on the three types of feature points respectively to obtain a plurality of cluster clusters and corresponding cluster center points of each type of feature points, specifically:
generating a corresponding feature point set by combining each type of feature points;
and performing density clustering on each type of feature point set by adopting a DBSCAN density clustering algorithm to obtain a plurality of clustering clusters of each type of feature point, and taking the average value point of all feature points in the clustering clusters as a clustering central point.
7. The maritime route network generation method according to claim 6, wherein the average value point of all the feature points in the cluster is used as a cluster center point, and specifically comprises:
Figure FDA0002869226790000027
wherein, waypoint is the average value point, i.e. the cluster center point, LATjLongitude, LON, representing the jth feature point in a clusterjAnd representing the latitude of the jth characteristic point in the cluster, and N representing the number of the characteristic points in the cluster.
8. The marine route network generation method of claim 1, further comprising:
and setting weights for corresponding route sections according to the connection times between two route points in the route network, and dividing route levels for each route section in the route network according to the weights to realize the classification of the route network.
9. An offshore route network generation apparatus comprising a processor and a memory, the memory having stored thereon a computer program which, when executed by the processor, implements the offshore route network generation method of any one of claims 1-8.
10. A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a maritime route network generation method according to any one of claims 1-8.
CN202011600738.3A 2020-12-29 2020-12-29 Method and device for generating airway network and computer storage medium Pending CN112613677A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011600738.3A CN112613677A (en) 2020-12-29 2020-12-29 Method and device for generating airway network and computer storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011600738.3A CN112613677A (en) 2020-12-29 2020-12-29 Method and device for generating airway network and computer storage medium

Publications (1)

Publication Number Publication Date
CN112613677A true CN112613677A (en) 2021-04-06

Family

ID=75249020

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011600738.3A Pending CN112613677A (en) 2020-12-29 2020-12-29 Method and device for generating airway network and computer storage medium

Country Status (1)

Country Link
CN (1) CN112613677A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113553682A (en) * 2021-07-12 2021-10-26 大连海事大学 Data-driven multi-level ship route network construction method
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
CN117391543A (en) * 2023-12-07 2024-01-12 武汉理工大学 Method and system for evaluating quality of offshore route network generated by track data
CN117931980A (en) * 2024-03-25 2024-04-26 深圳大学 LNG ship transportation network construction method, system and terminal

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108680163A (en) * 2018-04-25 2018-10-19 武汉理工大学 A kind of unmanned boat route search system and method based on topological map
CN109447880A (en) * 2018-10-10 2019-03-08 广州市勤思网络科技有限公司 Road network abstracting method waterborne and system
CN109543715A (en) * 2018-10-23 2019-03-29 武汉理工大学 A kind of ship air route is extracted and the method for track deviation detection
CN109708638A (en) * 2018-12-03 2019-05-03 江苏科技大学 A kind of ship track point extracting method
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

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108680163A (en) * 2018-04-25 2018-10-19 武汉理工大学 A kind of unmanned boat route search system and method based on topological map
CN109447880A (en) * 2018-10-10 2019-03-08 广州市勤思网络科技有限公司 Road network abstracting method waterborne and system
CN109543715A (en) * 2018-10-23 2019-03-29 武汉理工大学 A kind of ship air route is extracted and the method for track deviation detection
CN109708638A (en) * 2018-12-03 2019-05-03 江苏科技大学 A kind of ship track point extracting method
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

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
中国物流与采购联合会 等: "《中国物流重点课题评估》", 30 September 2009 *
李慧 等: "港口水域船舶航路网络复杂度", 《中国航海》 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113553682A (en) * 2021-07-12 2021-10-26 大连海事大学 Data-driven multi-level ship route network construction method
CN113553682B (en) * 2021-07-12 2022-09-06 大连海事大学 Data-driven multi-level ship route network construction method
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
CN114063126B (en) * 2021-11-15 2022-07-29 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
CN117391543A (en) * 2023-12-07 2024-01-12 武汉理工大学 Method and system for evaluating quality of offshore route network generated by track data
CN117391543B (en) * 2023-12-07 2024-03-15 武汉理工大学 Method and system for evaluating quality of offshore route network generated by track data
CN117931980A (en) * 2024-03-25 2024-04-26 深圳大学 LNG ship transportation network construction method, system and terminal
CN117931980B (en) * 2024-03-25 2024-07-09 深圳大学 LNG ship transportation network construction method, system and terminal

Similar Documents

Publication Publication Date Title
CN112613677A (en) Method and device for generating airway network and computer storage medium
CN108763558B (en) Crowdsourcing map road quality improvement method based on map matching
JP3481168B2 (en) Digital map location information transmission method
US20060007022A1 (en) Geographic data transmitting method, information delivering apparatus and information terminal
EP1172632B1 (en) Server, method and program for updating road information in map information providing system, and recording medium with program recorded
US5519619A (en) Route planning method for hierarchical map routing and apparatus therefor
DE602004012364T2 (en) Guidance device, system and method
EP1783723A2 (en) Road area extracting apparatus for extracting a road area from a block map, deformed map automatic generation system for generating a deformed map from road area data obtained by the road area extracting apparatus, map information providing system, geographical information providing system and geographical information describing method
US20040212627A1 (en) Map data transmitting method, map data transmitting apparatus, information device and map data transmitting system
KR20080072668A (en) Schematic destination maps
US9069655B2 (en) On-vehicle apparatus, and method and computer program for transmitting positional information
CN112213113B (en) Method for selecting and planning actual road test scene of intelligent driving mobile device
CN105628044A (en) Vehicle-mounted navigating device based on position real-time updating and road section attributes and navigating method
EP2659227B1 (en) Incremental network generation providing seamless network
CN114637305B (en) Unmanned aerial vehicle shortest path planning method and device
JP2000046567A (en) Method and device for navigation and record medium where same method is recorded
US10949682B2 (en) Method for ascertaining a piece of topological information of an intersection
KR20190107252A (en) A System of Providing Theme Travel AI Curation Based on AR through Customization Learning of Virtual Character
JP4578553B2 (en) Route guidance device, route guidance method, route guidance program, and recording medium
JP2009031073A (en) Navigation system, route searching server, terminal device, and route guiding method
JP2008039488A (en) Route searching system, road data generator, route searching data and program and route searching method for server apparatus
JP2006071627A (en) Positional information transmitter, positional information receiver, positional information transmitting method, and positional information transmission program
JP2005147982A (en) Map-matching method and system for conducting the same
JP2005249654A (en) Navigation system
Chao A Study on map-matching and map inference problems

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20210406

RJ01 Rejection of invention patent application after publication