CN115660027B - Multi-equipment sea area target data generation method and system supporting small samples - Google Patents
Multi-equipment sea area target data generation method and system supporting small samples Download PDFInfo
- Publication number
- CN115660027B CN115660027B CN202211234485.1A CN202211234485A CN115660027B CN 115660027 B CN115660027 B CN 115660027B CN 202211234485 A CN202211234485 A CN 202211234485A CN 115660027 B CN115660027 B CN 115660027B
- Authority
- CN
- China
- Prior art keywords
- data
- track
- sea area
- submarine
- real
- 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
Images
Classifications
-
- 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
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a method and a system for generating multi-equipment sea area target data supporting small samples, wherein the method comprises the following steps: acquiring sea area original data; constructing a data generation model based on sea area original data; and obtaining the generated track data of the ship and the generated track data of the submarine based on the data generation model. The multi-equipment sea area target data generation system supporting the small samples constructed by the invention can generate multi-equipment scene data of the submarine, radar and sonar based on the input data of the equipment configuration module, and can view the configuration data for reference and adjustment. By adopting the technical scheme, sufficient multi-mode sea area target data can be obtained on the basis of small sample data, reliable submarine track data is provided for subsequent sea area target research work, a submarine track database is expanded, the expansion of a submarine track data set is realized, and then radar and sonar multi-equipment data generation is completed on the basis of the generated submarine track data.
Description
Technical Field
The invention belongs to the technical field of sea area monitoring, and particularly relates to a method and a system for generating multi-equipment sea area target data supporting small samples.
Background
The sea area is a new living development space and resource treasury for human beings. With the development of observation technology, the wide application of various sensors, monitoring systems and means for receiving external remote sensing information of various satellites is gradually prosperous in the development of maritime industry. China is used as a land-sea composite country, has rich ocean resources, has special strategic positions, and is particularly important for maritime safety.
In order to better maintain sea area safety and realize sea area monitoring, target detection and re-identification, abnormal event warning, danger prediction and other algorithm analysis are required to be carried out on sea area targets, but a large amount of data is required, and the quality requirement on a data set is high. However, the following problems exist with real data that cannot be used for algorithm training. Firstly, the data contains sensitive information such as position, real-time motion and the like, and is influenced by factors such as data confidentiality and the like, the number of disclosures is limited, the speed is low, and the searching is difficult. Secondly, the data acquisition work of sea area targets mainly focuses on single sensor means, the time span and the equipment detection capability are limited, the space coverage capability is insufficient, and the acquired data quality is not uniform. Finally, in an actual sea area application scene, the whole working cycle of the sea area walk target and the monitoring equipment is mostly in a normal working state, and data of an abnormal scene are difficult to collect. In summary, the lack of an effective data source is one of the key factors restricting the research of the related algorithms of the sea area monitoring management. The acquired sea area real data has the characteristics of small samples and unbalanced distribution, so that in the subsequent research, the accuracy of results obtained by complex algorithm processing is poor, and the actual application requirements are difficult to meet.
Therefore, how to obtain sufficient multi-mode sea area target data based on small sample data and apply the multi-mode sea area target data to the technical field of sea area monitoring is a difficult problem to be solved urgently.
Disclosure of Invention
The invention aims to provide a multi-device sea area target data generation method and system supporting small samples, so as to solve the problems.
In order to achieve the above object, in one aspect, the present invention provides a method for generating multi-device sea area target data supporting small samples, including:
acquiring sea area original data; the sea area original data comprise track data of a ship and track data of a submarine;
constructing a data generation model based on sea area original data;
and obtaining the generated track data of the ship and the generated track data of the submarine based on the data generation model.
Optionally, preprocessing is needed to be performed on the sea area original data before the data generation model is built, noise points are removed, and real sea area data are obtained, wherein the real sea area data comprise real ship track data and real submarine generation track data.
Optionally, constructing the data generation model includes:
mixing based on real ship track dataSuperposition coding to construct a first hidden vector Z A ；
Aliasing encoding is carried out on the basis of generated track data of a real submarine to construct a second hidden vector Z B ；
First hidden vector Z constructed by using track decoder of submarine A Decoding to obtain generated track data of the submarine; second hidden vector Z constructed by decoder of ship track B Decoding to obtain generated track data of the ship; repeating the above process until the first hidden vector Z A And a second hidden vector Z B And if the same distribution space is satisfied, the optimization of the generated algorithm model is completed.
Optionally, before performing the aliasing encoding, adopting a transfer learning method, taking real ship track data as source field data and real submarine track data as target field data, and respectively performing synchronous training on the ship track and the submarine track.
In order to achieve the above object, the present invention further discloses a multi-device sea area target data generating system supporting small samples, including:
the acquisition module is used for acquiring sea area original data in the sea area to be detected;
the data generation module is used for processing the sea area original data and generating simulation data meeting the requirements;
and the view display module is used for inquiring the generated result and referring to the use.
Optionally, the system further comprises a device configuration module, the device configuration module comprising:
a database for storing data related to the sea area;
the data table is used for storing related data of the equipment in the sea area to be detected;
and the attribute configuration module is used for configuring the attributes of the acquisition module based on the information in the data table.
Optionally, the device configuration module further includes a data storage module for storing simulation data.
Optionally, the device configuration module further includes an abnormal event simulation module, configured to simulate an abnormal event occurring in the acquisition module based on the set occurrence probability of the abnormal event.
Optionally, the abnormal event generated by the analog acquisition module adopts a double-probability joint distribution mode.
Optionally, the data generating module includes:
the submarine navigation path generating unit is used for generating three-dimensional navigation path data of the submarine navigation of the cruise equipment;
the sonar data generation unit is used for generating data of the working state of the monitoring equipment sonar;
and the radar data generation unit is used for generating data of the working state of the radar of the monitoring equipment.
The invention has the technical effects that: the invention discloses a multi-equipment sea area target data generation method supporting small samples, which comprises the following steps: acquiring sea area original data; constructing a data generation model based on sea area original data; and obtaining the generated track data of the ship and the generated track data of the submarine based on the data generation model. The multi-equipment sea area target data generation system supporting the small samples constructed by the invention can generate multi-equipment scene data of the submarine, radar and sonar based on the input data of the equipment configuration module, and can view the configuration data for reference and adjustment. By adopting the technical scheme, sufficient multi-mode sea area target data can be obtained on the basis of small sample data, reliable submarine track data is provided for subsequent sea area target research work, a submarine track database is expanded, the expansion of a submarine track data set is realized, and then radar and sonar multi-equipment data generation is completed on the basis of the generated submarine track data.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a flow chart of a method for generating multi-device sea area target data supporting small samples according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a multi-device sea area target data generation system supporting small samples according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a model structure for optimizing a data generation model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a sonar data generation method according to an embodiment of the present invention.
Detailed Description
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
As shown in fig. 1, in this embodiment, a method for generating target data of a multi-device sea area supporting small samples is provided, including:
s100, acquiring sea area original data; the sea area original data comprise track data of a ship and track data of a submarine;
s200, constructing a data generation model based on sea area original data;
and S300, obtaining generated track data of the ship and generated track data of the submarine based on the data generation model.
In an alternative embodiment, preprocessing the sea area original data is further included after the sea area original data is obtained, noise points are removed, and real sea area data are obtained, wherein the real sea area data comprise real ship track data and real submarine generating track data. The noise points are abnormal track points, the abnormal track points are found through speed calculation, and the abnormal track points are deleted. The abnormal track points are: some track points have points with problems of abnormal positions and large track offsets.
If the position of each track noise point is found carefully in a large number of data sets, not only is time consuming but also the cost is high. Therefore, in this embodiment, the original data set is first divided into regions, geographical position information of a certain key region is defined, and track points not in the region are deleted. Secondly, taking a water ship track data set as an example, abnormal track points are found, and for ship data with a large number of track points, the influence of deleting a small part of track points is not great.
In an alternative embodiment, as shown in FIG. 3, constructing the data generation model includes:
performing aliasing encoding based on real ship track data to construct a first hidden vector Z A ；
Aliasing encoding is carried out on the basis of generated track data of a real submarine to construct a second hidden vector Z B ；
First hidden vector Z constructed by using track decoder of submarine A Decoding to obtain generated track data of the submarine; second hidden vector Z constructed by decoder of ship track B Decoding to obtain generated track data of the ship; the process is repeated until the first hidden vector Z A And a second hidden vector Z B And if the same distribution space is satisfied, the optimization of the generated algorithm model is completed.
In this embodiment, the data generation model takes a time series of fixed step samples as input, takes a VAE model as a main body, takes a GRU model as an encoder and a decoder, and analyzes correlation of time series data by the GRU.
The method comprises the steps of taking real ship track data as input of a VAE1, performing aliasing encoding on the real ship track data through a GRU encoder EncoderA, fitting the real ship track data to obtain the mean value and variance of sample distribution of a real ship track sequence, and constructing a first hidden vector Z containing deep information of the real sample A . The generated track data of the submarine is used as the input of the VAE2, aliasing encoding is carried out on the generated track data of the submarine through a GRU encoder EncoderB, the mean value and the variance of the sample distribution of the real submarine track sequence are obtained, and the second hidden vector Z is obtained B The method comprises the steps of carrying out a first treatment on the surface of the First hidden vector Z constructed by using submarine track decoder DecoderB to EncoderA A Decoding is carried out, and generated track data of the submarine is obtained. Similarly, a second hidden vector Z constructed by using a ship track decoder DecoderA to EncoderB B DecodingObtaining generation track data of the ship; repeating the above process until the hidden vector Z obtained from the real data of the water vessel A Hidden vector Z acquired from real data of underwater vehicle B And if the same distribution space is met, the optimization of the generation algorithm model is completed, the expansion of a small number of samples of the navigation path of the underwater vehicle is realized, and the generation of the navigation path data of the underwater vehicle is completed.
Further, as shown in fig. 4, a schematic diagram of a sonar data generation method is shown, in which a picture background is a mapping plane of a side scan range, a coordinate system is established according to a working range of the side scan sonar, a position where the side scan sonar is located is an O point, and a sector-shaped middle line (marked with a white line) is set as a positive direction of 0 °.
In an alternative embodiment, before performing aliasing encoding, a migration learning method is adopted, real ship track data is used as source field data, real submarine track data is used as target field data, and synchronous training is performed on the ship track and the submarine track respectively.
In one embodiment, as shown in fig. 2, the invention discloses a multi-device sea area target data generation system supporting small samples, comprising:
the acquisition module is used for acquiring sea area original data in the sea area to be detected;
the data generation module is used for processing the sea area original data and generating simulation data meeting the requirements; the simulation data can further expand the database of the target data for the underwater vehicle data with small samples and unbalanced distribution characteristics;
and the view display module is used for inquiring the generated result and referring to the use.
Specifically, the target of the parade in the sea area comprises a submarine, so that the sea area original data is data related to the submarine, for example, a sonar sensor and a radar sensor can be used for monitoring the submarine;
in this embodiment, the view display module provides the operation interface for the researcher to visually query target information in different time periods and different area ranges in the form of web application, and when a specific target is observed, statistics and display are performed on ship or submarine track point data meeting the preset query time range and the requirements of the sea area, so that the multi-mode data are displayed at the same time. And reading the data records of the self and the monitoring sensor through the switching of the dynamic tag.
Furthermore, the front-end page of the display module can be checked by using CSS, javaScript and html, a visual operation page is provided for researchers, and a background is written by using java based on a Spring Boot frame and is responsible for realizing background business logic and data information. And the researchers input the time period and the area range of the query in the corresponding text box of the html webpage according to the own needs, the system queries the track data information of the time and the area range in the database, and the information reference is carried out by the researchers in a longitude and latitude dotting form after statistics. The back end is provided with a response state code and response information message, and the front end judges the interface state according to the returned corresponding information.
In an alternative embodiment, a multi-device sea area target data generation system supporting small samples further comprises a device configuration module comprising:
a database for storing data related to the sea area;
the data table is used for storing related data of the equipment in the sea area to be detected;
and the attribute configuration module is used for configuring the attributes of the acquisition module based on the information in the data table.
In the embodiment, a MySQL database is used for storing data such as a submarine navigation path and the like, and seven data tables including a submarine navigation attribute information table, a submarine navigation path point information table, a sonar sensor information table, a radar sensor information table, a flight path information table, an abnormal configuration information table and an abnormal event information table are arranged to store related data.
Specifically, the attribute information table of the underwater vehicle stores the data information of all the attribute of the underwater vehicle, and the table mainly comprises information such as target ID, longitude and latitude position, start and stop time and the like;
the information table of the navigation points of the underwater vehicle stores the data information of all the navigation points of the underwater vehicle, and the table mainly comprises information such as the navigation ID, the position data of the navigation points of the underwater vehicle, the storage time and the like;
the sonar sensor information table stores target data information monitored by the sonar, the table mainly comprises information of the position of a target monitored by the sonar, the angle of the target and the like, the target type is stored by using TINYINT, 0 represents a submarine, 1 represents a frogman, 2 represents reefs and 3 represents marine organisms;
the radar sensor information table stores information of targets monitored by a radar, the table mainly comprises information such as positions acquired by radar scanning targets, distances between the targets and the radar, and the like, the types of the targets are stored by using TINYIN, 0 represents a ship, and 1 represents a submarine;
the track information table is used for storing information of all tracks, and mainly comprises information of track types, track states, track start dates and the like, wherein the track types are stored by using TINYIN, 0 represents a ship, 1 represents a submarine, 2 represents a radar, and 3 represents a sonar;
the abnormal configuration information table stores information of abnormal event attributes, and the table comprises information such as a walk target, probability of abnormal event occurrence of a monitoring sensor and the like;
the abnormal event information table stores information of occurrence of abnormal events, and mainly comprises information of start and stop time of the abnormal events, types of the abnormal events and the like.
The checking and displaying module is connected with the attribute setting and configuring module and is used for checking configuration information, confirming, editing and modifying the configuration information, generating target data meeting the requirement after confirmation, and storing the generated data into the MySQL database.
In an alternative embodiment, the device configuration module further comprises a data storage module for storing simulation data.
In an optional embodiment, the device configuration module further includes an abnormal event simulation module, configured to simulate an abnormal event occurring in the acquisition module based on the set occurrence probability of the abnormal event. The abnormal event simulation module is connected with the attribute configuration module,
in this embodiment, three major classes, five minor classes of exception events are defined altogether. Events are classified into three main categories according to the device body in which the abnormal event occurs: the system comprises a sonar sensor event, a radar sensor event and an underwater submarine event, wherein the sonar sensor event and the radar sensor event are respectively in a non-working abnormal state. The abnormal event definition of the underwater vehicle is that the abnormal occurrence is perceived based on track data, and the abnormal occurrence is not limited to a certain position point in a space domain or the problem of the underwater vehicle sub-track, and a certain probability is related to various factors such as time dimension, data acquisition means and the like.
In an alternative embodiment, the abnormal events generated by the analog acquisition module take the form of a dual probability joint distribution. For the cruise target underwater vehicle, a relation coefficient between the cruise target underwater vehicle and the navigation distance is defined. As the distance travelled by a submarine increases, the probability of an abnormal event occurring therein increases. The correlation coefficients between the submarine and the distance travelled will also vary with different types of anomaly. Similarly, for sonar and radar sensor monitoring devices, reading probability values for abnormal event types, the sea needs to define their functional relationship with influencing factors (e.g., working time).
In an alternative embodiment, the data generation module includes:
the submarine navigation path generating unit is used for generating three-dimensional navigation path data of the submarine navigation of the cruise equipment;
the sonar data generation unit is used for generating data of the working state of the monitoring equipment sonar;
and the radar data generation unit is used for generating data of the working state of the radar of the monitoring equipment.
In the embodiment, a submarine track generating unit generates three-dimensional track data and calculates and analyzes probability of an abnormal event for a cruise equipment submarine according to an equipment configuration module and an abnormal simulation module; the sonar data generation unit is used for generating data of the working state of the monitoring equipment sonar according to the settings of the sonar detection scanning direction, the detection distance and the like; and the radar data generation unit is used for generating data of the working state of the radar of the monitoring equipment according to the settings of the radar detection moving step length, the time interval and the like.
Further, the scanning direction, the scanning angle and the detection distance of the side-scan sonar are selected in the configuration module, and the direction of the target object is detected based on the positive direction. According to the depth of the sea area where the target object is located and the longitude and latitude position points obtained after projection on the sea level, the distance between the position points and the sonar sensor is calculated, and according to the Pythagorean theorem and the trigonometric function, the position of the target after scanning and the distance and the angle between the target and the sonar are obtained.
In the description of the present specification, reference to the terms "one embodiment," "one particular embodiment," "some embodiments," "for example," "an example," "a particular example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. The order of steps involved in the embodiments is illustrative of the practice of the invention, and is not limited and may be suitably modified as desired.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (7)
1. A multi-device sea area target data generation method supporting small samples, comprising:
acquiring sea area original data; the sea area original data comprise track data of a ship and track data of a submarine;
preprocessing sea area original data based on the sea area original data, removing noise points to obtain real sea area data, and constructing a data generation model based on the real sea area data; the real sea area data comprise real ship track data and real submarine generated track data;
the constructing of the data generation model comprises the following steps: adopting a transfer learning method, taking real ship track data as source field data and real submarine track data as target field data, and respectively carrying out synchronous training on the ship track and the submarine track;
performing aliasing encoding based on the trained real ship track data to construct a first hidden vector
The method comprises the steps of carrying out a first treatment on the surface of the Performing aliasing encoding based on the generated track data of the trained real submarine to construct a second hidden vector +.>
The method comprises the steps of carrying out a first treatment on the surface of the First hidden vector constructed by using track decoder of submarine>
Decoding to obtain generated track data of the submarine; second hidden vector constructed by decoder of ship track>
Decoding to obtain generated track data of the ship; repeating the above process until the first hidden vector +.>
And a second hidden vector->
The optimization of the generated algorithm model is completed if the same distribution space is satisfied;
and obtaining the generated track data of the ship and the generated track data of the submarine based on the data generation model.
2. A multi-device sea area target data generation system supporting small samples, comprising:
the acquisition module is used for acquiring sea area original data in the sea area to be detected, wherein the sea area original data comprise track data of a ship and track data of a submarine;
the data generation module is used for processing the sea area original data, removing noise points to obtain real sea area data, and constructing a data generation model based on the real sea area data; obtaining generation track data of a ship and generation track data of a submarine based on a data generation model, wherein the real sea area data comprise real ship track data and real submarine generation track data;
the constructing of the data generation model comprises the following steps: adopting a transfer learning method, taking real ship track data as source field data and real submarine track data as target field data, and respectively carrying out synchronous training on the ship track and the submarine track;
performing aliasing encoding based on the trained real ship track data to construct a first hidden vector
The method comprises the steps of carrying out a first treatment on the surface of the Performing aliasing encoding based on the generated track data of the trained real submarine to construct a second hidden vector +.>
The method comprises the steps of carrying out a first treatment on the surface of the First hidden vector constructed by using track decoder of submarine>
Decoding to obtain generated track data of the submarine; second hidden vector constructed by decoder of ship track>
Decoding to obtain generated track data of the ship; repeating the above process until the first hidden vector +.>
And a second hidden vector->
The optimization of the generated algorithm model is completed if the same distribution space is satisfied;
and the view display module is used for inquiring the generated result and referring to the use.
3. The system of claim 2, further comprising a device configuration module, the device configuration module comprising:
a database for storing data related to the sea area;
the data table is used for storing related data of the equipment in the sea area to be detected;
and the attribute configuration module is used for configuring the attributes of the acquisition module based on the information in the data table.
4. The system of claim 3, wherein the device configuration module further comprises a data storage module for storing simulation data.
5. The system of claim 4, wherein the device configuration module further comprises an abnormal event simulation module for simulating an abnormal event occurring in the acquisition module based on the set occurrence probability of the abnormal event.
6. The system of claim 5, wherein the anomaly events occurring at the simulation acquisition module take the form of a dual probability joint distribution.
7. The system of claim 5, wherein the data generation module comprises:
the submarine navigation path generating unit is used for generating three-dimensional navigation path data of the submarine navigation of the cruise equipment;
the sonar data generation unit is used for generating data of the working state of the monitoring equipment sonar;
and the radar data generation unit is used for generating data of the working state of the radar of the monitoring equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211234485.1A CN115660027B (en) | 2022-10-10 | 2022-10-10 | Multi-equipment sea area target data generation method and system supporting small samples |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211234485.1A CN115660027B (en) | 2022-10-10 | 2022-10-10 | Multi-equipment sea area target data generation method and system supporting small samples |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115660027A CN115660027A (en) | 2023-01-31 |
| CN115660027B true CN115660027B (en) | 2023-05-23 |
Family
ID=84987859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211234485.1A Active CN115660027B (en) | 2022-10-10 | 2022-10-10 | Multi-equipment sea area target data generation method and system supporting small samples |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660027B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112132346A (en) * | 2020-09-24 | 2020-12-25 | 中国科学院空天信息创新研究院 | Ship navigation track prediction method based on ship type |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3091358B1 (en) * | 2018-12-27 | 2020-12-11 | Thales Sa | Device for generating a set of simulated sea clutter data, associated method and computer program |
| CN113177264B (en) * | 2021-05-11 | 2022-06-24 | 北京邮电大学 | Sea area target object multi-dimensional data simulation method and system based on generation countermeasure network |
| CN113988259B (en) * | 2021-10-27 | 2024-05-14 | 河北工业大学 | Real-time abnormality detection method for thermal power generating unit operation parameters based on VAE-GRU |
| CN114997296A (en) * | 2022-05-26 | 2022-09-02 | 中国人民解放军战略支援部队信息工程大学 | Unsupervised track anomaly detection method and unsupervised track anomaly detection system based on GRU-VAE model |
-
2022
- 2022-10-10 CN CN202211234485.1A patent/CN115660027B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112132346A (en) * | 2020-09-24 | 2020-12-25 | 中国科学院空天信息创新研究院 | Ship navigation track prediction method based on ship type |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115660027A (en) | 2023-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2951533C (en) | Automated generation of digital elevation models | |
| Mitchell et al. | Sensitivity of fine‐scale species distribution models to locational uncertainty in occurrence data across multiple sample sizes | |
| Stewart Jr | Multisensor modeling underwater with uncertain information | |
| Wawrzyniak et al. | MSIS image postioning in port areas with the aid of comparative navigation methods | |
| Smith | The navigation surface: a multipurpose bathymetric database | |
| CN112526490B (en) | Underwater small target sonar detection system and method based on computer vision | |
| CN113486574A (en) | Sound velocity profile completion method and device based on historical data and machine learning | |
| CN114463620A (en) | Side-scan sonar marine substrate identification method and device based on YOLOv5 | |
| Makar et al. | Seabed Topography Changes in the Sopot Pier Zone in 2010–2018 Influenced by Tombolo Phenomenon | |
| CN115660027B (en) | Multi-equipment sea area target data generation method and system supporting small samples | |
| Drap et al. | Underwater cartography for archaeology in the VENUS project | |
| Lovrinčević | Quality assessment of an automatic sounding selection process for navigational charts | |
| Dias et al. | Detection of discrepancies between nautical charts and new survey data using GIS techniques | |
| Young et al. | Initialization and setup of the Coastal Model Test Bed: integrated bathymetry | |
| Stewart | A non-deterministic approach to 3-D modeling underwater | |
| CN116299374B (en) | Sonar imaging underwater automatic calibration positioning method and system based on machine vision | |
| EP4152270A1 (en) | Method of generating an interactive three-dimensional simulation of a section of an industrial facility | |
| Klockmann | Optimization of software for modeling acoustic monitoring systems | |
| Jia et al. | A Case-Based Reasoning Method for Generalizing Depth Contours considering Both Navigational Safety Assurance and Line Shape Preservation | |
| Kermarrec et al. | Optimal Surface Fitting of Point Clouds Using Local Refinement: Application to GIS Data | |
| Lehman | Mapping: Measuring, modelling and monitoring the oceans | |
| Mostafi | Visualizing geospatial uncertainty in marine animal tracks | |
| Maleika et al. | Virtual multibeam echosounder in investigations on sea bottom modeling | |
| CN114815653A (en) | Unmanned ship task simulation test method and device | |
| Ecochard et al. | Case Study: Mapping Half Moon Caye’s Reef Using the Adaptive Bathymetric System (ABS) |
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 |