CN115270920A - Ship target classical trajectory generation method based on density space clustering - Google Patents
Ship target classical trajectory generation method based on density space clustering Download PDFInfo
- Publication number
- CN115270920A CN115270920A CN202210706104.9A CN202210706104A CN115270920A CN 115270920 A CN115270920 A CN 115270920A CN 202210706104 A CN202210706104 A CN 202210706104A CN 115270920 A CN115270920 A CN 115270920A
- Authority
- CN
- China
- Prior art keywords
- space block
- point
- target
- points
- track
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The invention provides a ship target classical trajectory generation method based on density space clustering, which specifically comprises the following steps: step 1, initializing cluster analysis of ship target activity tracks; step 2, generating a target frequent activity area; and 3, generating a ship target classical track, and meanwhile, providing a ship target classical track generation system based on density spatial clustering. By utilizing the method and the system, the track association quality measurement evaluation and the large-density track data processing means based on the big data are introduced, and the original algorithm is modified, so that the track association quality is used as the judgment condition of the track association, and the track association is rapidly and accurately carried out.
Description
Technical Field
The invention relates to the field of machine learning, in particular to a ship target classical trajectory generation method based on density space clustering.
Background
DBSCAN (Density-Based Spatial Clustering of applications with noise) is a Density-Based Spatial Clustering algorithm, can find clusters of any shape, and has the capability of resisting noise. The algorithm divides the area with sufficient density into clusters and finds arbitrarily shaped clusters in a spatial database with noise, which defines clusters as the largest set of density-connected points. The algorithm utilizes the concept of density-based clustering, i.e., requiring that the number of objects (points or other spatial objects) contained within a certain region in the clustering space is not less than some given threshold. The DBSCAN algorithm has the obvious advantages of high clustering speed and capability of effectively processing noise points and finding spatial clusters of any shapes. But because it directly operates on the whole database and uses a global parameter for representing the density when clustering, it also has two obvious weaknesses: when the data volume is increased, the I/O consumption supported by a large memory is also greatly required; when the density of spatial clustering is not uniform and the difference of clustering intervals is large, the clustering quality is poor.
The clustering analysis in data mining divides data according to the similarity degree, and the target is that the inter-cluster distance is the largest, and the intra-cluster distance is the smallest, namely, the greater the similarity in the clusters is, the better the difference between the clusters is, and the better the difference between the clusters is. The track clustering is the expansion of clustering analysis on a space-time track, and aims to divide space-time objects with similar behaviors into a class based on the similarity of time or space, find the moving mode of an object through clustering analysis, analyze the moving rule of the object and predict the possible future motion behavior. The track clustering algorithm based on the targets is mainly divided into two types, namely clustering by taking the whole track as a research object and clustering by dividing the track into a plurality of sub-tracks. The similarity between tracks can be visually evaluated, the influence of input parameters is small, local abnormal information is easy to ignore for complex tracks, and the clustering effect on high-dimensional track data is poor. The high-dimensional track clustering algorithm can better identify the local characteristics of the track, effectively process high-dimensional track data, can find track clusters in any shapes by combining a density-based clustering algorithm BSCAN, but the clustering efficiency is low due to the fact that the DBSCAN algorithm consumes a large amount of I/O along with the increase of the data scale.
Disclosure of Invention
In view of the above, the present invention has been made to provide a solution that overcomes or at least partially solves the above mentioned problems. Therefore, one aspect of the present invention provides a ship target classical trajectory generation method based on density spatial clustering, which specifically comprises the steps of:
step 1, initializing cluster analysis of ship target activity tracks;
forming a core point in the space block region and a boundary point in the space block region in the space block;
forming noise points according to the core points and the boundary points, and deleting the noise points in the space block area;
then, deleting the corresponding space block by judging the accessibility of the density among the residual point traces;
forming a frequent moving area of the ship target and generating a track point pi of the space block;
and 3, generating a ship target classical track.
Optionally, step 1 specifically includes:
(1) Setting the size of a target point track neighborhood radius Eps of an active area, and initially setting L0 nautical miles;
(2) Setting a minimum point number MinPts included in each field, and initially setting the MinPts as LY _ PtMinNum;
(3) Setting the size of a space block divided by the target activity area as w0 x h0;
(4) The target trace number threshold in the space block is set to KJK _ PtMinNum.
Optionally, step 2 specifically includes:
(1) Acquiring historical moving track point data of a ship target;
(2) According to the size of the set space block, counting the number of traces in each space block area;
(3) Filtering the space blocks of which the track points are smaller than a threshold value according to the set threshold value;
(4) In a space block, forming a core point in the area of the space block according to the fact that an Eps neighborhood of a track point at least comprises the minimum number LY _ PtMinNum of the track point;
(5) In the space block, forming boundary points in a space block area according to the fact that if the flight path is in the neighborhood of a certain core point but not the core point;
(6) Forming noise points according to the core points and the boundary points, and deleting the noise points in the space block area;
(7) Determining density reachability between the remaining traces, the trace p being reachable from trace q with respect to L0 and LY _ PtMinNum densities, in dependence on if there is a trace chain of points p1, …, pi, …, pn in the remaining traces that satisfies p1= p and pn = q, pi being directly reachable from pi +1 with respect to L0 and LY _ PtMinNum densities; thereby judging whether the density of the space block is up; if the density is not reachable, deleting the space block;
(8) Recording all the remaining space blocks to form a ship target frequent activity area;
(9) And calculating the spatial average value of the density of all core points in each space block to be used as the track point pi of the space block.
Optionally, step 3 specifically includes:
(1) According to the distance nearest principle, connecting the waypoints pi and p (i + 1) in the space block, and processing by using a point-passing curve;
(2) Setting an entry point and an exit point of a target in a spatial region;
(3) And loading all target moving track point data on the map platform, and simultaneously loading the formed track point curve to perform manual adjustment to form the ship target classical track point.
The invention also provides a ship target classical trajectory generation system based on density space clustering, which specifically comprises an initialization module, an activity area generation module and a target classical trajectory generation module;
the initialization module is used for clustering analysis initialization of the ship target activity track;
the active region generation module is used for generating a target frequent active region,
namely, the active region generating module forms a core point in the space block region and a boundary point in the space block region in the space block;
forming noise points according to the core points and the boundary points, and deleting the noise points in the space block area;
then the active area generation module deletes the corresponding space block by judging the accessibility of the density between the residual traces; forming a frequent moving area of the ship target and generating a track point pi of the space block;
the target classical flight path generation module is used for generating a ship target classical flight path.
Optionally, the initialization module is specifically configured to:
(1) Setting the size of a target point track neighborhood radius Eps of an active area, and initially setting L0 nautical miles;
(2) Setting a minimum point number MinPts included in each field, and initially setting the MinPts as LY _ PtMinNum;
(3) Setting the size of a space block divided by the target activity area as w0 x h0;
(4) The target trace number threshold in the space block is set to KJK _ PtMinNum.
Optionally, the activity area generating module is specifically configured to:
(1) Acquiring historical moving track point data of a ship target;
(2) Counting the number of traces in each space block area according to the set size of the space block;
(3) Filtering the space blocks of which the track points are smaller than a threshold value according to the set threshold value;
(4) In the space block, forming a core point in the area of the space block according to the fact that an Eps neighborhood of the track point at least comprises the minimum number of route points LY _ PtMinNum;
(5) In the space block, forming boundary points in a space block area according to the fact that if the flight path is in the neighborhood of a certain core point but not the core point;
(6) Forming noise points according to the core points and the boundary points, and deleting the noise points in the space block area;
(7) Judging density accessibility among the residual traces, according to the facts that if a trace chain p1, …, pi, …, pn exists in the residual traces, p1= p and pn = q are met, pi is directly reachable from pi +1 with respect to L0 and LY _ PtMinNum density, and trace p is reachable from trace q with respect to L0 and LY _ PtMinNum density; thereby judging whether the density of the space block is up; if the density is not reachable, deleting the space block;
(8) Recording all the remaining space blocks to form a ship target frequent activity area;
(9) And calculating the spatial average value of the density of all core points in each space block to serve as the track point pi of the space block.
Optionally, the target classical trajectory generation module is specifically configured to:
(1) According to the distance nearest principle, connecting the waypoints pi and p (i + 1) in the space block, and processing by using a point-passing curve;
(2) Setting an entry point and an exit point of a target in a spatial region;
(3) And loading all target moving track point data on the map platform, and simultaneously loading the formed track point curve to perform manual adjustment to form the ship target classical track point.
The technical scheme provided in the embodiment of the application at least has the following technical effects or advantages:
in order to improve the found track quality, track association quality measurement evaluation and a large-density track data processing means based on big data are introduced, and the original algorithm is modified, so that the track association quality is used as a track association judgment condition, and the track association is rapidly and accurately carried out.
The above description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the technical solutions of the present invention and the objects, features, and advantages thereof more clearly understandable.
Drawings
Various additional advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 shows a flow chart of a method for generating a classical trajectory of a ship target based on density space clustering;
FIG. 2 illustrates an instantiated initial model build diagram;
FIG. 3 illustrates an instantiated initial target track point location diagram;
FIG. 4 shows a schematic diagram of a space block with fewer instantiated filtered target track points;
FIG. 5 illustrates an instantiation core point determination diagram;
FIG. 6 illustrates an instantiation boundary point determination diagram;
FIG. 7 illustrates an instantiation noise point determination diagram;
FIG. 8 shows a schematic diagram of instantiating a spatial block of culling noise point residuals;
FIG. 9 illustrates an instantiated density unreachable spatial chunk determination diagram;
FIG. 10 illustrates an instantiated remnant space block diagram;
FIG. 11 illustrates an instantiated remnant space block density center generation diagram;
FIG. 12 is a schematic diagram illustrating exemplary remnant space block track point connections;
FIG. 13 illustrates a schematic diagram of an instantiated human intervention generating a target classical trajectory;
fig. 14 shows a schematic diagram of a ship target classical trajectory generation system based on density space clustering.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The invention aims to solve the problem that a DBSCAN algorithm consumes a large amount of I/O to cause low clustering efficiency along with the increase of data scale, and provides a ship target classical trajectory generation method based on density space clustering, as shown in FIG. 1, the method specifically comprises the following steps:
step 1, constructing a ship target activity track clustering analysis initialization model.
(1) Setting the size of a target point track neighborhood radius Eps of an active area, and initially setting L0 nautical miles;
(2) Setting a minimum point number MinPts included in each field, and initially setting the MinPts as LY _ PtMinNum;
(3) Setting the size of a space block divided by the target activity area as w0 x h0;
(4) Setting a target trace number threshold value in the space block to be KJK _ PtMinNum;
(5) And forming a ship target activity track clustering analysis initialization model based on the parameters.
An example of the specific model is shown in fig. 2, for example, the minimum point number MinPts =3 in each domain, and the target point track number threshold KJK _ PtMinNum =3 in the space block.
And 2, generating a target frequent activity area.
(1) Acquiring historical moving track point data of a ship target;
(2) Counting the number of traces in each space block area according to the set size of the space block;
specific target track point positions and statistical examples are shown in fig. 3, which shows specific numerical values of the positions and the counted numbers of the target track points in each space block.
(3) Filtering the space blocks of which the track points are smaller than a threshold value according to the set threshold value;
specifically, the space block example shown in fig. 4 is obtained by filtering the space blocks with fewer target track points based on the space block at the target track point position shown in fig. 3.
(4) In the space block, forming a core point in the area of the space block according to the fact that an Eps neighborhood of the track point at least comprises the minimum number of route points LY _ PtMinNum;
an example of the specific core point determination is shown in fig. 5.
The figure selects 5 blocks, each block is schematically represented by selecting a point, and a circle with each point as a center and Eps as a radius is represented; and calculating the number of target track points in the circle, wherein the number of points in the circle is greater than or equal to MinPts and is used as a core point, and the solid point is used as a core point in the graph 5.
(5) In the space block, forming boundary points in a space block area according to the fact that if the flight path is in the neighborhood of a certain core point but not the core point;
an example of the specific boundary point determination is shown in fig. 6.
In the figure, one target track point in 1 block is selected for illustration, and a circle with the center of each point location and Eps as the radius is shown; and calculating the number of target track points in the circle, wherein the number of the target track points in the circle is smaller than MinPts and is taken as a boundary point, meanwhile, the number of the target track points (including the track points) in the circle is larger than 1, and solid points in the graph 6 are taken as boundary points.
(6) Forming noise points according to the core points and the boundary points, and deleting the noise points in the space block area;
an example of the specific noise point determination is shown in fig. 7.
Noise points are points in the area of circles with the radius of Eps, which are not in any block, and the solid points in fig. 7 are noise points.
An example of a spatial block with specific culled noise points remaining is shown in fig. 8.
The remaining spatial blocks include only blocks of core points and boundary points.
(7) Judging density accessibility among the residual traces, according to the facts that if a trace chain p1, …, pi, …, pn exists in the residual traces, p1= p and pn = q are met, pi is directly reachable from pi +1 with respect to L0 and LY _ PtMinNum density, and trace p is reachable from trace q with respect to L0 and LY _ PtMinNum density; thereby judging whether the density of the space block is up; if the density is not reachable, deleting the space block;
an example of the specific density unreachable space block determination is shown in fig. 9.
Numbering p (i, j) on each residual target track point, wherein i represents a block, and j represents a point; the number of the residual blocks is n, and the number of the target track points in the ith block is m (i). Calculating the distance between p (i, j) and any other point in the block, recording each point with the distance from p (i, j) being less than Eps and with the reachable density, forming m (i) sets, carrying out element comparison on the m (i) sets, merging two sets with the same point, comparing the merged set with the rest sets again until each set is compared, and if the number of the last sets is more than 1, determining that the density is not reachable.
(8) Recording all the remaining space blocks to form a ship target frequent activity area;
an example of a specific remaining space block is shown in fig. 10.
(9) And calculating the spatial average value of the density of all core points in each space block to be used as the track point pi of the space block.
An example of the specific remaining space block density center generation is shown in fig. 11.
The density spatial average is the average of the geographic coordinates of the corresponding track point.
I.e., x = (x 1+ x2+. + xn)/n;
y＝(y1+y2+…+yn)/n；
the geographical coordinates of the spatial track point are (xi, yi); i =1, … …, n
The hollow point is the density center point in fig. 11.
And 3, generating a ship target classical track.
(1) According to the distance nearest principle, connecting the waypoints pi and p (i + 1) in the space block, and processing by using a point-passing curve;
an example of a particular course point line is shown in fig. 12.
(2) Setting an entry point and an exit point of a target in a spatial region;
(3) And loading all target moving track point data on the map platform, and simultaneously loading the formed track point curve to perform manual adjustment to form the ship target classical track point.
An example of generating a target classical track by specific manual intervention is shown in fig. 13.
The invention further provides a ship target classical trajectory generation system based on density spatial clustering, which specifically comprises an initialization module, an activity region generation module and a target classical trajectory generation module.
The initialization module is used for initializing the cluster analysis of the ship target activity track.
The method specifically comprises the following steps: the initialization module sets the size of a target point track neighborhood radius Eps of an active area and initially sets L0 nautical miles;
setting a minimum point number MinPts included in each field, and initially setting the MinPts as LY _ PtMinNum;
setting the size of a space block divided by the target activity area as w0 x h0;
the target trace number threshold in the space block is set to KJK _ PtMinNum.
The activity area generation module is used for generating a target frequent activity area.
The method specifically comprises the following steps: the activity area generation module acquires historical activity track point data of a ship target;
then, counting the number of traces in each space block region according to the set size of the space block;
the active area generation module filters the space blocks of which the track points are smaller than a threshold value according to a set threshold value;
in the space block, according to the fact that an Eps neighborhood of the track point at least comprises the minimum number of the track points LY _ PtMinNum, a core point in the space block area is formed;
in the space block, the activity area generation module forms boundary points in the space block area according to the fact that if the flight path falls in the neighborhood of a certain core point but not the core point;
then, forming noise points according to the core points and the boundary points, and deleting the noise points in the space block area;
the active region generation module judges density reachability among the remaining traces, and the trace point p is reachable from the trace point q with respect to the densities of L0 and LY _ PtMinNum according to the principle that if one trace point chain p1, …, pi, …, pn exists in the remaining trace points, p1= p and pn = q are satisfied, and pi is reachable from pi +1 with respect to the direct densities of L0 and LY _ PtMinNum; thereby judging whether the density of the space block is up; if the density is not reachable, deleting the space block;
meanwhile, the activity area generation module records all the remaining space blocks to form a ship target frequent activity area;
and calculating the spatial average of the densities of all core points in each space block as the course points pi of the space block.
The target classical flight path generation module is used for generating a ship target classical flight path.
The method specifically comprises the following steps: the target classical flight path generation module is used for setting an entry point and an exit point of a target in a space region;
then, according to the principle of the nearest distance, connecting the waypoints pi and p (i + 1) in the space block, and processing by using a point-passing curve;
and the target classical track generation module loads all target activity track point data on a map platform, and loads the formed track point curve at the same time to perform manual adjustment to form a ship target classical track point.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim.
Claims (8)
1. A ship target classical trajectory generation method based on density space clustering specifically comprises the following steps:
step 1, initializing cluster analysis of ship target activity tracks;
step 2, generating a target frequent activity area;
forming, in a spaceblock, a core point within the spaceblock region and a boundary point within the spaceblock region;
forming noise points according to the core points and the boundary points, and deleting the noise points in the space block area;
then, deleting the corresponding space block by judging the density accessibility among the residual traces; forming a frequent moving area of the ship target and generating a track point pi of the space block;
and 3, generating a ship target classical track.
2. The method according to claim 1, wherein step 1 is specifically:
(1) Setting the size of a target point track neighborhood radius Eps of an active area, and initially setting L0 nautical miles;
(2) Setting a minimum point number MinPts included in each field, and initially setting the MinPts as LY _ PtMinNum;
(3) Setting the size of a space block divided by the target activity area as w0 x h0;
(4) The threshold for the number of target traces in a spatial block is set to KJK _ PtMinNum.
3. The method according to claim 1, wherein step 2 is specifically:
(1) Acquiring historical moving track point data of a ship target;
(2) Counting the number of traces in each space block area according to the set size of the space block;
(3) Filtering the space blocks of which the track points are smaller than a threshold value according to the set threshold value;
(4) In the space block, forming a core point in the area of the space block according to the fact that an Eps neighborhood of the track point at least comprises the minimum number of route points LY _ PtMinNum;
(5) In the space block, forming boundary points in a space block area according to the condition that the flight path is in the neighborhood of a certain core point but not the core point;
(6) Forming noise points according to the core points and the boundary points, and deleting the noise points in the space block area;
(7) Judging density accessibility among the residual traces, according to the facts that if a trace chain p1, …, pi, …, pn exists in the residual traces, p1= p and pn = q are met, pi is directly reachable from pi +1 with respect to L0 and LY _ PtMinNum density, and trace p is reachable from trace q with respect to L0 and LY _ PtMinNum density; thereby judging whether the density of the space block is up; if the density is not reachable, deleting the space block;
(8) Recording all the remaining space blocks to form a ship target frequent activity area;
(9) And calculating the spatial average value of the density of all core points in each space block to serve as the track point pi of the space block.
4. The method according to claim 1, wherein step 3 is specifically:
(1) According to the distance nearest principle, connecting the waypoints pi and p (i + 1) in the space block, and processing by using a point-passing curve;
(2) Setting an entry point and an exit point of a target in a spatial region;
(3) And loading all target moving track point data on the map platform, and simultaneously loading the formed track point curve to perform manual adjustment to form the ship target classical track point.
5. A ship target classical trajectory generation system based on density space clustering specifically comprises an initialization module, an activity region generation module and a target classical trajectory generation module;
the initialization module is used for clustering analysis initialization of the ship target activity track;
the active region generation module is used for generating a target frequent active region,
the active region generation module forms a core point in the space block region and a boundary point in the space block region in the space block;
forming noise points according to the core points and the boundary points, and deleting the noise points in the space block area;
then the active area generation module deletes the corresponding space block by judging the accessibility of the density between the residual traces; forming a frequent moving area of the ship target and generating a track point pi of the space block;
the target classical flight path generation module is used for generating a ship target classical flight path.
6. The system of claim 5, wherein the initialization module is specifically configured to:
(1) Setting the size of a target point track neighborhood radius Eps of an active area, and initially setting L0 nautical miles;
(2) Setting a minimum point number MinPts included in each field, and initially setting the MinPts as LY _ PtMinNum;
(3) Setting the size of a space block divided by the target activity area as w0 x h0;
(4) The threshold for the number of target traces in a spatial block is set to KJK _ PtMinNum.
7. The system of claim 5, wherein the active region generation module is specifically configured to:
(1) Acquiring historical moving track point data of a ship target;
(2) Counting the number of traces in each space block area according to the set size of the space block;
(3) Filtering the space blocks of which the track points are smaller than a threshold value according to the set threshold value;
(4) In the space block, forming a core point in the area of the space block according to the fact that an Eps neighborhood of the track point at least comprises the minimum number of route points LY _ PtMinNum;
(5) In the space block, forming boundary points in a space block area according to the fact that if the flight path is in the neighborhood of a certain core point but not the core point;
(6) Forming noise points according to the core points and the boundary points, and deleting the noise points in the space block area;
(7) Determining density reachability between the remaining traces, the trace p being reachable from trace q with respect to L0 and LY _ PtMinNum densities, in dependence on if there is a trace chain of points p1, …, pi, …, pn in the remaining traces that satisfies p1= p and pn = q, pi being directly reachable from pi +1 with respect to L0 and LY _ PtMinNum densities; thereby judging whether the density of the space block is up; if the density is not reachable, deleting the space block;
(8) Recording all the remaining space blocks to form a ship target frequent activity area;
(9) And calculating the spatial average value of the density of all core points in each space block to serve as the track point pi of the space block.
8. The system of claim 5, wherein the target classical trajectory generation module is specifically configured to:
(1) According to the distance nearest principle, connecting the waypoints pi and p (i + 1) in the space block, and processing by using a point-passing curve;
(2) Setting an entry point and an exit point of a target in a spatial region;
(3) And loading all target moving track point data on the map platform, and simultaneously loading the formed track point curve to perform manual adjustment to form the ship target classical track point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210706104.9A CN115270920B (en) | 2022-06-21 | 2022-06-21 | Ship target classical track generation method based on density spatial clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210706104.9A CN115270920B (en) | 2022-06-21 | 2022-06-21 | Ship target classical track generation method based on density spatial clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115270920A true CN115270920A (en) | 2022-11-01 |
| CN115270920B CN115270920B (en) | 2023-07-18 |
Family
ID=83761459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210706104.9A Active CN115270920B (en) | 2022-06-21 | 2022-06-21 | Ship target classical track generation method based on density spatial clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115270920B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309383A (en) * | 2019-06-17 | 2019-10-08 | 武汉科技大学 | Ship trajectory clustering analysis method based on improved DBSCAN algorithm |
| 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 |
| CN111650581A (en) * | 2020-06-15 | 2020-09-11 | 南京莱斯电子设备有限公司 | Radar global target track automatic starting method based on environment perception |
| EP3739295A1 (en) * | 2019-05-13 | 2020-11-18 | S.A.T.E. - Systems and Advanced Technologies Engineering S.R.L. | Method for determining an optimal naval navigation routes from historical gnss data of naval trajectories |
| CN113032378A (en) * | 2021-03-05 | 2021-06-25 | 北京工业大学 | Ship behavior pattern mining method based on clustering algorithm and pattern mining |
| CN113298195A (en) * | 2021-07-27 | 2021-08-24 | 中国电子科技集团公司第十五研究所 | Method and device for generating classical trajectory of offshore target and storage medium |
| CN113887590A (en) * | 2021-09-22 | 2022-01-04 | 中国电子科技集团公司第二十九研究所 | Target typical track and area analysis method |
| US20220037033A1 (en) * | 2020-07-31 | 2022-02-03 | Accenture Global Solutions Limited | Systems and methods for implementing density variation (densvar) clustering algorithms |
| CN114091578A (en) * | 2021-11-03 | 2022-02-25 | 浙江海洋大学 | Ship track clustering method based on curve length distance |
| CN114330509A (en) * | 2021-12-06 | 2022-04-12 | 中科星图股份有限公司 | Method for predicting activity rule of aerial target |
| CN114564545A (en) * | 2022-01-13 | 2022-05-31 | 武汉理工大学 | System and method for extracting ship experience course based on AIS historical data |
-
2022
- 2022-06-21 CN CN202210706104.9A patent/CN115270920B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3739295A1 (en) * | 2019-05-13 | 2020-11-18 | S.A.T.E. - Systems and Advanced Technologies Engineering S.R.L. | Method for determining an optimal naval navigation routes from historical gnss data of naval trajectories |
| CN110309383A (en) * | 2019-06-17 | 2019-10-08 | 武汉科技大学 | Ship trajectory clustering analysis method based on improved DBSCAN algorithm |
| 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 |
| CN111650581A (en) * | 2020-06-15 | 2020-09-11 | 南京莱斯电子设备有限公司 | Radar global target track automatic starting method based on environment perception |
| US20220037033A1 (en) * | 2020-07-31 | 2022-02-03 | Accenture Global Solutions Limited | Systems and methods for implementing density variation (densvar) clustering algorithms |
| CN113032378A (en) * | 2021-03-05 | 2021-06-25 | 北京工业大学 | Ship behavior pattern mining method based on clustering algorithm and pattern mining |
| CN113298195A (en) * | 2021-07-27 | 2021-08-24 | 中国电子科技集团公司第十五研究所 | Method and device for generating classical trajectory of offshore target and storage medium |
| CN113887590A (en) * | 2021-09-22 | 2022-01-04 | 中国电子科技集团公司第二十九研究所 | Target typical track and area analysis method |
| CN114091578A (en) * | 2021-11-03 | 2022-02-25 | 浙江海洋大学 | Ship track clustering method based on curve length distance |
| CN114330509A (en) * | 2021-12-06 | 2022-04-12 | 中科星图股份有限公司 | Method for predicting activity rule of aerial target |
| CN114564545A (en) * | 2022-01-13 | 2022-05-31 | 武汉理工大学 | System and method for extracting ship experience course based on AIS historical data |
Non-Patent Citations (1)
| Title |
|---|
| 王加胜，刘永学，杨昆，李满春，孙超: "基于空间聚类分析的南海主要航线提取方法", 《交通运输工程学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115270920B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112347993B (en) | Expressway vehicle behavior and track prediction method based on vehicle-unmanned aerial vehicle cooperation | |
| CN112526513B (en) | Millimeter wave radar environment map construction method and device based on clustering algorithm | |
| Rossi et al. | Vehicle trajectory prediction and generation using LSTM models and GANs | |
| CN112556698B (en) | Ship behavior change and abnormality identification method, equipment and medium | |
| CN113284369B (en) | Prediction method for actually measured airway data based on ADS-B | |
| CN113639757B (en) | Map matching method and system based on bidirectional scoring model and backtracking correction mechanism | |
| Huang et al. | Research on Real‐Time Anomaly Detection of Fishing Vessels in a Marine Edge Computing Environment | |
| Samson | Mineral resource estimates with machine learning and geostatistics | |
| Kaklis et al. | Trajectory mining and routing: A cross-sectoral approach | |
| CN115270920A (en) | Ship target classical trajectory generation method based on density space clustering | |
| Moreira et al. | The impact of data quality in the context of pedestrian movement analysis | |
| CN117689693A (en) | Abnormal local track detection method and device based on graph comparison self-supervision learning | |
| CN117877318A (en) | Ship track prediction method and system based on CNN and improved LSTM and attention mechanism | |
| CN116151107A (en) | Method, system and electronic equipment for identifying ore potential of magma type nickel cobalt | |
| Ouyang et al. | Fast 3D point cloud target tracking based on polar-voxel encoding | |
| CN117036966B (en) | Learning method, device, equipment and storage medium for point feature in map | |
| Reyes et al. | Data Stream Processing Method for Clustering of Trajectories | |
| KR102042490B1 (en) | System and method for estimating external forces acting on ship by MapReduce | |
| Reyes¹ et al. | of Traffic Congestion Patterns | |
| Bariviera | Data Stream Processing Method for Clustering of Trajectories | |
| Kim et al. | Research Article A Study on Travel Time Estimation of Diverging Traffic Stream on Highways Based on Timestamp Data | |
| Rodríguez-García et al. | A SO2 Pollution Concentrations Prediction Approach Using Autoencoders | |
| CN118396517A (en) | Off-line customer access and path planning method and system based on geographic position | |
| Asif et al. | An Adaptive Framework for Traffic Congestion Prediction using Deep Learning | |
| CN116861241A (en) | Space debris collision probability prediction method, system, terminal and storage medium based on artificial intelligence |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |