CN111813877B - Track extraction method and device - Google Patents
Track extraction method and device Download PDFInfo
- Publication number
- CN111813877B CN111813877B CN201910294950.2A CN201910294950A CN111813877B CN 111813877 B CN111813877 B CN 111813877B CN 201910294950 A CN201910294950 A CN 201910294950A CN 111813877 B CN111813877 B CN 111813877B
- Authority
- CN
- China
- Prior art keywords
- point
- track
- representative
- route
- representative point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 39
- 238000010586 diagram Methods 0.000 claims abstract description 82
- 238000000034 method Methods 0.000 claims abstract description 30
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000012952 Resampling Methods 0.000 claims description 5
- 230000001174 ascending effect Effects 0.000 claims description 5
- 238000012986 modification Methods 0.000 claims 2
- 230000004048 modification Effects 0.000 claims 2
- 230000008569 process Effects 0.000 abstract description 11
- 238000012546 transfer Methods 0.000 abstract description 4
- 238000004422 calculation algorithm Methods 0.000 description 12
- 238000012937 correction Methods 0.000 description 10
- 239000000284 extract Substances 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G3/00—Traffic control systems for marine craft
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Remote Sensing (AREA)
- General Engineering & Computer Science (AREA)
- Ocean & Marine Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Navigation (AREA)
Abstract
The application discloses a track extraction method and a track extraction device, wherein the method comprises the steps of obtaining historical track data to be extracted; extracting key points of each track according to the historical track data; clustering the key points, and extracting representative points from each category; and connecting the representative points to generate an air route branch diagram. The method provided by the application has good adaptability to complex ocean vessel track data, and can well show the sequence relation among various points in the sailing process and the transfer sequence of the vessel on the whole sailing line based on the track branch diagram.
Description
Technical Field
The invention relates to the technical field of data mining of computer science and technology, in particular to a track extraction method and a track extraction device.
Background
With the progress of data acquisition and data processing technology, many organizations currently pre-mine valuable information from massive track data. The track is the actual path of an aircraft or a ship, and in the maritime field, the identification of the track of the ship has important significance for the problems of port operation and management, trade relation analysis, maritime traffic management and the like.
The prior art refers to an extraction method of land target track data, and grouping processing is carried out on the similarity between track sequences. However, for ocean track data with long duration, uneven data acquisition interval and quality and strong correlation of data quality with geographical area, it is difficult to define similarity measurement with good properties, and the required calculation amount is relatively large, and it is difficult to adapt to a large-scale data set through distributed processing, so that it is difficult to mine the real topological relation between each line from an initial port to a destination port.
In view of this, how to develop a track extraction method in a complex track data environment is a problem to be solved.
Disclosure of Invention
In view of the above-mentioned drawbacks or shortcomings in the prior art, it is desirable to provide a track extraction method and apparatus, which have good adaptability to complex track data, and can extract real navigation conditions between the starting points of the tracks.
In a first aspect, the present application provides a track extraction method, including:
acquiring historical track data to be extracted;
extracting key points of each track according to the historical track data;
clustering the key points, and extracting representative points from each category;
And connecting the representative points to generate an air route branch diagram.
In a second aspect, the present application provides a track extraction device, including:
The acquisition module is used for acquiring historical track data to be extracted;
the key point extraction module is used for extracting key points of each track according to the historical track data;
the representative point extraction module is used for clustering the key points and extracting representative points from each category;
and the generation module is used for connecting the representative points and generating a route branch diagram.
In summary, the method and the device for extracting the track provided by the embodiment of the application firstly extract key points from each piece of track data, then cluster the key points, extract representative points from each category, and finally generate a track branching diagram by connecting each representative point with a directed edge, wherein the step of extracting the key points avoids directly constructing similarity measurement on the track data, thereby further describing that the method has good adaptability to complex track data; compared with the prior art, the complexity of the algorithm for clustering the key points is lower, and the clustering can be completed only by traversing the key point data once; through the generated route branch diagram, the transfer relation between each point trace in the process from the starting point to the end point can be completely drawn, and the whole navigation condition can be exactly extracted.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:
Fig. 1 is a basic flow diagram of a track extraction method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a first route branching diagram in an embodiment of the present application;
FIG. 3 is a schematic diagram of a final route branching diagram in an embodiment of the present application;
fig. 4 is a basic flow diagram of a track extraction device according to an embodiment of the present application;
Fig. 5 is a schematic diagram of a computer system according to the present application.
Detailed Description
The application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be noted that, for convenience of description, only the portions related to the application are shown in the drawings.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
The embodiment of the application provides a track extraction method, which is applied to a terminal. It should be noted that, the terminals according to the embodiments of the present application may include, but are not limited to, a Personal Computer (Personal Computer, PC), a Personal digital assistant (Personal DIGITAL ASSISTANT, PDA), a Tablet Computer (Tablet Computer), a wireless handheld device, a mobile phone, and the like.
For easy understanding and explanation, the track extraction method and apparatus provided in the embodiments of the present application are described in detail below with reference to fig. 1 to 4.
Please refer to fig. 1, which is a basic flow chart of a track extraction method according to an embodiment of the present application, the method includes the following steps:
s101, acquiring historical track data to be extracted.
Specifically, the historical track data refers to track data obtained through historical collection, wherein each track data is a point track, and the attribute of each collected point track comprises: the track ID, the track ID in the track ID, the longitude, the latitude and the time. For example, in the maritime field, the historical track data refers to the track data of a plurality of vessels historically reaching the port B from the port a, and may also be the track data of the same vessel historically reaching the port B from the port a. The ID herein, identification, refers to a code for identification and recognition.
S102, extracting key points of each track according to the historical track data.
The track data in each historical track is firstly ordered, generally ascending, according to the time of each track data, so as to generate a track sequence of each track. In order to better distinguish the individual track sequences, all track sequences to be extracted can be encoded.
Furthermore, before the step of extracting the key points of each track, the history track data needs to be preprocessed, and the specific preprocessing is based on the track sequence, and the steps are as follows:
Step one: and removing abnormal data and/or repeated data in the historical track data to obtain first track data. The abnormal data refers to comparing the speed of each point track in the track sequence with a set speed, if the speed is inconsistent, the speed of the point track is considered to be the abnormal speed, the point track needs to be removed from the track, and preferably, the set speed takes 20m/s or any value in the range of 10m/s to 30 m/s; the repeated data means that the time point of a certain point trace in the track is repeatedly acquired, if the point trace is found to have the same acquisition time, only the earliest received point trace is reserved, and the rest point traces are removed from the track.
Until there is no abnormal data and/or repeated data in each historical track, the track data after being removed is defined as first track data.
Step two: and segmenting each piece of first track data, and resampling the segmented tracks to obtain second track data.
The first track data are first sorted, typically in ascending order, according to a time sequence, so as to regenerate the track sequence of each track.
Then, specific segmentation is carried out on the first track data, and the segmentation rule is as follows: for example, in the maritime field, for the same track, if the time interval between a certain track and the next track is less than 2 hours or the distance interval between the certain track and the next track is greater than 40 seas, the track is disconnected from the track, so that the track is segmented until all tracks are segmented, and thus, each track has a plurality of segmented tracks. It should be noted that, the trace belongs to the previous leg, the next trace belongs to the next leg, and the previous leg and the next leg are disconnected from the trace, but the trace is reserved.
And resampling a plurality of segmented tracks on each track, specifically resampling the points belonging to the same segmented track according to a preset time interval, wherein the preset time interval is preferably 5 minutes, and can also be arbitrarily valued between 1 minute and 1 hour. In this way, the track data at this time is defined as the second track data until resampling is completed for all of the plurality of segmented tracks.
Step three: and removing abnormal data in the second track data according to the first preset speed to obtain third track data.
The second track data are first sorted, typically in ascending order, according to a time sequence, so as to regenerate the track sequence of each track.
Specifically, the distance between two adjacent tracks in the same track sequence is calculated, the average speed of the track is calculated according to the distance and the time between the adjacent tracks, the average speed is compared with the first preset speed, if the average speed is larger than the first preset speed, the first track in the adjacent tracks in the same track sequence is taken as an abnormal point to be removed, and therefore, no abnormal data exists in the second track data, and the track data at the moment are defined as third track data. Preferably, the first preset speed is 20m/s, and can be arbitrarily selected from 10m/s to 30 m/s.
Through the preprocessing of the historical track data, the segmentation track preprocessing, the elimination of various abnormal points in the track data, the sorting and sorting of the track data are carried out again, and the complexity and the error rate of the subsequent key point extraction are reduced.
Further, extracting key points of each track specifically includes: according to each track sequence, key points on each track are extracted one by one, and key point sequences of each track are generated, and it is to be noted that each track sequence can be a track sequence which is not preprocessed or a track sequence after preprocessing.
The method for extracting the key points comprises the following steps:
And taking the starting point of each track as a first key point, taking the end point as a last key point, sequentially calculating the course difference of each track from the nearest key point and the speed of each track from the first key point, and extracting the current point as the key point if the course difference of the current point from the nearest key point is larger than a preset angle and the speed of the current point is larger than a second preset speed.
Preferably, the preset angle is 15 degrees, and can take any value between 5 degrees and 20 degrees, preferably,
Preferably, the second preset speed is 0.1m/s, and can be arbitrarily value between 0.1m/s and 2 m/s.
It should be noted that, each time a key point is extracted, the current point is associated with the current point, and the relevant attribute of the key point is extracted and stored, where the relevant attribute includes the ID, time, longitude, latitude, track sequence ID, and ID of the previous key point. The ID herein, identification, refers to a code for identification and recognition.
Thus, the extraction of the key points and the key point attributes in all tracks is completed until the last key point is finished, and each track is corresponding to a key point sequence.
Further, according to the key point sequence of each track, calculating the length parameter of the key point on each track.
Specifically, the length parameter of the starting point of each track is defined as 0, the length parameter of the ending point is defined as 1, the distance between two adjacent key points is calculated sequentially from the starting point, the distance is added with the length parameter of the last key point to form the total mileage of the current key point, and the value obtained by dividing the total mileage of the current key point by the total mileage of the ending point is used as the length parameter of the key point. Thus, the calculation of the length parameter is completed for all the key points on the track, and the value range of the length parameter is 0 to 1.
The extraction algorithm of the key points of the embodiment has low complexity, and can be completed only by traversing the historical track data once; in the process of extracting the key points, the point tracks with small adjacent course changes in the track are removed according to the course difference, so that the complexity of clustering of the subsequent key points is simplified; the relevant attribute of each key point in each track sequence is recorded, and a bedding is made for further mining more attribute information later; meanwhile, the sequence of each key point in the whole route can be specified according to the length parameter of each key point, so that the sequence between adjacent key points of different routes can be compared, and the sequence between adjacent key points of the same route can be compared.
And S103, clustering the key points, and extracting representative points from each category.
Firstly, clustering key points in all tracks, specifically, projecting all the obtained key points in each track sequence from a geographic coordinate system to a plane coordinate system, and then obtaining corresponding coordinate points, and uniformly inputting the coordinate points into a clustering algorithm for clustering.
Preferably, in this embodiment, clustering of the key points adopts a DBSCAN clustering algorithm, specifically, coordinates of the key points are input into the DBSCAN algorithm in a unified manner, wherein a distance threshold in the DBSCAN algorithm is set to be a preset distance, each category at least contains a preset number of key points, and when the condition is met, the key points are aggregated into one category. In addition, after clustering is finished, noise points appearing in the DBSCAN algorithm, which are key points not in any known category, need to be removed. It will be appreciated that for better identification of the categories, the final categories are encoded, i.e. there is a category ID for each category.
Preferably, the preset distance is 20 km, and can also take any value between 5 km and 50 km.
Preferably, the preset number is 5, and can be any value between 3 and 20.
In the embodiment, the extracted key points are directly clustered, and all historical track data are not required to be clustered, so that the clustering complexity is reduced, compared with the prior art, the method and the device avoid the direct construction of complex similarity measurement on complex track data, have good adaptability to track data with long duration, uneven data acquisition interval and quality and strong correlation between data quality and geographic areas in practical application, and ensure that the method and the device can adapt to large-scale track data in a distributed environment.
Next, representative points are extracted from each known class, and the specific steps include:
Step one: if the key points in the counted category belong to a plurality of track sequences, the category is reserved, otherwise, the category is deleted.
Preferably, the number of the track sequences is 3, and the track sequences can be arbitrarily valued between 1 and 10.
Step two: and calculating the average longitude, the average latitude and the average length parameter of each reserved category, and taking the point of the position where the average longitude, the average latitude and the average length parameter are located as a representative point.
Specifically, based on the key points contained in the category, preferably, an arithmetic average method is adopted to calculate average longitude, average latitude and average length parameters of all the key points, and the calculated points uniquely corresponding to the average longitude, average latitude and average length parameters in the category are used as representative points of the category, so that the representative points in all the categories are extracted.
In addition, the average longitude, average latitude, and average length parameter calculated each time are also required to be stored as the longitude, latitude, and length parameters of the representative point.
It will be appreciated that for better identification of the extracted representative points, the representative points are encoded, i.e. each representative point has a representative point ID which is not only in a one-to-one correspondence with the above-mentioned class IDs, but also numerically identical.
The first step removes the category with fewer key points in the category, and the second step further extracts the representative point as a node in the subsequent route branching diagram.
S104, connecting the representative points to generate a route branching diagram.
Specifically, the connection relation between the representative points is connected and established, and in this embodiment, based on each key point sequence, each representative point is sequentially connected in a form of a directed edge to generate a first route branch diagram.
More specifically, starting from the first key point in the key point sequence according to each key point sequence, taking the representative point ID corresponding to the key point as a top point set, taking the ordered tuple from the representative point corresponding to the last key point to the representative point corresponding to the current key point on the same track as a directed edge, and connecting all the representative points in sequence by utilizing a directed edge mode, so as to finally generate a first route branch diagram.
It should be noted that, in the airline branch graph, the weight of each directed edge is the number of occurrences of the corresponding ordered tuple. For example: adjacent representative points v 1 and v 2 exist in the first route branch diagram, three ordered tuples from v 1 to v 2 exist, and then the weight of the directed edge v 1→v2 is 3.
Further, the connection relation in the first route pattern is corrected to generate a second route branch pattern, and correction refers to removal of the directed edges meeting the rule condition.
Specifically, the removal rule includes:
rule one: and if the weight of the directed edge is smaller than a preset value, removing the directed edge.
Preferably, the preset number is 3, and can be any value between 1 and 15.
Rule II: and if the difference value of the length parameters of the end point and the starting point of the directed edge is larger than a first preset threshold value or smaller than a second preset threshold value, removing the directed edge from the first route pattern.
For example: assuming that there is a directed edge, the starting point of which is v 1, the end point of which is v 2, and the corresponding length parameters of which are r (v 1) and r (v 2), respectively, if the value of r (v 2)-r(v1) is greater than a first threshold value, or the value of r (v 2)-r(v1) is less than a second threshold value, the directed edge v 1→v2 is removed from the first route pattern, and after the removal of the directed edge, the first route pattern is marked as a second route pattern.
Preferably, the first threshold is 0.2, and may be any value between 0.1 and 0.8.
Preferably, the second threshold is-0.01, and can be arbitrarily chosen between-0.1 and 0.1.
In addition, before the rule one step, removing the rule further includes: the same directional edges as the start and end points in the first route branching diagram are removed because the start and end points are in the same class.
The embodiment removes unreasonable directed edges in the first route branch diagram, and a plurality of connected subgraphs may exist in the second route branch diagram for various reasons, wherein the connected subgraphs refer to fragments with connectivity, and the connected subgraphs include representative points with zero in degree and representative points with zero out degree.
Further, correcting the connection relationship in the second route map includes adding a directed edge for a representative point having an entry of zero. The representative point with zero incidence indicates that no directed edge takes the representative point as an end point, and the representative point with zero incidence indicates that no directed edge takes the representative point as an end point.
Specifically, the adding rule includes:
rule one: if the directed edge takes the representative point with zero entering degree as the end point, the difference value of the length parameters of the end point and the starting point of the directed edge is larger than zero, and the exiting degree of the starting point is zero, the directed edge is added to the second route branch diagram to generate a third route branch diagram.
For example: assuming that a directed edge is terminated by a representative point v with zero entering degree, the starting point of the directed edge is s, the corresponding length parameters are r (v) and r(s), if r (v) -r(s) > 0 is satisfied and the exiting degree of the starting point s is zero, the directed edge s- > v is added into the second route, and after no directed edge satisfying the condition exists in the second route branch diagram, the second route branch diagram is marked as a third route branch diagram.
Rule II: if the third route branch diagram also has the representative point with zero entering degree, arranging each representative point in the third route branch diagram according to the length parameter ascending order of each representative point, then connecting the last representative point of the representative points with the representative point to generate a directed edge, and adding the directed edge into the third route branch diagram to generate a fourth route branch diagram.
For example: assuming that the third route branch diagram has a representative point v i with zero incidence, arranging all the representative points in the second route diagram according to the length parameter ascending order of the representative points, connecting the last representative point v i-1 of the representative point v i with the representative point v i to form a directed edge v i-1→vi, adding the directed edge v i-1→vi into the third route diagram, and after the step is finished, only leaving one initial representative point in the third route branch diagram to have zero incidence, so that the third route branch diagram is marked as a fourth route branch diagram.
Further, the connection relation in the fourth route branch diagram is corrected to obtain a final route branch diagram, and the specific correction rule includes:
Rule one: if a plurality of representative points with zero degree exist in the fourth route branch diagram, only the representative point with the maximum length parameter is reserved, and the other representative points with zero degree and the directed edges thereof are removed.
Rule II: and if the first representative point, the second representative point, the third representative point, the directed edge from the first representative point to the second representative point, the directed edge from the second representative point to the third representative point, and the substructure of the directed edge from the first representative point to the third representative point exist in the fourth route branching diagram, and the shortest distance from the second representative point to the navigation section where the first representative point and the third representative point are located is smaller than twice of the preset distance, removing the second representative point.
For example: assuming that the fourth route branching diagram is detected to have the representative point v 1, the representative point v 2, the representative point v 3, the directed edge v 1→v2, the directed edge v 2→v3 and the sub-structure of the directed edge v 1→v3, the distance from the representative point v 1 to the representative point v 3 is marked as v 1v3, and the shortest distance from the representative point v 2 to the distance v 1v3 is less than twice the preset distance, at this time, the representative point v 2 is actually on the distance v 1v3, so that the representative point v 2 is removed. And when the redundancy is removed specifically, starting from the representative point v 1 with the minimum length parameter which meets the condition in the fourth route branch diagram, and iteratively removing redundancy from the fourth route branch diagram each time according to the second rule until no substructure appears in the fourth route branch diagram.
Preferably, the preset distance refers to a preset distance in the process of clustering the key points by using a DBSCAN algorithm, and the preset distance is 20 km, and can also be arbitrarily valued between 5 km and 50 km.
In this embodiment, by removing unreasonable directed edges in the route branching diagram, completing the missing directed edges, processing the representative points with zero output degree, and eliminating redundant edges, each step of correction process can be completed by traversing the route branching diagram only once for the directed edges or the representative points meeting the conditions, and compared with the prior art, the correction algorithm and the mode thereof have lower complexity.
According to the invention, through the final route branch diagram, the transfer relation between each representative point on the route of the ship in the process from the initial port to the terminal port can be completely drawn, the route information associated with each ship in each time period can be more exactly searched, the affiliated route can be searched according to the corresponding route, so that the attribute information such as the ship type, busyness, holding draft and the like on each route can be further mined, and important support is better provided for port operation and management, trade relation analysis, offshore traffic management and the like.
To facilitate better understanding of S101 to S104 described above, description will be made by taking an example of extracting a sailing route of a ship in the maritime field.
As shown in fig. 2, which is a schematic diagram of a first route branching diagram in an embodiment of the present application, a is a starting port, B is an ending port, and connecting lines in the diagram are formed by connecting original track data points according to a time sequence, wherein a plurality of original track data points are missing in the middle.
The method for extracting the flight path branch map of each piece of historical flight path data comprises the following specific steps of:
s101, acquiring historical track data to be extracted;
S102, extracting key points of each track according to the historical track data;
s103, clustering the key points, and extracting representative points from each category;
S104, connecting the representative points to generate a route branching diagram.
The bubbles in fig. 2 are representative points extracted through steps S101, S102 and S103, and then the representative points are connected through step S104 to generate a first route branching diagram, as shown in fig. 2.
As shown in fig. 3, which is a schematic diagram of a final route branching diagram in an embodiment of the present application, based on the first route branching diagram in fig. 2, the final route branching diagram in fig. 3 obtained through the following correction steps specifically includes:
the first correction step: the connection relation in the first route pattern is corrected to generate a second route branch pattern, and correction refers to removal of the directed edges meeting the rule condition.
And a correction step II: and the connection relation in the second route map is primarily corrected to generate a third route branch map, and the third route branch map is further corrected to generate a fourth route branch map, and the method specifically comprises the step of adding a directed edge for a representative point with zero incidence.
And a correction step III: correcting the connection in the fourth route branching diagram to obtain a final route branching diagram, wherein the correction includes correcting the representative point problem with zero degree of departure and removing redundancy.
In fig. 3, each number is the ID of each representative point, that is, the ID corresponding to each category, each line segment is a directed edge connecting adjacent representative points, and through the final route branching diagram in fig. 3, the migration relationship between each representative point in the process of the ship from port a to port B is completely drawn, so that the navigation condition from port a to port B can be extracted more precisely, and the navigation method has good guiding significance for the navigation, shipping and trade of the actual ocean-going ship, maritime law enforcement and other behaviors.
The method avoids constructing complex similarity measurement on the ocean vessel track data by extracting key points, and has good adaptability to the ocean vessel track data in the embodiment; the complexity of the key point extraction algorithm is low, and the extraction can be completed only by one traversal; only the extracted key points are clustered, and all the track data are not clustered, so that the method can adapt to the clustering of the large-scale track data; the process of generating and correcting the track branch graph is completed only by traversing the corresponding directed edges or representative points.
It should be noted that, in this embodiment, the descriptions of the same steps and the same content as those in other embodiments may refer to the descriptions in other embodiments, and are not repeated here.
Based on the foregoing embodiments, the embodiments of the present application provide a track extraction device, which may be applied to the track extraction method provided in the embodiments corresponding to fig. 1 to 3. Referring to fig. 4, a basic flow diagram of a track extraction device according to an embodiment of the present application is shown, where the track extraction device includes:
An acquisition module 201, configured to acquire historical track data to be extracted;
a key point extracting module 202, configured to extract key points of each track according to the historical track data;
the representative point extraction module 203 is configured to cluster the key points and extract representative points from each category;
And the generating module 204 is used for connecting the representative points and generating an air route branching diagram.
In the above embodiment of the present application, the acquiring module 201 is configured to acquire historical track data to be extracted.
In particular, for example, in the maritime field, the historical track data refers to the track data of a plurality of vessels historically reaching the port B from the port a, and may also be the track data of the same vessel historically reaching the port B from the port a.
In the above embodiment of the present application, the key point extracting module 202 is configured to extract key points of each track according to the historical track data.
Further, prior to the step of extracting key points for each track, pre-processing of historical track data is required.
Further, extracting key points of each track specifically includes: and extracting key points on each track one by one according to each track sequence, and generating a key point sequence of each track.
Further, according to the key point sequence of each track, calculating the length parameter of the key point on each track.
In the above embodiment of the present application, the representative point extraction module 203 is configured to cluster the key points and extract representative points from each category.
Preferably, the clustering of the key points in this embodiment adopts a DBSCAN clustering algorithm.
Further, representative points are extracted from each of the known categories.
In the above embodiment of the present application, the generating module 204 is configured to connect the representative points to generate the route branching map.
Further, the connection relationship between the representative points is connected and established, and in this embodiment, based on each key point sequence, each representative point is sequentially connected in a form of a directed edge to generate a first route branch diagram.
Further, the connection relation in the first route pattern is corrected to generate a second route branch pattern, and correction refers to removal of the directed edges meeting the rule condition.
Further, correcting the connection relationship in the second route map includes adding a directed edge for a representative point having an entry of zero.
Further, the connection relation in the fourth route branch diagram is corrected to obtain a final route branch diagram.
In summary, the method and the device for extracting the track provided by the embodiment of the application firstly extract key points from each piece of track data, then cluster the key points, extract representative points from each category, and finally generate a track branching diagram by connecting each representative point with a directed edge, wherein the step of extracting the key points avoids directly constructing similarity measurement on the track data, thereby further describing that the method has good adaptability to complex track data; compared with the prior art, the complexity of the algorithm for clustering the key points is lower, and the clustering can be completed only by traversing the key point data once; through the generated route branch diagram, the transfer relation between each point trace in the process from the starting point to the end point can be completely drawn, and the whole navigation condition can be exactly extracted.
Based on the foregoing embodiments, embodiments of the present application provide a computer system. Referring to fig. 5, the computer system 300 includes a Central Processing Unit (CPU) 301 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage section into a Random Access Memory (RAM) 303. In the RAM303, various programs and data required for the system operation are also stored. The CPU 301, ROM 302, and RAM303 are connected to each other through a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.
The following components are connected to the I/O interface 305: an input section 306 including a keyboard, a mouse, and the like; an output portion 307 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 308 including a hard disk or the like; and a communication section 309 including a network interface card such as a LAN card, a modem, or the like. The communication section 309 performs communication processing via a network such as the internet. The drive 310 is also connected to the I/O interface 305 as needed. A removable medium 311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed on the drive 310 as needed, so that a computer program read therefrom is installed into the storage section 308 as needed.
In particular, the process described above with reference to flowchart 1 may be implemented as a computer software program according to an embodiment of the application. For example, embodiment 1 of the present application includes a computer program product including a computer program loaded on a computer-readable medium, the computer program being executed by the CPU 301 to realize the steps of:
acquiring historical track data to be extracted;
extracting key points of each track according to the historical track data;
clustering the key points, and extracting representative points from each category;
And connecting the representative points to generate an air route branch diagram.
In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 309, and/or installed from the removable medium 311.
The computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products for trace extraction according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases. The described units or modules may also be provided in a processor, for example, as: a processor includes an acquisition module, a key point extraction module, a representative point extraction module, and a generation module. Wherein the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.
As another aspect, the present application also provides a computer-readable medium that may be contained in the terminal described in the above embodiment; or may exist alone without being fitted into the terminal. The computer readable medium carries one or more programs which, when executed by one of the terminals, cause the terminal to implement the track extraction method as in the above embodiment.
For example, the terminal may implement as shown in fig. 1: s101, acquiring historical track data to be extracted; s102, extracting key points of each track according to the historical track data; s103, clustering the key points, and extracting representative points from each category; s104, connecting the representative points to generate a route branching diagram.
It should be noted that although in the above detailed description several modules or units of a terminal for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Furthermore, although the steps of the methods in the present disclosure are depicted in a particular order in the drawings, this does not require or imply that the steps must be performed in that particular order, or that all illustrated steps be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware.
The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the application referred to in the present application is not limited to the specific combinations of the technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the inventive concept. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.
Claims (4)
1. A track extraction method is characterized in that:
acquiring historical track data to be extracted;
extracting key points of each track according to the historical track data;
The key points of extracting each track comprise: taking the starting point of each track as a first key point, taking the end point as a last key point, and extracting the current point as a key point if the course difference between the current point and the nearest key point is larger than a preset angle and the speed of the current point is larger than a second preset speed;
clustering the key points, and extracting representative points from each category;
The extracting representative points from each category comprises: if the key points in the category belong to a plurality of track sequences, the category is reserved, otherwise, the category is deleted; calculating the average longitude, the average latitude and the average length parameter of each reserved category, and taking the point of the position where the average longitude, the average latitude and the average length parameter are located as a representative point;
connecting each representative point to generate a route branch diagram;
the step of connecting each representative point comprises the steps of establishing a connection relation:
Extracting key points on each track one by one based on each track sequence, and generating a key point sequence of each track; sequentially connecting representative points in a form of directed edges based on the key point sequences to generate a first route branch diagram;
Correcting the connection relation in the first route map to generate a second route branch map;
correcting the connection relation in the second route map to generate a third route branch map;
adding the directed edge to the third route branch graph to generate a fourth route branch graph;
Correcting the connection relation in the fourth route branch diagram to obtain a final route branch diagram;
Wherein said modifying the connection relationship in the first route pattern to generate a modification in a second route branch pattern includes removing directed edges that satisfy a rule, the removal rule including:
if the weight of the directed edge is smaller than a preset value, removing the directed edge;
If the difference value of the length parameters of the end point and the starting point of the directed edge is larger than a first preset threshold value or smaller than a second preset threshold value, the directed edge is removed from the first route pattern;
Correcting the connection relation in the second route map, wherein the connection relation comprises adding a directed edge for a representative point with zero incidence, and the adding rule comprises:
If the directional edge takes the representative point as the end point, the difference value of the length parameters of the end point and the starting point of the directional edge is larger than zero, and the degree of departure of the starting point is zero, adding the directional edge to the second route branch diagram to generate a third route branch diagram;
if the third route branch diagram also has a representative point with zero entering degree, arranging each representative point in the third route branch diagram in ascending order according to the length parameters of each representative point, then connecting the last representative point of the representative points with the representative point to generate a directed edge, and adding the directed edge to the third route branch diagram to generate a fourth route branch diagram;
Correcting the connection relation in the fourth route branch diagram to obtain a final route branch diagram, including:
If a plurality of representative points with zero degree exist in the fourth route branch diagram, only the representative point with the maximum length parameter is reserved, and the representative points with the zero degree and the directed edges thereof are removed;
and if the first representative point, the second representative point, the third representative point, the directed edge from the first representative point to the second representative point, the directed edge from the second representative point to the third representative point, and the substructure of the directed edge from the first representative point to the third representative point exist in the fourth route branching diagram, and the shortest distance from the second representative point to the navigation section where the first representative point and the third representative point are located is smaller than twice of the preset distance, removing the second representative point.
2. The method of track extraction according to claim 1, wherein,
Before the step of extracting the key points of each track, preprocessing the historical track data, wherein the preprocessing comprises the following steps:
Removing abnormal data and/or repeated data in the historical track data to obtain first track data;
Segmenting each piece of first track data, and resampling the segmented tracks to obtain second track data;
and removing abnormal data in the second track data according to the first preset speed to obtain third track data.
3. The track extraction method according to claim 1, wherein the length parameter of the key point on each track is calculated according to the key point sequence of each track.
4. A track extraction device is characterized in that,
The acquisition module is used for acquiring historical track data to be extracted;
the key point extraction module is used for extracting key points of each track according to the historical track data;
The key points of extracting each track comprise: taking the starting point of each track as a first key point, taking the end point as a last key point, and extracting the current point as a key point if the course difference between the current point and the nearest key point is larger than a preset angle and the speed of the current point is larger than a second preset speed;
the representative point extraction module is used for clustering the key points and extracting representative points from each category;
The extracting representative points from each category comprises: if the key points in the category belong to a plurality of track sequences, the category is reserved, otherwise, the category is deleted; calculating the average longitude, the average latitude and the average length parameter of each reserved category, and taking the point of the position where the average longitude, the average latitude and the average length parameter are located as a representative point;
The generation module is used for connecting each representative point and generating a route branch diagram;
the step of connecting each representative point comprises the steps of establishing a connection relation:
Extracting key points on each track one by one based on each track sequence, and generating a key point sequence of each track; sequentially connecting representative points in a form of directed edges based on the key point sequences to generate a first route branch diagram;
Correcting the connection relation in the first route map to generate a second route branch map;
correcting the connection relation in the second route map to generate a third route branch map;
adding the directed edge to the third route branch graph to generate a fourth route branch graph;
Correcting the connection relation in the fourth route branch diagram to obtain a final route branch diagram;
Wherein said modifying the connection relationship in the first route pattern to generate a modification in a second route branch pattern includes removing directed edges that satisfy a rule, the removal rule including:
if the weight of the directed edge is smaller than a preset value, removing the directed edge;
If the difference value of the length parameters of the end point and the starting point of the directed edge is larger than a first preset threshold value or smaller than a second preset threshold value, the directed edge is removed from the first route pattern;
Correcting the connection relation in the second route map, wherein the connection relation comprises adding a directed edge for a representative point with zero incidence, and the adding rule comprises:
If the directional edge takes the representative point as the end point, the difference value of the length parameters of the end point and the starting point of the directional edge is larger than zero, and the degree of departure of the starting point is zero, adding the directional edge to the second route branch diagram to generate a third route branch diagram;
if the third route branch diagram also has a representative point with zero entering degree, arranging each representative point in the third route branch diagram in ascending order according to the length parameters of each representative point, then connecting the last representative point of the representative points with the representative point to generate a directed edge, and adding the directed edge to the third route branch diagram to generate a fourth route branch diagram;
Correcting the connection relation in the fourth route branch diagram to obtain a final route branch diagram, including:
If a plurality of representative points with zero degree exist in the fourth route branch diagram, only the representative point with the maximum length parameter is reserved, and the representative points with the zero degree and the directed edges thereof are removed;
and if the first representative point, the second representative point, the third representative point, the directed edge from the first representative point to the second representative point, the directed edge from the second representative point to the third representative point, and the substructure of the directed edge from the first representative point to the third representative point exist in the fourth route branching diagram, and the shortest distance from the second representative point to the navigation section where the first representative point and the third representative point are located is smaller than twice of the preset distance, removing the second representative point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910294950.2A CN111813877B (en) | 2019-04-12 | 2019-04-12 | Track extraction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910294950.2A CN111813877B (en) | 2019-04-12 | 2019-04-12 | Track extraction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111813877A CN111813877A (en) | 2020-10-23 |
| CN111813877B true CN111813877B (en) | 2024-05-03 |
Family
ID=72843961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910294950.2A Active CN111813877B (en) | 2019-04-12 | 2019-04-12 | Track extraction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111813877B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112885099B (en) * | 2021-03-10 | 2022-05-17 | 华录易云科技有限公司 | Method, device and equipment for determining key points of vehicle track |
| CN113267192B (en) * | 2021-05-26 | 2023-04-14 | 海南太美航空股份有限公司 | Method and system for improving cross route rendering efficiency |
| CN113269669B (en) * | 2021-05-26 | 2023-05-09 | 海南太美航空股份有限公司 | Hierarchical rendering method and system for airlines |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS63111484A (en) * | 1986-10-28 | 1988-05-16 | Furuno Electric Co Ltd | Track display device |
| JPH05224935A (en) * | 1992-02-13 | 1993-09-03 | Meidensha Corp | Meta-rule generating method for expert system |
| WO2004107210A1 (en) * | 2003-05-28 | 2004-12-09 | Celestar Lexico-Sciences, Inc. | Pathway information display device |
| CN105389670A (en) * | 2015-12-07 | 2016-03-09 | 浙江大学 | Power grid node importance degree determination method |
| CN106546244A (en) * | 2016-10-26 | 2017-03-29 | 吉林大学 | It is a kind of to hinder the method that boat thing determines ship's navigation local optimum path for convex |
| CN106600502A (en) * | 2016-08-16 | 2017-04-26 | 南京航空航天大学 | Topological modeling method of multi-airport terminal area course network |
| 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 |
-
2019
- 2019-04-12 CN CN201910294950.2A patent/CN111813877B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS63111484A (en) * | 1986-10-28 | 1988-05-16 | Furuno Electric Co Ltd | Track display device |
| JPH05224935A (en) * | 1992-02-13 | 1993-09-03 | Meidensha Corp | Meta-rule generating method for expert system |
| WO2004107210A1 (en) * | 2003-05-28 | 2004-12-09 | Celestar Lexico-Sciences, Inc. | Pathway information display device |
| CN105389670A (en) * | 2015-12-07 | 2016-03-09 | 浙江大学 | Power grid node importance degree determination method |
| CN106600502A (en) * | 2016-08-16 | 2017-04-26 | 南京航空航天大学 | Topological modeling method of multi-airport terminal area course network |
| CN106546244A (en) * | 2016-10-26 | 2017-03-29 | 吉林大学 | It is a kind of to hinder the method that boat thing determines ship's navigation local optimum path for convex |
| 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 |
Non-Patent Citations (4)
| Title |
|---|
| Mingyu Liu ; Yong Ding ; Xiang Wang ; Xiaolang Yan.Gamma correction with revised piecewise curve and edge directed error diffusion.IEEE.2009,全文. * |
| 基于AIS航迹和Douglas-Peucker算法的航线自动生成方法研究;张树凯;杨家轩;蔡垚;史国友;;重庆交通大学学报(自然科学版);33(06);79-117 * |
| 基于位置服务的智能交通应用关键技术研究;何雯;工程科技Ⅱ辑;20160715;全文 * |
| 基于贝叶斯网络的船撞桥风险评估研究;杨祥睿;工程科技Ⅰ辑;20160415;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111813877A (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111813877B (en) | Track extraction method and device | |
| CN110413905B (en) | Method, device and equipment for acquiring road alignment and storage medium | |
| CN109993064B (en) | Method for extracting connection path between road network nodes in picture | |
| CN113344089B (en) | Model training method and device and electronic equipment | |
| CN114564545A (en) | System and method for extracting ship experience course based on AIS historical data | |
| CN112634612B (en) | Intersection flow analysis method and device, electronic equipment and storage medium | |
| CN116028499B (en) | Detection information generation method, electronic device, and computer-readable medium | |
| CN113985406B (en) | Target track splicing method for marine radar | |
| CN114581794A (en) | Geographic digital twin information acquisition method and device, electronic equipment and storage medium | |
| CN112883236A (en) | Map updating method, map updating device, electronic equipment and storage medium | |
| CN116524209A (en) | Line structure light line extraction method and device, storage medium and electronic equipment | |
| CN113780532A (en) | Training method, device and equipment for semantic segmentation network and storage medium | |
| CN112798006B (en) | Method, device, storage medium and terminal for analyzing difference points of different paths | |
| CN116347346B (en) | Fence drawing method and device | |
| CN116828397B (en) | Track information acquisition method and device, electronic equipment and storage medium | |
| CN112233131B (en) | Method, device and equipment for dividing land block and storage medium | |
| CN114677570B (en) | Road information updating method, device, electronic equipment and storage medium | |
| CN116415381A (en) | Virtual offshore traffic network construction method and device, electronic equipment and storage medium | |
| CN116828391B (en) | Method for detecting AIS abnormal switch | |
| CN107832348B (en) | Method for processing network data stream from intelligent acquisition terminal to cloud | |
| CN117671181B (en) | Method and system for constructing smart city contracture map based on big data | |
| CN114419357B (en) | Data processing method, data processing device, computer and readable storage medium | |
| CN114383600B (en) | Processing method and device for map, electronic equipment and storage medium | |
| CN118245826A (en) | Sewage treatment area dividing method, device, equipment and storage medium | |
| CN115376004A (en) | Method and system for excavating channel boundary and center line facing AIS ship track big data |
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 |