CN110889380A - Ship identification method and device and computer storage medium - Google Patents

Ship identification method and device and computer storage medium Download PDF

Info

Publication number
CN110889380A
CN110889380A CN201911197420.2A CN201911197420A CN110889380A CN 110889380 A CN110889380 A CN 110889380A CN 201911197420 A CN201911197420 A CN 201911197420A CN 110889380 A CN110889380 A CN 110889380A
Authority
CN
China
Prior art keywords
ship
ais data
obtaining
image
position information
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
Application number
CN201911197420.2A
Other languages
Chinese (zh)
Other versions
CN110889380B (en
Inventor
石慧峰
贺广均
冯鹏铭
夏正欢
张涛
王进
赵志龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Satellite Information Engineering
Original Assignee
Beijing Institute of Satellite Information Engineering
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Satellite Information Engineering filed Critical Beijing Institute of Satellite Information Engineering
Priority to CN201911197420.2A priority Critical patent/CN110889380B/en
Publication of CN110889380A publication Critical patent/CN110889380A/en
Application granted granted Critical
Publication of CN110889380B publication Critical patent/CN110889380B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases

Abstract

The invention discloses a ship identification method, a device and a computer storage medium, wherein the method comprises the following steps: acquiring AIS data and SAR images of a first automatic identification system of a first set time sequence of a first ship; the SAR image includes at least one second ship; determining a second ship associated with the first ship from the at least one second ship based on the first AIS data and the SAR image; determining a category of the first ship based on the first AIS data and a second ship associated with the first ship.

Description

Ship identification method and device and computer storage medium
Technical Field
The invention relates to the technical field of target detection and information processing, in particular to a ship identification method, a ship identification device and a computer storage medium.
Background
Ships serve as main carriers of marine traffic and play an irreplaceable role in marine activities undertaken by human beings. Currently, with the development of a high-resolution wide-Aperture Synthetic Aperture Radar (SAR) technology, a combined mode of a satellite-mounted SAR (referred to as a satellite-mounted SAR for short) is more and more widely applied to ship monitoring. However, due to the influence of speckle noise inherent in the SAR technology and the limitation of image spatial resolution in a conventional imaging mode of the satellite-borne SAR, the conventional satellite-borne SAR is difficult to acquire ship invariant feature information, and the conventional satellite-borne SAR cannot solve the problems of position offset and defocusing generated during the operation of a ship, so that the ship type is difficult to accurately identify.
Disclosure of Invention
In view of the above, the present invention provides a ship identification method, apparatus and computer storage medium, which at least partially solve the above technical problems.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
in a first aspect, an embodiment of the present invention provides a ship identification method, where the method includes:
acquiring AIS data and SAR images of a first automatic identification system of a first set time sequence of a first ship; the SAR image includes at least one second ship;
determining a second ship associated with the first ship from the at least one second ship based on the first AIS data and the SAR image;
determining a category of the first ship based on the first AIS data and a second ship associated with the first ship.
In the above solution, said determining a second ship associated with the first ship from the at least one second ship based on the first AIS data and the SAR image includes:
obtaining a trajectory function of the first ship based on the first AIS data; the trajectory function is a functional relationship between time and the position of the first ship;
acquiring first position information of the first ship based on the track function and the imaging time of the SAR image;
obtaining second position information of each second ship in the SAR image;
obtaining a second ship associated with the first ship from each second ship based on the first location information of the first ship and the second location information of each second ship.
In the above solution, the obtaining a trajectory function of the first ship based on the first AIS data includes:
performing first analysis on the first AIS data to obtain a first analysis result;
obtaining third position information corresponding to each moment of the first ship in the first set time sequence based on the first analysis result;
determining a movement track scatter diagram of the first ship based on the third position information corresponding to each moment;
and carrying out first processing on the moving track scatter diagram according to a first set algorithm to obtain a track function of the first ship.
In the above scheme, the obtaining second location information of each second ship in the SAR image includes:
performing second processing on the SAR image to obtain an SAR image with position information;
detecting the SAR image with the position information to obtain a ship detection result;
and obtaining second position information of each second ship based on the ship detection result.
In the above scheme, the obtaining second location information of each second ship based on the ship detection result includes:
based on the ship detection result, obtaining a slice image corresponding to each second ship from the SAR image with the position information;
obtaining the central position information of the slice image corresponding to each second ship based on the slice image corresponding to each second ship;
and taking the central position information of the slice image corresponding to each second ship as the second position information of each second ship.
In the foregoing solution, the obtaining, from each second ship, a second ship associated with the first ship based on the first location information of the first ship and the second location information of each second ship includes:
respectively determining distance information corresponding to the first ship and each second ship based on the first position information and each second position information;
determining a second ship closest to the first ship from each second ship based on the distance information corresponding to the first ship and each second ship;
and taking a second ship closest to the first ship as a second ship associated with the first ship.
In the foregoing solution, the determining the category of the first ship based on the first AIS data and the second ship associated with the first ship includes:
acquiring the sailing speed and the sailing direction of the first ship based on the first AIS data;
obtaining a corrected image of a second ship associated with the first ship based on the sailing speed, the sailing direction and a pre-stored compensation model;
and determining the class of the first ship based on the corrected image and a ship classification model obtained by pre-training.
In the above solution, the obtaining a corrected image of a second ship associated with the first ship based on the sailing speed, the sailing direction and a pre-stored compensation model includes:
inputting the sailing speed and the sailing direction into the pre-stored compensation model to obtain a corrected echo signal of the first ship;
performing focusing imaging processing on the first ship again based on the corrected echo signal to obtain a refocused image;
the refocused image is taken as a corrected image of a second ship associated with the first ship.
In the above aspect, the method further includes:
acquiring second AIS data of a second set time sequence; the second AIS data comprises first AIS data corresponding to at least two first ships;
obtaining first AIS data corresponding to each of the at least two first ships based on the second AIS data;
determining a second ship associated with each first ship from the at least one second ship based on the first AIS data and the SAR image corresponding to each first ship;
determining a category corresponding to each first ship based on the first AIS data corresponding to each first ship and the second ship associated with each first ship.
In a second aspect, an embodiment of the present invention further provides a ship identification apparatus, where the apparatus includes: an obtaining module, a first determining module, and a second determining module, wherein,
the acquisition module is used for acquiring first automatic identification system AIS data and synthetic aperture radar SAR images of a first set time sequence of a first ship; the SAR image includes at least one second ship;
the first determining module is configured to determine a second ship associated with the first ship from the at least one second ship based on the first AIS data and the SAR image;
the second determining module is configured to determine a category of the first ship based on the first AIS data and a second ship associated with the first ship.
In the foregoing aspect, the first determining module includes: a first obtaining unit, a second obtaining unit, a third obtaining unit, and a fourth obtaining unit, wherein,
the first obtaining unit is configured to obtain a trajectory function of the first ship based on the first AIS data; the trajectory function is a functional relationship between time and the position of the first ship;
the second obtaining unit is configured to obtain first location information of the first ship based on the trajectory function and the imaging time of the SAR image;
the third obtaining unit is used for obtaining second position information of each second ship in the SAR image;
the fourth obtaining unit is configured to obtain, from each second ship, a second ship associated with the first ship based on the first location information of the first ship and the second location information of each second ship.
In the foregoing scheme, the first obtaining unit is specifically configured to: performing first analysis on the first AIS data to obtain a first analysis result; obtaining third position information corresponding to each moment of the first ship in the first set time sequence based on the first analysis result; determining a movement track scatter diagram of the first ship based on the third position information corresponding to each moment; and carrying out first processing on the moving track scatter diagram according to a first set algorithm to obtain a track function of the first ship.
In the above scheme, the third obtaining unit includes a first obtaining sub-unit, a second obtaining sub-unit, and a third obtaining sub-unit, wherein,
the first obtaining subunit is configured to perform second processing on the SAR image to obtain an SAR image with position information;
the second obtaining subunit is configured to perform detection processing on the SAR image with the position information to obtain a ship detection result;
the third obtaining subunit is configured to obtain second position information of each second ship based on the ship detection result.
In the foregoing scheme, the third obtaining subunit is specifically configured to: based on the ship detection result, obtaining a slice image corresponding to each second ship from the SAR image with the position information; obtaining the central position information of the slice image corresponding to each second ship based on the slice image corresponding to each second ship; and taking the central position information of the slice image corresponding to each second ship as the second position information of each second ship.
In the foregoing scheme, the fourth obtaining unit is specifically configured to: respectively determining distance information corresponding to the first ship and each second ship based on the first position information and each second position information; determining a second ship closest to the first ship from each second ship based on the distance information corresponding to the first ship and each second ship; and taking a second ship closest to the first ship as a second ship associated with the first ship.
In the foregoing solution, the second determining module includes: a fifth obtaining unit, a sixth obtaining unit, and a determining unit, wherein,
the fifth obtaining unit is configured to obtain a sailing speed and a sailing direction of the first ship based on the first AIS data;
the sixth obtaining unit is configured to obtain a corrected image of a second ship associated with the first ship based on the sailing speed, the sailing direction, and a pre-stored compensation model;
the determining unit is used for determining the category of the first ship based on the corrected image and a ship classification model obtained by pre-training.
In the foregoing scheme, the sixth obtaining unit is specifically configured to: inputting the sailing speed and the sailing direction into the pre-stored compensation model to obtain a corrected echo signal of the first ship; performing focusing imaging processing on the first ship again based on the corrected echo signal to obtain a refocused image; the refocused image is taken as a corrected image of a second ship associated with the first ship.
In the above solution, the apparatus further comprises: a third obtaining module;
the obtaining module is further configured to: acquiring second AIS data of a second set time sequence; the second AIS data comprises first AIS data corresponding to at least two first ships;
the third obtaining module is configured to obtain, based on the second AIS data, first AIS data corresponding to each of the at least two first vessels;
the first determining module is further configured to: determining a second ship associated with each first ship from the at least one second ship based on the first AIS data and the SAR image corresponding to each first ship;
the second determining module is further configured to: determining a category corresponding to each first ship based on the first AIS data corresponding to each first ship and the second ship associated with each first ship.
In a third aspect, an embodiment of the present invention provides a computer storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of any of the methods described above.
In a fourth aspect, an embodiment of the present invention provides a ship identification apparatus, where the ship identification apparatus includes: a processor and a memory for storing a computer program operable on the processor, wherein the processor is operable to perform the steps of the method of any preceding claim when the computer program is executed by the processor.
The embodiment of the invention provides a ship identification method, a device and a computer storage medium, wherein the method comprises the following steps: acquiring AIS data and SAR images of a first automatic identification system of a first set time sequence of a first ship; the SAR image includes at least one second ship; determining a second ship associated with the first ship from the at least one second ship based on the first AIS data and the SAR image; determining a category of the first ship based on the first AIS data and a second ship associated with the first ship. By adopting the ship identification method and device provided by the embodiment of the invention, the AIS is fused into the traditional SAR image, so that the position correction and refocusing imaging of the ship in the SAR image can be carried out by utilizing AIS data obtained by correlation matching aiming at the problems of position deviation and defocusing generated by ship movement in the SAR image, the ship image with accurate and fine imaging position is obtained, and the accurate type of the first ship can be obtained based on the ship image and AIS data obtained by the refocusing imaging.
Drawings
Fig. 1 is a schematic flow chart of a ship identification method according to an embodiment of the present invention;
FIG. 2 is a graphical representation of a trajectory function for a first vessel provided by an embodiment of the present invention;
fig. 3 is a schematic view of an application scenario for obtaining a corrected view of a second ship associated with the first ship according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an association between each first ship corresponding to the second AIS data and each second ship in the SAR image according to the embodiment of the present invention;
fig. 5 is a detailed flowchart schematic diagram of a ship identification method according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a ship identification device provided in an embodiment of the present invention;
fig. 7 is a schematic diagram of a hardware structure of a ship identification device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.
For the convenience of understanding, the ship and SAR related technologies will be briefly described below.
Ships serve as main carriers of marine traffic and play an irreplaceable role in human activities in the sea. In civil aspects, ship monitoring can be applied to the fields of fishery management, illegal immigration monitoring, marine traffic safety, marine environment protection, marine search and rescue and the like; in military terms, ship monitoring can be applied to the national marine safety fields of information reconnaissance, sea battlefield situation perception and the like. The satellite-borne SAR has the advantage of all-weather earth observation all the day, so that real-time monitoring of ships on the sea surface becomes possible, and the satellite-borne SAR is more and more widely applied to ship monitoring at the present stage along with the development of high-resolution wide-range SAR technology. However, due to the influence of speckle noise inherent in the SAR technology and the limitation of image spatial resolution in the conventional imaging mode of the satellite-borne SAR, the conventional satellite-borne SAR is difficult to acquire ship invariant feature information. Meanwhile, when a moving ship is monitored by adopting a satellite-borne SAR, the phenomena of position deviation, defocusing and the like generated in the SAR imaging process further increase the difficulty in identifying the type of the ship. Therefore, on the basis of the SAR technology, the ship type identification method based on the SAR technology has important significance in combination with other sensor information.
An Automatic Identification System (AIS) is a novel auxiliary navigation System, and dynamic information and static information of ships can be broadcasted in real time by matching with a positioning System, wherein the dynamic information can comprise actual positions, ship speeds, courses, changed course rates and the like of the ships; the static information may include the ship's name, call sign (various codes used in radio communication), draft (i.e., depth submerged), ship dimensions, and whether dangerous cargo is loaded, etc. The AIS has the characteristics of rich information, high positioning accuracy, all weather all the day and the like, and is widely applied to marine monitoring, particularly offshore area ship monitoring. With the rapid development of satellite-borne AIS platform (satellite-borne AIS for short) technology, ship monitoring research on a large scale, even global oceans, by using the satellite-borne AIS has become a hotspot. However, the start-up and shut-down of the transceivers of the satellite-borne AIS in the ships are completely dependent on the people on the ships, and the ship information broadcasted in real time can be artificially counterfeited, so the satellite-borne AIS cannot be applied to non-cooperative ship monitoring. Where a non-cooperative ship refers to a ship that is likely to provide false information.
Based on the above, the embodiment of the invention provides a ship identification method and device, which can be used for integrating AIS into traditional SAR image ship detection to realize refocusing and imaging of a moving ship and fine ship type identification, and can be used for detecting and discovering non-cooperative ships.
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, a flow diagram of a ship identification method is shown. The method comprises the following steps:
s101: acquiring AIS data and SAR images of a first automatic identification system of a first set time sequence of a first ship; the SAR image includes at least one second ship;
s102: determining a second ship associated with the first ship from the at least one second ship based on the first AIS data and the SAR image;
s103: determining a category of the first ship based on the first AIS data and a second ship associated with the first ship.
It should be noted that the first ship may refer to any kind of ship that travels on the sea, for example, the first ship may be classified according to the use of the ship, and the first ship may be a transportation ship, a fishery ship, an engineering ship, or the like. AIS may be located at a base station, mobile station or satellite on the ground; wherein, the AIS can be a Very High Frequency (VHF) radio communication system designed for ship foundations and roadbed platforms; the AIS can also be arranged on a satellite to detect and track a first ship far away from a coastline, so that a sensitive area can be monitored continuously in a large range. Wherein the sensitive region may refer to a region near a national boundary between countries in a sea area, or the like.
The first ship and the second ship referred to herein respectively refer to a ship detected by AIS and a ship detected by SAR. Wherein, AIS and SAR can also can install different equipment for installing same equipment, no matter install same equipment, and the mode that AIS and SAR cooperate together and then discern first naval vessel classification is similar. The above-described device may be a ship-mounted device or a satellite. The inventive concept is explained below only by way of an example in which AIS and SAR are commonly installed in a satellite.
In practical applications, the first AIS data includes a message type in 22, for example, the message type with the message ID (identity) code 1 and the message type with the message ID code 3 are both location reports of the first ship, and the location reports mainly include: a Maritime Mobile Service Identity (MMSI) code of the first ship, latitude and longitude information of the first ship, navigation direction information of the first ship, a navigation speed of the first ship to the ground, a probability of the first ship changing the navigation direction, and the like. For another example, the message type with the message ID code of 5 is static information of the first ship, and the static information includes two parts: the first part is invariable information, such as MMSI code, call sign, length and width of the first ship, etc.; the second part is information that varies with flight shift, such as the destination port for a particular flight, the time expected to arrive at the destination port, etc.
In some embodiments, the first AIS data may be AIS data of the first vessel acquired within half an hour before and after the SAR image is generated, that is, the first set time sequence is a time sequence acquired within half an hour before and after the SAR image is generated, and each time in the first set time sequence corresponds to a set of AIS data, for example, the first set time sequence is: (AIS1T1, AIS1T2, AIS1T3, AIS1T4, AIS1T5), and at this time the first AIS data may include: the location longitude of the first vessel (AIS1x1, AIS1x2, AIS1x3, AIS1x4, AIS1x5), the location dimension of the first vessel (AIS1y1, AIS1y2, AIS1y3, AIS1y4, AIS1y5), the track direction of the first vessel (AIS1a1, AIS1a2, AIS1A3, AIS1a4, AIS1a5), the location voyage speed of the first vessel (AIS1S1, AIS1S2, AIS1S3, AIS1S4, AIS1S 5).
In the practical application process, the SAR is an active microwave imaging device, the scattering characteristic of the target is actively extracted by means of the microwave signal emitted by the SAR, and the SAR can observe the target all day long and all weather, and can even observe and image the target by penetrating through a covering object and a camouflage object.
In some embodiments, for S102, may include:
obtaining a trajectory function of the first ship based on the first AIS data; the trajectory function is a functional relationship between time and the position of the first ship;
acquiring first position information of the first ship based on the track function and the imaging time of the SAR image;
obtaining second position information of each second ship in the SAR image;
obtaining a second ship associated with the first ship from each second ship based on the first location information of the first ship and the second location information of each second ship.
In some embodiments, said obtaining a trajectory function for the first ship based on the first AIS data comprises:
performing first analysis on the first AIS data to obtain a first analysis result;
obtaining third position information corresponding to each moment of the first ship in the first set time sequence based on the first analysis result;
determining a movement track scatter diagram of the first ship based on the third position information corresponding to each moment;
and carrying out first processing on the moving track scatter diagram according to a first set algorithm to obtain a track function of the first ship.
It should be noted that, based on the foregoing, the first AIS data is data of the first vessel in the first set time series, and includes location information. The first analysis is a processing procedure of analyzing the position information included in each moment in the first set time sequence in the first AIS data. Here, the third location information is location information corresponding to each time of the first vessel in the first set time series, which is included in the first AIS data. The third location information may include longitude and latitude of the first ship at each time, for example, at time T1, the corresponding location longitude of the first ship is AIS1x 1; position dimension of the first vessel: AIS1y 1.
In some embodiments, determining the movement trajectory scatter diagram of the first ship based on the third location information corresponding to each time point is to: using the longitude in the third position information corresponding to each moment as an X-axis coordinate; taking the dimension in the third position information corresponding to each moment as a Y-axis coordinate; and adding a coordinate point consisting of the third position information corresponding to each moment to the XY rectangular coordinate system to form a moving track scatter diagram of the first ship.
It should be noted that, the first setting algorithm is a fitting algorithm, which means that the moving track of the first ship, that is, the track function of the first ship, can be obtained based on the third position information corresponding to each time in the moving track scattergram of the first ship. In practical applications, the first setting algorithm may be a least square method. For example, based on the aforementioned first AIS data, a trajectory function of the first ship may be obtained, the curve of which is represented as shown in fig. 2.
In some embodiments, obtaining first location information of the first vessel based on the trajectory function and an imaging instant of the SAR image comprises: and substituting the imaging time of the SAR image into the track function to obtain first position information of the first ship. The first position information is position information of a position where a first ship is located at the moment, wherein the position information is calculated according to the track function of the first ship at the imaging moment of the SAR image.
In some embodiments, the obtaining second location information for each second ship in the SAR image comprises:
performing second processing on the SAR image to obtain an SAR image with position information;
detecting the SAR image with the position information to obtain a ship detection result;
and obtaining second position information of each second ship based on the ship detection result.
It should be noted that the SAR image is an image obtained by imaging the acquired echo signal of the satellite where the SAR is located by using a linear frequency modulation Scaling (CS) imaging processing algorithm based on the orbit parameter of the satellite where the SAR is located and the SAR load design parameter. The SAR image is an SAR echo backscattering coefficient image. The orbital parameters of a satellite are used to describe various parameters of the position, shape and orientation of the satellite in space, such as the orbital plane inclination (the angle between the equatorial plane and the orbital plane of the satellite), the altitude (the distance of the satellite from the earth's surface), and the like.
Here, the second processing includes view-through, filtering, and geocoding processing on the SAR image. Based on this, after the SAR image is subjected to the second processing, the SAR image with the position information can be obtained, and the SAR image with the position information is a backscattering intensity image.
In some embodiments, the performing detection processing on the SAR image with the location information to obtain a ship detection result includes: according to G0And a constant false alarm ship detection algorithm of a Gamma (Gamma) combined distribution model is used for detecting and processing the SAR image with the position information to obtain a ship detection result. In addition, G is0Is a G-0 distribution.
In an actual application process, the ship detection result includes a slice image of each second ship in the SAR image, where each slice image includes one second ship.
In some embodiments, the obtaining second location information of each second ship based on the ship detection result includes:
based on the ship detection result, obtaining a slice image corresponding to each second ship from the SAR image with the position information;
obtaining the central position information of the slice image corresponding to each second ship based on the slice image corresponding to each second ship;
and taking the central position information of the slice image corresponding to each second ship as the second position information of each second ship.
The center position information may be obtained by summing the position coordinate point at the uppermost left corner and the position coordinate point at the lowermost right corner of the slice image, and then obtaining an average value, which is used as the center position information. Namely: the center position information of the slice image corresponding to each second ship is obtained by summing the position coordinate point at the leftmost upper corner and the position coordinate point at the rightmost lower corner of each slice image and calculating the average value, so as to obtain the second position information of each second ship. The second location information is also latitude and longitude coordinates.
In some embodiments, the obtaining a second ship associated with the first ship from each second ship based on the first location information of the first ship and the second location information of each second ship comprises:
respectively determining distance information corresponding to the first ship and each second ship based on the first position information and each second position information;
determining a second ship closest to the first ship from each second ship based on the distance information corresponding to the first ship and each second ship;
and taking a second ship closest to the first ship as a second ship associated with the first ship.
It should be noted that the second ship associated with the first ship substantially obtains an image representation for the first ship based on SAR. Namely: the second ship associated with the first ship is the first ship. The distance information is a distance between the first ship and a second ship in the SAR image.
In an actual application process, the determining distance information corresponding to the first ship and each second ship respectively based on the first location information and each second location information includes: and respectively calculating the distance between the first ship and each second ship based on the first position information and each second position information.
It should be noted that, in the actual application process, the second ship closest to the first ship may be obtained by taking the first location information of the first ship as a central point and calculating to obtain the second ship in the SAR image closest to the central point according to a nearest neighbor search algorithm.
In some embodiments, said determining a classification of said first ship based on said first AIS data and a second ship associated with said first ship comprises:
acquiring the sailing speed and the sailing direction of the first ship based on the first AIS data;
obtaining a corrected image of a second ship associated with the first ship based on the sailing speed, the sailing direction and a pre-stored compensation model;
and determining the class of the first ship based on the corrected image and a ship classification model obtained by pre-training.
Based on the foregoing, the first AIS data includes the travel speed and the travel direction of the first ship. Therefore, the vessel speed and the vessel direction can be obtained based on the first AIS data.
In some embodiments, said obtaining a corrected image of a second vessel associated with said first vessel based on said navigational speed, said navigational direction and a pre-stored compensation model comprises:
inputting the sailing speed and the sailing direction into the pre-stored compensation model to obtain a corrected echo signal of the first ship;
performing focusing imaging processing on the first ship again based on the corrected echo signal to obtain a refocused image;
the refocused image is taken as a corrected image of a second ship associated with the first ship.
Note that the prestored compensation model is a doppler shift compensation model. The navigation speed and the navigation direction are also the navigation speed and the navigation direction of a second ship associated with the first ship.
In practical applications, the above process of obtaining a corrected image of the second ship associated with the first ship may be understood as follows: after the first ship and the second ship associated with the first ship are successfully associated, the navigation speed and the navigation direction of the first ship are used as the navigation speed and the navigation direction of the second ship associated with the first ship, and then based on the navigation speed and the navigation direction, a Doppler frequency shift compensation model is used for carrying out imaging correction on the first ship (namely, the second ship associated with the first ship), so as to obtain a refocused image (namely, a corrected image) of the first ship (namely, the second ship associated with the first ship) at a real position.
Exemplarily, as shown in fig. 3, it shows a schematic diagram of an application scenario for obtaining a correction map of a second ship associated with the first ship according to an embodiment of the present invention. In this scenario, the method includes: a satellite 301, wherein the satellite 301 operates in a right-side view mode and carries a SAR and a first ship 302, and the first ship 302 is located right to the satellite 301; the track direction of the satellite 301 is the azimuth velocity v; the distance between the satellite 301 and the first ship 302 is Rr(ii) a The first vessel 302 has a velocity v in the direction of the distancerVelocity in azimuth va。
Ignoring the change in acceleration, the distance between the first vessel 302 and the satellite 301 varies over time as:
Figure BDA0002295018050000151
taylor expansion is performed when t is equal to 0 in the formula (1), high-order terms are omitted, and the approximation value is
Figure BDA0002295018050000152
When the SAR emission signal is a carrier frequency-added linear frequency modulation signal:
s(τ)＝a(τ)exp(j2πωτ-jπKrτ2) (3)
where a (τ) is the rectangular envelope of the transmitted pulse, ω is the carrier frequency, KrIs a linear frequency modulation.
The echo signal obtained at time t is:
Figure BDA0002295018050000153
wherein S (tau, t) is a correction echo signal; rho is a backscattering coefficient; w (t) is the azimuth antenna pattern.
Based on the description of the formula (4), the echo signal obtained at the time t is increased by the backscattering coefficient rho of the first ship and the azimuth antenna directional pattern W (t) compared with the transmitting signal, and the SAR transmitting signal has the delay of twice the distance of the first ship.
In some embodiments, the obtaining of the corrected echo signal for the first vessel may be to bring equation (2) into equation (4) and retain only the baseband signal. And after the correction echo signal is obtained, carrying out secondary imaging processing on the first ship based on the correction echo signal to obtain a refocused image of the first ship, wherein the refocused image of the first ship is a corrected image.
In some embodiments, determining the classification of the first ship based on the revised image and a ship classification model obtained from pre-training comprises:
and inputting the corrected image into the ship classification model obtained by pre-training to obtain the category of the first ship.
In practical application, the classification of the first ship may be divided based on different classification strategies, for example, according to ship usage, including: transport vessels, fishery vessels, engineering vessels; as another example, cooperative vessels and non-cooperative vessels are included, depending on whether they cooperate with AIS. The embodiment of the invention illustrates the concept of the invention by taking as an example that the first ship can be classified into five types, namely a transport ship, a fishery ship, an engineering ship, a tugboat and the like.
In some embodiments, the pre-trained ship classification model may be obtained by obtaining refocused SAR images of each ship by using AIS data and echo signals of a high-resolution three-way satellite carrying an SAR, taking the refocused SAR images of each ship as a sample picture set, and then training the sample picture set by using a deep learning method to obtain different types of ship deep learning classification models (i.e., ship classification models).
In the practical application process, the obtaining of the ship classification model specifically comprises the following steps:
obtaining a plurality of sample pictures and mark data of each sample picture, wherein the sample pictures contain ships of different types, and the mark data is used for marking the type corresponding to each ship in the corresponding sample picture;
and performing learning training based on the plurality of sample pictures and the labeled data of each sample picture to obtain a ship classification model.
It should be noted that the plurality of sample pictures form a sample picture set of learning training, and in order to increase the universality of the pre-trained ship classification model, the sample pictures may be from different application scenarios, for example, the sample pictures may be obtained in a 50-view ocean area in a bunching mode by using a high-score-three sign.
In some embodiments, the obtaining process of the sample picture set may specifically include the following steps:
step A: collecting high-resolution third-order bunching mode data of a 50-scene ocean area, carrying out imaging processing on the data to obtain an SAR image, retrieving all AIS data of an imaging area within half an hour before and after the SAR image is imaged according to the imaging time and the imaging area of the SAR image, analyzing all AIS data, obtaining each first ship corresponding to each successfully matched AIS data and each second ship in the SAR image by adopting the matching mode, carrying out imaging correction on each first ship corresponding to each AIS data by adopting the image correction mode to obtain a refocused image of each first ship, namely obtaining a corrected image of each first ship;
and B: and cutting the corrected image of each first ship to obtain an image slice corresponding to the corrected image of each first ship. The size of the image slice comprises 299 x 299 horizontal and vertical pixel points.
It should be noted that, for less than 299 × 299 image slices, a four-side zero padding method is adopted to obtain 299 × 299 image slices; the image slices are larger than 299 x 299, and the image slices with the size of 299 x 299 are obtained by adopting a mode of resampling and cutting out the corrected image of each first ship;
and C: and (4) combining AIS data, dividing the obtained multiple image slices into five types according to a transport ship, a fishery ship, an engineering ship, a tugboat and the like, thereby obtaining a ship type classification model training data set.
The number of image slices is not less than 2000.
In some embodiments, the ship classification model is obtained by training a training dataset based on the ship classification model by using a google lenet inclusion v3 network structure. In the training process, training is carried out according to the proportion of 4:1 of the training set and the verification set, a batch gradient descent method is adopted for training, the batch size is set to be 16, the initial learning rate is set to be 0.01, and the iteration times are set to be 5000 times.
It should be noted that, in the foregoing method, an identification process of the first ship is set forth, and in an actual application process, the acquired second AIS data includes a plurality of first AIS data of the first ship, where the identification process may be as follows:
acquiring second AIS data of a second set time sequence; the second AIS data comprises first AIS data corresponding to at least two first ships;
obtaining first AIS data corresponding to each of the at least two first ships based on the second AIS data;
determining a second ship associated with each first ship from the at least one second ship based on the first AIS data and the SAR image corresponding to each first ship;
determining a category corresponding to each first ship based on the first AIS data corresponding to each first ship and the second ship associated with each first ship.
The second set time series is also a time series obtained from the SAR image within half an hour before and after the generation, and may be the same as or different from the first set time series.
In some embodiments, obtaining, based on the second AIS data, first AIS data corresponding to each of the at least two first vessels includes:
performing second analysis on the second AIS data to obtain a second analysis result;
obtaining a marine mobile service identification code MMSI of each of the at least two first ships based on the second analysis result;
and obtaining first AIS data corresponding to each of the at least two first ships from the second analysis result based on each MMSI.
The second parsing means parsing the second AIS data according to the AIS protocol. The MMSI is a unique identification of a ship, for example, the MMSI of a certain ship is 671633000, and when the 671633000 is identified, it can be determined that the certain ship is identified.
In an actual application process, for the first AIS data and the SAR image corresponding to each first ship, the second ship associated with each first ship is determined from the at least one second ship one by one according to the association manner, and a specific determination process refers to the foregoing description and is not described herein again.
Exemplarily, as shown in fig. 4, a schematic diagram of an association between each first ship and each second ship in the SAR image corresponding to the second AIS data provided by the embodiment of the present invention is shown. In fig. 4, AIS1-SAR1, AIS2-SAR2, AIS3-SAR3, AIS4-SAR4, AIS5-SAR5, AIS6-SAR6, AIS7-SAR7, and AIS8-SAR8 are pairs of successful association matching of the second AIS data with each ship in the SAR image, and SAR9 and SAR10 do not successfully associate the corresponding first AIS data in matching, and therefore are output as suspected AIS data missing ships.
In an actual application process, the identification of each first ship type of the at least two first ships may be performed one by one according to the foregoing identification manner, and the specific identification process refers to the foregoing description and is not described herein again.
To facilitate understanding of the present invention, as shown in fig. 5, a detailed flow diagram of a ship identification method provided by an embodiment of the present invention is shown.
It should be noted that the ship identification method is applied to satellite-borne SAR and AIS platforms and mainly comprises four parts: the method comprises the steps of preprocessing AIS data and SAR echo signal data, matching the AIS data with the ship in the SAR image in a time-space unified mode, correcting the AIS data corresponding to the ship in an imaging mode, and identifying the type of the ship corresponding to the AIS data.
The specific ship type identification process comprises the following steps:
step 1: analyzing second AIS data of a second set time sequence acquired by the satellite-borne AIS platform in real time to generate a moving track function of each ship in the SAR imaging area;
it should be noted that, for step 1, the following steps are specifically included:
step 1 a: according to the SAR image imaging time and the imaging area, the second AIS data is analyzed and retrieved, and an AIS ship information database of the imaging area within half an hour before and after the SAR image imaging is obtained; wherein the AIS ship information database is also the aforementioned second AIS data.
Step 1 b: taking the MMSI as a unique value, a moving trajectory database of each ship in the SAR image imaging area is generated, taking a ship with the MMSI as 671633000 as an example, a moving trajectory table of the ship is generated, and the moving trajectory table contains acquisition times (AIS1T1, AIS1T2, AIS1T3, AIS1T4, AIS1T5), ship position longitude (AIS1x1, AIS1x2, AIS1x3, AIS1x4, AIS1x5), ship position dimension (AIS1y1, AIS1y2, AIS1y3, AIS1y4, AIS1y5), ship heading directions (AIS1a1, AIS1a2, AIS1A3, AIS1a4, AIS1a5), and AIS1S1, AIS1S1 and AIS1x 1).
Step 1 c: based on a moving track database of each ship, obtaining a moving track curve of each ship by adopting least square fitting, and generating a moving track of each ship, for example, taking a ship with MMSI of 671633000 as an example, using ship moving track table information with MMSI of 671633000, obtaining a moving track curve of the ship by adopting least square fitting, and generating a track function (AIS1Tx, AIS1Ty) of the ship, wherein f (t);
step 2: and (4) bringing the SAR image imaging time T into the track function of each ship, and estimating to obtain the longitude and latitude coordinate values of each ship at the SAR image imaging time.
For example, the SAR image imaging time T is brought into the track function (AIS1Tx, AIS1Ty) f (T) of the ship, and longitude and latitude coordinate values (AIS 1T-SAR) of the ship are obtainedX，AIS1T-SARY) And in the same method, the longitude and latitude coordinate values of each ship at the SAR image imaging moment are obtained through calculation.
And step 3: and performing multi-view, filtering and geocoding processing on the SAR image to obtain an SAR backscattering intensity image with position information.
The SAR image is obtained by utilizing satellite orbit parameters and SAR load design parameters, utilizing a CS imaging algorithm to perform imaging processing on the acquired echo signals of the satellite-borne SAR, and performing modulus calculation to obtain a backscattering coefficient image of the echo signals of the satellite-borne SAR.
And 4, step 4: by using a base based on G0And a constant false alarm ship detection algorithm of the Gamma combined distribution model is used for detecting each ship in the SAR image to obtain a ship detection result of the SAR image.
And 5: and obtaining slice images of each second ship in the SAR image based on the ship detection result of the SAR image, adding the upper left corner point and the lower right corner point of each slice image, averaging, and calculating to obtain the pixel center position of each slice image as the longitude and latitude coordinate value (SARx, SARy) of each second ship in the SAR image.
Step 6: and calculating to obtain a second ship in the SAR image closest to the central point of each ship by adopting a nearest neighbor search algorithm by taking the longitude and latitude coordinate values of each ship at the SAR image imaging moment obtained by estimation as the central point.
Illustratively, the coordinate values (AIS1T-SARx, AIS1T-SARy) of the ships are used as central points, and a nearest neighbor search algorithm is adopted to calculate a second ship of the SAR image closest to the central points.
And 7: associating the first AIS data of the corresponding first ship with a second ship of the SAR image successfully matched to obtain the navigation speed and the navigation direction of the second ship in the SAR image, and performing imaging correction on the first ship by using a Doppler frequency shift compensation model to obtain a corrected image of the first ship at the real position; and outputting the second ship with the unsuccessfully matched SAR image as the ship with suspected AIS data missing.
And 8: the method comprises the steps of constructing a corrected image of each first ship in AIS data by using echo signals of a high-resolution three-satellite and synchronous AIS data, processing the corrected image of each first ship to obtain image slices containing the first ship, using a set formed by the image slices as a sample picture set, and training the sample picture set by using a deep learning method to obtain a ship classification model.
In practical application, the step 8 specifically includes the following steps:
step 8 a: collecting high-resolution third-order bunching mode data of a 50-scene ocean area, carrying out imaging processing on the data to obtain an SAR image, retrieving all AIS data of an imaging area within half an hour before and after the SAR image is imaged according to the SAR image imaging time and the imaging area, analyzing all AIS data, obtaining each first ship corresponding to each AIS data which is successfully matched and each second ship in the SAR image by adopting the association matching mode, carrying out imaging correction on each first ship corresponding to each AIS data by adopting the image correction mode to obtain a refocused image of each first ship, namely obtaining a corrected image of each first ship;
and step 8 b: and cutting the corrected image of each first ship to obtain an image slice corresponding to the corrected image of each first ship. The size of the image slice comprises 299 x 299 with horizontal and vertical pixel points, the image slice with the size less than 299 x 299 adopts a method of zero filling around, and the image slice with the size more than 299 x 299 adopts a mode of resampling and cutting a corrected image of each first ship to obtain the image slice with the size 299 x 299;
and step 8 c: and (3) combining AIS data, dividing the obtained multiple image slices into five types according to a transport ship, a fishery ship, an engineering ship, a tugboat and the like, wherein the number of SAR image slices of different types of ships is more than 2000, and thus obtaining a training data set of the ship classification model.
And step 8 d: aiming at a training data set of the ship classification model, a GoogLeNet inclusion V3 network structure is adopted to obtain the ship type classification model through training. In the training process, training is carried out according to the proportion of 4:1 of the training set and the verification set, a batch gradient descent method is adopted for training, the batch size is set to be 16, the initial learning rate is set to be 0.01, and the iteration times are set to be 5000 times.
And step 9: and (4) classifying to obtain the type of each first ship by using the ship type classification model and taking the corrected picture of each first ship in the step (7) as input.
According to the ship identification method provided by the embodiment of the invention, the AIS is fused into the traditional SAR, the position deviation and defocusing problems generated by ship motion are solved, the AIS data obtained by correlation matching is used for carrying out position correction and refocusing imaging on ships in the SAR image, the ship image with accurate and fine imaging position is obtained, and the accurate type of the first ship can be obtained based on the ship image and the AIS data obtained by refocusing imaging.
Based on the same inventive concept, the embodiment of the invention also provides a ship identification device, as shown in fig. 6, which shows a schematic structural diagram of the ship identification device. The apparatus 60 comprises: an acquisition module 601, a first determination module 602, and a second determination module 603, wherein,
the acquisition module 601 is configured to acquire first automatic identification system AIS data and a synthetic aperture radar SAR image of a first set time sequence of a first ship; the SAR image includes at least one second ship;
the first determining module 602 is configured to determine, based on the first AIS data and the SAR image, a second ship associated with the first ship from the at least one second ship;
the second determining module 603 is configured to determine the category of the first ship based on the first AIS data and a second ship associated with the first ship.
In some embodiments, the first determination module 602 includes: a first obtaining unit, a second obtaining unit, a third obtaining unit, and a fourth obtaining unit, wherein,
the first obtaining unit is configured to obtain a trajectory function of the first ship based on the first AIS data; the trajectory function is a functional relationship between time and the position of the first ship;
the second obtaining unit is configured to obtain first location information of the first ship based on the trajectory function and the imaging time of the SAR image;
the third obtaining unit is used for obtaining second position information of each second ship in the SAR image;
the fourth obtaining unit is configured to obtain, from each second ship, a second ship associated with the first ship based on the first location information of the first ship and the second location information of each second ship.
In some embodiments, the first obtaining unit is specifically configured to: performing first analysis on the first AIS data to obtain a first analysis result; obtaining third position information corresponding to each moment of the first ship in the first set time sequence based on the first analysis result; determining a movement track scatter diagram of the first ship based on the third position information corresponding to each moment; and carrying out first processing on the moving track scatter diagram according to a first set algorithm to obtain a track function of the first ship.
In some embodiments, the third obtaining unit comprises a first obtaining sub-unit, a second obtaining sub-unit, and a third obtaining sub-unit, wherein,
the first obtaining subunit is configured to perform second processing on the SAR image to obtain an SAR image with position information;
the second obtaining subunit is configured to perform detection processing on the SAR image with the position information to obtain a ship detection result;
the third obtaining subunit is configured to obtain second position information of each second ship based on the ship detection result.
In some embodiments, the third obtaining subunit is specifically configured to: based on the ship detection result, obtaining a slice image corresponding to each second ship from the SAR image with the position information; obtaining the central position information of the slice image corresponding to each second ship based on the slice image corresponding to each second ship; and taking the central position information of the slice image corresponding to each second ship as the second position information of each second ship.
In some embodiments, the fourth obtaining unit is specifically configured to: respectively determining distance information corresponding to the first ship and each second ship based on the first position information and each second position information; determining a second ship closest to the first ship from each second ship based on the distance information corresponding to the first ship and each second ship; and taking a second ship closest to the first ship as a second ship associated with the first ship.
In some embodiments, the second determining module 603 comprises: a fifth obtaining unit, a sixth obtaining unit, and a second determining unit, wherein,
the fifth obtaining unit is configured to obtain a sailing speed and a sailing direction of the first ship based on the first AIS data;
the sixth obtaining unit is configured to obtain a corrected image of a second ship associated with the first ship based on the sailing speed, the sailing direction, and a pre-stored compensation model;
the second determining unit is used for determining the category of the first ship based on the corrected image and a ship classification model obtained by pre-training.
In some embodiments, the sixth obtaining unit is specifically configured to: inputting the sailing speed and the sailing direction into the pre-stored compensation model to obtain a corrected echo signal of the first ship; performing focusing imaging processing on the first ship again based on the corrected echo signal to obtain a refocused image; the refocused image is taken as a corrected image of a second ship associated with the first ship.
In some embodiments, the apparatus further comprises: a third obtaining module;
the obtaining module 601 is further configured to: acquiring second AIS data of a second set time sequence; the second AIS data comprises first AIS data corresponding to at least two first ships;
the third obtaining module is configured to obtain, based on the second AIS data, first AIS data corresponding to each of the at least two first vessels; the first determining module 602 is further configured to: determining a second ship associated with each first ship from the at least one second ship based on the first AIS data and the SAR image corresponding to each first ship; the second determining module 603 is further configured to: determining a category corresponding to each first ship based on the first AIS data corresponding to each first ship and the second ship associated with each first ship.
It should be noted that the embodiment of the present invention provides a ship identification apparatus and the foregoing method, which are the same inventive concept, and all of the inventive concept is to fuse the AIS into the conventional SAR, perform position correction and refocusing imaging on the ship in the SAR image by using the AIS data obtained by correlation matching, to obtain a ship image with an accurate and fine imaging position, and obtain an accurate type of the first ship based on the ship image and the AIS data obtained by the refocusing imaging. Therefore, the meaning of the words appearing herein is the same as that described previously and will not be described further herein.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the foregoing method embodiments, and the foregoing storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The embodiment of the invention also provides a ship identification device, which comprises: a processor and a memory for storing a computer program capable of running on the processor, wherein the processor is configured to execute the steps of the above-described method embodiments stored in the memory when running the computer program.
Fig. 7 is a schematic diagram of a hardware structure of an adjusting apparatus according to an embodiment of the present invention, where the ship identification apparatus 70 includes: the at least one processor 701, the memory 702, and optionally, the ship identification apparatus 70 may further include at least one communication interface 703, and the various components in the ship identification apparatus 70 are coupled together through a bus system 704, and it is understood that the bus system 704 is used to implement connection communication between these components. The bus system 704 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled in fig. 7 as the bus system 704.
It will be appreciated that the memory 702 can be either volatile memory or nonvolatile memory, and can include both volatile and nonvolatile memory. Among them, the nonvolatile Memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a magnetic random access Memory (FRAM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical disk, or a Compact Disc Read-Only Memory (CD-ROM); the magnetic surface storage may be disk storage or tape storage. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Enhanced Synchronous Dynamic Random Access Memory (Enhanced DRAM), Synchronous Dynamic Random Access Memory (SLDRAM), Direct Memory (DRmb Access), and Random Access Memory (DRAM). The memory 702 described in connection with the embodiments of the invention is intended to comprise, without being limited to, these and any other suitable types of memory.
The memory 702 in the present embodiment is used to store various types of data to support the operation of the ship identification device 70. Examples of such data include: any computer program for operating on the ship identification device 70, such as implementations of digital-to-analog, fourier, etc., a program implementing a method of an embodiment of the present invention may be contained in the memory 702. The method disclosed in the above embodiments of the present invention may be applied to the processor 701, or implemented by the processor 701. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The processor may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed by the embodiment of the invention can be directly implemented by a hardware decoding processor, or can be implemented by combining hardware and software modules in the decoding processor. The software modules may be located in a storage medium having a memory and a processor reading the information in the memory and combining the hardware to perform the steps of the method.
In an exemplary embodiment, the ship identification Device 70 may be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, Micro Controllers (MCUs), microprocessors (microprocessors), or other electronic components for performing the above-described methods.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms. The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment. In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.

Claims (12)

1. A method for identifying a ship, the method comprising:
acquiring AIS data and SAR images of a first automatic identification system of a first set time sequence of a first ship; the SAR image includes at least one second ship;
determining a second ship associated with the first ship from the at least one second ship based on the first AIS data and the SAR image;
determining a category of the first ship based on the first AIS data and a second ship associated with the first ship.
2. The method of claim 1, wherein determining a second ship associated with the first ship from the at least one second ship based on the first AIS data and the SAR image comprises:
obtaining a trajectory function of the first ship based on the first AIS data; the trajectory function is a functional relationship between time and the position of the first ship;
acquiring first position information of the first ship based on the track function and the imaging time of the SAR image;
obtaining second position information of each second ship in the SAR image;
obtaining a second ship associated with the first ship from each second ship based on the first location information of the first ship and the second location information of each second ship.
3. The method of claim 2, wherein said obtaining a trajectory function for the first ship based on the first AIS data comprises:
performing first analysis on the first AIS data to obtain a first analysis result;
obtaining third position information corresponding to each moment of the first ship in the first set time sequence based on the first analysis result;
determining a movement track scatter diagram of the first ship based on the third position information corresponding to each moment;
and carrying out first processing on the moving track scatter diagram according to a first set algorithm to obtain a track function of the first ship.
4. The method of claim 2, wherein the obtaining second location information for each second ship in the SAR image comprises:
performing second processing on the SAR image to obtain an SAR image with position information;
detecting the SAR image with the position information to obtain a ship detection result;
and obtaining second position information of each second ship based on the ship detection result.
5. The method of claim 4, wherein obtaining second location information for each second ship based on the ship detection results comprises:
based on the ship detection result, obtaining a slice image corresponding to each second ship from the SAR image with the position information;
obtaining the central position information of the slice image corresponding to each second ship based on the slice image corresponding to each second ship;
and taking the central position information of the slice image corresponding to each second ship as the second position information of each second ship.
6. The method of claim 2, wherein the obtaining a second ship associated with the first ship from each second ship based on the first location information of the first ship and the second location information of each second ship comprises:
respectively determining distance information corresponding to the first ship and each second ship based on the first position information and each second position information;
determining a second ship closest to the first ship from each second ship based on the distance information corresponding to the first ship and each second ship;
and taking a second ship closest to the first ship as a second ship associated with the first ship.
7. The method of claim 1, wherein said determining a classification of the first ship based on the first AIS data and a second ship associated with the first ship comprises:
acquiring the sailing speed and the sailing direction of the first ship based on the first AIS data;
obtaining a corrected image of a second ship associated with the first ship based on the sailing speed, the sailing direction and a pre-stored compensation model;
and determining the class of the first ship based on the corrected image and a ship classification model obtained by pre-training.
8. The method of claim 7, wherein obtaining a corrected image of a second vessel associated with the first vessel based on the vessel speed, the vessel heading, and a pre-stored compensation model comprises:
inputting the sailing speed and the sailing direction into the pre-stored compensation model to obtain a corrected echo signal of the first ship;
performing focusing imaging processing on the first ship again based on the corrected echo signal to obtain a refocused image;
the refocused image is taken as a corrected image of a second ship associated with the first ship.
9. The method of claim 1, further comprising:
acquiring second AIS data of a second set time sequence; the second AIS data comprises first AIS data corresponding to at least two first ships;
obtaining first AIS data corresponding to each of the at least two first ships based on the second AIS data;
determining a second ship associated with each first ship from the at least one second ship based on the first AIS data and the SAR image corresponding to each first ship;
determining a category corresponding to each first ship based on the first AIS data corresponding to each first ship and the second ship associated with each first ship.
10. A ship identification device, the device comprising: an obtaining module, a first determining module, and a second determining module, wherein,
the acquisition module is used for acquiring first automatic identification system AIS data and synthetic aperture radar SAR images of a first set time sequence of a first ship; the SAR image includes at least one second ship;
the first determining module is configured to determine a second ship associated with the first ship from the at least one second ship based on the first AIS data and the SAR image;
the second determining module is configured to determine a category of the first ship based on the first AIS data and a second ship associated with the first ship.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 9.
12. An information processing apparatus characterized by comprising: a processor and a memory for storing a computer program operable on the processor, wherein the processor is operable to perform the steps of the method of any of claims 1 to 9 when the computer program is executed.
CN201911197420.2A 2019-11-29 2019-11-29 Ship identification method and device and computer storage medium Active CN110889380B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911197420.2A CN110889380B (en) 2019-11-29 2019-11-29 Ship identification method and device and computer storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911197420.2A CN110889380B (en) 2019-11-29 2019-11-29 Ship identification method and device and computer storage medium

Publications (2)

Publication Number Publication Date
CN110889380A true CN110889380A (en) 2020-03-17
CN110889380B CN110889380B (en) 2022-10-28

Family

ID=69749406

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911197420.2A Active CN110889380B (en) 2019-11-29 2019-11-29 Ship identification method and device and computer storage medium

Country Status (1)

Country Link
CN (1) CN110889380B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111626129A (en) * 2020-04-27 2020-09-04 中国人民解放军军事科学院国防科技创新研究院 Ship target joint detection method based on satellite AIS and infrared camera
CN112598733A (en) * 2020-12-10 2021-04-02 广州市赋安电子科技有限公司 Ship detection method based on multi-mode data fusion compensation adaptive optimization
CN114463224A (en) * 2022-04-14 2022-05-10 广东海洋大学 Ocean target image restoration and identification method and system based on SAR technology
CN114624656A (en) * 2022-03-08 2022-06-14 北京卫星信息工程研究所 Satellite-borne multi-baseline dual-band radar system and space target detection method thereof
CN114972918A (en) * 2022-05-30 2022-08-30 中国人民解放军国防科技大学 Remote sensing image ship target identification method based on integrated learning and AIS data

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7817079B1 (en) * 2008-04-17 2010-10-19 The United States Of America As Represented By The Secretary Of The Navy System and method for collection of global AIS and radar track information
CN108960143A (en) * 2018-07-04 2018-12-07 北京航空航天大学 Detect deep learning method in a kind of naval vessel in High Resolution Visible Light remote sensing images
CN109001780A (en) * 2018-06-22 2018-12-14 航天恒星科技有限公司 A kind of adaptive SAR satellite surface vessel target In-flight measurement method
CN109507665A (en) * 2018-10-30 2019-03-22 北京空间飞行器总体设计部 It is a kind of based on spaceborne AIS real time information guidance star on autonomous imaging method
CN109726616A (en) * 2017-10-30 2019-05-07 中电科海洋信息技术研究院有限公司 A kind of detection of naval vessel and recognition methods and device
CN109766811A (en) * 2018-12-31 2019-05-17 复旦大学 The end-to-end detection and recognition methods of sea ship in a kind of satellite-borne SAR image
CN110147807A (en) * 2019-01-04 2019-08-20 上海海事大学 A kind of ship intelligent recognition tracking
CN110389366A (en) * 2019-08-05 2019-10-29 中国人民解放军军事科学院国防科技创新研究院 A kind of naval target method for estimating based on multi-source SAR satellite

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7817079B1 (en) * 2008-04-17 2010-10-19 The United States Of America As Represented By The Secretary Of The Navy System and method for collection of global AIS and radar track information
CN109726616A (en) * 2017-10-30 2019-05-07 中电科海洋信息技术研究院有限公司 A kind of detection of naval vessel and recognition methods and device
CN109001780A (en) * 2018-06-22 2018-12-14 航天恒星科技有限公司 A kind of adaptive SAR satellite surface vessel target In-flight measurement method
CN108960143A (en) * 2018-07-04 2018-12-07 北京航空航天大学 Detect deep learning method in a kind of naval vessel in High Resolution Visible Light remote sensing images
CN109507665A (en) * 2018-10-30 2019-03-22 北京空间飞行器总体设计部 It is a kind of based on spaceborne AIS real time information guidance star on autonomous imaging method
CN109766811A (en) * 2018-12-31 2019-05-17 复旦大学 The end-to-end detection and recognition methods of sea ship in a kind of satellite-borne SAR image
CN110147807A (en) * 2019-01-04 2019-08-20 上海海事大学 A kind of ship intelligent recognition tracking
CN110389366A (en) * 2019-08-05 2019-10-29 中国人民解放军军事科学院国防科技创新研究院 A kind of naval target method for estimating based on multi-source SAR satellite

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
周树道等: "基于SAR图像的海洋舰船目标检测技术", 《微计算机应用》 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111626129A (en) * 2020-04-27 2020-09-04 中国人民解放军军事科学院国防科技创新研究院 Ship target joint detection method based on satellite AIS and infrared camera
CN112598733A (en) * 2020-12-10 2021-04-02 广州市赋安电子科技有限公司 Ship detection method based on multi-mode data fusion compensation adaptive optimization
CN112598733B (en) * 2020-12-10 2021-08-03 广州市赋安电子科技有限公司 Ship detection method based on multi-mode data fusion compensation adaptive optimization
CN114624656A (en) * 2022-03-08 2022-06-14 北京卫星信息工程研究所 Satellite-borne multi-baseline dual-band radar system and space target detection method thereof
CN114624656B (en) * 2022-03-08 2023-03-28 北京卫星信息工程研究所 Satellite-borne multi-baseline dual-band radar system and space target detection method thereof
CN114463224A (en) * 2022-04-14 2022-05-10 广东海洋大学 Ocean target image restoration and identification method and system based on SAR technology
CN114972918A (en) * 2022-05-30 2022-08-30 中国人民解放军国防科技大学 Remote sensing image ship target identification method based on integrated learning and AIS data
CN114972918B (en) * 2022-05-30 2024-04-19 中国人民解放军国防科技大学 Remote sensing image ship target identification method based on integrated learning and AIS data

Also Published As

Publication number Publication date
CN110889380B (en) 2022-10-28

Similar Documents

Publication Publication Date Title
CN110889380B (en) Ship identification method and device and computer storage medium
Specht et al. Comparative analysis of positioning accuracy of GNSS receivers of Samsung Galaxy smartphones in marine dynamic measurements
Wang et al. Urban positioning on a smartphone: Real-time shadow matching using GNSS and 3D city models
US10378905B2 (en) Auxiliary berthing method and system for vessel
Adjrad et al. Enhancing least squares GNSS positioning with 3D mapping without accurate prior knowledge
US8154438B1 (en) Registration of latitude/longitude coordinates using range detection sensors and digital nautical charts
Chaturvedi et al. Ship recognition by integration of SAR and AIS
KR20170102992A (en) Ship auxiliary docking method and system
US7840075B2 (en) Marine radar system with three-dimensional memory
EP4082890A1 (en) Administrative server in ship navigation assistance system, ship navigation assistance method, and ship navigation assistance program
Bai et al. Using Sky‐pointing fish‐eye camera and LiDAR to aid GNSS single‐point positioning in urban canyons
WO2015127540A1 (en) System and method for tracking and forecasting the positions of marine vessels
Groves et al. Shadow matching: Improved GNSS accuracy in urban canyons
CN109345599B (en) Method and system for converting ground coordinates and PTZ camera coordinates
CN111161353A (en) Vehicle positioning method and device, readable storage medium and computer equipment
Naus et al. Assessment of ship position estimation accuracy based on radar navigation mark echoes identified in an Electronic Navigational Chart
CN114488230A (en) Doppler positioning method and device, electronic equipment and storage medium
CN111950617A (en) On-satellite real-time fusion processing method and system for multi-source guide information
CN105928521A (en) Navigation method and system for sailing
KR20130036145A (en) A moving information determination apparatus, a receiver, and a method thereby
CN112505671A (en) Millimeter wave radar target positioning method and device under GNSS signal missing environment
Hyla et al. Analysis of radar integration possibilities in inland mobile navigation
CN114371484A (en) Vehicle positioning method and device, computer equipment and storage medium
CN107430004A (en) Method for the method for the water surface speed of at least one ship of calculating and for deriving the shift vectors on the path of the ship at each point
Moore et al. Accuracy Assessment of Two GPS Fidelity Prediction Services in Urban Terrain

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