KR20160150404A - Vessel image detecting method - Google Patents

Vessel image detecting method Download PDF

Info

Publication number
KR20160150404A
KR20160150404A KR1020150088347A KR20150088347A KR20160150404A KR 20160150404 A KR20160150404 A KR 20160150404A KR 1020150088347 A KR1020150088347 A KR 1020150088347A KR 20150088347 A KR20150088347 A KR 20150088347A KR 20160150404 A KR20160150404 A KR 20160150404A
Authority
KR
South Korea
Prior art keywords
hull side
side model
image
ship
data
Prior art date
Application number
KR1020150088347A
Other languages
Korean (ko)
Other versions
KR101711931B1 (en
Inventor
허희영
양진혁
원석희
이근영
Original Assignee
삼성중공업 주식회사
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 삼성중공업 주식회사 filed Critical 삼성중공업 주식회사
Priority to KR1020150088347A priority Critical patent/KR101711931B1/en
Publication of KR20160150404A publication Critical patent/KR20160150404A/en
Application granted granted Critical
Publication of KR101711931B1 publication Critical patent/KR101711931B1/en

Links

Images

Classifications

    • G06K9/6201—
    • B63B9/00—
    • G06K9/00771—
    • G06K9/6204—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)

Abstract

A vessel image detecting method of the present invention comprises a step of photographing at least one vessel with a camera and receiving an image; a step of receiving at least one vessel side model from a database; a step of comparing the at least one vessel side model with the vessel side of the at least one vessel; and a step of receiving object information corresponding to the one vessel side model if the vessel side model of the vessel side and the at least one vessel side model match. So, calculation amount can be minimized.

Description

[0001] VESSEL IMAGE DETECTING METHOD [0002]

The present invention relates to a ship image detection method.

CCTV cameras are installed on the rooftop of buildings or large cranes to monitor vessels placed on the wall or dock. Supervisors monitor the presence of vessels, work conditions, and emergency situations such as fire by using images taken with these cameras.

However, it is counter-productive for the supervisor to remember a lot of information related to the ship or to search for additional information.

Therefore, it is preferable to implement the augmented reality by automatically mapping the information of the ship to the image. However, when the general image detection method is applied as it is, there is a problem that the augmented reality implementation is delayed and rapid supervision can not be performed due to a large amount of computation. High-cost hardware is required to perform these operations quickly.

Therefore, there is a need for a ship image detection method that is optimized for ships and minimizes the amount of computation.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and an object of the present invention is to provide a method of detecting a ship image that is optimized for a ship and minimizes a calculation amount.

According to another aspect of the present invention, there is provided a method for detecting a ship image comprising: capturing at least one ship with a camera and receiving an image; Receiving at least one hull side model from a database; Comparing the at least one hull side model with a hull side of the at least one ship; And receiving object information corresponding to the one hull side model if the hull side model of one of the hull side and the at least one hull side model is matched.

Receiving location information and a photographing direction of the camera; And estimating a coordinate range of the image using the position information and the photographing direction.

The at least one hull side model may be a hull side model predicted to be in the estimated coordinate range of the plurality of hull side models stored in the database.

And synthesizing the object information with the image.

The object information may include at least one of a ship name, production information, and shipping information.

The at least one hull side model may include geometry information and color information of the hull side, respectively.

A computer program according to an embodiment of the present invention includes: receiving image data of at least one ship; Receiving at least one hull side model data; Comparing the at least one hull side model data and the image data; And a step of receiving, when a part of the hull side model data of the at least one hull side model data coincides with the part of the image data, the object information data corresponding to the one hull side model data, And stored in the medium.

And estimating a coordinate range of the image data using the position information and the photographing direction of the camera that generated the image data.

The at least one hull side model data may be hull side model data predicted to be in the estimated coordinate range of at least one hull side model data stored in the database.

And synthesizing the target information data with the image data.

According to the embodiment of the present invention, it is possible to provide a ship image detection method that is optimized for a ship and minimizes the amount of calculation.

FIG. 1 is a view for explaining an image of a ship taken by a camera in a method of detecting a ship image according to an embodiment of the present invention.
2 is a diagram illustrating a plurality of hull side models stored in a database according to an embodiment of the present invention.
3 is a view for explaining a step of comparing a ship and a hull side model according to an embodiment of the present invention.
4 is a view for explaining a step in which object information is implemented in the form of an augmented reality according to an embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art to which the present invention pertains. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.

In the drawings, the thickness is enlarged to clearly represent the layers and regions. Like parts are designated with like reference numerals throughout the specification. It will be understood that when an element such as a layer, film, region, plate, or the like is referred to as being "on" another portion, it includes not only the element directly over another element, Conversely, when a part is "directly over" another part, it means that there is no other part in the middle.

Also, throughout the specification, when an element is referred to as "including" an element, it is understood that the element may include other elements as well, without departing from the other elements unless specifically stated otherwise. Also, throughout the specification, the term "on " means to be located above or below a target portion, and does not necessarily mean that the target portion is located on the image side with respect to the gravitational direction.

FIG. 1 is a view for explaining an image of a ship taken by a camera in a method of detecting a ship image according to an embodiment of the present invention.

Referring to FIG. 1, a camera 10 attached to a high building, a large crane, or the like is photographing a quay wall or a dock. The photographed image 100 includes at least one vessel 110.

The position information of the camera 10 and the photographing direction of the camera 10 are received and the coordinate range of the image 100 can be estimated using the position information and the photographing direction. The positional information of the fixed camera 10 may be previously informed. When the camera 10 is of the mobile type, the position can be recognized through the GPS system. The photographing direction of the camera 10 can be measured from an angle sensor (not shown) or the like attached to the camera 10. [ In addition, zoom in / out information of the camera 10 can be additionally used to estimate the coordinate range of the image 100 more accurately.

There is an advantage that the calculation amount can be primarily reduced by performing the method of detecting the ship image only within the estimated coordinate range. This is described in more detail in the description of FIG.

2 is a diagram illustrating a plurality of hull side models stored in a database according to an embodiment of the present invention. The database may refer to a group of data stored in a recording medium such as a hard disk of a computer performing the method of detecting a ship image of the present invention. However, the database may not necessarily be stored in a hard disk of a computer performing a ship image detection method, but may be stored in a removable recording medium such as a CD, a DVD, or a USB storage medium, or a database server may be separately constructed. Methods of using a database in a computational manner can be implemented by those skilled in the art in various other ways. In the present invention, the term " computer " refers to a computing device capable of processing a manufactured program without being limited to a form such as a desktop, a notebook, a portable terminal, and a server.

2, an exemplary plurality of hull side models 210, 220, 230 are shown. A plurality of hull side models 210, 220, 230 can be extracted from the CAD drawing that was used to dry the ship. The hull side models 210, 220, and 230 include geometry information of the hull side surface. Further, the hull side models 210, 220, and 230 may further include color information on the hull side surface.

The present invention relates to a method of detecting a ship image by comparing only the ship side model (210, 220, 230) with a ship side hull side of an image of the ship, To determine which ship it is. Therefore, there is an advantage that the computation amount can be reduced secondarily by comparing only a part of the image.

Depending on the amount of shipment and the location of the ship, some of the side of the ship may be below sea level. At this time, it is possible to compare with the ship side models 210, 220 and 230 in consideration of the ship side exposed on the sea surface by referring to the information on the ship quantity and the shipment position. At this time, since the side portion of the hull to be compared is reduced, the calculation amount can be reduced to a third level.

3 is a view for explaining a step of comparing a ship and a hull side model according to an embodiment of the present invention. Referring to FIG. 3, the side surface 115 of the ship 110 of the image 100 is indicated by a dotted line.

1 to 3, a method of detecting a ship image of the present invention will be described below.

First, a computer for performing the method of detecting a ship image of the present invention receives an image 100 including at least one ship 110 photographed from the camera 10. As described above, the computer can further receive the position information and the photographing direction of the camera 10, and can estimate the coordinate range of the image 100 using the position information and the photographing direction. The estimation of the coordinate range is to calculate the coordinate range in which the image 100 is photographed, reflecting the predetermined error range. In calculating the coordinate range, it is possible to calculate the coordinate range more accurately by referring to a reference object previously installed in a specific coordinate or an existing building or the like.

The computer then receives at least one hull side model 210, 220, 230 from the database.

At least one hull side model 210, 220, 230 may be a hull side model predicted to be in an estimated coordinate range of a plurality of hull side models stored in the database. That is, by referring to the already established shipbuilding plan or shipment plan, it is possible to know which ship is in the estimated coordinate range. Such shipbuilding or shipment plans may be stored in a database and pre-stored in the database.

The computer then compares at least one hull side model 210, 220, 230 with hull side 115 of at least one vessel 110. At this time, instead of comparing all of the hull side model stored in the database with the hull side surface 115, only the hull side model predicted to be in the coordinate range is compared with the hull side surface 115, have.

Referring to FIG. 3, in this embodiment, the ship side model 230 and the ship side surface 115 coincide with each other. Thus, the computer terminates the ship image detection algorithm and receives object information corresponding to the selected hull side model 230. Such target information may be at least one of the ship name, production information (drying schedule, product details, current work process, delivery date, launch date, inspection status, trial operation status, etc.), and shipping information.

If there is no hull side model that is consistent with the hull side 115 as a result of comparison, it may include an additional step of comparing the hull side model predicted to be in the estimated coordinate range, as well as the remaining hull side model stored in the database.

The 3D model of the hull side models 210, 220, and 230 is rotated while matching the hull side face 115 of the image 100 with the ship 110 in a different direction, Can be detected.

Next, the augmented reality image may be implemented by synthesizing the object information to the image 100. [ 4 is a view for explaining a step in which object information is implemented in the form of an augmented reality according to an embodiment of the present invention. Referring to FIG. 4, a composite image 300 implemented with an augmented reality image by combining object information 320 with an existing image is shown.

In another embodiment, if a specific image such as smoke is detected, a fire alarm may be displayed at the location and a fire alarm may be sent to the yard.

The ship image detecting method of the present invention described so far can be produced by a computer program stored in a recording medium for driving by a computer.

Such a computer program includes receiving image data of at least one vessel photographed. Such image data may be a digital image of an image photographed by a camera and recorded on a recording medium. The computer program may further include estimating a coordinate range of the image data using the position information and the photographing direction of the camera that generated the image data.

The computer program then includes receiving at least one hull side model data. The at least one hull side model data may be hull side model data predicted to be in an estimated coordinate range of at least one hull side model data stored in the database.

The computer program then includes comparing the at least one hull side model data to the image data. When comparing only the hull side model data that is expected to be in the estimated coordinate range, the calculation amount decreases primarily because there is no need to compare all the hull side model data stored in the database with the hull side. In addition, since the vessel can be recognized by comparing only the side of the ship rather than the entire side of the ship, there is an advantage that the calculation amount is reduced secondarily.

The computer program then includes receiving object information data corresponding to one of the hull side model data if a portion of the hull side model data and at least one hull side model data match. Such target information data may be at least one of the ship name, production information (drying schedule, product details, current work process, delivery date, launch date, inspection status, trial operation status, etc.), and shipping information.

In addition, the computer program may further comprise a step of image-synthesizing the object information data to the image data to generate composite image data in which the augmented reality is implemented.

It is to be understood that both the foregoing general description and the following detailed description of the present invention are illustrative and explanatory only and are intended to be illustrative of the invention and are not to be construed as limiting the scope of the invention as defined by the appended claims. It is not. Therefore, those skilled in the art will appreciate that various modifications and equivalent embodiments are possible without departing from the scope of the present invention. Accordingly, the true scope of the present invention should be determined by the technical idea of the appended claims.

10: Camera
100: Video
110: Ship
115: Hull side
210, 220, 230: Hull side model
300: Composite video

Claims (10)

Photographing at least one ship with a camera and receiving an image;
Receiving at least one hull side model from a database;
Comparing the at least one hull side model with a hull side of the at least one ship; And
And receiving object information corresponding to the one hull side model if the hull side model of one of the hull side and the at least one hull side model is matched
Ship image detection method. The method according to claim 1,
Receiving location information and a photographing direction of the camera; And
And estimating a coordinate range of the image using the position information and the photographing direction
Ship image detection method. 3. The method of claim 2,
Said at least one hull side model comprising:
A hull side model which is predicted to be in the estimated coordinate range among a plurality of hull side models stored in the database
Ship image detection method. The method of claim 3,
And synthesizing the object information to the image
Ship image detection method. 5. The method of claim 4,
Wherein the object information includes at least one of a vessel name, production information, and shipping information
Ship image detection method. 5. The method of claim 4,
Wherein the at least one hull side model includes geometric shape information and color information of the hull side,
Ship image detection method. The method comprising: receiving image data of at least one vessel;
Receiving at least one hull side model data;
Comparing the at least one hull side model data and the image data; And
Receiving the object information data corresponding to the one hull side model data when the hull side model data of one of the at least one hull side model data and a part of the image data coincide with each other, Stored in
Computer program. 8. The method of claim 7,
And estimating a coordinate range of the image data using the positional information and the photographing direction of the camera that generated the image data
Computer program. 9. The method of claim 8,
Wherein the at least one hull side model data comprises:
The hull side model data, which is predicted to be in the estimated coordinate range out of at least one hull side model data stored in the database,
Computer program. 10. The method of claim 9,
And synthesizing the target information data to the image data
Computer program.
KR1020150088347A 2015-06-22 2015-06-22 Vessel image detecting method KR101711931B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150088347A KR101711931B1 (en) 2015-06-22 2015-06-22 Vessel image detecting method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150088347A KR101711931B1 (en) 2015-06-22 2015-06-22 Vessel image detecting method

Publications (2)

Publication Number Publication Date
KR20160150404A true KR20160150404A (en) 2016-12-30
KR101711931B1 KR101711931B1 (en) 2017-03-03

Family

ID=57737193

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150088347A KR101711931B1 (en) 2015-06-22 2015-06-22 Vessel image detecting method

Country Status (1)

Country Link
KR (1) KR101711931B1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007316997A (en) * 2006-05-26 2007-12-06 Fujitsu Ltd Vehicle type determining program and apparatus
KR100990764B1 (en) * 2010-05-03 2010-10-29 (주)에디넷 System and method of image monitoring harbor
KR20140104899A (en) * 2013-02-21 2014-08-29 삼성전자주식회사 Electronic device and method for operating an electronic device
KR20140121156A (en) * 2013-04-05 2014-10-15 주식회사 브이플랩 Search Method by Object Recognition on Image and Search Server thereof

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007316997A (en) * 2006-05-26 2007-12-06 Fujitsu Ltd Vehicle type determining program and apparatus
KR100990764B1 (en) * 2010-05-03 2010-10-29 (주)에디넷 System and method of image monitoring harbor
KR20140104899A (en) * 2013-02-21 2014-08-29 삼성전자주식회사 Electronic device and method for operating an electronic device
KR20140121156A (en) * 2013-04-05 2014-10-15 주식회사 브이플랩 Search Method by Object Recognition on Image and Search Server thereof

Also Published As

Publication number Publication date
KR101711931B1 (en) 2017-03-03

Similar Documents

Publication Publication Date Title
US10262224B1 (en) Optical flow estimation using a neural network and egomotion optimization
Gracias et al. Underwater video mosaics as visual navigation maps
US9892516B2 (en) Three-dimensional coordinate computing apparatus, three-dimensional coordinate computing method, and non-transitory computer readable recording medium having therein program for three-dimensional coordinate computing
US9466107B2 (en) Bundle adjustment based on image capture intervals
US9321173B2 (en) Tracking and following people with a mobile robotic device
JP2017512991A (en) Target object detection method, detection apparatus, and robot
US9305361B2 (en) Resolving homography decomposition ambiguity based on orientation sensors
Wang et al. Stereovision based obstacle detection system for unmanned surface vehicle
JP2005528707A (en) Feature mapping between data sets
KR20180136895A (en) Abnormality detection apparatus and vehicle system
KR20200095888A (en) Method for context awareness of unmanned ship system and apparatus for the same
CN111445531A (en) Multi-view camera navigation method, device, equipment and storage medium
WO2014067684A1 (en) Method to enhance underwater localization
KR20170100204A (en) Apparatus and method for target tracking using 3d bim
JP7420135B2 (en) Information processing device, information processing method, and program
JP2005180949A (en) Automatic berthing system for vessel
WO2021051227A1 (en) Method and device for determining orientation information of image in three-dimensional reconstruction
Shah et al. Condition assessment of ship structure using robot assisted 3D-reconstruction
EP3860908A1 (en) System and method for assisting docking of a vessel
JP2018173882A (en) Information processing device, method, and program
KR101711931B1 (en) Vessel image detecting method
RU2679200C1 (en) Data from the video camera displaying method and system
KR101828710B1 (en) Apparatus and method for object occlusion detection
WO2020166401A1 (en) Learning data generation device, method, and program
US20180040128A1 (en) Verification of business processes using spatio-temporal data

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant