CN114166137A - Intelligent detection system and method for ship-to-ship filling interval - Google Patents
Intelligent detection system and method for ship-to-ship filling interval Download PDFInfo
- Publication number
- CN114166137A CN114166137A CN202111423527.1A CN202111423527A CN114166137A CN 114166137 A CN114166137 A CN 114166137A CN 202111423527 A CN202111423527 A CN 202111423527A CN 114166137 A CN114166137 A CN 114166137A
- Authority
- CN
- China
- Prior art keywords
- ship
- filling
- station
- thermal imaging
- distance
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title abstract description 11
- 238000001931 thermography Methods 0.000 claims abstract description 43
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000003287 optical effect Effects 0.000 claims abstract description 6
- 238000002347 injection Methods 0.000 claims description 10
- 239000007924 injection Substances 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 6
- 238000000926 separation method Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 238000009434 installation Methods 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003949 liquefied natural gas Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an intelligent detection system and method for ship-to-ship filling intervals, wherein the intelligent detection system comprises an intelligent thermal imaging binocular camera module, a multi-line laser radar module, a processing module and a plurality of acousto-optic alarm modules; the intelligent thermal imaging binocular camera module comprises two thermal imaging cameras, the two thermal imaging cameras are respectively installed on a bow portion and a stern portion of a filling side of a filling ship, optical axes of the two thermal imaging cameras are parallel, the multi-line laser radar is installed on the filling side and close to a filling pipe, the processing module is used for calculating a filling interval according to information collected by the intelligent thermal imaging binocular camera module and the multi-line laser radar module, and the sound-light alarm module sends different signals according to the filling interval. The invention can improve the degree of unmanned intelligence when filling the ship by the ship, particularly can accurately detect the filling interval of the ship by the ship after automatically identifying the filling station, and can realize the anti-collision function while protecting the hose.
Description
Technical Field
The invention belongs to the technical field of intelligent detection and alarm of ships, and particularly relates to an intelligent detection system and method for a ship-to-ship filling interval.
Background
The low-temperature liquid cargo filling ship can realize non-port filling when filling the ship, and can also carry out filling simultaneously with cargo loading and unloading, namely, the low-temperature liquid cargo filling ship has higher flexibility in the aspects of filling position, filling speed, filling amount and the like. However, compared with shore-based filling, filling a ship by a ship has more potential risks, such as ship bumping and ship collision caused by excessive movement between ships and bad sea conditions. Generally, when a large ship passes through a filling operation nearby at a high speed, the ship may shake to generate relative displacement of front and back, up and down; if the relative positions of the two ships are abnormally changed, the hoses are timely and emergently separated and sealed in advance, and the leakage accident caused by the breakage of the hoses is avoided. Therefore, in the prior art, before filling the liquefied natural gas ship into the ship, a set of ship body Separation detectors (VSDs) are manually bound to the bow parts and the stern parts of the two ships respectively, and the safe operation of filling the hoses is guaranteed by indirectly measuring the filling distance (the linear distance of the hoses) between the bow parts and the stern parts of the two ships. The working principle is that three ropes with different lengths are respectively bound between the bow part and the stern part of two ships, and a mechanical device is triggered by the tension degrees of the three ropes so as to indirectly reflect the filling distance between the two ships. Although the principle of the method is simple, the method has the problems of low precision, large influence of human factors and the like; if the binding position on the injection ship is different, the injection interval of the trigger mechanical device is different in practice. More importantly, the method can only detect whether the relative positions of the two ships are too far away, and cannot detect whether the distance between the two ships is too close, so that the potential risk of collision exists when the ships fill the ships.
In fact, the relative displacement between the two ships includes the position relation of front and back and up and down, so that the protection distance of the hose is not the fine distance of "point to point" in a three-dimensional space, but the protection distance of the hose is not "face to face" or "point to face". Therefore, an intelligent detection alarm system is needed to be designed aiming at special working conditions during ship-to-ship filling operation, and functions of hose protection, anti-collision and the like are achieved by detecting filling intervals of two ships.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an intelligent detection system for a ship-to-ship filling interval, which integrates modules of image recognition, radar ranging, detection alarm and the like, and can realize functions of hose protection, anti-collision and the like during ship-to-ship filling. In addition, the invention also provides an intelligent detection method for the ship-to-ship filling interval.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides an intelligent detection system for a ship-to-ship filling interval, which comprises an intelligent thermal imaging binocular camera module, a multi-line laser radar module, a processing module and a plurality of acousto-optic alarm modules, wherein the intelligent thermal imaging binocular camera module is connected with the processing module;
the intelligent thermal imaging binocular camera module comprises two thermal imaging cameras, the two thermal imaging cameras are respectively installed on a bow portion and a stern portion of a filling side of a filling ship, optical axes of the two thermal imaging cameras are parallel, the multi-line laser radar is installed on the filling side and close to a filling pipe, the processing module is used for calculating a filling interval according to information collected by the intelligent thermal imaging binocular camera module and the multi-line laser radar module, and the sound-light alarm module sends different signals according to the filling interval.
The second aspect of the invention provides an intelligent detection method for a ship-to-ship filling interval, which is based on the intelligent detection system and comprises the following steps:
firstly, acquiring a graph and training an image recognition depth network of an intelligent thermal imaging binocular camera module;
step two, the intelligent thermal imaging binocular camera module detects whether a two-dimensional target of the annotated station appears in the captured picture in real time, and if the target is found, the step three is carried out;
starting a multi-line laser radar module to perform real-time scanning, and establishing a side model of the ship to be injected;
marking the annotated station in the annotated ship side model;
tracking the injected station and calculating the real-time distance between the injecting station and the injected station by the processing module;
judging whether the distance between the filling ship and the filled ship is in a safe distance or not;
and step seven, outputting an alarm signal.
As a preferred technical solution, the fourth step includes the following steps:
s4.1, calibrating the injection station in two-dimensional images recognized by the intelligent thermal imaging binocular camera;
s4.2, calculating the depth of the pixel points of the annotated station;
and S4.3, marking the pixel points of the annotated station in a radar coordinate system.
As a preferred technical scheme, the first step is specifically as follows:
and collecting pictures of the injection station under different angles, different distances and different light rays of a plurality of injection shore stations, inputting the pictures into the intelligent thermal imaging binocular camera module, and training an image recognition depth network.
As a preferred technical scheme, the second step is specifically as follows:
detecting whether a remarked station appears in a two-dimensional picture captured by the intelligent thermal imaging binocular camera module in real time;
if the two-dimensional picture is detected to have no annotated station, continuously circulating the step two to detect whether the two-dimensional picture has the annotated station in real time;
and if the two-dimensional picture is detected to have the annotated station, executing the third step to establish an annotated ship side model.
As a preferred technical scheme, the step five specifically comprises the following steps:
defining the length of a filling hose as L and the real-time distance between a filling station and a filling station as Lt;
When 0.35L < LtLess than 0.57L, belonging to a safe distance;
when 0.3L is less than LtL is not more than 0.35L or not more than 0.57LtLess than 0.585L, belonging to a first dangerous distance;
when l is more than or equal to 4.5mtL is less than 0.3L or less than or equal to 0.585LtLess than 0.775L belonging to the second dangerous distance;
when L is more than or equal to 0.775LtAnd belongs to the third dangerous distance category.
And as a preferable technical scheme, when the real-time distance belongs to the safe distance, continuously and circularly judging whether the real-time distance is in the safe distance or not, and when the real-time distance does not belong to the safe distance, executing the step seven and sending out an alarm signal.
As a preferred technical scheme, the seventh step is specifically as follows:
when the dangerous distance type is a first-class dangerous distance, starting a first-class cargo alarm, and performing a yellow acousto-optic alarm on an alarm lamp post in the cabin and the deck area of the filling ship;
when the dangerous distance type is a second dangerous distance, starting a secondary cargo alarm, and performing red acousto-optic alarm on the alarm lamp post in the cabin and the deck area of the filling ship;
and when the dangerous distance type is a third dangerous distance type, starting a general ship alarm, transmitting a signal to the emergency separation connector, and preparing the hose to be emergently separated and closed.
Compared with the prior art, the invention has the following technical effects:
the invention can improve the degree of unmanned intelligence when filling ships to ships, can accurately detect the filling intervals (linear intervals of hoses) of ships to ships after automatically identifying the filling stations, and can realize the anti-collision function while protecting the hoses. To a certain extent, the method can be integrated into an intelligent navigation or intelligent cargo management system of an intelligent ship to support high-quality development of intelligent ship technology.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of the intelligent detection method of the present invention.
Fig. 2 is a schematic structural diagram of the intelligent detection system of the present invention.
FIG. 3 is a schematic diagram of the depth calculation of the pixel points of the annotated station according to the present invention.
Wherein the reference numerals are specified as follows: the multi-line laser radar device comprises a multi-line laser radar 1, a bow thermal imaging camera 2, a stern thermal imaging camera 3 and a filling side 4.
Detailed Description
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention.
The embodiment provides an intelligent detection system for a ship-to-ship filling interval, which comprises an intelligent thermal imaging binocular camera module, a multi-line laser radar 1 module, a processing module and a plurality of acousto-optic alarm modules;
the intelligent thermal imaging binocular camera module comprises two thermal imaging cameras, namely a bow thermal imaging camera 2 and a stern thermal imaging camera 3, the two thermal imaging cameras are respectively installed on the bow and the stern of a filling side 4 of a filling ship, the two thermal imaging cameras are the same in model and parallel in optical axis, the multiline laser radar 1 is installed on the filling side 4 close to a position near a filling pipe and free of obstacles, the processing module is used for calculating a filling interval according to information collected by the intelligent thermal imaging binocular camera module and the multiline laser radar 1, and the acousto-optic alarm module sends different signals according to the filling interval.
The embodiment also provides an intelligent detection method for the ship-to-ship filling interval, which comprises the following steps:
step one, image acquisition and deep network training:
collecting pictures of the injected stations of the injected ship under different angles, different distances and different light rays of a plurality of injecting shore stations, inputting the pictures into the intelligent thermal imaging binocular camera module, and training an image recognition depth network;
step two, detecting whether the two-dimensional picture appears in the annotated station in real time:
detecting whether a remarked station appears in a two-dimensional picture captured by the intelligent thermal imaging binocular camera module in real time;
if the two-dimensional picture is detected to have no annotated station, continuously circulating the step two to detect whether the two-dimensional picture has the annotated station in real time;
if the two-dimensional picture is detected to have the annotated station, executing the third step to establish an annotated ship side model;
step three, establishing an annotated ship side model:
starting the multi-line laser radar 1 module to scan in real time, and establishing a side model of the ship to be injected;
and fourthly, the processing module performs data processing to calibrate the injection station in the injection ship side model:
after a station to be annotated is identified in two-dimensional images of the intelligent thermal imaging binocular camera, the station to be annotated needs to be calibrated in the two-dimensional images, then the depth of a pixel point of the station to be annotated is calculated, and finally the pixel point of the station to be annotated is calibrated in a radar coordinate system, and the method comprises the following steps:
1) calibrating a subject station to two-dimensional images
The position of the injected station is calibrated in two-dimensional images, and the pixel point a of the injected station can be calculated through the conversion of a pixel coordinate system-an image coordinate system-a camera coordinate systemiRespectively in the bow camera coordinate system OC1-XC1-YC1Plane and stern camera coordinate system OC2-XC2-YC2Coordinates on a plane (a)XCi-1,aYCi-1)、(aXCi-2,aYCi-2);
Assuming a stem pixel coordinate system O1-U1-V1Using the upper left of the image as the origin of coordinates, U1Shaft and V1Axes are parallel to the image plane edges, respectively, in units: pixels/millimeter (pixel/mm); therefore, the pixel coordinate of the center point of the stem image is (c)u-1,cv-1);
Assuming a stem image coordinate system o1-x1-y1Using the central point of the imaging plane as the origin of coordinates, x1Axis and y1Axes are parallel to the image plane edges, respectively, in units: millimeters (mm);
assuming bow camera coordinate system OC1-XC1-YC1-ZC1Is the optical center O of the bow cameraC1Is the midpoint, ZC1The axis being the optical axis perpendicular to the imaging plane of the camera, XC1、YC1The axis conforms to the right hand rule;
stem pixel coordinate system O1-U1-V1Heading image coordinate system o1-x1-y1Conversion: after the position of the station to be annotated is identified in the two-dimensional image of the bow, the pixel point a of the station to be annotated can be calibratediHas a stem pixel coordinate of (a)ui-1,avi-1) Calculating the pixel point a of the injected station according to the conversion relation between the pixel coordinate system and the image coordinate systemiThe two-dimensional image coordinate set of the bow part is (a)xi-1,ayi-1) Comprises the following steps:
in the formula, alpha and beta are pixel points in x1Axis, y1The dimension ratio on the axis is determined by the intrinsic parameters of the camera;
bow image coordinate system o1-x1-y1Heading camera coordinate system OC1-XC1-YC1-ZC1Conversion: the transformation relation between the image coordinate system and the camera coordinate system can calculate the pixel point a of the annotated stationiIn the bow camera coordinate system OC1-XC1-YC1The coordinate on the plane is (a)XCi-2,aYCi-2) Comprises the following steps:
wherein f is the focal length of the camera and is determined by the internal parameters of the bow camera, and the unit is as follows: pixels (pixels);
according to the above-mentioned conversion method of pixel coordinate system-image coordinate system-camera coordinate system, pixel point a can be calculated out by the same methodiAt stern camera coordinate system OC2-XC2-YC2The coordinate set on the plane is (a)XCi-2,aYCi-2);
2) Calculating the depth of the pixel point of the annotated station
According to the triangle similarity principle, the pixel point a of the annotated station can be calculatediDepth a ofZCi:
Wherein d is the base line distance between the fore part and the stern part, f is the focal length of the camera, aXCi-1,aXCi-2For the pixel point a of the annotated stationiRespectively on the horizontal coordinates of the fore camera coordinate system and the stern camera coordinate system;
thus, the pixel point a can be knowniThe coordinate sets of the fore camera coordinate system and the stern camera coordinate system are respectively (a)XCi-1,aYCi-1,aZCi)、(aXCi-2,aYCi-2,aZCi);
3) Calibrating pixel points of a annotated station to a radar coordinate system
Because a certain distance exists between the installation positions of the binocular camera and the radar, the relation of rotation and three-dimensional translation exists between the fore camera coordinate system, the stern camera coordinate system and the radar coordinate system at the same time;
assuming that the relationship between the bow thermal imaging camera 2 and the radar in rotation and three-dimensional translation existing at the installation position of the filling side 4 is that the three-order rotation matrix S is diag (S)X,sY,sZ) Third-order translation vector D ═ D (D)X dY dZ)T
Then, the pixel point a of the annotated stationiThe relation between the matrix C in the bow camera coordinate system and the corresponding point cloud matrix R in the radar coordinate system is as follows:
C=MR
wherein the content of the first and second substances,
C=[aXCi-1 aYCi-1 aZCi 1]TR=[aXRi aYRi aZRi 1]T;s, D, the relevant parameters are determined by the external position parameters of the bow camera and the radar installation;
therefore, in the model of the side of the annotated ship, the pixel a is connected with the annotated stationiThe corresponding point cloud matrix R can be expressed as:
wherein (a)XCi-1,aYCi-1,aZCi) Is a pixel point a of the annotated stationiCoordinates in the bow camera coordinate system, (a)XRi,aYRi,aZRi) Is a pixel point a of the annotated stationiCoordinates in a radar coordinate system;
step five, tracking the annotated station and calculating the real-time distance:
Step six, judging whether the distance is within a safe distance:
assuming that the length of the hose equipped on the filling vessel is 20m, the real-time distance L calculated according to the fifth steptAnd judging whether the distance is within a safe distance:
when 0.35L < Lt< 0.57L, i.e. 7m < LtIf the distance is less than 11.4m, the mobile terminal belongs to the safe distance;
when it is 0.3L<ltL is not more than 0.35L or not more than 0.57Lt< 0.585L, i.e.
6m<ltL is less than or equal to 7m or 11.4mt< 11.7m belongs to a first category of dangerous distances;
when l is more than or equal to 4.5tL is less than 0.3L or less than or equal to 0.585Lt< 0.775L, i.e.
4.5≤ltL is less than 6m or 11.7mt< 11.5m belongs to the second category of dangerous distances;
when L is more than or equal to 0.775LtI.e. 15.5 m.ltoreq.ltTo a third category of dangerous distances;
when the real-time distance belongs to the safe distance, continuously circulating the step six to judge whether the real-time distance is in the safe distance; when the real-time distance belongs to any dangerous distance, executing the seventh step to output an alarm signal;
step seven, outputting an alarm signal:
outputting a corresponding alarm signal according to the judged dangerous distance type:
when the dangerous distance type is a first-class dangerous distance, starting a first-class cargo alarm, and performing a yellow acousto-optic alarm on an alarm lamp post in the cabin and the deck area of the filling ship;
when the dangerous distance type is a second dangerous distance, starting a secondary cargo alarm, and performing red acousto-optic alarm on the alarm lamp post in the cabin and the deck area of the filling ship;
and when the dangerous distance type is a third dangerous distance type, starting a general ship alarm, transmitting a signal to the emergency separation connector, and preparing the hose to be emergently separated and closed.
Although the present invention has been described in detail with respect to the above embodiments, it will be understood by those skilled in the art that modifications or improvements based on the disclosure of the present invention may be made without departing from the spirit and scope of the invention, and these modifications and improvements are within the spirit and scope of the invention.
Claims (8)
1. An intelligent detection system for ship-to-ship filling intervals is characterized by comprising an intelligent thermal imaging binocular camera module, a multi-line laser radar module, a processing module and a plurality of acousto-optic alarm modules;
the intelligent thermal imaging binocular camera module comprises two thermal imaging cameras, the two thermal imaging cameras are respectively installed on a bow portion and a stern portion of a filling side of a filling ship, optical axes of the two thermal imaging cameras are parallel, the multi-line laser radar is installed on the filling side and close to a filling pipe, the processing module is used for calculating a filling interval according to information collected by the intelligent thermal imaging binocular camera module and the multi-line laser radar module, and the sound-light alarm module sends different signals according to the filling interval.
2. An intelligent detection method for ship-to-ship filling intervals, which is based on the intelligent detection system for ship-to-ship filling intervals of claim 1, and is characterized by comprising the following steps:
firstly, acquiring a graph and training an image recognition depth network of an intelligent thermal imaging binocular camera module;
step two, the intelligent thermal imaging binocular camera module detects whether a two-dimensional target of the annotated station appears in the captured picture in real time, and if the target is found, the step three is carried out;
starting a multi-line laser radar module to perform real-time scanning, and establishing a side model of the ship to be injected;
marking the annotated station in the annotated ship side model;
tracking the injected station and calculating the real-time distance between the injecting station and the injected station by the processing module;
judging whether the distance between the filling ship and the filled ship is in a safe distance or not;
and step seven, outputting an alarm signal.
3. The intelligent detection method for the ship-to-ship filling interval according to claim 2, wherein the fourth step comprises the following steps:
s4.1, calibrating the injection station in two-dimensional images recognized by the intelligent thermal imaging binocular camera;
s4.2, calculating the depth of the pixel points of the annotated station;
and S4.3, marking the pixel points of the annotated station in a radar coordinate system.
4. The intelligent detection method for the ship-to-ship filling interval according to claim 2, wherein the first step is specifically as follows:
and collecting pictures of the injection station under different angles, different distances and different light rays of a plurality of injection shore stations, inputting the pictures into the intelligent thermal imaging binocular camera module, and training an image recognition depth network.
5. The intelligent detection method for the ship-to-ship filling interval according to claim 2, wherein the second step is specifically as follows:
detecting whether a remarked station appears in a two-dimensional picture captured by the intelligent thermal imaging binocular camera module in real time;
if the two-dimensional picture is detected to have no annotated station, continuously circulating the step two to detect whether the two-dimensional picture has the annotated station in real time;
and if the two-dimensional picture is detected to have the annotated station, executing the third step to establish an annotated ship side model.
6. The intelligent detection method for the ship-to-ship filling interval according to claim 2, wherein the fifth step is specifically as follows:
defining the length of a filling hose as L and the real-time distance between a filling station and a filling station as Lt;
When 0.35L < LtLess than 0.57L, belonging to a safe distance;
when 0.3L is less than LtL is not more than 0.35L or not more than 0.57LtLess than 0.585L, belonging to a first dangerous distance;
when l is more than or equal to 4.5mtL is less than 0.3L or less than or equal to 0.585LtLess than 0.775L belonging to the second dangerous distance;
when L is more than or equal to 0.775LtAnd belongs to the third dangerous distance category.
7. The intelligent detection method for the ship-to-ship filling interval according to claim 4, wherein when the real-time distance belongs to the safe distance, the sixth step of continuous circulation judges whether the real-time distance is in the safe distance, and when the real-time distance does not belong to the safe distance, the seventh step of continuous circulation is executed, and an alarm signal is sent out.
8. The intelligent detection method for the ship-to-ship filling interval according to claim 5, wherein the seventh step is specifically as follows:
when the dangerous distance type is a first-class dangerous distance, starting a first-class cargo alarm, and performing a yellow acousto-optic alarm on an alarm lamp post in the cabin and the deck area of the filling ship;
when the dangerous distance type is a second dangerous distance, starting a secondary cargo alarm, and performing red acousto-optic alarm on the alarm lamp post in the cabin and the deck area of the filling ship;
and when the dangerous distance type is a third dangerous distance type, starting a general ship alarm, transmitting a signal to the emergency separation connector, and preparing the hose to be emergently separated and closed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111423527.1A CN114166137A (en) | 2021-11-26 | 2021-11-26 | Intelligent detection system and method for ship-to-ship filling interval |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111423527.1A CN114166137A (en) | 2021-11-26 | 2021-11-26 | Intelligent detection system and method for ship-to-ship filling interval |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114166137A true CN114166137A (en) | 2022-03-11 |
Family
ID=80481137
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111423527.1A Pending CN114166137A (en) | 2021-11-26 | 2021-11-26 | Intelligent detection system and method for ship-to-ship filling interval |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114166137A (en) |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN203784632U (en) * | 2014-01-27 | 2014-08-20 | 江苏海企港华燃气发展有限公司 | Filling device of overwater natural gas filling station |
CN104197183A (en) * | 2014-01-27 | 2014-12-10 | 江苏海企港华燃气发展有限公司 | Natural gas charging station process flow on water and charging device |
US20180012498A1 (en) * | 2015-01-15 | 2018-01-11 | Nanjing University 5D Technology Co., Ltd. | Auxiliary berthing method and system for vessel |
CN108121251A (en) * | 2017-11-24 | 2018-06-05 | 浙江海洋大学 | Marine fuel filling device and control method |
CN108665499A (en) * | 2018-05-04 | 2018-10-16 | 北京航空航天大学 | A kind of low coverage aircraft pose measuring method based on parallax method |
CN109631782A (en) * | 2017-10-05 | 2019-04-16 | 美国亚德诺半导体公司 | System and method for measuring bridge gap |
CN112509333A (en) * | 2020-10-20 | 2021-03-16 | 智慧互通科技股份有限公司 | Roadside parking vehicle track identification method and system based on multi-sensor sensing |
CN113192274A (en) * | 2021-04-23 | 2021-07-30 | 沪东中华造船(集团)有限公司 | Staff cabin safety monitoring method based on wireless communication |
CN113223075A (en) * | 2021-03-11 | 2021-08-06 | 大连海事大学 | Ship height measuring system and method based on binocular camera |
CN113501088A (en) * | 2021-06-25 | 2021-10-15 | 沪东中华造船(集团)有限公司 | Side-leaning system and side-leaning method applied to LNG filling ship |
CN113627473A (en) * | 2021-07-06 | 2021-11-09 | 哈尔滨工程大学 | Water surface unmanned ship environment information fusion sensing method based on multi-mode sensor |
CN113639099A (en) * | 2021-07-21 | 2021-11-12 | 上海外高桥造船有限公司 | Marine low-temperature liquid fuel or cargo filling hose support and filling system |
CN113673386A (en) * | 2021-08-06 | 2021-11-19 | 南京航空航天大学 | Method for marking traffic signal lamp in prior-to-check map |
-
2021
- 2021-11-26 CN CN202111423527.1A patent/CN114166137A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN203784632U (en) * | 2014-01-27 | 2014-08-20 | 江苏海企港华燃气发展有限公司 | Filling device of overwater natural gas filling station |
CN104197183A (en) * | 2014-01-27 | 2014-12-10 | 江苏海企港华燃气发展有限公司 | Natural gas charging station process flow on water and charging device |
US20180012498A1 (en) * | 2015-01-15 | 2018-01-11 | Nanjing University 5D Technology Co., Ltd. | Auxiliary berthing method and system for vessel |
CN109631782A (en) * | 2017-10-05 | 2019-04-16 | 美国亚德诺半导体公司 | System and method for measuring bridge gap |
CN108121251A (en) * | 2017-11-24 | 2018-06-05 | 浙江海洋大学 | Marine fuel filling device and control method |
CN108665499A (en) * | 2018-05-04 | 2018-10-16 | 北京航空航天大学 | A kind of low coverage aircraft pose measuring method based on parallax method |
CN112509333A (en) * | 2020-10-20 | 2021-03-16 | 智慧互通科技股份有限公司 | Roadside parking vehicle track identification method and system based on multi-sensor sensing |
CN113223075A (en) * | 2021-03-11 | 2021-08-06 | 大连海事大学 | Ship height measuring system and method based on binocular camera |
CN113192274A (en) * | 2021-04-23 | 2021-07-30 | 沪东中华造船(集团)有限公司 | Staff cabin safety monitoring method based on wireless communication |
CN113501088A (en) * | 2021-06-25 | 2021-10-15 | 沪东中华造船(集团)有限公司 | Side-leaning system and side-leaning method applied to LNG filling ship |
CN113627473A (en) * | 2021-07-06 | 2021-11-09 | 哈尔滨工程大学 | Water surface unmanned ship environment information fusion sensing method based on multi-mode sensor |
CN113639099A (en) * | 2021-07-21 | 2021-11-12 | 上海外高桥造船有限公司 | Marine low-temperature liquid fuel or cargo filling hose support and filling system |
CN113673386A (en) * | 2021-08-06 | 2021-11-19 | 南京航空航天大学 | Method for marking traffic signal lamp in prior-to-check map |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109283538B (en) | Marine target size detection method based on vision and laser sensor data fusion | |
CN110414396B (en) | Unmanned ship perception fusion algorithm based on deep learning | |
WO2016112714A1 (en) | Assistant docking method and system for vessel | |
CN107203222B (en) | Method for realizing ship water gauge image and video shooting by unmanned aerial vehicle | |
Yan et al. | Autonomous underwater vehicle vision guided docking experiments based on L-shaped light array | |
JP2018503915A (en) | Ship auxiliary docking method and system | |
CN115147723B (en) | Inland ship identification and ranging method, inland ship identification and ranging system, medium, equipment and terminal | |
WO2020099016A1 (en) | System and method for measuring the distance to an object in water | |
CN108693535A (en) | A kind of detection system for obstacle and detection method for underwater robot | |
CN107830860B (en) | A kind of unmanned boat lifting recycling visual guide method | |
CN113223075A (en) | Ship height measuring system and method based on binocular camera | |
CN109931909A (en) | A kind of offshore fan tower column state method for inspecting and device based on unmanned plane | |
KR102520844B1 (en) | Method and device for monitoring harbor and ship considering sea level | |
CN113525631A (en) | Underwater terminal docking system and method based on optical visual guidance | |
CN113763484A (en) | Ship target positioning and speed estimation method based on video image analysis technology | |
CN116453276A (en) | Marine wind power electronic fence monitoring and early warning method and system | |
CN109612333A (en) | A kind of vision auxiliary guide system vertically recycled towards reusable rocket | |
CN110667783A (en) | Unmanned boat auxiliary driving system and method thereof | |
CN115131720A (en) | Ship berthing assisting method based on artificial intelligence | |
CN205582304U (en) | Channel boats and ships traffic volume survey system | |
CN114166137A (en) | Intelligent detection system and method for ship-to-ship filling interval | |
CN112946685A (en) | Wharf berthing safety monitoring system and method based on three-dimensional laser radar | |
CN117173215A (en) | Inland navigation ship whole-course track identification method and system crossing cameras | |
CN115792912A (en) | Method and system for sensing environment of unmanned surface vehicle based on fusion of vision and millimeter wave radar under weak observation condition | |
CN110091962A (en) | A kind of 30 10,000 tons mammoth tanker berthing monitoring methods and device based on virtual wall |
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 |