CN107945580A - Marine traction system AIS virtually guards against mark designation system and method - Google Patents
Marine traction system AIS virtually guards against mark designation system and method Download PDFInfo
- Publication number
- CN107945580A CN107945580A CN201711146209.9A CN201711146209A CN107945580A CN 107945580 A CN107945580 A CN 107945580A CN 201711146209 A CN201711146209 A CN 201711146209A CN 107945580 A CN107945580 A CN 107945580A
- Authority
- CN
- China
- Prior art keywords
- information
- traction
- model
- towing cable
- pulling
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G3/00—Traffic control systems for marine craft
- G08G3/02—Anti-collision systems
Landscapes
- Engineering & Computer Science (AREA)
- Ocean & Marine Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
- Navigation (AREA)
Abstract
The present invention provides a kind of sea traction system AIS and virtually guards against mark designation system, including towing cable sensor, millimetre-wave radar, processor and the memory being arranged on traction ship;There is computer program in memory to call for the processor, establishes long speed motion model, normal acceleration movement model and turning motion model, using interacting multiple model algorithm pull the tracking of body, obtain effectively pulling body information;Shape according to body is pulled carries out data fitting, obtain pulling the shape and orientation of body, the information and the length of towing cable and relative bearing carried with reference to traction ship, obtains traction ship, towing cable and the overall posture information for pulling body, chooses virtual warning mark and is sent to shippping traffic.The present invention includes the position of traction system and dynamic on the electronic chart of passing ships in the form of virtually guarding against target, makes traction system be easier to be identified by his ship under the conditions of poor visibility etc..
Description
Technical field
The invention belongs to intelligent naval technology field, and in particular to a kind of sea traction system AIS virtually guards against mark sign
System and method.
Background technology
With the increase of the activity such as marine transportation, ocean development, the demand of marine towing operation is increasing, including platform
Traction, marine salvage, traction transport etc..Marine traction is that a difficulty is big, and program is complicated, the high operation on the sea of technical requirements.
When be subject to strong wind, surge influenced when external disturbance when, traction ship and target pull body and yawing, meeting occur on predetermined course line
Towing cable stress is increased suddenly, cause disconnected cable and trigger accident.For effectively buffering traction during towing cable stress change dramatically,
Often release the towing cable (reaching 800-1000 meters) of sufficient length.If passing ships cannot identify dragging body, easily from traction ship with
Pass through, crash between dragging body.It is also more difficult to marine traction system identification at present.
The content of the invention
The technical problem to be solved in the present invention is:There is provided a kind of sea traction system AIS virtually guard against mark designation system and
The position of traction system and dynamic, can easily be included the electron sea in passing ships by method in the form of virtually guarding against target
On figure, traction system is set to be easier to be identified by his ship under the conditions of poor visibility etc..
The technical solution taken by the invention to solve the above technical problem is:A kind of sea traction system AIS is virtually warned
Guard against mark designation system, it is characterised in that:It includes towing cable sensor, millimetre-wave radar, the processor being arranged on traction ship
And memory, dragging body is connected with by towing cable after traction ship;Wherein,
Towing cable sensor is used for the length and relative bearing for obtaining towing cable;Millimetre-wave radar is used to obtain the pose for pulling body
Information;
Have computer program in memory to call for the processor, for performing following steps:
Data prediction:The posture information of the dragging body obtained to millimetre-wave radar is screened, and retains valid data;
Target following:Long speed motion model, normal acceleration movement model and turning motion model are established, utilizes interactive mode
Multiple Models Algorithm pull the tracking of body, obtains effectively pulling body information;
Pose resolves:Body information is pulled to effective, data fitting is carried out according to the shape for pulling body, obtains pulling body
The towing cable that shape and orientation, the GPS information carried with reference to traction ship and digital compass information and towing cable sensor obtain
Length and relative bearing, obtain traction ship, towing cable and the overall posture information for pulling body, if being chosen from overall posture information
Dry data point is marked as virtual warning;
Information is sent:The AIS systems carried by traction ship send virtual warning target information to shippping traffic.
By such scheme, some data points are chosen in the following manner:1 is pulled at ship empennage, pulls body 2-3
It is a, towing cable 2-4.
By such scheme, the target following is specially:First, long speed motion model, normal acceleration movement are established
Model and turning motion model, for emulating real motion model;Then, it is right according to the valid data after data prediction
The predicted state for pulling body is corrected, and optimal estimation is carried out to system mode;Model probability mixer is calculated shared by 3 kinds of models
Probability and proportion;Target state after the output mixing of state estimation mixer, is effective dragging body information.
The marker method that mark designation system is realized virtually is guarded against using the marine traction system AIS, it is characterised in that:
It comprises the following steps:
The posture information for pulling body is obtained using millimetre-wave radar, the information of acquisition is screened, retains valid data;
Using interacting multiple model algorithm pull the tracking of body, its median filter selects classical Kalman filtering
Device, interaction models select three kinds of constant velocity motion model, normal acceleration movement model and turning motion model models;
Body information is pulled to effective, data fitting is carried out according to the shape for pulling body, obtains pulling shape and the side of body
Position, the length and phase of the towing cable that the GPS information and digital compass information and towing cable sensor carried with reference to traction ship obtains
To orientation, traction ship, towing cable and the overall posture information for pulling body are obtained, some data points are chosen from overall posture information
As virtual warning mark;
The AIS systems carried by traction ship send virtual warning target information to shippping traffic.
The interacting multiple model algorithm is specially:
First, long speed motion model, normal acceleration movement model and turning motion model are established, for emulating really
Motion model;Then, according to the valid data after data prediction, the predicted state for pulling body is corrected, to system shape
State carries out optimal estimation;Model probability mixer calculates probability and proportion shared by 3 kinds of models;The output mixing of state estimation mixer
Target state afterwards, is effective dragging body information.
Beneficial effects of the present invention are:By being indicated respectively to traction ship, towing cable and dragging body, some data points are chosen
As virtual warning mark, virtual warning target information is sent to shippping traffic and is identified, so that easily by traction system
Position and dynamic be shown in the form of virtually guarding against target on the electronic chart of passing ships, make traction system in visibility not
It is easier to be identified have the advantages that safe, economical and efficient by his ship under the conditions of good grade.
Brief description of the drawings
Fig. 1 is the structure diagram of one embodiment of the invention.
Fig. 2 is the method flow diagram of one embodiment of the invention.
Fig. 3 is interacting multiple model algorithm flow chart in one embodiment of the invention.
Fig. 4 is the millimetre-wave radar scanning figure of one embodiment of the invention.
Fig. 5 is that the complete object of one embodiment of the invention pulls volume morphing figure.
Fig. 6 is that the target of one embodiment of the invention pulls body and its virtual warning sign is intended to.
Fig. 7 (a) is that the traction ship of one embodiment of the invention combines sign picture with dragging body.
Fig. 7 (b) is virtual warning target display figure on the electronic chart of one embodiment of the invention.
Fig. 8 is the millimetre-wave radar scanning figure of further embodiment of this invention.
Fig. 9 is that the complete object of further embodiment of this invention pulls volume morphing figure.
Figure 10 (a) is that the traction ship of further embodiment of this invention combines sign picture with dragging body.
Figure 10 (b) is virtual warning target display figure on the electronic chart of further embodiment of this invention.
Embodiment
With reference to instantiation and attached drawing, the present invention will be further described.
The present invention provides a kind of sea traction system AIS and virtually guards against mark designation system, as shown in Figure 1, it includes setting
Towing cable sensor, millimetre-wave radar, processor and memory on traction ship, are connected with after traction ship by towing cable and dragged
Drag body;Wherein, towing cable sensor is used for the length and relative bearing for obtaining towing cable;Millimetre-wave radar is used to obtain the position for pulling body
Appearance information;Have computer program in memory to call for the processor, as shown in Fig. 2, for performing following steps:
Data prediction:The posture information of the dragging body obtained to millimetre-wave radar is screened, and retains valid data.In the least
The data of metre wave radar collection can obtain the water surface and pull distance of the body target under rectangular coordinate system after controller is handled
Information and velocity information.But since false target often occurs in the influence of water surface clutter, falseness can be filtered out using threshold method
Target.The position for pulling body target any time is write as to the form of vector:
Z=[x, y, v]
In formula:X represents to pull the lateral separation between body and millimetre-wave radar, y represent to pull body and millimetre-wave radar it
Between fore-and-aft distance, v represents to pull the relative velocity between body and millimetre-wave radar.Due to equipment acquisition problems, millimeter wave thunder
Often there is null object in signal up to return, such issues that can directly be filtered out by program.In addition millimetre-wave radar detection pulls
During body, since horizontal plane reflects, invalid signals can be detected.This epoch is short, poor continuity, and numerical value can often occur
Bounce.Here signal can produce interference to normal detection, it is therefore desirable to filter out.
When carrying out filtering out invalid targets using threshold method, the following relation of adjacent capture setting twice:
Consider that traction ship and the possible speed travel speed setpoint distance threshold value of target are k1、k2, threshold speed k3。
Target, invalid targets can be filtered out by choosing suitable threshold value, finally identify valid data.
Target following:To ensure dragging body information stability that millimetre-wave radar detects, target following is carried out to it, is considered
There is stronger mobility when pulling body movement, detect the tracking for using interacting multiple model algorithm pull body, it is described
Multi-model includes three kinds of constant velocity motion model, normal acceleration movement model and turning motion model basic exercise models.The calculation
Method contains three kinds of wave filters (corresponding to three kinds of common motion models respectively), a model probability estimator, an interactive mode
Affector (the import and export end of wave filter), an estimation mixer (output terminal of wave filter).Interactive affector utilizes model
The interaction estimation of probability and each wave filter of Model transfer probability calculation, result is input in wave filter, wave filter binding capacity
Survey the probability that data calculate the possibility, then novel model of calculating of new estimation and model.Eventually through state mixer meter
Calculate total state.
Pose resolves:Body information is pulled to effective, data fitting is carried out according to the shape for pulling body, obtains pulling body
The towing cable that shape and orientation, the GPS information carried with reference to traction ship and digital compass information and towing cable sensor obtain
Length and relative bearing, obtain traction ship, towing cable and the overall posture information for pulling body, if being chosen from overall posture information
Dry data point is marked as virtual warning.Linear filtering is included using Kalman filter and alpha-beta-γ wave filters, nonlinear filtering
Extended Kalman filter and unwise filtering and particle filter.Some data points are chosen in the following manner:Pull ship tail
1 at the wing, body 2-3 is pulled, towing cable 2-4 (is set) according to the length of towing cable.
It is the premise for ensureing good tracking effect to establish suitable target following model.To ensure good tracking effect,
Interactive multi-model track algorithm is used in the present invention, but realizes constant velocity motion model, normal acceleration movement model, turn
Three kinds of model interactions of motion model, more preferable estimating target motion state.
Constant velocity motion model assumes that target pulls body and moves with uniform velocity, its state vector is X=[x, y, vX, vy];Chang Jia
Speed motion model assumes that target does uniformly accelerated motion, its state vector is X=[x, y, vX, vy, ax, ay];Turn Models introduce
The concept of turning rate, its state vector are X=[x, y, vX, vy, Ψ].
Interacting multiple model algorithm is the automatic identification and handoff algorithms between the model proposed based on bayesian theory, is schemed
3 be the flow chart of interacting multiple model algorithm.At the arbitrarily tracking moment, by the model for setting the possible model quantity of corresponding target
Wave filter carries out real-time model detection, and the probability of weight coefficient and model modification is set to each wave filter, finally weighting meter
Calculation draws current optimal estimation state, so as to achieve the purpose that adaptive.
For based on the state estimation on 3 model bases,State for model j is estimated
Meter.W (k) is the possibility vector of model, and u (k) is the probability vector of model.For the k-1 moment
The output of j-th of wave filter.ForReciprocation as a result,
Its input as k moment wave filters j.Z (k) is that the measurement at k moment inputs.
Traction posture calculation method based on millimetre-wave radar:Some data points are obtained after millimetre-wave radar is scanned,
Data point, which is pre-processed, and is filtered can obtain effective target dragging body relevant information, and obtained effective target is pulled body
It is fitted.
When it is rectangle to pull body, scanned tablet pattern, obtains Fig. 4.Dragging posture to millimetre-wave radar carries out
Resolve, target is subjected to minimum outsourcing rectangle fitting, complete target can be obtained and pull posture information, as shown in Figure 5.Will
After rectangular target is fitted, then body is pulled to target and carries out virtual warning target drafting, pulled in target and three are placed on body
Virtual warning mark, as shown in Figure 6.Towing cable by traction ship and target dragging body and between the two carries out virtual warning target connection
Sign is closed, as shown in Fig. 7 (a).Launch virtual warning target relevant information finally by AIS transmitters, on electronic chart
Mark is virtually guarded against to effective AIS, as shown in Fig. 7 (b).
When it is circle to pull body, scanned tablet pattern, obtains Fig. 8.Dragging posture to millimetre-wave radar carries out
Resolve, target is subjected to minimum circumscribed circle fitting, complete target can be obtained and pull posture information, as shown in Figure 9.Find
Circular feature point, carries out joint sign, such as Figure 10 (a) institutes by traction ship with towing cable again after placing virtual warning mark on it
Show.Launch virtual warning mark relevant information finally by AIS transmitters, effective AIS obtained on electronic chart and virtually guards against mark,
As shown in Figure 10 (b).
Information is sent:The AIS systems carried by traction ship send virtual warning target information to shippping traffic.
The marker method that mark designation system is realized virtually is guarded against using the marine traction system AIS, it includes following
Step:
The posture information for pulling body is obtained using millimetre-wave radar, the information of acquisition is screened, retains valid data;
Long speed motion model, normal acceleration movement model and turning motion model are established, is calculated using interactive multi-model
Method pull the tracking of body, obtains effectively pulling body information;
Body information is pulled to effective, data fitting is carried out according to the shape for pulling body, obtains pulling shape and the side of body
Position, the length and phase of the towing cable that the GPS information and digital compass information and towing cable sensor carried with reference to traction ship obtains
To orientation, traction ship, towing cable and the overall posture information for pulling body are obtained, some data points are chosen from overall posture information
As virtual warning mark.
The AIS systems carried by traction ship send virtual warning target information to shippping traffic.
In the present embodiment, to traction ship, towing cable, pull body and indicate respectively, at traction ship empennage, target drags
Drag body and towing cable between the two indicates 6 virtual warning target positions altogether;6 virtual warning mark latitude and longitude informations are turned
AIS system commands are changed to, being sent to shippping traffic using AIS transmitters is identified, so as to easily by traction system
Position and dynamic be shown in the form of virtually guarding against target on the electronic chart of passing ships, make traction system in visibility not
It is easier to be identified have the advantages that safe, economical and efficient by his ship under the conditions of good grade.
It is appreciated that embodiment as described herein can be by hardware, software, firmware, middleware, microcode or its any combination
To realize.For hardware implementation mode, processing unit can be at one or more application-specific integrated circuits (ASIC), digital signal
Manage device (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA),
Processor, controller, microprocessor, microcontroller, be designed to perform the other electronic units or its group of function described herein
Realized in closing., can be by it when with software, firmware, middleware or microcode, program code or code segment to realize embodiment
Be stored in the machine readable media of such as storage assembly.
Above example is merely to illustrate the design philosophy and feature of the present invention, and its object is to make technology in the art
Personnel can understand present disclosure and implement according to this, and protection scope of the present invention is not limited to above-described embodiment.So it is all according to
The equivalent variations made according to disclosed principle, mentality of designing or modification, within protection scope of the present invention.
Claims (5)
1. a kind of sea traction system AIS virtually guards against mark designation system, it is characterised in that:It includes being arranged on traction ship
Towing cable sensor, millimetre-wave radar, processor and memory, dragging body is connected with by towing cable after traction ship;Wherein,
Towing cable sensor is used for the length and relative bearing for obtaining towing cable;Millimetre-wave radar is used to obtain the pose letter for pulling body
Breath;
Have computer program in memory to call for the processor, for performing following steps:
Data prediction:The posture information of the dragging body obtained to millimetre-wave radar is screened, and retains valid data;
Target following:Long speed motion model, normal acceleration movement model and turning motion model are established, utilizes interactive multimode
Type algorithm pull the tracking of body, obtains effectively pulling body information;
Pose resolves:Body information is pulled to effective, data fitting is carried out according to the shape for pulling body, obtains pulling the shape of body
And orientation, the GPS information carried with reference to traction ship and digital compass information and the length of the towing cable of towing cable sensor acquisition
And relative bearing, traction ship, towing cable and the overall posture information for pulling body are obtained, some numbers are chosen from overall posture information
Marked as virtual warning at strong point;
Information is sent:The AIS systems carried by traction ship send virtual warning target information to shippping traffic.
2. sea traction system AIS according to claim 1 virtually guards against mark designation system, it is characterised in that:Described
Some data points are chosen in the following manner:1 is pulled at ship empennage, pulls body 2-3, towing cable 2-4.
3. sea traction system AIS according to claim 1 virtually guards against mark designation system, it is characterised in that:Described
Target following is specially:
First, long speed motion model, normal acceleration movement model and turning motion model are established, for emulating real movement
Model;Then, according to the valid data after data prediction, the predicted state for pulling body is corrected, to system mode into
Row optimal estimation;Model probability mixer calculates probability and proportion shared by 3 kinds of models;Mesh after the output mixing of state estimation mixer
Motion state is marked, is effective dragging body information.
4. virtually guarding against the marker method that mark designation system is realized using the marine traction system AIS described in claim 1, it is special
Sign is:It comprises the following steps:
The posture information for pulling body is obtained using millimetre-wave radar, the information of acquisition is screened, retains valid data;
Establish long speed motion model, normal acceleration movement model and turning motion model, using interacting multiple model algorithm into
Row pulls the tracking of body, obtains effectively pulling body information;
Body information is pulled to effective, data fitting is carried out according to the shape for pulling body, obtains pulling the shape and orientation of body, knot
Close GPS information and digital compass information and the length and contra of the towing cable of towing cable sensor acquisition that traction ship carries
Position, obtains traction ship, towing cable and the overall posture information for pulling body, some data point conducts is chosen from overall posture information
Virtual warning mark;
The AIS systems carried by traction ship send virtual warning target information to shippping traffic.
5. marker method according to claim 4, it is characterised in that:The interacting multiple model algorithm is specially:
First, long speed motion model, normal acceleration movement model and turning motion model are established, for emulating real movement
Model;Then, according to the valid data after data prediction, the predicted state for pulling body is corrected, to system mode into
Row optimal estimation;Model probability mixer calculates probability and proportion shared by 3 kinds of models;Mesh after the output mixing of state estimation mixer
Motion state is marked, is effective dragging body information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711146209.9A CN107945580B (en) | 2017-11-17 | 2017-11-17 | System and method for marking AIS virtual warning marks of marine towing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711146209.9A CN107945580B (en) | 2017-11-17 | 2017-11-17 | System and method for marking AIS virtual warning marks of marine towing system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107945580A true CN107945580A (en) | 2018-04-20 |
CN107945580B CN107945580B (en) | 2020-04-21 |
Family
ID=61931736
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711146209.9A Active CN107945580B (en) | 2017-11-17 | 2017-11-17 | System and method for marking AIS virtual warning marks of marine towing system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107945580B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110580826A (en) * | 2019-09-02 | 2019-12-17 | 武汉理工大学 | Multi-mode electronic safety warning device and method for ship |
CN111965636A (en) * | 2020-07-20 | 2020-11-20 | 重庆大学 | Night target detection method based on millimeter wave radar and vision fusion |
CN112540622A (en) * | 2020-04-10 | 2021-03-23 | 广州极飞科技有限公司 | Radar data processing method and device and operation equipment |
CN113393708A (en) * | 2020-03-13 | 2021-09-14 | 青岛海洋地质研究所 | Method and device for collision avoidance of workboat and workboat |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105070101A (en) * | 2015-07-17 | 2015-11-18 | 武汉理工大学 | Cartridge type platform traction risk early warning and visualization system |
CN105667736A (en) * | 2015-12-31 | 2016-06-15 | 中交第一航务工程局有限公司 | Navigation system for long-distance towing |
CN107016879A (en) * | 2017-05-19 | 2017-08-04 | 武汉理工大学 | Virtually guard against mark system and method in a kind of construction ship operation area based on AIS/GPRS |
-
2017
- 2017-11-17 CN CN201711146209.9A patent/CN107945580B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105070101A (en) * | 2015-07-17 | 2015-11-18 | 武汉理工大学 | Cartridge type platform traction risk early warning and visualization system |
CN105667736A (en) * | 2015-12-31 | 2016-06-15 | 中交第一航务工程局有限公司 | Navigation system for long-distance towing |
CN107016879A (en) * | 2017-05-19 | 2017-08-04 | 武汉理工大学 | Virtually guard against mark system and method in a kind of construction ship operation area based on AIS/GPRS |
Non-Patent Citations (3)
Title |
---|
HIROAKI TAKA: "Construction of a marine traffic monitoring system around the world", 《2013 MTS/IEEE OCEANS-BERGEN》 * |
张帆: "筒型平台拖带偏航风险预警研究", 《中国安全科学学报》 * |
王学林: "长江VTS船舶动态管理***的研究与实现", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110580826A (en) * | 2019-09-02 | 2019-12-17 | 武汉理工大学 | Multi-mode electronic safety warning device and method for ship |
CN113393708A (en) * | 2020-03-13 | 2021-09-14 | 青岛海洋地质研究所 | Method and device for collision avoidance of workboat and workboat |
CN112540622A (en) * | 2020-04-10 | 2021-03-23 | 广州极飞科技有限公司 | Radar data processing method and device and operation equipment |
CN111965636A (en) * | 2020-07-20 | 2020-11-20 | 重庆大学 | Night target detection method based on millimeter wave radar and vision fusion |
Also Published As
Publication number | Publication date |
---|---|
CN107945580B (en) | 2020-04-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102658233B1 (en) | Harbor monitoring device and harbor monitoring method | |
CN107945580A (en) | Marine traction system AIS virtually guards against mark designation system and method | |
CN109409283B (en) | Method, system and storage medium for tracking and monitoring sea surface ship | |
US20190204416A1 (en) | Target object detecting device, method of detecting a target object and computer readable medium | |
Leira et al. | Automatic detection, classification and tracking of objects in the ocean surface from UAVs using a thermal camera | |
CN111899568B (en) | Bridge anti-collision early warning system, method and device and storage medium | |
Symington et al. | Probabilistic target detection by camera-equipped UAVs | |
CN101214851A (en) | Intelligent all-weather actively safety early warning system and early warning method thereof for ship running | |
KR20210090572A (en) | Device and method for monitoring a berthing | |
US11320269B2 (en) | Information processing apparatus, information processing method, and information processing program | |
US20220406104A1 (en) | Implement management system for implement wear detection and estimation | |
CN111323756B (en) | Marine radar target detection method and device based on deep learning | |
Zsedrovits et al. | Visual detection and implementation aspects of a UAV see and avoid system | |
Lyu et al. | Sea-surface object detection based on electro-optical sensors: A review | |
CN112967320A (en) | Ship target detection tracking method based on bridge collision avoidance | |
Eaton et al. | Maritime border security using sensors, processing, and platforms to detect dark vessels | |
EP4104659A1 (en) | Implement management system for determining implement state | |
CN112816956A (en) | Method and device for acquiring radar target information | |
Li et al. | Algorithm of obstacle avoidance for autonomous surface vehicles based on LIDAR detection | |
Wang et al. | Deep learning-based robust positioning scheme for imaging sonar guided dynamic docking of autonomous underwater vehicle | |
Kim et al. | Multi-Target Tracking Considering the Uncertainty of Deep Learning-based Object Detection of Marine Radar Images | |
US11288523B2 (en) | Pseudo-range estimation from a passive sensor | |
CN107341087A (en) | A kind of O&M pre-alarm and prevention system architecture based on multi-sensor information fusion | |
Wu et al. | RISTrack: Robust Infrared Ship Tracking With Modified Appearance Feature Extraction and Matching Strategy | |
Castaldo et al. | Data fusion using a factor graph for ship tracking in harbour scenarios |
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 |