CN113277028A - Ship monitoring method, device and system and computer storage medium - Google Patents
Ship monitoring method, device and system and computer storage medium Download PDFInfo
- Publication number
- CN113277028A CN113277028A CN202110841100.7A CN202110841100A CN113277028A CN 113277028 A CN113277028 A CN 113277028A CN 202110841100 A CN202110841100 A CN 202110841100A CN 113277028 A CN113277028 A CN 113277028A
- Authority
- CN
- China
- Prior art keywords
- ship
- point cloud
- target ship
- target
- cloud data
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B39/00—Equipment to decrease pitch, roll, or like unwanted vessel movements; Apparatus for indicating vessel attitude
- B63B39/12—Equipment to decrease pitch, roll, or like unwanted vessel movements; Apparatus for indicating vessel attitude for indicating draught or load
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Ocean & Marine Engineering (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a ship monitoring method, a ship monitoring device, a ship monitoring system and a computer storage medium. Wherein, the method comprises the following steps: scanning the river channel in real time to obtain current point cloud data of the river channel; differentiating all point cloud data in the current time period with background point cloud data of a river channel respectively to obtain a first height h from a deck of a target ship to a horizontal plane; if the first height h cannot be directly obtained: acquiring the type of a target ship, fitting to obtain a boundary line between a ship board and a deck of the target ship according to the type of the ship and the overall contour information of the ship obtained through difference, and calculating the height from the boundary line to the horizontal plane to obtain a first height h; and calculating and feeding back the load of the target ship according to the pre-acquired ship body information of the target ship and the first height h. By the method and the device, the first height h from the deck of the target ship to the horizontal plane can be accurately calculated whether the ship is shielded or not. And the draught condition of the ship can be more visual, and the error is smaller.
Description
Technical Field
The invention relates to the technical field of ships, in particular to a ship monitoring method, a ship monitoring device, a ship monitoring system and a computer storage medium.
Background
When the ship runs in a river channel, real-time monitoring is needed, and the monitored illegal ship is alarmed to a monitoring center.
In the prior art, two monitoring methods are mainly adopted, one method is to install a sensor on a ship body, and after the ship body is lowered below a waterline, a wireless module is used for alarming to a monitoring department. The requirement of a wireless network is high, equipment is required to be waterproof, and the wireless network is high in cost and difficult to popularize and manage due to the fact that one ship is used for one machine. The other is to identify through the sensors arranged at the bank, on the bridge, on the water float and at the water bottom fixed position, so as to realize the spot check of the appointed bayonet and greatly reduce the cost. Identification hardware such as infrared, sonar, laser, etc. is commonly included. The accuracy of identification through infrared and sonar is low, the error is large, and the supervision range is small. The existing laser equipment, such as a single laser beam installed on a bridge, monitors the height of the ship exposed out of the water surface, and the single laser beam lacks perception of the overall shape of the ship, so that when a plurality of ships pass through the bridge, the river channel is wide, the ship carrying shape is complex, and the ship navigation condition is complex, accurate judgment is difficult to perform; and the single laser has high requirement on the scanning angle, needs to scan right above the ship and can only be installed on the bridge.
The cost is high because one wireless module is installed on one ship in the prior art; the accuracy of identification through infrared and sonar is low, the error is large, and the supervision range is small; and the single laser has high requirement on the scanning angle, needs to scan right above the ship and can only be installed on a bridge, and an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the invention provides a ship monitoring method, a device, a system and a computer storage medium, which aim to solve the problem that in the prior art, one ship is provided with one wireless module, so that the cost is high; the accuracy of identification through infrared and sonar is low, the error is large, and the supervision range is small; and the single laser has high requirement on the scanning angle, needs to scan right above the ship and can only be installed on a bridge.
In order to achieve the above object, in one aspect, the present invention provides a ship monitoring method, including: scanning the river channel in real time to obtain current point cloud data of the river channel; differentiating all point cloud data in the current time period with background point cloud data of the river channel respectively to obtain a first height h from a deck of the target ship to a horizontal plane; calculating and feeding back the load of the target ship according to the pre-acquired ship body information of the target ship and the first height h; when the difference between all point cloud data in the current time period and the background point cloud data of the river channel is respectively carried out, and the first height h from the deck of the target ship to the horizontal plane cannot be directly obtained: the method comprises the steps of obtaining the type of a target ship, fitting to obtain a boundary line between a ship board and a deck of the target ship according to the type of the target ship and overall contour information of the ship obtained through difference, calculating the height from the boundary line to the horizontal plane, and obtaining a first height h from the deck of the target ship to the horizontal plane.
Optionally, the obtaining the type of the target ship and fitting the overall profile information of the ship according to the type of the target ship and the difference to obtain the boundary line between the side and the deck of the target ship includes: acquiring the type of a target ship from AIS information of the target ship; obtaining type contour information according to the type of the target ship, and fitting the type contour with the overall contour of the ship obtained through difference; and taking the boundary line of the ship board and the deck in the type contour information obtained after fitting as the boundary line of the ship board and the deck of the target ship.
Optionally, the position information of the target ship is acquired while the hull information of the target ship is acquired in advance; determining a target ship in the parallel ships according to the position information; when a target ship in the parallel ships cannot be determined according to the position information, capturing the parallel ships in real time and storing an integral point cloud set of the parallel ships; and clustering the whole point cloud set to distinguish parallel ships and determine a target ship in the parallel ships.
Optionally, the clustering the whole point cloud sets to distinguish parallel ships includes: when the distance between the point clouds is judged to be smaller than a preset radius threshold value, the point clouds are gathered into one type; and when the shortest distance between the two clusters is judged to be within the preset width range, combining the two clusters into one class to obtain a ship.
Optionally, the scanning the river in real time to obtain the current point cloud data of the river includes: scanning the river channel in real time to obtain current original point cloud data of the river channel; performing plane fitting on the current original point cloud data of the river channel to obtain a horizontal plane; and filtering the point cloud data below the horizontal plane to obtain the current point cloud data of the river channel.
Optionally, the step of differentiating all the point cloud data in the current time period with the background point cloud data of the river respectively to obtain a first height h from a deck of the target ship to a horizontal plane includes: differentiating all point cloud data in the current time period with background point cloud data of the river channel respectively to obtain a plurality of point cloud increasing sets in the current time period; splicing the point cloud incremental sets to obtain an integral point cloud set of the target ship; and identifying the integral point cloud set of the target ship to obtain a deck of the target ship, and calculating a first height h from the deck to the horizontal plane.
Optionally, the splicing the multiple point cloud incremental sets to obtain an overall point cloud set of the target ship includes: performing down-sampling on the point cloud increasing sets to obtain a plurality of point cloud sets to be analyzed; calculating to obtain the average advancing speed of the target ship according to the position change of the previous point cloud set to be analyzed and the current point cloud set to be analyzed and the volume of the target ship; according to the average advancing speed, sequentially obtaining a plurality of subsequent point cloud sets to be analyzed of the target ship by scanning the advancing target ship; splicing all point cloud sets to be analyzed to obtain an integral point cloud set of a preprocessed target ship; and filtering the integral point cloud set of the preprocessed target ship to obtain the integral point cloud set of the target ship.
Optionally, the calculating and feeding back the load of the target ship according to the pre-acquired hull information of the target ship and the first height h includes: acquiring the name plate information of the target ship, and inquiring the volume of the target ship and a second height H from the deck of the target ship to the bottom of the target ship from a database according to the name plate information; calculating according to the first height H and the second height H to obtain the draft of the target ship, and calculating according to the draft and the volume of the target ship to obtain the displacement of the target ship; when the water displacement of the target ship is judged to exceed a preset load or the draft depth calculation is wrong, the target ship is snapshot in real time and an integral point cloud set of the target ship is stored; and alarming to a monitoring center.
In another aspect, the present invention provides a vessel monitoring device, comprising: the scanning unit is used for scanning the river channel in real time to obtain current point cloud data of the river channel; the difference unit is used for respectively carrying out difference on all point cloud data in the current time period and background point cloud data of the river channel to obtain a first height h from a deck of the target ship to a horizontal plane; the calculating unit is used for calculating and feeding back the load of the target ship according to the pre-acquired ship body information of the target ship and the first height h; when the difference between all point cloud data in the current time period and the background point cloud data of the river channel is respectively carried out, and the first height h from the deck of the target ship to the horizontal plane cannot be directly obtained: and the fitting unit is used for acquiring the type of the target ship, fitting to obtain a boundary line between a ship board and a deck of the target ship according to the type of the ship and the overall profile information of the ship obtained through difference, calculating the height from the boundary line to the horizontal plane, and obtaining the first height h from the deck of the target ship to the horizontal plane.
Optionally, the fitting unit includes: the acquisition subunit is used for acquiring the type of the target ship from the AIS information of the target ship; the fitting subunit is used for obtaining type contour information according to the type of the target ship and fitting the type contour with the overall contour of the ship obtained through the difference; and the target subunit is used for taking the boundary line of the ship board and the deck in the type contour information obtained after fitting as the boundary line of the ship board and the deck of the target ship.
Optionally, the scanning unit includes: the scanning subunit is used for scanning the river channel in real time to obtain current original point cloud data of the river channel; the plane fitting subunit is used for performing plane fitting on the current original point cloud data of the river channel to obtain a horizontal plane; and the filtering subunit is used for filtering the point cloud data below the horizontal plane to obtain the current point cloud data of the river channel.
Optionally, the difference unit includes: the difference subunit is used for respectively carrying out difference on all point cloud data in the current time period and background point cloud data of the river channel to obtain a plurality of point cloud increasing sets in the current time period; the splicing subunit is used for splicing the point cloud increasing sets to obtain an integral point cloud set of the target ship; and the calculating subunit is used for identifying the whole point cloud set of the target ship to obtain a deck of the target ship and calculating a first height h from the deck to a horizontal plane.
Optionally, the computing unit includes: the information acquisition subunit is used for acquiring the name plate information of the target ship, and inquiring the volume of the target ship and a second height H from the deck of the target ship to the bottom of the target ship from a database according to the name plate information; the displacement calculation subunit is used for calculating according to the first height H and the second height H to obtain the draft of the target ship and calculating according to the draft and the volume of the target ship to obtain the displacement of the target ship; the judging subunit is used for snapshotting the target ship in real time and storing an integral point cloud set of the target ship when the water displacement of the target ship is judged to exceed a preset load or the draft depth calculation is wrong; and alarming to a monitoring center.
On the other hand, the invention also provides a ship monitoring system which comprises the ship monitoring device.
In another aspect, the present invention also provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the above-mentioned vessel monitoring method.
The invention has the beneficial effects that:
the invention provides a ship monitoring method, which is characterized in that current point cloud data of a river channel are obtained by scanning ships passing through the river channel; and respectively differentiating all point cloud data in the current time period with the background point cloud data of the river channel to obtain a first height h from the deck of the target ship to the horizontal plane, if the first height h from the deck of the target ship to the horizontal plane cannot be directly obtained: the method comprises the steps of obtaining the type of a target ship, fitting to obtain a boundary line between a ship board and a deck of the target ship according to the type of the target ship and overall contour information of the ship obtained through difference, calculating the height from the boundary line to the horizontal plane, and obtaining a first height h from the deck of the target ship to the horizontal plane. By the method, the first height h from the deck of the target ship to the horizontal plane can be accurately calculated no matter whether the ship is shielded or not. The ship average advancing speed is calculated, and the continuous scanning results of the ship are spliced to obtain the ship integral point cloud set, so that the ship draught condition is more visual, and the error is smaller. Further, the present invention can distinguish parallel ships and determine a target ship among the parallel ships.
Drawings
Fig. 1 is a flowchart of a ship monitoring method according to an embodiment of the present invention;
FIG. 2 is a flow chart of fitting to obtain the boundary between the side and the deck of the target vessel according to an embodiment of the present invention;
FIG. 3 is a flowchart of acquiring point cloud data above a horizontal plane according to an embodiment of the present invention;
FIG. 4 is a flow chart for obtaining a first height h from the deck of a target vessel to the horizontal plane, provided by an embodiment of the present invention;
FIG. 5 is a flowchart of calculating and feeding back the load of a target vessel according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a ship monitoring device according to an embodiment of the present invention;
FIG. 7 is a schematic structural diagram of a fitting unit provided in an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a differential unit according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the prior art, two monitoring methods are mainly adopted, one method is to install a sensor on a ship body, and after the ship body is lowered below a waterline, a wireless module is used for alarming to a monitoring department. The requirement of a wireless network is high, equipment is required to be waterproof, and the wireless network is high in cost and difficult to popularize and manage due to the fact that one ship is used for one machine. The other is to identify through the sensors arranged at the bank, on the bridge, on the water float and at the water bottom fixed position, so as to realize the spot check of the appointed bayonet and greatly reduce the cost. Identification hardware such as infrared, sonar, laser, etc. is commonly included. The accuracy of identification through infrared and sonar is low, the error is large, and the supervision range is small. The existing laser equipment, such as a single laser beam installed on a bridge, monitors the height of the ship exposed out of the water surface, and the single laser beam lacks perception of the overall shape of the ship, so that when a plurality of ships pass through the bridge, the river channel is wide, the ship carrying shape is complex, and the ship navigation condition is complex, accurate judgment is difficult to perform; and the single laser has high requirement on the scanning angle, needs to scan right above the ship and can only be installed on the bridge.
Accordingly, the present invention provides a ship monitoring method, and fig. 1 is a flowchart of a ship monitoring method according to an embodiment of the present invention, as shown in fig. 1, the method includes:
s101, scanning a river channel in real time to obtain current point cloud data of the river channel;
in an optional embodiment, a 200m wide river channel is scanned in real time by a laser scanning device to obtain current point cloud data of the river channel, and if a ship exists in the river channel, the current point cloud data of the river channel is the sum of background point cloud data and ship point cloud data; and the ship is driven, the laser scanning device can be used for scanning one section by one section, and the point cloud data of the section of the ship can be obtained if the ship section of 50m is scanned currently.
S102, differentiating all point cloud data in the current time period with background point cloud data of the river channel respectively to obtain a first height h from a deck of the target ship to a horizontal plane;
and (3) the ship is moved in real time, all point cloud data in the time period when the ship is moved are respectively differenced with the background point cloud data of the river channel, namely the background point cloud data are removed, only the target ship point cloud data in the river channel are obtained, so that the deck point cloud data of the target ship, namely a plurality of point cloud sets, are obtained, and then the first height h from the deck to the horizontal plane is calculated.
S104, when the difference between all point cloud data in the current time period and background point cloud data of the river channel is respectively carried out, and the first height h from the deck of the target ship to the horizontal plane cannot be directly obtained:
the method comprises the steps of obtaining the type of a target ship, fitting to obtain a boundary line between a ship board and a deck of the target ship according to the type of the target ship and overall contour information of the ship obtained through difference, calculating the height from the boundary line to the horizontal plane, and obtaining a first height h from the deck of the target ship to the horizontal plane.
In an optional embodiment, when the difference between all the point cloud data in the current time period and the background point cloud data of the river cannot directly obtain the first height h from the deck of the target ship to the horizontal plane (that is, the deck of the target ship is blocked, and the blocking is serious so that the first height h from the deck of the target ship to the horizontal plane cannot be directly obtained): obtaining the type of a target ship, specifically obtaining the specific model of the target ship, assuming that the target ship is a passenger ship with one model, fitting to obtain a boundary line between a ship board and a deck of the target ship according to the overall contour line of the passenger ship with the model and the overall contour information of the ship obtained through difference (namely, the boundary line between the ship board and the deck of the target ship can be obtained by performing outer frame superposition on the overall contour line of the passenger ship with the model to be obtained and the overall contour information of the ship obtained through difference); and calculating the height from the boundary line to the horizontal plane to obtain a first height h from the deck of the target ship to the horizontal plane.
S103, calculating and feeding back the load of the target ship according to the pre-acquired ship body information of the target ship and the first height h;
the method comprises the steps of scanning a river channel in real time, obtaining name plate information of a target ship, calculating load of the target ship according to the name plate information and a first height h, judging the load, and sending early warning to a monitoring center if the load is overloaded.
According to the method, the first height h from the deck of the target ship to the horizontal plane can be accurately calculated whether the ship is shielded or not.
In an alternative implementation manner, fig. 2 is a flowchart for fitting to obtain a boundary line between a side and a deck of a target ship according to an embodiment of the present invention, as shown in fig. 2, where the S104 includes:
s1041, acquiring the type of a target ship from AIS information of the target ship;
in an optional implementation manner, the type of the target ship, specifically, the specific model corresponding to the target ship, is obtained in real time according to the size of the target ship and the unshielded contour line in the AIS information of the target ship.
S1042, obtaining type contour information according to the type of the target ship, and fitting the type contour with the overall contour of the ship obtained through the difference;
and after the type of the target ship is obtained (for example, a passenger ship with a specific type is obtained), obtaining the complete contour information of the passenger ship with the type, and fitting the complete contour of the passenger ship with the type with the integral contour of the target ship obtained by the difference. Namely, the outline of the outer frames of the two frames are subjected to superposition calculation.
And S1043, taking the boundary line of the ship board and the deck in the type contour information obtained after fitting as the boundary line of the ship board and the deck of the target ship.
After fitting, the boundary line between the side and the deck of the passenger-cargo ship of the type (namely, the boundary line corresponds to the shielding part of the target ship) can be directly obtained, and the boundary line is used as the boundary line between the side and the deck of the target ship.
In an optional embodiment, the position information of the target ship is acquired while the hull information of the target ship is acquired in advance; determining a target ship in the parallel ships according to the position information; when a target ship in the parallel ships cannot be determined according to the position information, capturing the parallel ships in real time and storing an integral point cloud set of the parallel ships; and clustering the whole point cloud set to distinguish parallel ships and determine a target ship in the parallel ships.
Specifically, the position information of the target ship is acquired, and the target ship in the parallel ships can be determined for the parallel multiple ships. And if the ship can not be determined, grabbing the parallel ship by using a gun to obtain an integral point cloud set of the parallel ship, and distinguishing the integral point cloud set through Euclidean clustering so as to distinguish the parallel ships and determine a target ship in the parallel ship. Furthermore, when a plurality of ships appear simultaneously, a plurality of ships in two frames are sampled by the cloud set of head points close to the scanner side and far away from the water surface, and the sampling gravity center position is taken to represent the positions of the ships to perform global optimal matching.
According to the invention, by the monitoring method, the integral point cloud set of the target ship can be obtained, so that the ship draught condition is more visual and the error is smaller; the scanning range is larger, so that the device can be installed on the shore, and even a wider river channel can be monitored by only one ship monitoring device; further, parallel ships can be distinguished in the invention to determine the target ship.
In an optional embodiment, the clustering the whole set of point clouds to distinguish parallel ships comprises: when the distance between the point clouds is judged to be smaller than a preset radius threshold value, the point clouds are gathered into one type; and when the shortest distance between the two clusters is judged to be within the preset width range, combining the two clusters into one class to obtain a ship.
Specifically, two parallel ships can be distinguished by Euclidean clustering (the preset radius threshold is set to be smaller than the possible distance between the two ships, so that the two ships can be dispersed into smaller targets), and particularly, excessive segmentation can occur in the process, so that the preset width range (8-12 meters) of the ships is set, and the small targets in the width range are integrated into one ship.
The distance between point clouds in the cluster required by the judgment of the European cluster is smaller than a preset radius threshold value (namely, the distance between the point clouds in one ship is smaller than the preset radius threshold value), and the preset radius threshold value is set to be 20cm in the application.
The excessive segmentation means that when the ship is in no-load, the distance between the ship sides on the left side and the right side of the ship is certain to exceed a preset radius threshold value, and the ship is divided into two ships; therefore, the width screening range (8-12 meters) of the ship needs to be set again at this moment, and small targets in the width screening range are integrated into a ship, namely, the left part and the right part of the ship are combined again to be integrated into a ship.
In an optional implementation manner, fig. 3 is a flowchart of acquiring point cloud data above a horizontal plane according to an embodiment of the present invention, and as shown in fig. 3, the S101 includes:
s1011, scanning the river channel in real time to obtain current original point cloud data of the river channel;
s1012, performing plane fitting on the current original point cloud data of the river channel to obtain a horizontal plane;
for a ship monitoring device installed on the shore, if no ship passes by a short distance off the shore (about 20cm from the nearest laser projection and about 30m from the river bank), the reflection of the laser in the area when the laser strikes the water surface is considered to occur. A horizontal plane formula in a point cloud space can be obtained by performing plane fitting on the point cloud data in the area range. Specifically, RANSAC (random sample consensus) is adopted to fit a plane instead of the least square method, considering that fluctuation of a horizontal plane brings errors to point cloud data (namely, the horizontal plane is a conceptual plane, and the actual horizontal plane fluctuates up and down).
Furthermore, the horizontal plane fluctuates due to weather influences, and the horizontal plane rises in rainy days, so that the height of the horizontal plane needs to be measured every 5min, and the accuracy of subsequent measurement is ensured.
And S1013, filtering the point cloud data below the horizontal plane to obtain the current point cloud data of the river channel.
In an alternative embodiment, there are currently ships, fish, trees on the bank side in the river; the current original point cloud data of the river channel comprises ship point cloud data, fish point cloud data and tree point cloud data; background point cloud data of the river channel comprise fish point cloud data and tree point cloud data; filtering the current point cloud data of the river channel below the horizontal plane and the background point cloud data of the river channel; obtaining current point cloud data of the river channel, wherein the current point cloud data comprises ship point cloud data above a horizontal plane and tree point cloud data above the horizontal plane; background point cloud data of the river channel is obtained, and the background point cloud data is filtered and comprises tree point cloud data above a horizontal plane (fish point cloud data are filtered because fish are below the horizontal plane).
By the method, point cloud data below a horizontal plane can be filtered, and z =0 is calculated at the plane, and the normal direction of the plane is the z-axis direction (in addition, the y-axis is fixed as the ship navigation direction, and the direction is not completely accurate and is only an approximate estimated direction). All subsequent acquired point cloud data are converted to the coordinate system.
In an alternative implementation manner, fig. 4 is a flowchart for obtaining a first height h from a deck of a target ship to a horizontal plane according to an embodiment of the present invention, as shown in fig. 4, where the S102 includes:
s1021, differentiating all point cloud data in the current time period with background point cloud data of the river channel respectively to obtain a plurality of point cloud increasing sets in the current time period;
the ship moves in real time, all point cloud data in the time period when the ship moves are respectively differentiated from background point cloud data of the river channel, namely the background point cloud data are removed, and only ship point cloud data in the river channel, namely a plurality of point cloud increasing sets, are obtained, so that the ship can be conveniently analyzed subsequently.
S1022, splicing the point cloud incremental sets to obtain an integral point cloud set of the target ship;
and splicing the point cloud incremental sets according to the ship advancing sequence to obtain the whole point cloud set of the target ship.
And S1023, identifying the whole point cloud set of the target ship to obtain a deck of the target ship, and calculating a first height h from the deck to a horizontal plane.
After the integral point cloud set of the target ship is obtained, identifying the target ship to obtain a deck of the target ship; generally, the portion of the side above the horizontal is a smooth curve that ends up at the deck where the point cloud data will make a large change. Based thereon, the deck of the target vessel may be identified. After the deck is identified, a first height h of the deck to the horizontal is calculated.
In an optional embodiment, the S1022 includes:
s10221, performing downsampling on the multiple point cloud increasing sets to obtain multiple point cloud sets to be analyzed;
and performing down-sampling on the plurality of point cloud increasing sets to filter out some unnecessary details, wherein the down-sampling specifically comprises the steps of using a cubic grid of 10 × 10cm, and calculating the gravity center of all points in each grid as a down-sampling result in the grid to obtain a plurality of point cloud sets to be analyzed.
S10222, calculating to obtain the average advancing speed of the target ship according to the position change of the previous point cloud set to be analyzed and the current point cloud set to be analyzed and the volume of the target ship;
and comparing the position change of the target ship point cloud sets to be analyzed in the upper frame and the lower frame. When the object enters a scanning range (y = y0) and one end of the object reaches the other boundary (y = -y0) of the scanning range, the average travelling speed of the target ship in the y-axis direction is calculated according to the volume and position change of the target ship and the point cloud set received every 0.5 second, and the average travelling speed is used as the subsequent average travelling speed v of the target ship.
S10223, sequentially obtaining a plurality of subsequent point cloud sets to be analyzed of the target ship by scanning the advancing target ship according to the average advancing speed;
s10224, all point cloud sets to be analyzed are spliced to obtain an integral point cloud set of the preprocessed target ship;
and (4) splicing the point cloud collection increasing parts to be analyzed obtained in each subsequent frame according to the average advancing speed v (the subsequent parts gradually enter the scanning area to generate the increasing parts because the target ship runs).
S10225, filtering the integral point cloud set of the preprocessed target ship to obtain the integral point cloud set of the target ship.
After the complete splicing, removing the points stacked in the y-axis direction to remove the point cloud superposition condition caused by errors in the direction and the speed when the target ship body runs, namely extracting the point cloud outline on the plane for given y0, and finally obtaining the whole point cloud set of the target ship body.
By the method, the whole point cloud set of the target ship can be obtained, so that the target ship has more visual draught condition and smaller error.
In an alternative embodiment, said calculating a first height h of the deck to the horizontal plane comprises: equally dividing the target ship whole point cloud set into three equal parts from top to bottom, and taking a point cloud set of the middle equal parts of the target ship; taking n yi points in the point cloud set of the middle equal part at equal intervals, and calculating a tangent plane f (z) = x at y = yi point, wherein the z value is when f' (z) has mutation; and averaging all z values within the error range to obtain a first height h from the deck to the horizontal plane.
Generally, the side portion of the vessel exposed to the water surface is a smooth curved surface that ends at the deck where the point cloud data will make a large change. That is, when y = y0, a tangent plane f (z) = x at any point on the board, and f' (z) is discontinuous at the boundary between the board and the deck. Then, for the whole point cloud set of the target hull, a point cloud set of the ship middle 1/3 is taken, n yi points are taken at equal intervals in the point cloud set of the middle 1/3, the z value of f' (z) when the sudden change occurs at y = yi is calculated, and the average value of z in the error range is calculated as the first height h from the deck to the horizontal plane.
In an optional implementation manner, fig. 5 is a flowchart of calculating and feeding back a load of a target ship according to an embodiment of the present invention, and as shown in fig. 5, the S103 includes:
s1031, acquiring the name plate information of the target ship, and inquiring the volume of the target ship and a second height H from a deck of the target ship to the bottom of the target ship from a database according to the name plate information;
and according to the name plate information of the ship, acquiring information such as the load, the width, the second height H from the bottom of the ship to the deck and the like of the ship from a background database, and facilitating the subsequent calculation of the displacement of the target ship.
S1032, calculating according to the first height H and the second height H to obtain draft of the target ship, and calculating according to the draft and the volume of the target ship to obtain displacement of the target ship;
the calculation formula of the target ship draft is as follows: d = H-H; d is the draft of the target vessel, H is the second height from the deck of the target vessel to the bottom thereof, and H is the first height from the deck of the target vessel to the horizontal plane.
And calculating the displacement of the target ship according to the draught and the volume of the target ship.
S1033, when the water displacement of the target ship is judged to exceed a preset load or the draft depth calculation is wrong, the target ship is snapshot in real time and an integral point cloud set of the target ship is stored; and alarming to a monitoring center.
Calculating a target ship with water displacement reaching a preset load designated percentage or a target ship with wrong draft d (if d is less than 0), considering that the target ship is overloaded, using a camera to snapshot the target ship, and storing an integral point cloud set of the ship; and alarming to a monitoring center, and storing the record for subsequent reference and data statistics.
Further, for the ship name plate information of the target ship which is not detected, judging the first height h from the deck of the target ship to the horizontal plane, and if h is less than or equal to 20cm, alarming to a monitoring center as overload; if h >20cm, as an artificial check.
Furthermore, for incomplete hull information (real-time position information and ship name plate information) in the target ship, judging a first height h from a deck of the target ship to a horizontal plane, and if h is less than or equal to 20cm, alarming to a monitoring center as overload; if h >20cm, as an artificial check.
Fig. 6 is a ship monitoring device according to an embodiment of the present invention, and as shown in fig. 6, the ship monitoring device includes:
the scanning unit 201 is configured to scan a river channel in real time to obtain current point cloud data of the river channel;
in an optional embodiment, a 200m wide river channel is scanned in real time by a laser scanning device to obtain current point cloud data of the river channel, and if a ship exists in the river channel, the current point cloud data of the river channel is the sum of background point cloud data and ship point cloud data; and the ship is driven, the laser scanning device can be used for scanning one section by one section, and the point cloud data of the section of the ship can be obtained if the ship section of 50m is scanned currently.
A difference unit 202, configured to perform difference between all point cloud data in the current time period and background point cloud data of the river respectively, so as to obtain a first height h from a deck of the target ship to a horizontal plane;
and (3) the ship is moved in real time, all point cloud data in the time period when the ship is moved are respectively differenced with the background point cloud data of the river channel, namely the background point cloud data are removed, only the target ship point cloud data in the river channel are obtained, so that the deck point cloud data of the target ship, namely a plurality of point cloud sets, are obtained, and then the first height h from the deck to the horizontal plane is calculated.
When the difference between all point cloud data in the current time period and the background point cloud data of the river channel is respectively carried out, and the first height h from the deck of the target ship to the horizontal plane cannot be directly obtained:
the fitting unit 204 is configured to obtain a type of the target ship, fit and obtain a boundary line between a ship board and a deck of the target ship according to the type of the target ship and the overall profile information of the ship obtained through difference, calculate a height from the boundary line to a horizontal plane, and obtain a first height h from the deck of the target ship to the horizontal plane.
In an optional embodiment, when the difference between all the point cloud data in the current time period and the background point cloud data of the river cannot directly obtain the first height h from the deck of the target ship to the horizontal plane (that is, the deck of the target ship is blocked, and the blocking is serious so that the first height h from the deck of the target ship to the horizontal plane cannot be directly obtained): obtaining the type of a target ship, specifically obtaining the specific model of the target ship, assuming that the target ship is a passenger ship with one model, fitting to obtain a boundary line between a ship board and a deck of the target ship according to the overall contour line of the passenger ship with the model and the overall contour information of the ship obtained through difference (namely, the boundary line between the ship board and the deck of the target ship can be obtained by performing outer frame superposition on the overall contour line of the passenger ship with the model to be obtained and the overall contour information of the ship obtained through difference); and calculating the height from the boundary line to the horizontal plane to obtain a first height h from the deck of the target ship to the horizontal plane.
The calculating unit 203 is configured to calculate and feed back a load of the target ship according to the pre-acquired hull information of the target ship and the first height h;
the method comprises the steps of scanning a river channel in real time, obtaining name plate information of a target ship, calculating load of the target ship according to the name plate information and a first height h, judging the load, and sending early warning to a monitoring center if the load is overloaded.
According to the method, the first height h from the deck of the target ship to the horizontal plane can be accurately calculated whether the ship is shielded or not.
In an alternative implementation manner, fig. 7 is a schematic structural diagram of a fitting unit provided in an embodiment of the present invention, and as shown in fig. 7, the fitting unit 204 includes:
an obtaining subunit 2041, configured to obtain, in the AIS information of the target vessel, a type of the target vessel;
in an optional implementation manner, the type of the target ship, specifically, the specific model corresponding to the target ship, is obtained in real time according to the size of the target ship and the unshielded contour line in the AIS information of the target ship.
A fitting subunit 2042, configured to obtain type profile information according to the type of the target ship, and fit the type profile with the overall profile of the ship obtained by the difference;
and after the type of the target ship is obtained (for example, a passenger ship with a specific type is obtained), obtaining the complete contour information of the passenger ship with the type, and fitting the complete contour of the passenger ship with the type with the integral contour of the target ship obtained by the difference. Namely, the outline of the outer frames of the two frames are subjected to superposition calculation.
And a target subunit 2043, configured to use the boundary line between the ship board and the deck in the type profile information obtained after fitting as the boundary line between the ship board and the deck of the target ship.
After fitting, the boundary line between the side and the deck of the passenger-cargo ship of the type (namely, the boundary line corresponds to the shielding part of the target ship) can be directly obtained, and the boundary line is used as the boundary line between the side and the deck of the target ship.
In an optional embodiment, the position information of the target ship is acquired while the hull information of the target ship is acquired in advance; determining a target ship in the parallel ships according to the position information; when a target ship in the parallel ships cannot be determined according to the position information, capturing the parallel ships in real time and storing an integral point cloud set of the parallel ships; and clustering the whole point cloud set to distinguish parallel ships and determine a target ship in the parallel ships.
Specifically, the position information of the target ship is acquired, and the target ship in the parallel ships can be determined for the parallel multiple ships. And if the ship can not be determined, grabbing the parallel ship by using a gun to obtain an integral point cloud set of the parallel ship, and distinguishing the integral point cloud set through Euclidean clustering so as to distinguish the parallel ships and determine a target ship in the parallel ship. Furthermore, when a plurality of ships appear simultaneously, a plurality of ships in two frames are sampled by the cloud set of head points close to the scanner side and far away from the water surface, and the sampling gravity center position is taken to represent the positions of the ships to perform global optimal matching.
According to the invention, by the monitoring method, the integral point cloud set of the target ship can be obtained, so that the ship draught condition is more visual and the error is smaller; the scanning range is larger, so that the device can be installed on the shore, and even a wider river channel can be monitored by only one ship monitoring device; further, parallel ships can be distinguished in the invention to determine the target ship.
In an optional embodiment, the clustering the whole set of point clouds to distinguish parallel ships comprises: when the distance between the point clouds is judged to be smaller than a preset radius threshold value, the point clouds are gathered into one type; and when the shortest distance between the two clusters is judged to be within the preset width range, combining the two clusters into one class to obtain a ship.
Specifically, two parallel ships can be distinguished by Euclidean clustering (the preset radius threshold is set to be smaller than the possible distance between the two ships, so that the two ships can be dispersed into smaller targets), and particularly, excessive segmentation can occur in the process, so that the preset width range (8-12 meters) of the ships is set, and the small targets in the width range are integrated into one ship.
The distance between point clouds in the cluster required by the judgment of the European cluster is smaller than a preset radius threshold value (namely, the distance between the point clouds in one ship is smaller than the preset radius threshold value), and the preset radius threshold value is set to be 20cm in the application.
The excessive segmentation means that when the ship is in no-load, the distance between the ship sides on the left side and the right side of the ship is certain to exceed a preset radius threshold value, and the ship is divided into two ships; therefore, the width screening range (8-12 meters) of the ship needs to be set again at this moment, and small targets in the width screening range are integrated into a ship, namely, the left part and the right part of the ship are combined again to be integrated into a ship.
In an alternative embodiment, the scanning unit 201 includes:
the scanning subunit 2011 is configured to scan the river channel in real time to obtain current original point cloud data of the river channel;
a plane fitting subunit 2012, configured to perform plane fitting on the current original point cloud data of the river to obtain a horizontal plane;
for a ship monitoring device installed on the shore, if no ship passes by a short distance off the shore (about 20cm from the nearest laser projection and about 30m from the river bank), the reflection of the laser in the area when the laser strikes the water surface is considered to occur. A horizontal plane formula in a point cloud space can be obtained by performing plane fitting on the point cloud data in the area range. Specifically, RANSAC (random sample consensus) is adopted to fit a plane instead of the least square method, considering that fluctuation of a horizontal plane brings errors to point cloud data (namely, the horizontal plane is a conceptual plane, and the actual horizontal plane fluctuates up and down).
Furthermore, the horizontal plane fluctuates due to weather influences, and the horizontal plane rises in rainy days, so that the height of the horizontal plane needs to be measured every 5min, and the accuracy of subsequent measurement is ensured.
And the filtering subunit 2013 is configured to filter the point cloud data below the horizontal plane to obtain the current point cloud data of the river.
In an alternative embodiment, there are currently ships, fish, trees on the bank side in the river; the current original point cloud data of the river channel comprises ship point cloud data, fish point cloud data and tree point cloud data; background point cloud data of the river channel comprise fish point cloud data and tree point cloud data; filtering the current point cloud data of the river channel below the horizontal plane and the background point cloud data of the river channel; obtaining current point cloud data of the river channel, wherein the current point cloud data comprises ship point cloud data above a horizontal plane and tree point cloud data above the horizontal plane; background point cloud data of the river channel is obtained, and the background point cloud data is filtered and comprises tree point cloud data above a horizontal plane (fish point cloud data are filtered because fish are below the horizontal plane).
By the method, point cloud data below a horizontal plane can be filtered, and z =0 is calculated at the plane, and the normal direction of the plane is the z-axis direction (in addition, the y-axis is fixed as the ship navigation direction, and the direction is not completely accurate and is only an approximate estimated direction). All subsequent acquired point cloud data are converted to the coordinate system.
In an alternative implementation manner, fig. 8 is a schematic structural diagram of a differential unit provided in an embodiment of the present invention, and as shown in fig. 8, the differential unit 202 includes:
the difference subunit 2021 is configured to perform difference between all the point cloud data in the current time period and the background point cloud data of the river respectively to obtain a plurality of point cloud increase sets in the current time period;
the ship moves in real time, all point cloud data in the time period when the ship moves are respectively differentiated from background point cloud data of the river channel, namely the background point cloud data are removed, and only ship point cloud data in the river channel, namely a plurality of point cloud increasing sets, are obtained, so that the ship can be conveniently analyzed subsequently.
The splicing subunit 2022 is configured to splice the multiple point cloud incremental sets to obtain an overall point cloud set of the target ship;
and splicing the point cloud incremental sets according to the ship advancing sequence to obtain the whole point cloud set of the target ship.
The calculating subunit 2023 is configured to identify the whole point cloud set of the target ship to obtain a deck of the target ship, and calculate a first height h from the deck to a horizontal plane.
After the integral point cloud set of the target ship is obtained, identifying the target ship to obtain a deck of the target ship; generally, the portion of the side above the horizontal is a smooth curve that ends up at the deck where the point cloud data will make a large change. Based thereon, the deck of the target vessel may be identified. After the deck is identified, a first height h of the deck to the horizontal is calculated.
In an alternative embodiment, the splicing subunit 2022 comprises:
performing down-sampling on the point cloud increasing sets to obtain a plurality of point cloud sets to be analyzed;
and performing down-sampling on the plurality of point cloud increasing sets to filter out some unnecessary details, wherein the down-sampling specifically comprises the steps of using a cubic grid of 10 × 10cm, and calculating the gravity center of all points in each grid as a down-sampling result in the grid to obtain a plurality of point cloud sets to be analyzed.
Calculating to obtain the average advancing speed of the target ship according to the position change of the previous point cloud set to be analyzed and the current point cloud set to be analyzed and the volume of the target ship;
and comparing the position change of the target ship point cloud sets to be analyzed in the upper frame and the lower frame. When the object enters a scanning range (y = y0) and one end of the object reaches the other boundary (y = -y0) of the scanning range, the average travelling speed of the target ship in the y-axis direction is calculated according to the volume and position change of the target ship and the point cloud set received every 0.5 second, and the average travelling speed is used as the subsequent average travelling speed v of the target ship.
According to the average advancing speed, sequentially obtaining a plurality of subsequent point cloud sets to be analyzed of the target ship by scanning the advancing target ship;
splicing all point cloud sets to be analyzed to obtain an integral point cloud set of a preprocessed target ship;
and (4) splicing the point cloud collection increasing parts to be analyzed obtained in each subsequent frame according to the average advancing speed v (the subsequent parts gradually enter the scanning area to generate the increasing parts because the target ship runs).
And filtering the integral point cloud set of the preprocessed target ship to obtain the integral point cloud set of the target ship.
After the complete splicing, removing the points stacked in the y-axis direction to remove the point cloud superposition condition caused by errors in the direction and the speed when the target ship body runs, namely extracting the point cloud outline on the plane for given y0, and finally obtaining the whole point cloud set of the target ship body.
By the method, the whole point cloud set of the target ship can be obtained, so that the target ship has more visual draught condition and smaller error.
In an alternative embodiment, said calculating a first height h of the deck to the horizontal plane comprises: equally dividing the target ship whole point cloud set into three equal parts from top to bottom, and taking a point cloud set of the middle equal parts of the target ship; taking n yi points in the point cloud set of the middle equal part at equal intervals, and calculating a tangent plane f (z) = x at y = yi point, wherein the z value is when f' (z) has mutation; and averaging all z values within the error range to obtain a first height h from the deck to the horizontal plane.
Generally, the side portion of the vessel exposed to the water surface is a smooth curved surface that ends at the deck where the point cloud data will make a large change. That is, when y = y0, a tangent plane f (z) = x at any point on the board, and f' (z) is discontinuous at the boundary between the board and the deck. Then, for the whole point cloud set of the target hull, a point cloud set of the ship middle 1/3 is taken, n yi points are taken at equal intervals in the point cloud set of the middle 1/3, the z value of f' (z) when the sudden change occurs at y = yi is calculated, and the average value of z in the error range is calculated as the first height h from the deck to the horizontal plane.
In an optional embodiment, the calculating unit 203 comprises:
an information obtaining subunit 2031, configured to obtain the name plate information of the target ship, and query, according to the name plate information, the volume of the target ship and a second height H from the deck to the bottom of the target ship from a database;
and according to the name plate information of the ship, acquiring information such as the load, the width, the second height H from the bottom of the ship to the deck and the like of the ship from a background database, and facilitating the subsequent calculation of the displacement of the target ship.
A drainage amount calculation subunit 2032, configured to calculate an draft of the target ship according to the first height H and the second height H, and calculate a drainage amount of the target ship according to the draft and a volume of the target ship;
the calculation formula of the target ship draft is as follows: d = H-H; d is the draft of the target vessel, H is the second height from the deck of the target vessel to the bottom thereof, and H is the first height from the deck of the target vessel to the horizontal plane.
And calculating the displacement of the target ship according to the draught and the volume of the target ship.
The judging subunit 2033 is configured to snap-shoot the target ship in real time and store the whole point cloud set of the target ship when it is determined that the displacement of the target ship exceeds a preset load or the draft depth calculation is incorrect; and alarming to a monitoring center.
Calculating a target ship with water displacement reaching a preset load designated percentage or a target ship with wrong draft d (if d is less than 0), considering that the target ship is overloaded, using a camera to snapshot the target ship, and storing an integral point cloud set of the ship; and alarming to a monitoring center, and storing the record for subsequent reference and data statistics.
Further, for the ship name plate information of the target ship which is not detected, judging the first height h from the deck of the target ship to the horizontal plane, and if h is less than or equal to 20cm, alarming to a monitoring center as overload; if h >20cm, as an artificial check.
Furthermore, for incomplete hull information (real-time position information and ship name plate information) in the target ship, judging a first height h from a deck of the target ship to a horizontal plane, and if h is less than or equal to 20cm, alarming to a monitoring center as overload; if h >20cm, as an artificial check.
The invention also provides a ship monitoring system which comprises the ship monitoring device.
The invention also provides a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the above-mentioned vessel monitoring method.
The storage medium stores the software, and the storage medium includes but is not limited to: optical disks, floppy disks, hard disks, erasable memory, etc.
The invention has the beneficial effects that:
the invention provides a ship monitoring method, which is characterized in that current point cloud data of a river channel are obtained by scanning ships passing through the river channel; and respectively differentiating all point cloud data in the current time period with the background point cloud data of the river channel to obtain a first height h from the deck of the target ship to the horizontal plane, if the first height h from the deck of the target ship to the horizontal plane cannot be directly obtained: the method comprises the steps of obtaining the type of a target ship, fitting to obtain a boundary line between a ship board and a deck of the target ship according to the type of the target ship and overall contour information of the ship obtained through difference, calculating the height from the boundary line to the horizontal plane, and obtaining a first height h from the deck of the target ship to the horizontal plane. By the method, the first height h from the deck of the target ship to the horizontal plane can be accurately calculated no matter whether the ship is shielded or not. The ship average advancing speed is calculated, and the continuous scanning results of the ship are spliced to obtain the ship integral point cloud set, so that the ship draught condition is more visual, and the error is smaller. Further, the present invention can distinguish parallel ships and determine a target ship among the parallel ships.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (15)
1. A method of monitoring a vessel, comprising:
scanning the river channel in real time to obtain current point cloud data of the river channel;
differentiating all point cloud data in the current time period with background point cloud data of the river channel respectively to obtain a first height h from a deck of the target ship to a horizontal plane;
calculating and feeding back the load of the target ship according to the pre-acquired ship body information of the target ship and the first height h;
when the difference between all point cloud data in the current time period and the background point cloud data of the river channel is respectively carried out, and the first height h from the deck of the target ship to the horizontal plane cannot be directly obtained:
the method comprises the steps of obtaining the type of a target ship, fitting to obtain a boundary line between a ship board and a deck of the target ship according to the type of the target ship and overall contour information of the ship obtained through difference, calculating the height from the boundary line to the horizontal plane, and obtaining a first height h from the deck of the target ship to the horizontal plane.
2. The method of claim 1, wherein the obtaining the type of the target ship and the fitting the boundary between the side and the deck of the target ship according to the type of the target ship and the overall profile information of the ship obtained by difference comprises:
acquiring the type of a target ship from AIS information of the target ship;
obtaining type contour information according to the type of the target ship, and fitting the type contour with the overall contour of the ship obtained through difference;
and taking the boundary line of the ship board and the deck in the type contour information obtained after fitting as the boundary line of the ship board and the deck of the target ship.
3. The method of claim 1, wherein:
the position information of the target ship is obtained while the ship body information of the target ship is obtained in advance;
determining a target ship in the parallel ships according to the position information;
when a target ship in the parallel ships cannot be determined according to the position information, capturing the parallel ships in real time and storing an integral point cloud set of the parallel ships; and clustering the whole point cloud set to distinguish parallel ships and determine a target ship in the parallel ships.
4. The method of claim 3, wherein clustering the whole set of point clouds to distinguish parallel vessels comprises:
when the distance between the point clouds is judged to be smaller than a preset radius threshold value, the point clouds are gathered into one type;
and when the shortest distance between the two clusters is judged to be within the preset width range, combining the two clusters into one class to obtain a ship.
5. The method of claim 1, wherein the scanning the river channel in real time to obtain current point cloud data of the river channel comprises:
scanning the river channel in real time to obtain current original point cloud data of the river channel;
performing plane fitting on the current original point cloud data of the river channel to obtain a horizontal plane;
and filtering the point cloud data below the horizontal plane to obtain the current point cloud data of the river channel.
6. The method of claim 1, wherein the differentiating all the point cloud data in the current time period with the background point cloud data of the river channel to obtain the first height h from the deck of the target ship to the horizontal plane comprises:
differentiating all point cloud data in the current time period with background point cloud data of the river channel respectively to obtain a plurality of point cloud increasing sets in the current time period;
splicing the point cloud incremental sets to obtain an integral point cloud set of the target ship;
and identifying the integral point cloud set of the target ship to obtain a deck of the target ship, and calculating a first height h from the deck to the horizontal plane.
7. The method of claim 6, wherein the piecing the plurality of point cloud augmentations to obtain an overall point cloud set for the target vessel comprises:
performing down-sampling on the point cloud increasing sets to obtain a plurality of point cloud sets to be analyzed;
calculating to obtain the average advancing speed of the target ship according to the position change of the previous point cloud set to be analyzed and the current point cloud set to be analyzed and the volume of the target ship;
according to the average advancing speed, sequentially obtaining a plurality of subsequent point cloud sets to be analyzed of the target ship by scanning the advancing target ship;
splicing all point cloud sets to be analyzed to obtain an integral point cloud set of a preprocessed target ship;
and filtering the integral point cloud set of the preprocessed target ship to obtain the integral point cloud set of the target ship.
8. The method according to claim 1, wherein the calculating and feeding back the load of the target ship according to the pre-acquired hull information of the target ship and the first height h comprises:
acquiring the name plate information of the target ship, and inquiring the volume of the target ship and a second height H from the deck of the target ship to the bottom of the target ship from a database according to the name plate information;
calculating according to the first height H and the second height H to obtain the draft of the target ship, and calculating according to the draft and the volume of the target ship to obtain the displacement of the target ship;
when the water displacement of the target ship is judged to exceed a preset load or the draft depth calculation is wrong, the target ship is snapshot in real time and an integral point cloud set of the target ship is stored; and alarming to a monitoring center.
9. A marine vessel monitoring device, comprising:
the scanning unit is used for scanning the river channel in real time to obtain current point cloud data of the river channel;
the difference unit is used for respectively carrying out difference on all point cloud data in the current time period and background point cloud data of the river channel to obtain a first height h from a deck of the target ship to a horizontal plane;
the calculating unit is used for calculating and feeding back the load of the target ship according to the pre-acquired ship body information of the target ship and the first height h;
when the difference between all point cloud data in the current time period and the background point cloud data of the river channel is respectively carried out, and the first height h from the deck of the target ship to the horizontal plane cannot be directly obtained:
and the fitting unit is used for acquiring the type of the target ship, fitting to obtain a boundary line between a ship board and a deck of the target ship according to the type of the ship and the overall profile information of the ship obtained through difference, calculating the height from the boundary line to the horizontal plane, and obtaining the first height h from the deck of the target ship to the horizontal plane.
10. The apparatus of claim 9, wherein the fitting unit comprises:
the acquisition subunit is used for acquiring the type of the target ship from the AIS information of the target ship;
the fitting subunit is used for obtaining type contour information according to the type of the target ship and fitting the type contour with the overall contour of the ship obtained through the difference;
and the target subunit is used for taking the boundary line of the ship board and the deck in the type contour information obtained after fitting as the boundary line of the ship board and the deck of the target ship.
11. The apparatus of claim 9, wherein the scanning unit comprises:
the scanning subunit is used for scanning the river channel in real time to obtain current original point cloud data of the river channel;
the plane fitting subunit is used for performing plane fitting on the current original point cloud data of the river channel to obtain a horizontal plane;
and the filtering subunit is used for filtering the point cloud data below the horizontal plane to obtain the current point cloud data of the river channel.
12. The apparatus of claim 9, wherein the difference unit comprises:
the difference subunit is used for respectively carrying out difference on all point cloud data in the current time period and background point cloud data of the river channel to obtain a plurality of point cloud increasing sets in the current time period;
the splicing subunit is used for splicing the point cloud increasing sets to obtain an integral point cloud set of the target ship;
and the calculating subunit is used for identifying the whole point cloud set of the target ship to obtain a deck of the target ship and calculating a first height h from the deck to a horizontal plane.
13. The apparatus of claim 9, wherein the computing unit comprises:
the information acquisition subunit is used for acquiring the name plate information of the target ship, and inquiring the volume of the target ship and a second height H from the deck of the target ship to the bottom of the target ship from a database according to the name plate information;
the displacement calculation subunit is used for calculating according to the first height H and the second height H to obtain the draft of the target ship and calculating according to the draft and the volume of the target ship to obtain the displacement of the target ship;
the judging subunit is used for snapshotting the target ship in real time and storing an integral point cloud set of the target ship when the water displacement of the target ship is judged to exceed a preset load or the draft depth calculation is wrong; and alarming to a monitoring center.
14. A vessel monitoring system, comprising: a vessel monitoring device as claimed in any one of claims 9 to 13.
15. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the vessel monitoring method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110841100.7A CN113277028B (en) | 2021-07-26 | 2021-07-26 | Ship monitoring method, device and system and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110841100.7A CN113277028B (en) | 2021-07-26 | 2021-07-26 | Ship monitoring method, device and system and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113277028A true CN113277028A (en) | 2021-08-20 |
| CN113277028B CN113277028B (en) | 2021-10-08 |
Family
ID=77287197
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110841100.7A Active CN113277028B (en) | 2021-07-26 | 2021-07-26 | Ship monitoring method, device and system and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113277028B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782700A (en) * | 2022-03-03 | 2022-07-22 | 中冶赛迪重庆信息技术有限公司 | Ship type feature acquisition method and system, electronic device and readable storage medium |
| CN116303523A (en) * | 2022-11-30 | 2023-06-23 | 杭州数聚链科技有限公司 | Automatic cargo ship identification sampling method and system |
| CN114782700B (en) * | 2022-03-03 | 2024-07-09 | 中冶赛迪信息技术(重庆)有限公司 | Ship-type feature acquisition method, system, electronic equipment and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170309188A1 (en) * | 2016-04-21 | 2017-10-26 | Marcura Equities FZE | Vessel traffic management system |
| CN108919299A (en) * | 2018-06-27 | 2018-11-30 | 武汉理工大学 | Ship freeboard intelligence sensing system and method based on multi-thread laser Surface scan |
| CN109375235A (en) * | 2018-11-30 | 2019-02-22 | 武汉理工大学 | Inland navigation craft freeboard detection method based on deeply neural network |
| CN113034569A (en) * | 2021-03-05 | 2021-06-25 | 武汉科技大学 | Point cloud data-based ship overrun early warning method and system |
-
2021
- 2021-07-26 CN CN202110841100.7A patent/CN113277028B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170309188A1 (en) * | 2016-04-21 | 2017-10-26 | Marcura Equities FZE | Vessel traffic management system |
| CN108919299A (en) * | 2018-06-27 | 2018-11-30 | 武汉理工大学 | Ship freeboard intelligence sensing system and method based on multi-thread laser Surface scan |
| CN109375235A (en) * | 2018-11-30 | 2019-02-22 | 武汉理工大学 | Inland navigation craft freeboard detection method based on deeply neural network |
| CN113034569A (en) * | 2021-03-05 | 2021-06-25 | 武汉科技大学 | Point cloud data-based ship overrun early warning method and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782700A (en) * | 2022-03-03 | 2022-07-22 | 中冶赛迪重庆信息技术有限公司 | Ship type feature acquisition method and system, electronic device and readable storage medium |
| CN114782700B (en) * | 2022-03-03 | 2024-07-09 | 中冶赛迪信息技术(重庆)有限公司 | Ship-type feature acquisition method, system, electronic equipment and readable storage medium |
| CN116303523A (en) * | 2022-11-30 | 2023-06-23 | 杭州数聚链科技有限公司 | Automatic cargo ship identification sampling method and system |
| CN116303523B (en) * | 2022-11-30 | 2023-10-17 | 杭州数聚链科技有限公司 | Automatic cargo ship identification sampling method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113277028B (en) | 2021-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108759973B (en) | Water level measuring method | |
| CN109711353B (en) | Ship waterline area identification method based on machine vision | |
| CN113277028B (en) | Ship monitoring method, device and system and computer storage medium | |
| CN110930357A (en) | In-service steel wire rope surface defect detection method and system based on deep learning | |
| CN208279212U (en) | Laser anti-collision detection system for track crane | |
| CN115456970B (en) | Method for identifying carrier line of topside-cut ship based on dimension-reduction regression | |
| CN106205214A (en) | A kind of ship berthing based on three-dimensional laser point cloud data monitoring system | |
| CN113034569A (en) | Point cloud data-based ship overrun early warning method and system | |
| CN109785632A (en) | A kind of magnitude of traffic flow statistical method and device | |
| CN108288268B (en) | Method for detecting ship landing in high-resolution remote sensing image based on projection analysis | |
| CN116704333B (en) | Single tree detection method based on laser point cloud data | |
| CN111597904B (en) | Identification method for inclination of tunnel cable bracket | |
| Litkey et al. | Single-scan TLS methods for forest parameter retrieval | |
| CN113449688A (en) | Power transmission tree obstacle recognition system based on image and laser point cloud data fusion | |
| CN116071694B (en) | Ship detection method, device and computer readable storage medium | |
| CN111694997A (en) | Navigation data analysis control method and system for unmanned ship | |
| CN116486212A (en) | Water gauge identification method, system and storage medium based on computer vision | |
| CA3237725A1 (en) | Systems and methods for draft calculation | |
| CN109917414B (en) | Ship freeboard measuring method and system based on laser technology | |
| CN115755088A (en) | Laser point cloud-based automatic measurement method for power transmission line engineering construction parameters | |
| CN107784682B (en) | Cable automatic extraction and reconstruction method based on three-dimensional point cloud data | |
| CN112488113A (en) | Remote sensing image rotating ship target detection method based on local straight line matching | |
| CN112733896A (en) | Ship lockage management method, device, system and storage medium | |
| CN116758480B (en) | Method for identifying illegal fishing boat fishing based on multi-model fusion and multi-parameter combination | |
| CN113534182B (en) | Method, equipment and storage medium for detecting rows of straw bundling crops |
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 |