CN115546651A - Multimode ship target detection and recognition system and device - Google Patents
Multimode ship target detection and recognition system and device Download PDFInfo
- Publication number
- CN115546651A CN115546651A CN202211464047.4A CN202211464047A CN115546651A CN 115546651 A CN115546651 A CN 115546651A CN 202211464047 A CN202211464047 A CN 202211464047A CN 115546651 A CN115546651 A CN 115546651A
- Authority
- CN
- China
- Prior art keywords
- ship
- detection
- remote sensing
- module
- identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Abstract
The invention relates to a multi-mode ship target detection and identification system and a device, wherein the system comprises a database module, a data visualization module, a ship detection and identification module and a data processing module, wherein the database module and the data visualization module are both arranged at a detection point; the device comprises a floating ring, a sea wave power unit, an anti-tilting support and a snapshot assembly. According to the invention, through the combination of the SAR technology and the AIS technology, the verification information of the ship can be obtained by utilizing the information exchange between the ship and the detection device in advance, if no ship verification information exists, a relay SAR ship detection unit is led out to be positioned at the edge of the protected pipeline, so that the detection and identification efficiency of the ship near the shore is improved, and the detection and identification range is effectively expanded.
Description
Technical Field
The invention belongs to the technical field of ship near-shore detection, and particularly relates to a multi-mode ship target detection and identification system and device.
Background
In order to protect submarine pipelines better, a set of ship detection and identification system needs to be established in a water area near the pipelines to detect the navigation state of passing ships, carry out real-time early warning on dangerous targets, transmit alarm information to an upper computer system in real time for processing, so that security management personnel can quickly respond to the alarm condition, and the safety of the submarine pipelines is effectively protected.
At present, through the existing ship identification system, the identification and detection range of the ship is only within the range of 20 nautical miles, and when the position of the ship and a pipeline is early-warned, the ship near the detection range cannot be early-warned in time, and then enters a pipeline laying area.
And many ships near the shore pass through image acquisition, and the environment near the shore is comparatively complicated, when carrying out the ship information check, need carry out a lot of preliminary treatment and characteristic separation step, has caused the deviation of target detection precision and identification precision.
Disclosure of Invention
The invention aims to solve the problems of small detection and identification range and more influence of target characteristics of near-shore detection, and provides a ship target detection and identification system and device with simple structure and reasonable design.
The invention realizes the purpose through the following technical scheme:
a multi-mode ship target detection and identification system comprises a database module, a data visualization module, a ship detection and identification module and a data processing module, wherein the database module and the data visualization module are installed at a detection point, and form a transceiving mechanism;
the ship detection and identification module comprises an SAR ship detection unit and an AIS ship identification unit, wherein the SAR ship detection unit is arranged in a near-shore area, close to a detection point, of a ship, the distance between the SAR ship detection unit and the detection point is adjustable, the SAR ship detection unit is based on characteristic detection and is used for snapshotting visible light remote sensing images at multiple points near the shore to obtain a plurality of visible light remote sensing images, and a data processing module is used for extracting target ship characteristics from the visible light remote sensing images;
the AIS ship identification unit is arranged in a ship and transmits static information and dynamic information to the data visualization module, and the static information and the dynamic information are used for comparing and updating the stored information in the database unit;
the database module is used for prestoring ship information, system login information, ship detection data sent by the data visualization module, processed data sent by the data processing module, identification information sent by the ship detection identification module and detected ship track data;
the data visualization module adopts an interactive visualization operation interface and is used for inputting system login information and displaying ship information and ship track data detected by the ship detection and identification module;
the data processing module comprises a feature extraction unit and a re-detection unit, wherein the feature extraction unit is used for extracting features from the visible light remote sensing image, sharing the features to the re-detection unit, finely blurring the feature part by the re-detection unit, recovering and restoring contrast, and identifying a target ship in the visible light remote sensing image;
the characteristic extraction unit extracts the characteristics of the visible light remote sensing image of the ship by using a threshold value binarization method, the detection unit realizes ship multi-target detection by using a convolutional neural network model, and the ship which accords with the characteristics in the visible light remote sensing image is identified and calibrated.
As a further optimization scheme of the invention: the AIS ship identification unit transmits static information including a ship name, a call sign, a ship length, a ship width, an IMO number and a ship type to the data visualization module.
As a further optimization scheme of the invention: the AIS ship identification unit transmits dynamic information including ship position (longitude and latitude), course, speed and navigation state to the data visualization module.
The SAR ship detection unit in the multi-mode ship target detection and identification system snappingly captures a target ship to obtain a visible light remote sensing image, and the device snappingly captures the target ship to obtain the visible light remote sensing image comprises a floating ring, a sea wave power unit, an anti-tilting bracket and a snapshotting assembly, wherein the floating ring is arranged on the sea level, the anti-tilting bracket is vertically arranged on the floating ring, the snapshotting assembly is arranged at the top of the anti-tilting bracket and is used for snapshotting the visible light remote sensing image of the ship, the sea wave power unit is arranged below the anti-tilting bracket, the tail end of the sea wave power unit extends to the position below the sea level, and the sea wave power unit generates power by utilizing the sea waves on the sea level and stores the power;
the candid photograph subassembly includes remote sensing candid photograph camera, adjusting part and inclination sensor, the adjusting part includes horizontal rotation piece, vertical rotation piece and horizontal rotation support, horizontal rotation piece locates the top of preventing inclining the support, is equipped with even arm between vertical rotation piece and the horizontal rotation piece, even the arm is "S" type structure, horizontal rotation support mounting is in the end of vertical rotation piece, remote sensing candid photograph camera is installed on horizontal rotation support, inclination sensor divides the inside of locating horizontal rotation piece, vertical rotation piece and horizontal rotation support, inclination sensor is used for detecting the remote sensing candid photograph camera for the level of sea level to, vertical and horizontal deflection angle to through horizontal rotation piece, vertical rotation piece and horizontal rotation support compensation for the level of sea level, vertical and horizontal deflection angle, make the remote sensing candid photograph camera maintain throughout with the sea level parallel to candid photograph.
As a further optimization scheme of the invention: a rope is arranged between the floating ring and the detection point, the detection point is also provided with a rope winding machine, the rope winding machine can drive the rope to be wound and unwound, the connection distance between the floating ring and the detection point is changed, and the floating ring can move around the edge of an area taking the rope winding machine as the circle center.
As a further optimization scheme of the invention: the tip of transversely rotating support is equipped with the transverse rotation piece, and horizontal rotation piece, vertical rotation piece and transverse rotation piece all include shell body, magnetizer, fixed magnetic pole, runing rest and electro-magnet, the runing rest is installed in the middle part of shell body, and the electro-magnet divides locates the periphery of runing rest, the end of electro-magnet is located to the magnetizer, and on the inside wall of shell body was located to the fixed magnetic pole annular, the magnetic pole of adjacent fixed magnetic pole is opposite, and magnetizer and fixed magnetic pole set up relatively, and the electro-magnet changes the magnetic pole of magnetizer, makes the magnetic pole of magnetizer the same with fixed magnetic pole or repel each other, and the magnetizer drives the runing rest and rotates the regulation round the center of shell body.
As a further optimization scheme of the invention: the sea wave power unit comprises a submergence cylinder, a movable rack, a floating plug and a power generation assembly, wherein the top end of the submergence cylinder and the floating barrel are fixedly installed, the floating plug moves along the axial direction of the submergence cylinder, the movable rack is vertically installed on the upper surface of the floating plug, and the movable rack is inserted into the power generation assembly.
As a further optimization scheme of the invention: the power generation assembly comprises a transmission gear, a micro-generator and a mounting bracket, the mounting bracket is arranged at the top of the submergence cylinder, the shaft end of the micro-generator is connected with the transmission gear, and the transmission gear is meshed and connected to the outer wall of the movable rack.
As a further optimization scheme of the invention: and the anti-tilting support is also provided with a wind power detector which is used for detecting the wind power value of the position of the SAR ship detection unit.
As a further optimization scheme of the invention: and the anti-tilting support is provided with a signal transceiver, the signal transceiver is in signal connection with the transceiving mechanism and the AIS ship identification unit, and the signal transceiver is used for relaying signal transmission between the target ship and the transceiving mechanism.
The invention has the beneficial effects that:
according to the invention, by combining the SAR technology and the AIS technology, the verification information of the ship can be obtained by exchanging information between the ship and the detection device in advance, if no ship verification information exists, a relay SAR ship detection unit is led out to be positioned at the edge of a protected pipeline, the detected range of the ship can be enlarged, the early warning interval is improved, stable snapshot is carried out on the ship by using a' chicken head stabilization principle in the SAR ship detection unit, the image characteristics of the ship are analyzed, the ship verification information is compared, the information is successfully identified, and the ship warning is connected;
or comparing the information in the database, the information is successfully identified if the information is consistent, and warning the ship to be far away by the contact way provided in the contact database, thereby improving the detection and identification efficiency of the ship near the shore and effectively expanding the detection and identification range.
Drawings
FIG. 1 is a system flow diagram of a multi-modal ship target detection and identification system according to the present invention;
FIG. 2 is a schematic diagram of detection and recognition of a multi-modal ship target detection and recognition system according to the present invention;
FIG. 3 is a schematic structural diagram of an SAR ship detection unit in the multi-modal ship target detection and recognition device provided by the invention;
FIG. 4 is a schematic view of the snapshot assembly of FIG. 3;
FIG. 5 is a schematic view of the structure of the rotating member in FIG. 4;
FIG. 6 is a schematic structural view of the wave power unit of FIG. 3;
FIG. 7 is a schematic diagram of the power generation assembly of FIG. 6;
fig. 8 is an enlarged view of a portion a in fig. 7.
In the figure: 100. a transceiver mechanism; 200. an SAR ship detection unit; 210. a floating ring; 220. a sea wave power unit; 221. submerging the barrel; 222. moving the rack; 223. a floating plug; 224. a power generation assembly; 224a, a transmission gear; 224b, a micro-generator; 225. a damping spring; 226. mounting a bracket; 230. a wind detector; 240. an anti-roll bracket; 250. a signal transceiver; 260. a snapshot assembly; 261. a horizontal rotation member; 261a, an electromagnet; 261b, an outer shell; 261c, a magnetizer; 261d, fixed magnetic pole; 261e, tilt angle sensor; 262. a connecting arm; 263. a longitudinal rotating member; 264. transversely rotating the bracket; 265. a remote sensing snapshot camera.
Detailed Description
The present application will now be described in further detail with reference to the drawings, it should be noted that the following detailed description is given for illustrative purposes only and is not to be construed as limiting the scope of the present application, as those skilled in the art will be able to make numerous insubstantial modifications and adaptations to the present application based on the above disclosure.
Example 1
Referring to fig. 1-2, the embodiment provides a multi-modal ship target detection and identification system, which includes a database module, a data visualization module, a ship detection and identification module, and a data processing module, where the database module and the data visualization module are installed at a detection point, and form a transceiver 100, and are connected with each other by signals, and the ship detection and identification module is located at the center of a ship detection area and connected with the data processing module;
the ship detection and identification module comprises an SAR ship detection unit 200 and an AIS ship identification unit, wherein the SAR ship detection unit 200 is arranged in a near-shore area, close to a detection point, where a ship passes through, the distance between the SAR ship detection unit 200 and the detection point is adjustable, the SAR ship detection unit 200 is based on characteristic detection and captures visible light remote sensing images at multiple points near the shore to obtain a plurality of visible light remote sensing images, and a data processing module is used for extracting target ship characteristics from the visible light remote sensing images;
the AIS ship identification unit is arranged in a ship and transmits static information and dynamic information to the data visualization module, and the static information and the dynamic information are used for comparing and updating the stored information in the database unit;
the database module is used for prestoring ship information, system login information, ship detection data sent by the data visualization module, processed data sent by the data processing module, identification information sent by the ship detection identification module and detected ship track data;
the data visualization module adopts an interactive visualization operation interface and is used for inputting system login information and displaying ship information and ship track data detected by the ship detection and identification module;
the data processing module comprises a feature extraction unit and a re-detection unit, wherein the feature extraction unit is used for extracting features from the visible light remote sensing image and sharing the features to the re-detection unit, and the re-detection unit carries out fine blurring on the feature part, restores the reduction contrast and identifies a target ship in the visible light remote sensing image;
the characteristic extraction unit extracts the characteristics of the visible light remote sensing image of the ship by using a threshold value binarization method, the detection unit realizes ship multi-target detection by using a convolutional neural network model, and the ship which accords with the characteristics in the visible light remote sensing image is identified and calibrated.
The AIS ship identification unit transmits static information including a ship name, a call sign, a ship length, a ship width, an IMO number and a ship type to the data visualization module.
The AIS ship identification unit transmits dynamic information including ship position (longitude and latitude), course, speed and navigation state to the data visualization module.
Referring to fig. 3-8, the apparatus for capturing and acquiring a visible light remote sensing image of a target ship and capturing and acquiring a visible light remote sensing image of the target ship by using the SAR ship detection unit 200 in the multi-modal ship target detection and identification system specifically includes: the sea wave remote sensing device comprises a floating ring 210, a sea wave power unit 220, an anti-tilting bracket 240 and a snapshot assembly 260, wherein the floating ring 210 is arranged on the sea level, the anti-tilting bracket 240 is vertically arranged on the floating ring 210, the snapshot assembly 260 is arranged at the top of the anti-tilting bracket 240, the snapshot assembly 260 is used for snapshotting a visible light remote sensing image of a ship, the sea wave power unit 220 is arranged below the anti-tilting bracket 240, the tail end of the sea wave power unit 220 extends to the lower side of the sea level, and the sea wave power unit 220 generates power by utilizing the sea waves on the sea level and stores the power;
the snapping assembly 260 comprises a remote sensing snapping camera 265, an adjusting assembly and an inclination angle sensor 261e, wherein the adjusting assembly comprises a horizontal rotating piece 261, a longitudinal rotating piece 263 and a transverse rotating support 264, the horizontal rotating piece 261 is arranged at the top end of the anti-tilting support 240, a connecting arm 262 is arranged between the longitudinal rotating piece 263 and the horizontal rotating piece 261, the connecting arm 262 is in an S-shaped structure, the transverse rotating support 264 is arranged at the tail end of the longitudinal rotating piece 263, the remote sensing snapping camera 265 is arranged on the transverse rotating support 264, the inclination angle sensor 261e is respectively arranged in the horizontal rotating piece 261, the longitudinal rotating piece 263 and the transverse rotating support 264, and the inclination angle sensor 261e is used for detecting the horizontal deflection angle, the longitudinal deflection angle and the transverse deflection angle of the remote sensing snapping camera 265 relative to the sea level and compensating the horizontal deflection angle, the longitudinal deflection angle and the transverse deflection angle relative to the sea level through the horizontal rotating piece 261, the longitudinal rotating piece 263 and the transverse rotating support 264, so that the remote sensing snapping camera 265 is always kept parallel to the sea level.
A rope is arranged between the floating ring 210 and the detection point, the detection point is also provided with a rope winding machine, the rope winding machine can drive the rope to be wound and unwound, the connection distance between the floating ring 210 and the detection point is changed, and the floating ring 210 can move around the edge of an area with the rope winding machine as the circle center.
The end of the transverse rotating bracket 264 is provided with a transverse rotating part, the transverse rotating part 261, the longitudinal rotating part 263 and the transverse rotating part all comprise an outer shell 261b, a magnetizer 261c, a fixed magnetic pole 261d, a rotating bracket and an electromagnet 261a, the rotating bracket is installed in the middle of the outer shell 261b, the electromagnet 261a is respectively arranged on the periphery of the rotating bracket, the magnetizer 261c is arranged at the tail end of the electromagnet 261a, the fixed magnetic pole 261d is arranged on the inner side wall of the outer shell 261b, the magnetizer 261c and the fixed magnetic pole 261d are oppositely arranged, the electromagnet 261a changes the magnetic pole of the magnetizer 261c, the magnetic pole of the magnetizer 261c is the same as or is opposite to the fixed magnetic pole 261d, and the magnetizer 261c drives the rotating bracket to rotate and adjust around the center of the outer shell 261 b.
The sea wave power unit 220 comprises a submergence cylinder 221, a moving rack 222, a floating plug 223 and a power generation assembly 224, wherein the top end of the submergence cylinder 221 is fixedly installed between the floating cylinders, the floating plug 223 moves along the axial direction of the submergence cylinder 221, the moving rack 222 is vertically installed on the upper surface of the floating plug 223, and the moving rack 222 is inserted into the power generation assembly 224.
It should be added that a damping spring 225 is arranged at the joint of the moving rack 222 and the floating plug 223, and the damping spring 225 is used for filtering vibration generated when the end surface of the submerged cylinder 221 abuts against the upper end surface of the floating plug 223;
the power generation assembly 224 comprises a transmission gear 224a, a micro-generator 224b and a mounting bracket 226, wherein the mounting bracket 226 is arranged at the top of the diving barrel 221, the shaft end of the micro-generator 224b is connected with the transmission gear 224a, and the transmission gear 224a is engaged and connected with the outer wall of the moving rack 222.
The anti-roll bracket 240 is further provided with a wind force detector 230, and the wind force detector 230 is used for detecting the wind force value of the position of the SAR ship detection unit 200.
The anti-roll bracket 240 is provided with a signal transceiver 250, the signal transceiver 250 is in signal connection with the transceiving mechanism 100 and the AIS ship identification unit, and the signal transceiver 250 is used for relaying signal transmission between the target ship and the transceiving mechanism 100.
It should be noted that, when the system and the device for detecting and identifying a multi-modal ship target are used, the specific detection and identification processes are as follows:
1. when the system is used, the SAR ship detection unit 200 needs to be released to the sea surface in the near-shore range of the detection point, and plays the roles of relaying and snapshot;
the snapshot process comprises the following steps: the remote sensing snapshot camera 265 utilizes the horizontal rotation piece 261, the longitudinal rotation piece 263 and the transverse rotation piece to adjust, the snapshot direction parallel to the sea level is always maintained to acquire images, wherein the horizontal rotation piece 261, the longitudinal rotation piece 263 and the transverse rotation piece are adjusted through magnetic pole conversion, namely if the rotation is needed to one side, a magnetizer 261c close to the adjacent fixed magnetic pole 261d is changed into the same magnetic pole, so that the magnetizer drives the rotation support to deflect to one side of the same magnetic pole, the change is changed through the current direction of the electromagnet 261a, and further the magnetic pole conversion is realized;
when the sea wave power unit 220 at the bottom side of the floating ring 210 works, sea waves enter through the submergence cylinder 221, the sea waves fluctuate to further drive the floating plug 223 to move up and down along the axial direction of the submergence cylinder 221, the movable rack 222 moves on the floating plug to drive the transmission gear 224a on the mounting bracket to rotate, namely the transmission gear 224a drives the gear connected with the tail end of the micro generator 224b to drive the micro generator 224b to move, the micro generator 224b is connected with the storage battery through a lead, and the storage battery stores electric power generated by the sea wave power unit 220 and provides electricity for equipment on the floating ring 210;
2. when a ship passes by, the SAR ship detection unit 200 snapshottes the ship, the snapshotting interval is 1-2s, a group of visible light remote sensing images are obtained, when the ship passes by the near shore in the visible light remote sensing images, static information and dynamic information are transmitted to the SAR ship detection unit 200 through the AIS ship identification unit, namely, basic information in the ship shot by the visible light remote sensing images is detected, and the ship characteristics are identified;
3. after the visible light remote sensing image of the ship is obtained, preprocessing and sea-land separation are carried out on the visible light remote sensing image, a characteristic extraction unit is used for marking and converting a connected region, and then a threshold value binarization method is used for extracting the characteristics of the visible light remote sensing image of the ship, wherein the detailed steps are as follows:
step 1: setting a threshold value T0 of an edge segmentation point of a visible light remote sensing image of the ship;
and 2, step: judging a maximum value of the wavelet transform of the ship visible light remote sensing image according to a threshold value T0, and setting a pixel point of the ship visible light remote sensing image to be 1 when the maximum value is larger than T0, otherwise setting the pixel point to be 0;
and step 3: and (3) overlapping and normalizing the ship visible light remote sensing image pixel points with the numerical value of 1 to obtain edge points E0 of the ship visible light remote sensing image, repeating the steps, and connecting all the ship visible light remote sensing image edge points to obtain the image characteristics of the visible light remote sensing image edge points.
And then realizing the multi-target detection of the ship in the image by utilizing a convolutional neural network model, wherein the specific operation steps are as follows:
the convolutional neural network model is composed of 5 convolutional layers, 3 x 3 convolutional operation, 2 pooling layers and two full-connection layers, and after the characteristics of the visible light remote sensing image of the ship are input into the convolutional neural network model, the visible light remote sensing image of the ship are input into the pooling layers after 5 times of convolutional operation and 3 x 3 times of convolutional mapping.
Merging the visible light remote sensing image characteristics of the ship by the pooling layer, and transmitting the visible light remote sensing image characteristics into the full connecting layer;
the full-connection layer maps the characteristics of the ship visible light remote sensing images into the sample marking space, the classification is used for outputting the identification result of the detected visible light remote sensing images, and the result is recorded as a detection multi-target detection result.
When a convolutional neural network model is used for detecting multiple targets of a ship, a pooling layer needs to perform scale conversion processing on characteristic vectors of visible light remote sensing images of the ship, and the expression formula is as follows:
in formula (1):
representing the characteristic vector of the initial ship visible light remote sensing image;
representing the characteristic vector of the ship visible light remote sensing image after scale transformation; d represents the pixel point distance; i represents the ith image feature vector;
and representing the characteristic vector of the ith ship visible light remote sensing image.
According to the result of the formula (1), the expression of the ship multi-target detection result output by the convolutional neural network model is as follows:
in the formula, y i Represents the target result, wherein i The scale factors are represented by a scale factor,
and representing the characteristic vector of the ith ship visible light remote sensing image.
According to the steps, migration iteration is carried out on the convolutional neural network model by using the formula (2), and ship multi-target detection in the image can be achieved.
4. After the target is detected, the dynamic information and the static information of the AIS ship identification unit can be obtained, the SAR ship detection unit 200 detects the actual characteristics of the ship, the data is packaged and transmitted to the transceiver mechanism 100 through the signal transceiver 250, the data visualization module in the transceiver mechanism 100 can display the ship information and the ship track data detected by the ship detection identification module, the ship information and the data in the static information and the dynamic information are compared in the database module, the data contract degree is compared, after the contract degree reaches the standard, the data is packaged and input into the database module, and the ship information and the track data of the detected ship are updated.
Although the embodiments of the present invention have been described with reference to the drawings, the present invention is not limited to the above specific embodiments, which are only illustrative and not restrictive, and those skilled in the art can make many forms without departing from the spirit and scope of the present invention and the claims.
Claims (10)
1. A multi-modal vessel target detection and identification system, characterized by: the ship detection and identification system comprises a database module, a data visualization module, a ship detection and identification module and a data processing module, wherein the database module and the data visualization module are both installed at a detection point, the database module and the data visualization module form a receiving and sending mechanism (100), the data visualization module, the ship detection and identification module and the data processing module are in signal connection with each other, the ship detection and identification module is arranged at the center of a ship detection area, and the data visualization module is connected with the data processing module;
the ship detection and identification module comprises an SAR ship detection unit (200) and an AIS ship identification unit, wherein the SAR ship detection unit (200) is arranged in a near-shore area, close to a detection point, where a ship passes through, the distance between the SAR ship detection unit (200) and the detection point is adjustable, the SAR ship detection unit (200) is based on characteristic detection and captures visible light remote sensing images at multiple points near the shore to obtain a plurality of visible light remote sensing images, and a data processing module is used for extracting target ship characteristics from the visible light remote sensing images;
the AIS ship identification unit is arranged in a ship and transmits static information and dynamic information to the data visualization module, and the static information and the dynamic information are used for comparing and updating the stored information in the database unit;
the database module is used for prestoring ship information, system login information, ship detection data sent by the data visualization module, processed data sent by the data processing module, identification information sent by the ship detection identification module and detected ship track data;
the data visualization module adopts an interactive visualization operation interface and is used for inputting system login information and displaying ship information and ship track data detected by the ship detection and identification module;
the data processing module comprises a feature extraction unit and a re-detection unit, wherein the feature extraction unit is used for extracting features from the visible light remote sensing image, sharing the features to the re-detection unit, finely blurring the feature part by the re-detection unit, recovering and restoring contrast, and identifying a target ship in the visible light remote sensing image;
the characteristic extraction unit extracts the characteristics of the visible light remote sensing image of the ship by using a threshold value binarization method, the detection unit realizes ship multi-target detection by using a convolutional neural network model, and the ship which accords with the characteristics in the visible light remote sensing image is identified and calibrated.
2. The multi-modal vessel target detection and identification system of claim 1, wherein: the AIS ship identification unit transmits static information including a ship name, a call sign, a ship length, a ship width, an IMO number and a ship type to the data visualization module.
3. The multi-modal vessel target detection and identification system of claim 1, wherein: and the AIS ship identification unit transmits dynamic information including ship position, course, speed and navigation state to the data visualization module.
4. The apparatus of claim 1, wherein the system is used in a multi-modal vessel target detection and identification system, and wherein: the sea wave power unit comprises a floating ring (210), a sea wave power unit (220), an anti-tilting support (240) and a snapshot assembly (260), wherein the floating ring (210) is arranged on the sea level, the anti-tilting support (240) is vertically arranged on the floating ring (210), the snapshot assembly (260) is arranged at the top of the anti-tilting support (240), the snapshot assembly (260) is used for snapshotting visible light remote sensing images of a ship, the sea wave power unit (220) is arranged below the anti-tilting support (240), the tail end of the sea wave power unit (220) extends to the position below the sea level, and the sea wave power unit (220) generates power by utilizing sea level sea waves and stores the power;
the remote sensing snapshot system is characterized in that the snapshot assembly (260) comprises a remote sensing snapshot camera (265), an adjusting assembly and an inclination angle sensor (261 e), the adjusting assembly comprises a horizontal rotating piece (261), a longitudinal rotating piece (263) and a transverse rotating support (264), the horizontal rotating piece (261) is arranged at the top end of the anti-tilting support (240), a connecting arm (262) is arranged between the longitudinal rotating piece (263) and the horizontal rotating piece (261), the connecting arm (262) is of an S-shaped structure, the transverse rotating support (264) is arranged at the tail end of the longitudinal rotating piece (263), the remote sensing snapshot camera (265) is arranged on the transverse rotating support (264), the inclination angle sensor (261 e) is respectively arranged in the horizontal rotating piece (261), the longitudinal rotating piece (263) and the transverse rotating support (264), the inclination angle sensor (261 e) is used for detecting the horizontal, longitudinal and transverse deflection angles of the remote sensing snapshot camera (265) relative to the sea level, and the horizontal rotating piece (261), the longitudinal and transverse deflection angles of the remote sensing snapshot camera (265) relative to the sea level are compensated through the horizontal rotating piece (261), the longitudinal rotating piece (263), and the transverse rotation support (264), and the horizontal rotation piece (265) and the remote sensing snapshot camera (265) is enabled to be always kept parallel to the sea level.
5. The apparatus of claim 4, wherein the system is further configured to: a rope is arranged between the floating ring (210) and the detection point, a rope winding machine is further arranged at the detection point, the rope winding machine can drive the rope to be wound and unwound, the connection distance between the floating ring (210) and the detection point is changed, and the floating ring (210) can move around the edge of an area with the rope winding machine as the circle center.
6. An apparatus for use in a multimodal vessel object detection and recognition system according to claim 4, wherein: the tip of transversely rotating support (264) is equipped with transverse rotation spare, and horizontal rotation spare (261), longitudinal rotation spare (263) and transverse rotation spare all include shell body (261 b), magnetizer (261 c), fixed magnetic pole (261 d), rotate support and electro-magnet (261 a), it installs in the middle part of shell body (261 b) to rotate the support, and electro-magnet (261 a) branch locates the periphery that rotates the support, the end of electro-magnet (261 a) is located in magnetizer (261 c), fixed magnetic pole (261 d) annular is located on the inside wall of shell body (261 b), the magnetic pole of adjacent fixed magnetic pole (261 d) is opposite, magnetizer (261 c) and fixed magnetic pole (261 d) set up relatively, and electro-magnet (261 a) change the magnetic pole of magnetizer (261 c), make the magnetic pole of magnetizer (261 c) the same or repel each other with fixed magnetic pole (261 d), and magnetizer (261 c) drive rotate the support and rotate the regulation round the center of shell body 261 b.
7. The apparatus of claim 4, wherein the system is further configured to: the sea wave power unit (220) comprises a submergence cylinder (221), a moving rack (222), a floating plug (223) and a power generation assembly (224), wherein the top end of the submergence cylinder (221) is fixedly mounted with a buoy, the floating plug (223) moves along the axial direction of the submergence cylinder (221), the moving rack (222) is vertically mounted on the upper surface of the floating plug (223), and the moving rack (222) is inserted into the power generation assembly (224).
8. An apparatus as claimed in claim 7, wherein the apparatus is used in a multimodal ship target detection and recognition system, and comprises: the power generation assembly (224) comprises a transmission gear (224 a), a micro-generator (224 b) and a mounting bracket (226), the mounting bracket (226) is arranged at the top of the submergence cylinder (221), the shaft end of the micro-generator (224 b) is connected with the transmission gear (224 a), and the transmission gear (224 a) is meshed and connected to the outer wall of the movable rack (222).
9. The apparatus of claim 4, wherein the system is further configured to: the anti-tilting support (240) is further provided with a wind power detector (230), and the wind power detector (230) is used for detecting the wind power value of the position of the SAR ship detection unit (200).
10. An apparatus for use in a multimodal vessel object detection and recognition system according to claim 4, wherein: the anti-roll bracket (240) is provided with a signal transceiver (250), the signal transceiver (250) is in signal connection with the transceiver (100) and the AIS ship identification unit, and the signal transceiver (250) is used for relaying signal transmission between the target ship and the transceiver (100).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211464047.4A CN115546651B (en) | 2022-11-17 | 2022-11-17 | Multimode ship target detection and recognition system and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211464047.4A CN115546651B (en) | 2022-11-17 | 2022-11-17 | Multimode ship target detection and recognition system and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115546651A true CN115546651A (en) | 2022-12-30 |
| CN115546651B CN115546651B (en) | 2023-02-28 |
Family
ID=84720143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211464047.4A Active CN115546651B (en) | 2022-11-17 | 2022-11-17 | Multimode ship target detection and recognition system and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115546651B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116226435A (en) * | 2023-05-09 | 2023-06-06 | 武汉理工大学三亚科教创新园 | Cross-modal retrieval-based association matching method for remote sensing image and AIS information |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714717A (en) * | 2012-10-09 | 2014-04-09 | 北京东方道迩信息技术股份有限公司 | Method for dynamically tracing ships and identifying behavior patterns of ships based SAR data |
| CN109636921A (en) * | 2018-12-17 | 2019-04-16 | 武汉理工大学 | Intelligent vision ship sensory perceptual system and data processing method based on cloud platform |
| CN109766823A (en) * | 2019-01-07 | 2019-05-17 | 浙江大学 | A kind of high-definition remote sensing ship detecting method based on deep layer convolutional neural networks |
| WO2019113137A2 (en) * | 2017-12-04 | 2019-06-13 | Gordon John Taylor Ii | Data retrieval and transmitting marine exploration vessel systems |
| CN111899450A (en) * | 2020-07-24 | 2020-11-06 | 宁波盛洋电子科技有限公司 | Method and system for monitoring ships entering and exiting port and finding dangerous ships |
| CN113378716A (en) * | 2021-06-11 | 2021-09-10 | 武汉大学 | Deep learning SAR image ship identification method based on self-supervision condition |
| CN113920407A (en) * | 2021-08-30 | 2022-01-11 | 合肥讯飞数码科技有限公司 | Ship target identification method and system based on multiband remote sensing image fusion |
| CN114355335A (en) * | 2021-12-13 | 2022-04-15 | 鹏城实验室 | Offshore small target detection system and method |
-
2022
- 2022-11-17 CN CN202211464047.4A patent/CN115546651B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714717A (en) * | 2012-10-09 | 2014-04-09 | 北京东方道迩信息技术股份有限公司 | Method for dynamically tracing ships and identifying behavior patterns of ships based SAR data |
| WO2019113137A2 (en) * | 2017-12-04 | 2019-06-13 | Gordon John Taylor Ii | Data retrieval and transmitting marine exploration vessel systems |
| CN109636921A (en) * | 2018-12-17 | 2019-04-16 | 武汉理工大学 | Intelligent vision ship sensory perceptual system and data processing method based on cloud platform |
| CN109766823A (en) * | 2019-01-07 | 2019-05-17 | 浙江大学 | A kind of high-definition remote sensing ship detecting method based on deep layer convolutional neural networks |
| CN111899450A (en) * | 2020-07-24 | 2020-11-06 | 宁波盛洋电子科技有限公司 | Method and system for monitoring ships entering and exiting port and finding dangerous ships |
| CN113378716A (en) * | 2021-06-11 | 2021-09-10 | 武汉大学 | Deep learning SAR image ship identification method based on self-supervision condition |
| CN113920407A (en) * | 2021-08-30 | 2022-01-11 | 合肥讯飞数码科技有限公司 | Ship target identification method and system based on multiband remote sensing image fusion |
| CN114355335A (en) * | 2021-12-13 | 2022-04-15 | 鹏城实验室 | Offshore small target detection system and method |
Non-Patent Citations (2)
| Title |
|---|
| 邢旭峰等: ""基于近海雷达与AIS探测目标融合算法研究"", 《海洋技术学报》 * |
| 高岚等: "合成孔径雷达图像船舶自动检测新方法", 《船海工程》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116226435A (en) * | 2023-05-09 | 2023-06-06 | 武汉理工大学三亚科教创新园 | Cross-modal retrieval-based association matching method for remote sensing image and AIS information |
| CN116226435B (en) * | 2023-05-09 | 2023-07-04 | 武汉理工大学三亚科教创新园 | Cross-modal retrieval-based association matching method for remote sensing image and AIS information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115546651B (en) | 2023-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110422281B (en) | Ocean Internet of things intelligent buoy, water surface or underwater target detection system and method thereof | |
| CN203337177U (en) | On-site monitoring and forecasting system for waterborne soft-yoke mooring system in Bohai Gulf | |
| US10054104B1 (en) | Autonomous underwater beacon locator | |
| CN115546651B (en) | Multimode ship target detection and recognition system and device | |
| CN106737703A (en) | Rescue robot under water and its rescue mode based on wireless telecommunications | |
| CN109084745A (en) | Submarine cable inspection submarine navigation device intelligent monitor system and Combinated navigation method | |
| CN112146654B (en) | Foresight imaging sonar underwater positioning and navigation method based on key constraint frame | |
| CN102495420A (en) | Underwater object precision positioning system and method | |
| CN111913406A (en) | Ship-shore collaborative simulation system for intelligent navigation and safety of ship | |
| CN210375200U (en) | Water surface or underwater target detecting instrument based on intelligent buoy | |
| CN111880192B (en) | Ocean monitoring buoy device and system based on water surface and underwater target early warning | |
| CN206773220U (en) | A kind of vessel detection instrument | |
| US20190079213A1 (en) | Automatic Harbor Surveillance System | |
| CN103852764A (en) | Submarine navigation monitoring system based on laser polarization detection | |
| CN113378920A (en) | Ship classification and identification method for low-resolution radar | |
| Eaton et al. | Maritime border security using sensors, processing, and platforms to detect dark vessels | |
| CN115857520A (en) | Unmanned aerial vehicle carrier landing state monitoring method based on combination of vision and ship state | |
| CN114548553A (en) | Ocean floating body motion forecasting system based on ocean wave image remote sensing and artificial intelligence | |
| KR102269384B1 (en) | support system for vessel operation and ship having the same | |
| US20200309905A1 (en) | System and method of persistent detection | |
| CN114396921A (en) | Qiantanjiang river tidal bore height and propagation speed measuring method based on unmanned aerial vehicle | |
| CN209833925U (en) | Device for maintaining the orientation of the bow and the relative position between the floating body and the ship | |
| CN111102969A (en) | Synchronous adjacent recording device for ocean noise source | |
| KR102428892B1 (en) | support system for vessel operation and ship having the same | |
| CN219957890U (en) | Submarine cable inspection 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 |