CN118707482B - A method and system for producing a time-frequency domain detection data set for high-frequency radar ship targets - Google Patents
A method and system for producing a time-frequency domain detection data set for high-frequency radar ship targetsInfo
- Publication number
- CN118707482B CN118707482B CN202410999453.3A CN202410999453A CN118707482B CN 118707482 B CN118707482 B CN 118707482B CN 202410999453 A CN202410999453 A CN 202410999453A CN 118707482 B CN118707482 B CN 118707482B
- Authority
- CN
- China
- Prior art keywords
- target
- time
- ship
- frequency
- spectrum
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/415—Identification of targets based on measurements of movement associated with the target
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
本发明公开一种高频雷达船舶目标时频域检测数据集制作方法及系统，本发明根据高频雷达接收数据，得到该场次数据的起止时间、雷达位置、距离‑慢时间谱；根据距离‑慢时间谱计算距离‑多普勒谱和各距离元的时频谱，根据距离‑多普勒谱计算一阶谱和地杂波的多普勒范围；根据高频雷达数据起止时间，得到船舶AIS信息，并通过计算将AIS船舶目标的径向距离和径向速度，进而计算得到目标距离元和目标多普勒频率，建立AIS目标数据库；根据AIS船舶的目标数据库信息，在对应距离元时频谱、以目标多普勒为中心生成标注预选框并保存目标标注文件；根据目标时频谱和目标标注文件，通过人工复核方式，完成目标标注，以实现高频雷达船舶目标时频域检测数据集的制作。
The present invention discloses a method and system for producing a time-frequency domain detection dataset for high-frequency radar ship targets. The method comprises the following steps: obtaining the start and end times, radar position, and range-slow time spectrum of the field data based on high-frequency radar reception data; calculating the range-Doppler spectrum and the time-frequency spectrum of each range element based on the range-slow time spectrum; and calculating the first-order spectrum and the Doppler range of ground clutter based on the range-Doppler spectrum; obtaining ship AIS information based on the start and end times of the high-frequency radar data, and calculating the radial range and radial velocity of the AIS ship target to obtain the target range element and the target Doppler frequency, thereby establishing an AIS target database; generating a pre-selected annotation box centered on the target Doppler frequency in the corresponding range element time-frequency spectrum based on the AIS ship target database information, and saving a target annotation file; and completing target annotation through manual review based on the target time-frequency spectrum and the target annotation file, thereby producing a time-frequency domain detection dataset for high-frequency radar ship targets.
Description
Technical Field
The invention relates to the field of high-frequency radar ship target time-frequency domain detection, in particular to a method and a system for manufacturing a high-frequency radar ship target time-frequency domain detection data set.
Background
The high-frequency radar has become one of key technologies for observing the ship dynamics in sea areas due to the advantages of the high-frequency radar such as all-day time, real-time performance, all-weather operation capability, beyond-sight distance monitoring range and the like. In general, a high-frequency radar adopts long coherent accumulation time to carry out detection work, and the scattering cross section of echo of a ship target is fluctuant, and is difficult to keep constant-speed running due to the influence of marine environment in the running process, so that the echo of the ship target has non-stationary characteristics.
The non-stationary characteristic of the ship target echo causes the phenomenon of energy diffusion on the range-doppler spectrum, and the use of a constant false alarm detector has poor detection effect under the situation due to the interference and noise of dense high-frequency signals. In view of the large range bin of high frequency radar, the target typically does not travel more than one range bin within a single-shot radar data, and thus the target echo exhibits a continuous or intermittent ridge line within the frequency spectrum at a single range bin. Therefore, many students at home and abroad improve the non-stationary target detection performance of the high-frequency radar by trying to switch the detection task from the range-Doppler domain to the time-frequency domain. At present, the time-frequency domain target detection of the high-frequency radar is mainly based on a graphic imaging processing technology, and the target detection task is converted into the problem of edge extraction in an image, but the method needs to set a large amount of parameters by virtue of manual experience.
In recent years, the deep learning target network shows excellent performance in an image target detection task, and provides a new thought for a ridge line detection task of a target time spectrum. It should be noted that, the deep learning network is a data-driven end-to-end target detection method, and in order to ensure the detection performance, a large amount of high-quality labeling data is required. Because the high-frequency radar can not image the target, when the target ridge line is marked, on one hand, the time-frequency ridge line needs to be determined to belong to the ship target, and on the other hand, the manual marking needs to take a great deal of manpower and time.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a method and a system for manufacturing a high-frequency radar ship target time-frequency domain detection data set, which utilize AIS information to generate a preselection labeling frame of a high-frequency radar time-frequency domain, provide reference for constructing the time-frequency domain target detection data set, and support the application of a deep neural network model in high-frequency radar target detection, thereby improving the detection performance of a frequency radar system on the ship target.
According to an aspect of the present disclosure, there is provided a method for producing a time-frequency domain detection data set of a high-frequency radar ship target, including:
According to the received data of the high-frequency radar, obtaining the start-stop time, the radar position and the distance-slow time spectrum of the high-frequency radar data field;
According to the distance-slow time spectrum, calculating to obtain a time spectrum of each distance element;
acquiring ship AIS information in a current starting and stopping time period according to the starting and stopping time of the high-frequency radar data field, calculating distance element and Doppler element information of a ship target according to the ship AIS information and the radar position, and establishing a ship AIS target database;
Reading the distance element and Doppler element information in the ship AIS target database, obtaining a time spectrum according to the distance element of the ship target, and generating a labeling preselection frame by taking the Doppler frequency of the ship target as the center according to the Doppler element of the ship target to obtain a primary screening labeling file;
rechecking the primary screening annotation file to form a secondary screening annotation file;
and processing a suspected target marking frame area which does not contain the preselected marking frame in the time spectrum of the ship target to form a new time spectrum, and deleting the suspected target marking frame which does not contain the preselected marking frame in the secondary screening marking file to obtain the final screening marking file.
As a further technical scheme, the method further comprises the step of storing the final screening annotation file and the corresponding time frequency spectrum to a time frequency domain detection data set of the high-frequency radar ship target.
As a further technical solution, after the distance-slow time spectrum is obtained, the method further includes:
generating a range-doppler spectrum using a fast fourier transform;
According to the distance-Doppler spectrum, combining with a sea clutter first-order Bragg scattering theorem, setting a signal-to-noise ratio threshold value, and calculating the Doppler range of the sea clutter first-order spectrum;
and according to the distance-Doppler spectrum, combining the ground clutter stationary characteristic to obtain a ground clutter Doppler range.
As a further technical solution, according to the ship AIS information and the radar position, the distance element and the doppler element information of the ship target are calculated, including:
According to the radar position and the ship target position, calculating to obtain the radial distance of the ship target, and calculating to obtain the distance element of the ship target according to the radial distance;
and calculating the radial speed of the ship target according to the radar position, the navigational speed and the navigational direction of the ship target, and calculating Doppler elements of the ship target according to the radial speed.
As a further technical scheme, the generation of the primary screening annotation file comprises the following steps:
reading distance element and Doppler element information of a ship target from an established ship AIS target database;
according to the distance element of the ship target, reading a time spectrum corresponding to the distance element;
and generating a ship target detection preselection annotation frame according to the Doppler element of the ship target, setting the category attribute of the preselection annotation frame, and storing the information of the preselection annotation frame into a primary screening annotation file.
As a further technical solution, rechecking the primary screening annotation file includes:
Judging whether a ship target time-frequency ridge exists in a preselected marking frame of the time spectrum, and if so, adjusting the size of the marking frame to enable all ship target time-frequency ridge lines to fall into the marking frame;
Judging whether a suspected target time-frequency ridge which does not contain a preselected label frame exists in the time frequency spectrum, if so, generating a target label frame and setting category attributes.
As a further technical scheme, after the secondary screening annotation file is obtained, the method further comprises the following steps:
setting 0 for a region with a non-ship marking frame category in the time spectrum to obtain a new time spectrum;
deleting the annotation frame with the annotation frame category of non-ship to obtain the final screening annotation file.
According to an aspect of the present invention, there is provided a high-frequency radar ship target time-frequency domain detection data set creation system including:
the first calculation module is used for obtaining the start-stop time, the radar position and the distance-slow time spectrum of the high-frequency radar data field according to the high-frequency radar receiving data;
The second calculation module is used for calculating the time spectrum of each distance element according to the distance-slow time spectrum;
the third calculation module is used for obtaining ship AIS information in the current starting and stopping time period according to the starting and stopping time of the high-frequency radar data field, calculating to obtain distance element and Doppler element information of a ship target according to the ship AIS information and the radar position, and establishing a ship AIS target database;
the first screening module is used for reading the distance element and Doppler element information in the ship AIS target database, obtaining a time spectrum according to the distance element of the ship target, and generating a marking preselection frame by taking the Doppler frequency of the ship target as the center according to the Doppler element of the ship target to obtain a primary screening marking file;
The second screening module is used for rechecking the primary screening annotation file to form a secondary screening annotation file;
And the third screening module is used for processing the suspected target marking frame area which does not contain the preselected marking frame in the time spectrum of the ship target to form a new time spectrum, and deleting the suspected target marking frame which does not contain the preselected marking frame in the secondary screening marking file to obtain the final screening marking file.
According to an aspect of the specification, the electronic device comprises at least one processor, at least one memory and a communication interface, wherein the processor, the memory and the communication interface are communicated with each other, the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the method.
According to an aspect of the present description, there is provided a non-transitory computer-readable storage medium storing computer instructions that cause the computer to perform the method.
Compared with the prior art, the invention has the beneficial effects that:
According to the method, firstly, AIS information is utilized to generate a preselected labeling frame for labeling the time-frequency ridge line of the high-frequency radar ship, and then, the time-frequency ridge of the ship target is rechecked by combining with manual experience, so that a high-frequency radar time-frequency target detection data set is constructed. The method designed by the invention has high accuracy, can improve the accuracy of target time-frequency ridge line marking by taking AIS information as a reference because a large amount of noise and interference exist in the time spectrum of the high-frequency radar echo, is convenient to operate, can reduce the workload of artificial marking according to a preselected marking frame generated by the AIS information, and provides powerful support for generating a high-quality high-frequency radar time-frequency target detection data set.
Drawings
For a clearer description of embodiments of the invention or of solutions according to the prior art, a brief description will be given below of the drawings used in the description of the embodiments or of the prior art, it being obvious that the drawings in the description below are some embodiments of the invention, and that other drawings are obtained from them without the aid of inventive labour for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for manufacturing a time-frequency domain detection data set of a high-frequency radar ship target according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a system for manufacturing a time-frequency domain detection data set of a high-frequency radar ship target according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of primary screening according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of secondary screening according to an embodiment of the present invention.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
It should be noted that:
The ship automatic identification system AIS (Automatic Identification System) can provide information such as a ship water Mobile communication service identification code MMSI (Maritime Mobile SERVICE IDENTITY), a position, a navigational speed, a course and the like, and is widely used as a reference mark in detecting the target detection performance of a radar system, so that the system can provide a basis for labeling the target detection of a high-frequency radar time-frequency domain. Based on the method, the AIS information-assisted high-frequency radar ship target time-frequency domain detection data set manufacturing method is designed, manual labeling labor and time cost can be reduced while labeling references are provided, the target labeling of the high-frequency radar time-frequency domain is facilitated, and powerful support is provided for manufacturing the high-frequency radar ship target time-frequency domain detection data set.
The terms "comprises" and "comprising," along with any variations thereof, in the description and claims of the invention and in the foregoing drawings, are intended to cover non-exclusive inclusion, such as a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus.
The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices. The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. In addition, the technical features of each embodiment or the single embodiment provided by the invention are combined with each other at will to form a new technical scheme, and the combination is not limited by the sequence of steps and/or the structural composition mode, but is necessarily based on the fact that the technical scheme can be realized by one of ordinary skill in the art, and when the technical scheme combination is contradictory or can not be realized, the technical scheme combination is considered to be absent and is not within the protection scope of the invention claimed.
The embodiment of the invention provides a method for manufacturing a high-frequency radar ship target time-frequency domain detection data set, which is shown in fig. 1 and comprises the following steps:
and step 1, obtaining the start-stop time, the radar position and the distance-slow time spectrum of the high-frequency radar data field according to the high-frequency radar receiving data.
Preferably, the distance-slow time spectrum is defined asThe dimension is as followsDimension(s), whereinIs the distance element to be observed at maximum,Is the frequency sweep cycle number, in the embodiment,。
And 2, calculating the time spectrum of each distance element according to the distance-slow time spectrum.
The method comprises the steps of (1) obtaining a range-slow time spectrum of each range element, firstly utilizing a multiple synchronous extrusion algorithm to generate a time spectrum of each range element, secondly utilizing fast Fourier transformation to generate a range-Doppler spectrum, thirdly, setting a signal-to-noise ratio threshold according to a sea clutter first-order Bragg scattering theorem based on the generated range-Doppler spectrum to calculate a Doppler range of a sea clutter first-order spectrum region, and finally obtaining a ground clutter Doppler range according to ground clutter static characteristics.
Further, after the Doppler range of the sea clutter first-order spectrum region and the ground clutter is obtained, 0 is set for the sea clutter first-order spectrum region and the ground clutter region of the time spectrum.
In the method according to the embodiment of the present invention, the time spectrum is defined asWhereinIs thatThe dimensions of the dimensions,Is the number of time-spectrum time-dimensional sampling points,Is the number of time-spectrum doppler frequency dimension samples,Representing the sequence number of the element of the observation distance,N is the maximum distance element to be observed, which, in embodiments,。
Preferably, the signal to noise ratio threshold described in step 2 is located as。
And 3, obtaining ship AIS information in the current starting and stopping time period according to the starting and stopping time of the high-frequency radar data field, calculating to obtain distance element and Doppler element information of a ship target according to the ship AIS information and the radar position, and establishing a ship AIS target database.
Preferably, according to the starting and ending time of the high-frequency radar data field obtained in the step 1, AIS data in the starting and ending time period are read, wherein the AIS data comprise MMSI, navigational speed, position, heading and other information of the ship.
Further, the building of the ship AIS target database provided by the embodiment of the invention comprises the following steps:
calculating to obtain the radial distance of the ship target according to the radar position obtained in the step 1 and the ship target position obtained based on the ship AIS information;
obtaining radial speed information of the ship target according to the radar position and the navigational speed and the navigational direction of the ship target obtained based on the ship AIS information in the step 1;
according to the radial distance and the radial speed of the ship target, respectively calculating the distance element and Doppler element information of the ship target;
And storing MMSI of the ship target, the target distance element and the target Doppler metadata into an AIS target information database.
It should be noted that, during a radar data field start-stop time period, AIS signals of a plurality of ships may be included. And respectively processing AIS signals of the plurality of ships to obtain distance element and Doppler element information of the plurality of ship targets, and storing the distance element and Doppler element information into a ship AIS target database.
And 4, reading the distance element and Doppler element information in the ship AIS target database, obtaining a time spectrum according to the distance element of the ship target, and generating a labeling preselection frame by taking the Doppler frequency of the ship target as the center according to the Doppler element of the ship target to obtain a primary screening labeling file.
Preferably, according to the AIS target information database obtained in the step 3, the distance meta information and Doppler meta information of the ship AIS are read one by one.
Further, according to the target distance meta information, reading the time spectrum corresponding to the target distance element obtained in the step 2, then according to the target Doppler information, taking the target Doppler as a center, generating a target detection pre-selection annotation frame, setting the annotation frame category attribute as 'vessel', as shown in fig. 3, and storing the pre-selection annotation frame information to the primary screening annotation file.
As a preferred embodiment, the pre-selected annotation frame size generated in step 4 isWhere L is the number of time-spectral time-dimensional sampling points,Is the number of doppler maxima of the target, which, in embodiments,。
And step 5, rechecking the primary screening annotation file to form a secondary screening annotation file.
Preferably, according to the time spectrum obtained in the step 2 and the primary screening annotation file in the step 4, firstly observing whether a ship echo time-frequency ridge exists in a preselection annotation frame in the time spectrum, if a target time-frequency ridge exists in the preselection frame, adjusting the size of the annotation frame so that the target time-frequency ridge completely falls into the annotation frame, if no target time-frequency ridge exists in the preselection frame, deleting the preselection annotation frame, then observing whether other suspected target time-frequency ridges which do not contain the preselection annotation frame exist in the frequency spectrum, if so, manually generating a target annotation frame, setting the annotation frame type as clear, as shown in fig. 4, and finally storing the annotation frame type to the secondary screening annotation file.
And 6, processing a suspected target labeling frame area which does not contain the preselected labeling frame in the time spectrum of the ship target to form a new time spectrum, and deleting the suspected target labeling frame which does not contain the preselected labeling frame in the secondary screening labeling to obtain a final screening labeling file. A suspected object that does not contain a preselected frame of label may be understood as a suspected object that resembles a time-frequency ridge of a ship object but does not contain AIS information.
Preferably, according to the secondary screening annotation file obtained in the step 5 and the Doppler range of the sea clutter first-order spectrum region and the ground clutter obtained in the step 2, firstly, setting 0 for a region with the class of the annotation frame being clear in the time spectrum, secondly, setting 0 for the time spectrum sea clutter first-order spectrum region and the ground clutter region, and storing the time spectrum of the operation of setting 0 as a preprocessed time spectrum, secondly, deleting the annotation frame with the class of clear, and finally storing the new annotation file to the final screening annotation file.
As an preferred embodiment, the method for manufacturing the time-frequency domain detection data set of the high-frequency radar ship target provided by the embodiment of the invention further includes:
And 7, judging whether the labeling file contains a target labeling frame (i.e. a labeling frame with a class of 'vessel') according to the final screening labeling file and the preprocessed time spectrum obtained in the step 6, if so, storing the final labeling file and the preprocessed time spectrum corresponding to the final labeling file into a data set, otherwise, deleting the final labeling file and the preprocessed time spectrum corresponding to the final labeling file.
The implementation basis of the embodiments of the present invention is realized by a device with a processor function to perform programmed processing. Therefore, in engineering practice, the technical solutions and the functions of the embodiments of the present invention are packaged into various modules. Based on this actual situation, on the basis of the above embodiments, an embodiment of the present invention provides a high-frequency radar ship target time-frequency domain detection data set creation system for executing a high-frequency radar ship target time-frequency domain detection data set creation method in the above method embodiment.
Referring to fig. 2, the system comprises a first calculation module, a second calculation module, a third calculation module and a third screening module, wherein the first calculation module is used for obtaining the starting and stopping time of high-frequency radar data, the radar position and the distance-slow time spectrum according to the high-frequency radar receiving data, the second calculation module is used for calculating the time spectrum of each distance element according to the distance-slow time spectrum, the third calculation module is used for obtaining ship AIS information in the current starting and stopping time period according to the starting and stopping time of the high-frequency radar data, the distance element and the Doppler element information of a ship target are calculated according to the ship AIS information and combined with the radar position, a ship AIS target database is established, the first screening module is used for reading the distance element and the Doppler element information in the ship AIS target database, obtaining the time spectrum according to the distance element of the ship target, generating a label preselecting frame with the Doppler frequency of the ship target as the center, the second screening module is used for checking the primary screening label file to form a secondary screening file, the third screening module is used for carrying out a new label-containing the label-containing frame of the ship target, and deleting the label-containing the pre-selected frame in the pre-selected frame is used for obtaining a final label-selected label frame.
According to the high-frequency radar ship target time-frequency domain detection data set manufacturing system provided by the embodiment of the invention, aiming at the problem that a high-frequency radar cannot perform target imaging and a target ridge line is required to be marked when the high-frequency radar cannot perform target imaging, the time-frequency ridge line is required to be determined to belong to a ship target and a large amount of manpower and time are required to be spent for manual marking, a plurality of modules in FIG. 2 are adopted, a preselection marking frame of the high-frequency radar time-frequency domain is generated by utilizing AIS information, reference is provided for constructing the target detection data set of the time-frequency domain, and the application of a deep neural network model in high-frequency radar target detection is supported, so that the detection performance of the high-frequency radar system on the ship target is improved.
It should be noted that, in addition to the method used for implementing the above method embodiment, the system embodiment provided by the present invention is also used for implementing the method in other method embodiments provided by the present invention, where the difference is merely that corresponding functional modules are provided, and the principle is basically the same as that of the above system embodiment provided by the present invention, so long as those skilled in the art obtain corresponding technical means by combining technical features with reference to specific technical solutions in other method embodiments on the basis of the above system embodiment, and the technical solutions formed by these technical means, and on the premise that the technical solutions are ensured to have practicability, the equipment in the above system embodiment is modified to obtain corresponding system class embodiments, and the method in other method class embodiments is implemented. For example:
Based on the foregoing content of the system embodiment, as a preferred embodiment, the system for producing a time-frequency domain detection dataset of a high-frequency radar ship target provided in the embodiment of the present invention further includes:
And the storage module is used for storing the final screening marking file and the corresponding time frequency spectrum to the time frequency domain detection data set of the high-frequency radar ship target.
Based on the foregoing content of the system embodiment, as a preferred embodiment, in the system for producing a time-frequency domain detection dataset of a high-frequency radar ship target provided in the embodiment of the present invention, the second calculation module is further configured to execute the following instructions:
generating a range-doppler spectrum using a fast fourier transform;
According to the distance-Doppler spectrum, combining with a sea clutter first-order Bragg scattering theorem, setting a signal-to-noise ratio threshold value, and calculating the Doppler range of the sea clutter first-order spectrum;
and according to the distance-Doppler spectrum, combining the ground clutter stationary characteristic to obtain a ground clutter Doppler range.
Further, after the Doppler range of the sea clutter first-order spectrum region and the ground clutter is obtained, 0 is set for the sea clutter first-order spectrum region and the ground clutter region of the time spectrum.
Based on the foregoing content of the system embodiment, as a preferred embodiment, in the system for producing a time-frequency domain detection dataset of a high-frequency radar ship target provided in the embodiment of the present invention, the third calculation module is further configured to execute the following instructions:
According to the radar position and the ship target position, calculating to obtain the radial distance of the ship target, and calculating to obtain the distance element of the ship target according to the radial distance;
and calculating the radial speed of the ship target according to the radar position, the navigational speed and the navigational direction of the ship target, and calculating Doppler elements of the ship target according to the radial speed.
Based on the foregoing content of the system embodiment, as a preferred embodiment, in the system for producing a time-frequency domain detection dataset of a high-frequency radar ship target provided in the embodiment of the present invention, the first screening module is further configured to execute the following instructions:
reading distance element and Doppler element information of a ship target from an established ship AIS target database;
according to the distance element of the ship target, reading a time spectrum corresponding to the distance element;
and generating a ship target detection preselection annotation frame according to the Doppler element of the ship target, setting the category attribute of the preselection annotation frame, and storing the information of the preselection annotation frame into a primary screening annotation file.
Based on the foregoing content of the system embodiment, as a preferred embodiment, in the system for producing a time-frequency domain detection dataset of a high-frequency radar ship target provided in the embodiment of the present invention, the second screening module is further configured to execute the following instructions:
Judging whether a ship target time-frequency ridge exists in a preselected marking frame of the time spectrum, and if so, adjusting the size of the marking frame to enable all ship target time-frequency ridge lines to fall into the marking frame;
Judging whether a suspected target time-frequency ridge which does not contain a preselected label frame exists in the time frequency spectrum, if so, generating a target label frame and setting category attributes.
Based on the foregoing content of the system embodiment, as a preferred embodiment, in the system for manufacturing a time-frequency domain detection dataset of a high-frequency radar ship target provided in the embodiment of the present invention, the third screening module is further configured to execute the following instructions:
setting 0 for a region with a non-ship marking frame category in the time spectrum to obtain a new time spectrum;
deleting the annotation frame with the annotation frame category of non-ship to obtain the final screening annotation file.
The method of the embodiment of the invention is realized by the electronic equipment, so that the related electronic equipment is necessary to be introduced. To this end, an embodiment of the present invention provides an electronic device, as shown in FIG. 5, comprising at least one processor (processor), a communication interface (Communications Interface), at least one memory (memory), and a communication bus, wherein the at least one processor, the communication interface, and the at least one memory communicate with each other via the communication bus. The at least one processor invokes the logic instructions in the at least one memory to perform all or part of the steps of the methods provided by the various method embodiments described above.
Further, the logic instructions in the at least one memory described above are implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention is essentially or what contributes to the prior art or that part of the technical solution is embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (being a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. The storage medium includes a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, and various media for storing program codes.
The system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements are or are not physically separated, and the elements shown as elements are or are not physical elements, are located in one place, or are also distributed over a plurality of network elements. The purpose of the embodiment is achieved by actually selecting some or all of the modules. Those of ordinary skill in the art will understand and implement the invention without undue burden.
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.
According to the method, starting and stopping time, radar position and distance-slow time spectrum of field data are obtained according to high-frequency radar receiving data, distance-Doppler spectrum and time spectrum of each distance element are obtained according to distance-slow time spectrum calculation, doppler ranges of first-order spectrum and ground clutter are obtained according to distance-Doppler spectrum calculation, ship AIS information is obtained according to the starting and stopping time of the high-frequency radar data, radial distance and radial speed of an AIS ship target are calculated, target distance elements and target Doppler frequency are obtained through calculation, an AIS target database is built, a labeling preselect frame is generated at the time spectrum of the corresponding distance elements by taking the target Doppler as the center according to AIS target database information of the AIS ship, a target labeling file is stored, and target labeling is completed in a manual review mode according to the target time spectrum and the target labeling file, so that a time-frequency domain detection data set of the high-frequency radar ship target is manufactured. The method can reduce the manpower and time cost of manual marking on the premise of ensuring the accuracy of marking the target.
It should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention, and not for limiting the same, and although the present invention has been described in detail with reference to the above-mentioned embodiments, it should be understood by those skilled in the art that the technical solution described in the above-mentioned embodiments may be modified or some or all of the technical features may be equivalently replaced, and these modifications or substitutions do not deviate from the essence of the corresponding technical solution from the technical solution of the embodiment of the present invention.
Claims (10)
1. The method for manufacturing the high-frequency radar ship target time-frequency domain detection data set is characterized by comprising the following steps of:
According to the received data of the high-frequency radar, obtaining the start-stop time, the radar position and the distance-slow time spectrum of the high-frequency radar data field;
According to the distance-slow time spectrum, calculating to obtain a time spectrum of each distance element;
acquiring ship AIS information in a current starting and stopping time period according to the starting and stopping time of the high-frequency radar data field, calculating distance element and Doppler element information of a ship target according to the ship AIS information and the radar position, and establishing a ship AIS target database;
Reading the distance element and Doppler element information in the ship AIS target database, obtaining a time spectrum according to the distance element of the ship target, and generating a labeling preselection frame by taking the Doppler frequency of the ship target as the center according to the Doppler element of the ship target to obtain a primary screening labeling file;
rechecking the primary screening annotation file to form a secondary screening annotation file;
and processing a suspected target marking frame area which does not contain the preselected marking frame in the time spectrum of the ship target to form a new time spectrum, and deleting the suspected target marking frame which does not contain the preselected marking frame in the secondary screening marking file to obtain the final screening marking file.
2. The method for producing the high-frequency radar ship target time-frequency domain detection data set according to claim 1, further comprising the step of storing the final screening annotation file and the corresponding time frequency spectrum into the high-frequency radar ship target time-frequency domain detection data set.
3. The method for producing a high-frequency radar ship target time-frequency domain detection data set according to claim 1, further comprising, after obtaining the distance-slow time spectrum:
generating a range-doppler spectrum using a fast fourier transform;
According to the distance-Doppler spectrum, combining with a sea clutter first-order Bragg scattering theorem, setting a signal-to-noise ratio threshold value, and calculating the Doppler range of the sea clutter first-order spectrum;
and according to the distance-Doppler spectrum, combining the ground clutter stationary characteristic to obtain a ground clutter Doppler range.
4. The method for producing the time-frequency domain detection data set of the high-frequency radar ship target according to claim 1, wherein the calculating the distance element and the Doppler element information of the ship target according to the ship AIS information and the radar position comprises the following steps:
According to the radar position and the ship target position, calculating to obtain the radial distance of the ship target, and calculating to obtain the distance element of the ship target according to the radial distance;
and calculating the radial speed of the ship target according to the radar position, the navigational speed and the navigational direction of the ship target, and calculating Doppler elements of the ship target according to the radial speed.
5. The method for producing the high-frequency radar ship target time-frequency domain detection data set according to claim 1, wherein the generation of the primary screening annotation file comprises the following steps:
reading distance element and Doppler element information of a ship target from an established ship AIS target database;
according to the distance element of the ship target, reading a time spectrum corresponding to the distance element;
and generating a ship target detection preselection annotation frame according to the Doppler element of the ship target, setting the category attribute of the preselection annotation frame, and storing the information of the preselection annotation frame into a primary screening annotation file.
6. The method for producing a time-frequency domain detection dataset of a high-frequency radar ship target according to claim 5, wherein the rechecking the primary screening annotation file comprises:
Judging whether a ship target time-frequency ridge exists in a preselected marking frame of the time spectrum, and if so, adjusting the size of the marking frame to enable all ship target time-frequency ridge lines to fall into the marking frame;
Judging whether a suspected target time-frequency ridge which does not contain a preselected label frame exists in the time frequency spectrum, if so, generating a target label frame and setting category attributes.
7. The method for producing a time-frequency domain detection data set of a high-frequency radar ship target according to claim 3, further comprising, after obtaining the secondary screening annotation file:
setting 0 for a region with a non-ship marking frame category in the time spectrum to obtain a new time spectrum;
deleting the annotation frame with the annotation frame category of non-ship to obtain the final screening annotation file.
8. A high-frequency radar ship target time-frequency domain detection data set manufacturing system is characterized by comprising:
the first calculation module is used for obtaining the start-stop time, the radar position and the distance-slow time spectrum of the high-frequency radar data field according to the high-frequency radar receiving data;
The second calculation module is used for calculating the time spectrum of each distance element according to the distance-slow time spectrum;
the third calculation module is used for obtaining ship AIS information in the current starting and stopping time period according to the starting and stopping time of the high-frequency radar data field, calculating to obtain distance element and Doppler element information of a ship target according to the ship AIS information and the radar position, and establishing a ship AIS target database;
the first screening module is used for reading the distance element and Doppler element information in the ship AIS target database, obtaining a time spectrum according to the distance element of the ship target, and generating a marking preselection frame by taking the Doppler frequency of the ship target as the center according to the Doppler element of the ship target to obtain a primary screening marking file;
The second screening module is used for rechecking the primary screening annotation file to form a secondary screening annotation file;
And the third screening module is used for processing the suspected target marking frame area which does not contain the preselected marking frame in the time spectrum of the ship target to form a new time spectrum, and deleting the suspected target marking frame which does not contain the preselected marking frame in the secondary screening marking file to obtain the final screening marking file.
9. An electronic device comprising at least one processor, at least one memory and a communication interface, wherein the processor, memory and communication interface are in communication with each other, wherein the memory stores program instructions for execution by the processor, and wherein the processor invokes the program instructions to perform the method of any of claims 1 to 7.
10. A non-transitory computer-readable storage medium storing computer instructions that cause the computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410999453.3A CN118707482B (en) | 2024-07-24 | 2024-07-24 | A method and system for producing a time-frequency domain detection data set for high-frequency radar ship targets |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410999453.3A CN118707482B (en) | 2024-07-24 | 2024-07-24 | A method and system for producing a time-frequency domain detection data set for high-frequency radar ship targets |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118707482A CN118707482A (en) | 2024-09-27 |
| CN118707482B true CN118707482B (en) | 2025-09-30 |
Family
ID=92817987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410999453.3A Active CN118707482B (en) | 2024-07-24 | 2024-07-24 | A method and system for producing a time-frequency domain detection data set for high-frequency radar ship targets |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118707482B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106199549A (en) * | 2016-06-30 | 2016-12-07 | 南京理工大学 | A kind of method using spectrum-subtraction to promote LFMCW radar signal to noise ratio |
| CN113534065A (en) * | 2021-07-20 | 2021-10-22 | 中国人民解放军海军航空大学 | Radar target micro-motion feature extraction and intelligent classification method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6278732B2 (en) * | 2014-02-25 | 2018-02-14 | 三菱電機株式会社 | Marine radar equipment |
| EP3822655B1 (en) * | 2019-11-13 | 2024-03-13 | Airbus Defence and Space Limited | Maritime surveillance radar |
-
2024
- 2024-07-24 CN CN202410999453.3A patent/CN118707482B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106199549A (en) * | 2016-06-30 | 2016-12-07 | 南京理工大学 | A kind of method using spectrum-subtraction to promote LFMCW radar signal to noise ratio |
| CN113534065A (en) * | 2021-07-20 | 2021-10-22 | 中国人民解放军海军航空大学 | Radar target micro-motion feature extraction and intelligent classification method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118707482A (en) | 2024-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104036239B (en) | Fast high-resolution SAR (synthetic aperture radar) image ship detection method based on feature fusion and clustering | |
| CN110031843B (en) | ROI (region of interest) -based SAR (synthetic Aperture Radar) image target positioning method, system and device | |
| CN109817023B (en) | An AIS target detection method in submarine cable waters | |
| CN116306790A (en) | A method, system, device and medium for real-time prediction of offshore ship trajectory based on CNN-GRU and attention mechanism | |
| CN109117802A (en) | Ship Detection towards large scene high score remote sensing image | |
| CN107274401A (en) | A kind of High Resolution SAR Images Ship Detection of view-based access control model attention mechanism | |
| WO2018000252A1 (en) | Oceanic background modelling and restraining method and system for high-resolution remote sensing oceanic image | |
| Chen et al. | Rain-contaminated region segmentation of X-band marine radar images with an ensemble of SegNets | |
| CN103020592B (en) | A kind of remote sensing images naval vessel based on local context detects false-alarm elimination method | |
| Shirowzhan et al. | Enhanced autocorrelation-based algorithms for filtering airborne lidar data over urban areas | |
| CN116226706B (en) | A method for identifying fishing net positioning markers based on group motion characteristics | |
| CN113536948A (en) | Fishing boat fishing behavior recognition method and device | |
| CN114936332A (en) | Method and device for analyzing ship traffic flow in water area of wind power plant and storage medium | |
| CN107133966A (en) | A kind of three-dimensional sonar image background dividing method based on sampling consistency algorithm | |
| CN112446303A (en) | Synthetic aperture radar sea ice drift detection method, system, equipment and application | |
| CN111505598B (en) | A three-feature joint detection device and method based on FRFT domain | |
| CN110501683B (en) | A classification method of sea and land clutter based on four-dimensional data features | |
| Parmiggiani et al. | Image processing for pancake ice detection and size distribution computation | |
| CN103886606A (en) | SAR image segmentation method based on joint generalized gamma distribution parameters | |
| CN102968786B (en) | A kind of non-supervisory remote sensing images potential target method for detecting area | |
| CN118707482B (en) | A method and system for producing a time-frequency domain detection data set for high-frequency radar ship targets | |
| CN114199305A (en) | Offshore area ecological environment risk monitoring method, device, equipment and storage medium | |
| Li et al. | Self-supervised network for oriented synthetic aperture radar ship detection based on self-distillation | |
| CN119355661B (en) | Radar data inversion method, marine meteorological detection method and device | |
| CN118283145B (en) | Net position meter identification method, device, readable storage medium and AIS system |
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 |