CN115660027A - Multi-device sea area target data generation method and system supporting small samples - Google Patents
Multi-device sea area target data generation method and system supporting small samples Download PDFInfo
- Publication number
- CN115660027A CN115660027A CN202211234485.1A CN202211234485A CN115660027A CN 115660027 A CN115660027 A CN 115660027A CN 202211234485 A CN202211234485 A CN 202211234485A CN 115660027 A CN115660027 A CN 115660027A
- Authority
- CN
- China
- Prior art keywords
- data
- sea area
- track
- underwater vehicle
- ship
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- 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
- Radar Systems Or Details Thereof (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a method and a system for generating multi-device 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 the sea area original data; and obtaining the generated track data of the ship and the generated track data of the underwater vehicle based on the data generation model. The multi-equipment sea area target data generation system supporting the small samples, which is constructed by the invention, can generate multi-scene data of the underwater vehicle, the radar and the sonar on the basis of the input data of the equipment configuration module, and can check the configuration data for reference and adjustment. By adopting the technical scheme, sufficient multi-modal sea area target data can be obtained on the basis of small sample data, reliable underwater vehicle track data is provided for subsequent sea area target research work, an underwater vehicle track database is expanded, the expansion of an underwater vehicle track data set is realized, and then the generation of radar and sonar multi-device data is completed on the basis of the generated underwater vehicle track data.
Description
Technical Field
The invention belongs to the technical field of sea area monitoring, and particularly relates to a multi-device sea area target data generation method and system supporting small samples.
Background
The sea area is a new living and developing space and resource treasury for human beings. With the development of observation technology, the development of shipping industry is gradually flourishing due to the wide application of various sensors, monitoring systems and means for receiving external various satellite remote sensing information. As a land-sea composite country, china has abundant marine resources, is special in strategic position, and is particularly important in marine safety.
In order to better maintain sea area safety and realize sea area monitoring, algorithm analysis such as target detection and re-identification, abnormal event warning, danger prediction and the like needs to be carried out on sea area targets, but a large amount of data is needed, and the requirement on the quality of a data set is high. However, the real data has the following problems 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 public quantity is limited, the speed is slow, and the searching is difficult. Secondly, the data acquisition work of the sea area target mostly focuses on a 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 operation period of the sea area wandering target and the monitoring equipment is mostly in a normal working state, and data of abnormal situations are difficult to acquire. In summary, the lack of effective data sources is one of the key factors restricting the research of algorithms related to sea area monitoring management. The acquired sea area real data has the characteristics of small samples and unbalanced distribution, so that the precision of results obtained by complex algorithm processing in subsequent researches is poor, and the actual application requirements are difficult to meet.
Therefore, how to obtain sufficient multi-modal sea area target data on the basis of small sample data and apply the multi-modal 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, and the method and system are used for solving 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 an underwater vehicle;
constructing a data generation model based on the sea area original data;
and obtaining the generated track data of the ship and the generated track data of the underwater vehicle based on the data generation model.
Optionally, before the data generation model is constructed, the sea area original data needs to be preprocessed to remove noise points, so that real sea area data is obtained, and the real sea area data comprises real track data of a ship and real track data generated by a submarine navigation device.
Optionally, building the data generation model comprises:
aliasing coding is carried out on track data based on a real ship, and a first hidden vector Z is constructed A ；
Aliasing coding is carried out on the generated flight path data based on the real underwater vehicle, and a second implicit vector Z is constructed B ；
First hidden vector Z constructed by track decoder pair of underwater vehicle A Decoding is carried out, and generated track data of the underwater vehicle are obtained; second hidden vector Z constructed by decoder of ship track B Decoding to obtain the generated track data of the ship; repeating the above process until the first implicit vector Z A And a second latent vector Z B And if the same distribution space is satisfied, the optimization of the generation algorithm model is completed.
Optionally, before performing aliasing coding, a transfer learning method is adopted, real ship track data is used as source field data, real underwater vehicle track data is used as target field data, and ship track and underwater vehicle track are synchronously trained respectively.
On the other hand, in order to achieve the above object, the present invention also discloses a multi-device sea area target data generation system supporting small samples, including:
the acquisition module is used for acquiring sea area original data in a sea area to be detected;
the data generation module is used for processing the sea area original data to generate simulation data meeting the requirements;
and the viewing display module is used for inquiring the generated result and referring to the generated result for use.
Optionally, the system further includes an apparatus configuration module, where the apparatus configuration module includes:
a database for storing data related to a sea area;
the data table is used for storing relevant data of equipment in the sea area to be tested;
and the attribute configuration module is used for performing attribute configuration on 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 the abnormal event occurring by the acquisition module based on the set occurrence probability of the abnormal event.
Optionally, the abnormal events occurring in the analog acquisition module adopt a double probability joint distribution mode.
Optionally, the data generating module includes:
the underwater vehicle track generation unit is used for generating three-dimensional track data of the underwater vehicle of the traveling equipment;
the sonar data generating 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 monitoring equipment radar.
The invention has the technical effects that: the invention discloses a multi-device 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 underwater vehicle based on the data generation model. The multi-equipment sea area target data generation system supporting the small samples, which is constructed by the invention, can generate multi-scene data of the underwater vehicle, the radar and the sonar on the basis of the input data of the equipment configuration module, and can check the configuration data for reference and adjustment. By adopting the technical scheme, sufficient multi-modal sea area target data can be obtained on the basis of small sample data, reliable underwater vehicle track data is provided for subsequent sea area target research work, an underwater vehicle track database is expanded, the expansion of an underwater vehicle track data set is realized, and then the generation of radar and sonar multi-device data is completed on the basis of the generated underwater vehicle track data.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
fig. 1 is a schematic flow chart of a method for generating multi-device sea area target data supporting a small sample according to an embodiment of the present invention;
FIG. 2 is a schematic structural 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 generating method according to an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
As shown in fig. 1, the present embodiment provides a method for generating multi-device sea area target data supporting a small sample, including:
s100, obtaining sea area original data; the sea area original data comprise track data of a ship and track data of an underwater vehicle;
s200, constructing a data generation model based on sea area original data;
and S300, obtaining the generated track data of the ship and the generated track data of the underwater vehicle based on the data generation model.
In an optional embodiment, after the sea area raw data is obtained, the sea area raw data is preprocessed to remove noise points to obtain real sea area data, and the real sea area data comprises track data of a real ship and generated track data of a real underwater vehicle. And searching for the abnormal track point through speed calculation, and deleting the abnormal track point. The abnormal track points are as follows: some track points have the problems of abnormal positions and large track offset.
If the positions of the noise points of each track are found out 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 specified, and track points that are not in this region are deleted. Secondly, take the marine vessel orbit data set as an example, look for unusual track point, for the marine vessel data that possess a large amount of track points, delete a small portion of track point, the influence is not very big.
In an alternative embodiment, as shown in FIG. 3, constructing the data generation model includes:
aliasing coding is carried out on track data based on a real ship, and a first hidden vector Z is constructed A ；
Aliasing coding is carried out on the generated flight path data based on the real underwater vehicle, and a second hidden vector Z is constructed B ；
First hidden vector Z constructed by track decoder pair of underwater vehicle A Decoding is carried out, and generated track data of the underwater vehicle are obtained; second hidden vector Z constructed by decoder of ship track B Decoding to obtain the generated track data of the ship; this process is repeated until the first hidden vector Z A And a second implicit vector Z B If the same distribution space is satisfied, the optimization of the generation algorithm model is completed。
In this embodiment, the data generation model takes a time sequence of fixed step sampling as an input, a VAE model as a main body, and a GRU model as an encoder and a decoder, and analyzes correlation of time sequence data through the GRU.
Using track data of a real ship as input of VAE1, performing aliasing coding on the track data of the real ship through a GRU encoder EncodeRA, fitting the aliasing coding to obtain a mean value and a variance of real ship track sequence sample distribution, and constructing a first implicit vector Z containing real sample deep information A . Taking the generated track data of the underwater vehicle as the input of VAE2, carrying out aliasing coding on the generated track data of the underwater vehicle through an EncoderB coder to obtain the mean value and the variance of the sample distribution of the track sequence of the real underwater vehicle, and obtaining a second hidden vector Z B (ii) a A first hidden vector Z constructed by an EncodeA by utilizing a DecoderB of an underwater vehicle track decoder A And decoding to obtain the generated track data of the underwater vehicle. Similarly, a second hidden vector Z constructed by a ship track decoder DecoderA to EncoderB is utilized B Decoding to obtain the generated track data of the ship; repeating the process till the hidden vector Z obtained by the real data of the water ship A Hidden vector Z obtained from real data of underwater vehicle B And if the same distribution space is satisfied, optimizing the generation algorithm model, expanding a small number of samples of the track of the underwater vehicle, and finishing the target of generating the track data of the underwater vehicle.
Further, as shown in fig. 4, a schematic diagram of a sonar data generating method, wherein the picture background is a side-scan sonar scanning range mapping plane, a coordinate system is established according to the working range of the side-scan sonar, the position of the side-scan sonar is an O point, and a fan-shaped middle line (marked by a white line) is set to be a 0 ° positive direction.
In an optional embodiment, before aliasing coding is performed, a transfer learning method is adopted, real ship track data is used as source domain data, real underwater vehicle track data is used as target domain data, and synchronous training is respectively performed on the ship track and the underwater vehicle track.
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 a sea area to be detected;
the data generation module is used for processing the sea area original data to generate simulation data meeting the requirements; the simulation data can further expand a database of the target data for underwater vehicle data with small samples and unbalanced distribution characteristics;
and the viewing display module is used for inquiring the generated result and referring to the generated result for use.
Specifically, the targets for traveling in the sea area include a submergence vehicle, so that the sea area raw data is relevant data of the submergence vehicle, for example, a sonar sensor and a radar sensor can be used for monitoring the submergence vehicle;
in this embodiment, the viewing and displaying module provides an operation interface for researchers to visually query target information in different time periods and different area ranges in a web application manner, and when a specific target is observed, ship or underwater vehicle track point data meeting the requirements of a preset query time range and a sea area is counted and displayed, and multi-mode data is displayed at the same time. And reading data records of the dynamic label and the monitoring sensor through switching of the dynamic label.
Furthermore, the front page of the display module can be viewed by using CSS, javaScript and html languages, a visual operation page is provided for researchers, and the background is compiled by using java language based on a Spring Boot frame and is responsible for realizing background service logic and data information. The researcher inputs the time period and the area range to be inquired in the corresponding text box of the html webpage according to the self requirement, the system inquires the flight path data information of the time and the area range in the database, and the information is provided for the researcher to refer through a longitude and latitude dotting mode after statistics. The back end sets response state code and message, and the front end judges interface state according to the returned information.
In an optional embodiment, a multi-device sea area target data generation system supporting small samples further comprises a device configuration module, the device configuration module comprising:
a database for storing data related to a sea area;
the data table is used for storing relevant data of equipment in the sea area to be tested;
and the attribute configuration module is used for performing attribute configuration on the acquisition module based on the information in the data table.
In the embodiment, a MySQL database is adopted to be responsible for storage of data such as the track of the underwater vehicle, and seven data tables including an underwater vehicle attribute information table, an underwater vehicle track point information table, a sonar sensor information table, a radar sensor information table, a track information table, an abnormal configuration information table and an abnormal event information table are arranged for storing relevant data.
Specifically, a submarine vehicle attribute information table stores data information of all submarine vehicle attributes, and the table mainly comprises information such as target ID, longitude and latitude positions, start and stop time and the like;
the track point information table of the underwater vehicle stores data information of all track points of the underwater vehicle, and the table mainly comprises track ID, position data of the track points of the underwater vehicle, storage time and other information;
the sonar sensor information table is used for storing data information of targets monitored by sonar, and mainly comprises information of positions of the targets monitored by the sonar, angles of the targets and the like, the types of the targets are stored by TINYINT, 0 represents a submarine, 1 represents a frogman, 2 represents a reef, and 3 represents marine organisms;
the radar sensor information table stores target information monitored by a radar, the table mainly comprises information such as positions obtained by scanning targets by the radar, distances between the targets and the radar, target types are stored by using TINYINT, 0 represents a ship, and 1 represents an underwater vehicle;
the flight path information table is used for storing information of all flight paths and mainly comprises information of flight path types, flight path states, flight path starting dates and the like, wherein the flight path types are stored by TINYINT, 0 represents a ship, 1 represents an underwater vehicle, 2 represents a radar and 3 represents a sonar;
the abnormal configuration information table stores the information of the abnormal event attribute, and the table comprises information of a wandering target, the probability of the abnormal event of the monitoring sensor and the like;
the abnormal event information table stores the information of the abnormal event, and the table mainly comprises the information of the abnormal event starting and ending time, the abnormal event type and the like.
The viewing and displaying module is connected with the attribute setting configuration module and used for viewing the configuration information, confirming and editing and modifying the configuration information, generating target data meeting the requirement after confirming without errors, and storing the generated data into the MySQL database.
In an optional 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 by 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 and five minor classes of abnormal events are defined. Events are classified into three categories according to the device body in which the abnormal event occurs: sonar sensor event, radar sensor event and underwater vehicle event, wherein sonar sensor event and radar sensor event are sonar, the radar is in non-work abnormal conditions respectively. The definition of the abnormal event of the underwater vehicle is realized, the abnormal occurrence is perceived on the basis of track data, the abnormal event is not only limited to a certain position point in a spatial domain or the problem of the sub-track of the underwater vehicle, and a certain probability is related to various factors such as time dimension, data acquisition means and the like.
In an optional embodiment, the abnormal events occurring in the simulation acquisition module are distributed in a dual probability joint mode. And for the traveling target underwater vehicle, defining a relation coefficient between the traveling target underwater vehicle and the traveling distance. As the distance traveled by the underwater vehicle is larger and larger, the probability of abnormal events of the underwater vehicle is increased. The correlation coefficient between the underwater vehicle and the sailing distance is different for different abnormal event types. Similarly, for sonar and radar sensor monitoring equipment, the probability value of the abnormal event type is read, and the sea needs to define the functional relationship between the abnormal event type and the influencing factors (such as working time).
In an optional embodiment, the data generating module includes:
the underwater vehicle track generation unit is used for generating three-dimensional track data of the underwater vehicle of the traveling equipment;
the sonar data generating 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 monitoring equipment radar.
In the embodiment, the underwater vehicle track generation unit generates three-dimensional track data and calculates and analyzes the probability of an abnormal event for the traveling equipment underwater vehicle according to the equipment configuration module and the abnormal simulation module; the sonar data generating 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 monitoring equipment radar according to the setting of the radar detection moving step length, the time interval and the like.
Furthermore, 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 on the basis of the positive direction. According to the depth of the sea area where the target object is located and longitude and latitude position points obtained after the target object is projected on the sea level, the distance between the position points and a sonar sensor is calculated, and according to the Pythagorean theorem and a trigonometric function, the position after the target is scanned and the distance and the angle between the target and the sonar are obtained.
In the description of the specification, reference to the description of "one embodiment," a specific embodiment, "" some embodiments, "" e.g., "an example," "a specific 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, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. 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 sequence of steps involved in the various embodiments is provided to schematically illustrate the practice of the invention, and the sequence of steps is not limited and can be suitably adjusted as desired.
As will be appreciated by one skilled in the art, 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 flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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 above-mentioned embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, and it should be understood that the above-mentioned embodiments are only examples of the present invention and should not be used to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A multi-device sea area target data generation method supporting small samples is characterized by comprising the following steps:
acquiring sea area original data; the sea area original data comprise track data of a ship and track data of an underwater vehicle;
constructing a data generation model based on the sea area original data;
and obtaining the generated track data of the ship and the generated track data of the underwater vehicle based on the data generation model.
2. The method according to claim 1, wherein the sea area raw data is preprocessed to remove noise points before the data generation model is constructed, so as to obtain real sea area data, wherein the real sea area data comprises track data of a real ship and generation track data of a real underwater vehicle.
3. The method of claim 2, wherein constructing a data generative model comprises:
aliasing coding is carried out on track data based on a real ship, and a first hidden vector Z is constructed A ；
Based onAliasing coding is carried out on the generated flight path data of the real underwater vehicle, and a second hidden vector Z is constructed B ；
First hidden vector Z constructed by track decoder pair of underwater vehicle A Decoding is carried out, and generated track data of the underwater vehicle are obtained; second hidden vector Z constructed by decoder of ship track B Decoding to obtain the generated track data of the ship; repeating the above process until the first implicit vector Z A And a second latent vector Z B And if the same distribution space is satisfied, the optimization of the generation algorithm model is completed.
4. The method according to claim 3, characterized in that before the aliasing coding is carried out, a transfer learning method is adopted, real ship track data is used as source domain data, real underwater vehicle track data is used as target domain data, and synchronous training is respectively carried out on the ship track and the underwater vehicle track.
5. A multi-device sea object data generation system supporting small samples, comprising:
the acquisition module is used for acquiring sea area original data in a sea area to be detected;
the data generation module is used for processing the sea area original data to generate simulation data meeting the requirements;
and the viewing display module is used for inquiring the generated result and referring to the generated result for use.
6. The system of claim 5, further comprising a device configuration module, the device configuration module comprising:
a database for storing data related to a sea area;
the data table is used for storing relevant data of equipment in the sea area to be tested;
and the attribute configuration module is used for performing attribute configuration on the acquisition module based on the information in the data table.
7. The system of claim 6, wherein the device configuration module further comprises a data storage module for storing simulation data.
8. The system of claim 6, wherein the device configuration module further comprises an abnormal event simulation module for simulating the abnormal event occurred by the obtaining module based on the set occurrence probability of the abnormal event.
9. The system of claim 8, wherein the abnormal events occurring in the analog acquisition module are distributed in a dual probability joint manner.
10. The system of claim 5, wherein the data generation module comprises:
the underwater vehicle track generation unit is used for generating three-dimensional track data of the underwater vehicle of the traveling equipment;
the sonar data generating 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 monitoring equipment radar.
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 true CN115660027A (en) | 2023-01-31 |
| CN115660027B 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) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118097342A (en) * | 2024-04-29 | 2024-05-28 | 广东省安全生产科学技术研究院 | Sonar-based model training method, estimating device, device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020136258A1 (en) * | 2018-12-27 | 2020-07-02 | Thales | Device for generating a simulated sea-clutter data set, and associated method and computer program |
| 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 |
| CN113177264A (en) * | 2021-05-11 | 2021-07-27 | 北京邮电大学 | Sea area target object multi-dimensional data simulation method and system based on generation countermeasure network |
| CN113988259A (en) * | 2021-10-27 | 2022-01-28 | 河北工业大学 | VAE-GRU-based real-time abnormity detection method for thermal power generating unit operation parameters |
| 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 (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020136258A1 (en) * | 2018-12-27 | 2020-07-02 | Thales | Device for generating a simulated sea-clutter data set, and associated method and computer program |
| 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 |
| CN113177264A (en) * | 2021-05-11 | 2021-07-27 | 北京邮电大学 | Sea area target object multi-dimensional data simulation method and system based on generation countermeasure network |
| CN113988259A (en) * | 2021-10-27 | 2022-01-28 | 河北工业大学 | VAE-GRU-based real-time abnormity detection method for thermal power generating unit operation parameters |
| 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 |
Non-Patent Citations (2)
| Title |
|---|
| TAO ZHANG ET AL.: ""Detection of AIS Closing Behavior and MMSI Spoofing Behavior of Ships Based on Spatiotemporal Data"" * |
| 姜佰辰;关键;周伟;何友;: "海上交通的船舶异常行为挖掘识别分析" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118097342A (en) * | 2024-04-29 | 2024-05-28 | 广东省安全生产科学技术研究院 | Sonar-based model training method, estimating device, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115660027B (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11573317B2 (en) | Augmented reality platform and method for use of same | |
| Tuell et al. | Overview of the coastal zone mapping and imaging lidar (CZMIL): a new multisensor airborne mapping system for the US Army Corps of Engineers | |
| US10339707B2 (en) | Automated generation of digital elevation models | |
| Stewart Jr | Multisensor modeling underwater with uncertain information | |
| CN104616345A (en) | Octree forest compression based three-dimensional voxel access method | |
| CN112652045A (en) | Point cloud fusion method for automatic driving virtual-real fusion test and application thereof | |
| CN108216249A (en) | The system and method detected for the ambient enviroment of vehicle | |
| Rosenberger et al. | Benchmarking and functional decomposition of automotive lidar sensor models | |
| CN106289283A (en) | Laser scanner write is utilized to take the system and method for grid map | |
| CN105411624A (en) | Ultrasonic three-dimensional fluid imaging and speed measuring method | |
| CN115660027A (en) | Multi-device sea area target data generation method and system supporting small samples | |
| CN112269849A (en) | Three-dimensional map display method, system, electronic equipment and storage medium | |
| CN115825067A (en) | Geological information acquisition method and system based on unmanned aerial vehicle and electronic equipment | |
| CN113177264B (en) | Sea area target object multi-dimensional data simulation method and system based on generation countermeasure network | |
| Pose et al. | AI-Prepared Autonomous Freshwater Monitoring and Sea Ground Detection by an Autonomous Surface Vehicle | |
| CN113433568B (en) | Laser radar observation simulation method and device | |
| Drap et al. | Underwater cartography for archaeology in the VENUS project | |
| Dias et al. | Detection of discrepancies between nautical charts and new survey data using GIS techniques | |
| Ngo | A methodology for validation of a radar simulation for virtual testing of autonomous driving | |
| Gomes et al. | Volumetric Occupancy Detection: A Comparative Analysis of Mapping Algorithms | |
| CN116299374B (en) | Sonar imaging underwater automatic calibration positioning method and system based on machine vision | |
| Stewart | A non-deterministic approach to 3-D modeling underwater | |
| EP4152270A1 (en) | Method of generating an interactive three-dimensional simulation of a section of an industrial facility | |
| D'Auria et al. | Surveys and new visions of the ancient centre of Naples | |
| Kuhnert et al. | Sensor-fusion based real-time 3D outdoor scene reconstruction and analysis on a moving mobile outdoor robot |
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 |