KR102520844B1 - Method and device for monitoring harbor and ship considering sea level - Google Patents

Abstract

The present invention relates to a harbor monitoring method performed by a computing means, and the harbor monitoring method according to one aspect of the present invention includes a ship object corresponding to a ship and a sea object corresponding to the sea having a first view attribute. acquiring a harbor image; Generating a segmentation image corresponding to the harbor image and having the first view attribute by performing image segmentation using an artificial neural network trained to output information about the type of object included in the input image from an input image - wherein the The segmentation image includes a first pixel labeled to correspond to the ship object and a second pixel labeled to correspond to the sea object -; From the segmentation image having the first view attribute based on first view conversion information used to convert the image having the first view attribute into an image having a second view attribute different from the first view attribute, generating a transform segmentation image having a 2-view attribute; and calculating berthing guide information of the ship based on the converted segmentation image - the berthing guide information is at least one of information about a distance to the quay wall of the ship and information about an approach speed of the ship to the quay wall. Including - including ;, wherein the generating of the transformed segmentation image comprises: obtaining sea level height information reflecting the height of the sea level; updating the first viewpoint conversion information by reflecting the sea level height information; and generating a transformed segmentation image having the second view property from the segmented image having the first view property based on the updated first view property transformation information.

Description

Port and ship monitoring method and device considering sea level {METHOD AND DEVICE FOR MONITORING HARBOR AND SHIP CONSIDERING SEA LEVEL}

The present invention relates to a method and device for monitoring ports and ships, and more particularly, to a method and device for monitoring ports and ships in consideration of sea level.

Many accidents occur in the operation of ships, berthing and unloading in ports, and the main cause of these accidents is known to be carelessness of human operation. Here, negligence in operation is mainly caused by the fact that the situation around the ship or in the port cannot be accurately monitored through the naked eye. Currently, various types of obstacle sensors are used to supplement this, but there are still limitations. For example, ECDIS has limitations due to GPS inaccuracy, AIS update cycle, and AIS unregistered moving objects, and radar has limitations due to non-scanning areas and noise. As a result, a visual confirmation process is still required for accurate detection of obstacles.

One object of the present invention is to provide a monitoring method and apparatus for monitoring the surroundings of ports and ships.

Another object of the present invention is to provide a monitoring device and method for grasping the surroundings and port conditions of a ship during berthing or unloading of a ship and guiding berthing or unloading.

The problem to be solved by the present invention is not limited to the above-mentioned problems, and problems not mentioned will be clearly understood by those skilled in the art from this specification and the accompanying drawings. .

According to one aspect of the present invention, in a harbor monitoring method performed by a computing means, acquiring a harbor image having a first view attribute and including a ship object corresponding to a ship and a sea object corresponding to the sea; Generating a segmentation image corresponding to the harbor image and having the first view attribute by performing image segmentation using an artificial neural network trained to output information about the type of object included in the input image from an input image - wherein the The segmentation image includes a first pixel labeled to correspond to the ship object and a second pixel labeled to correspond to the sea object -; From the segmentation image having the first view attribute based on first view conversion information used to convert the image having the first view attribute into an image having a second view attribute different from the first view attribute, generating a transform segmentation image having a 2-view attribute; and calculating berthing guide information of the ship based on the converted segmentation image - the berthing guide information is at least one of information about a distance to the quay wall of the ship and information about an approach speed of the ship to the quay wall. Including - including ;, wherein the generating of the transformed segmentation image comprises: obtaining sea level height information reflecting the height of the sea level; updating the first viewpoint conversion information by reflecting the sea level height information; and generating a transformed segmentation image having the second view property from the segmentation image having the first view property based on the updated first view property transformation information.

According to another aspect of the present invention, in a method for monitoring the vicinity of a ship performed by a computing means, obtaining a maritime image including an obstacle object corresponding to an obstacle around the ship and a sea object corresponding to the sea having a first view attribute step; generating a segmentation image corresponding to the resolution image and having the first view attribute by performing image segmentation using an artificial neural network trained to output information about a type of an object included in the input image from an input image; The segmentation image includes a first pixel labeled to correspond to the obstacle object and a second pixel labeled to correspond to the sea object -; From the segmentation image having the first view attribute based on first view conversion information used to convert the image having the first view attribute into an image having a second view attribute different from the first view attribute, generating a transform segmentation image having a 2-view attribute; and calculating navigation guide information of the ship based on the transformed segmentation image - the navigation guide information is at least one of information about a distance of the ship to the obstacle and information about an approaching speed of the ship to the obstacle. Including one - including ;, wherein the generating of the transformed segmentation image comprises: obtaining sea level height information reflecting the height of the sea level; updating the first viewpoint conversion information by reflecting the sea level height information; and generating a transformed segmentation image having the second view property from the segmentation image having the first view property based on the updated first view property transformation information. .

According to another aspect of the present invention, in a harbor monitoring method performed by a computing means, obtaining a first image having a first view and including a ship object corresponding to a ship and a sea object corresponding to the sea; generating a second image having a top view different from the first view by projecting the first image onto a first plane parallel to the sea level; Calculating berthing guide information based on the second image - The berthing guide information includes at least one of information about a distance to the quay wall of the ship and information about an approach speed of the ship to the quay wall - ; obtaining sea level height information corresponding to a height of a second plane formed at a height different from the first plane and parallel to the first plane; and correcting the calculated eyepiece guide information by reflecting a height difference between the first plane and the second plane.

According to another aspect of the present invention, in a harbor monitoring method performed by a computing means, obtaining a first image having a first view and including a ship object corresponding to a ship and a sea object corresponding to the sea; obtaining sea level height information reflecting the height of sea level; In order to project the first image onto a first plane formed parallel to the sea level and parallel to the sea level, viewpoint conversion information for projecting the image onto a second plane parallel to the sea level but formed at a different height from the sea level is used as the sea level height information. Updating based on; converting the first image into a second image having a top view different from the first view by using the updated viewpoint conversion information; And calculating berthing guide information based on the second image - the berthing guide information includes at least one of information about a distance to the quay wall of the ship and information about an approach speed of the ship to the quay wall A port monitoring method comprising -; may be provided.

The solutions to the problems of the present invention are not limited to the above-described solutions, and solutions not mentioned will be clearly understood by those skilled in the art from this specification and the accompanying drawings. You will be able to.

According to the present invention, it is possible to monitor the vicinity of a ship and a port using a monitoring device and method.

In addition, according to the present invention, by using the monitoring device and method, it is possible to grasp the surroundings and port conditions of the ship when the ship is berthing or leaving the ship, and guide the berthing or leaving the ship.

Effects of the present invention are not limited to the above-mentioned effects, and effects not mentioned will be clearly understood by those skilled in the art from this specification and the accompanying drawings.

1 is a diagram of a port monitoring method considering sea level according to an embodiment.
2 is a diagram of a monitoring device according to an embodiment.
3 and 4 are diagrams for explaining an installation position of a sensor module according to an embodiment.
5 and 6 are diagrams of an embodiment of a monitoring device according to an embodiment.
7 is a diagram for describing image segmentation according to an exemplary embodiment.
8 is a table related to allocation of identification values in which information on the type and distance of an object is simultaneously reflected according to an exemplary embodiment.
9 is a diagram of a learning step and an inference step of an artificial neural network according to an embodiment.
10 is a diagram for explaining eyepiece guide information according to an embodiment.
11 is a diagram for explaining berthing guide information between a ship and a quay according to an embodiment.
12 is a diagram for explaining a method of acquiring eyepiece guide information according to an embodiment.
13 is a diagram related to viewpoint conversion according to an exemplary embodiment.
14 to 20 are views for explaining acquisition of berthing guide information in consideration of sea level height information according to an embodiment.
21 to 23 are diagrams for examples of sea level height information acquisition according to an embodiment.
24 is a view related to fog removal according to an embodiment.
25 is a diagram for explaining an eyepiece guide information output step according to an embodiment.
26 is a diagram related to an eyepiece guide information output step according to an embodiment.
27 is a diagram for explaining navigation guide information according to an exemplary embodiment.

The embodiments described in this specification are intended to clearly explain the spirit of the present invention to those skilled in the art to which the present invention belongs, and the present invention is not limited by the embodiments described in this specification, and the present invention The scope of should be construed as including modifications or variations that do not depart from the spirit of the present invention.

The terms used in this specification have been selected as general terms that are currently widely used as much as possible in consideration of the functions in the present invention, but they may vary depending on the intention, custom, or the emergence of new technologies of those skilled in the art in the technical field to which the present invention belongs. can However, in the case where a specific term is defined and used in an arbitrary meaning, the meaning of the term will be separately described. Therefore, the terms used in this specification should be interpreted based on the actual meaning of the term and the overall content of this specification, not the simple name of the term.

The drawings accompanying this specification are intended to easily explain the present invention, and the shapes shown in the drawings may be exaggerated as necessary to aid understanding of the present invention, so the present invention is not limited by the drawings.

If it is determined that a detailed description of a known configuration or function related to the present invention in this specification may obscure the gist of the present invention, a detailed description thereof will be omitted if necessary.

According to one aspect of the present invention, in a harbor monitoring method performed by a computing means, acquiring a harbor image having a first view attribute and including a ship object corresponding to a ship and a sea object corresponding to the sea; Generating a segmentation image corresponding to the harbor image and having the first view attribute by performing image segmentation using an artificial neural network trained to output information about the type of object included in the input image from an input image - wherein the The segmentation image includes a first pixel labeled to correspond to the ship object and a second pixel labeled to correspond to the sea object -; From the segmentation image having the first view attribute based on first view conversion information used to convert the image having the first view attribute into an image having a second view attribute different from the first view attribute, generating a transform segmentation image having a 2-view attribute; and calculating berthing guide information of the ship based on the converted segmentation image - the berthing guide information is at least one of information about a distance to the quay wall of the ship and information about an approach speed of the ship to the quay wall. Including - including ;, wherein the generating of the transformed segmentation image comprises: obtaining sea level height information reflecting the height of the sea level; updating the first viewpoint conversion information by reflecting the sea level height information; and generating a transformed segmentation image having the second view property from the segmentation image having the first view property based on the updated first view property transformation information.

Here, in the updating step, the first viewpoint conversion information generated based on the reference plane may be updated by reflecting the sea level height information.

Here, the berthing guide information may be calculated based on a boundary area, which is an area in contact with the sea surface of the ship.

Here, the information on the distance to the quay wall of the vessel corresponds to the distance to the quay wall in the boundary area, and the information on the approach speed to the quay wall corresponds to the approach speed to the quay wall in the boundary area. It can be.

Here, the eyepiece guide information may be calculated based on a first point included in the boundary area and corresponding to the bow of the ship and a second point corresponding to the stern of the ship.

Here, the information on the distance from the quay wall of the ship corresponds to the distances of the first point and the second point from the quay wall, and the information on the speed of approach to the quay wall corresponds to the first point and the information on the approach speed to the quay wall. It may correspond to the approach speed of the second point to the quay wall.

Here, the harbor image may include a first harbor image and a second harbor image at least partially overlapping the first harbor image and a monitoring region.

Here, the obtaining of the sea level height information includes calculating the sea level height information based on an overlap area, which is an area where a monitoring area of the first harbor image and a monitoring area of the second harbor image overlap. can do.

Here, the obtaining of the sea level height information may further include determining the overlap area based on feature points of the first and second bay images that match each other.

Here, the harbor image further includes a quay wall object corresponding to the quay wall, and the obtaining of the sea level height information includes a shade corresponding to a sea that is occluded by the quay wall and is not represented in the harbor image. Calculating the sea level height information based on the region; may include.

Here, the obtaining of the sea level height information may include calculating the sea level height information based on an area where the height measurement object included in the harbor image is exposed above the sea level.

Here, the obtaining of the sea level height information may include receiving the sea level height information from a sensor for measuring the sea level height information.

Here, the acquiring of the sea level height information may include receiving the sea level height information from a vessel traffic service system (VTS system).

Here, the berthing guide information may further include at least one of information about a distance between the ship and an adjacent ship and information about an approach speed to the adjacent ship.

Here, the port monitoring method is based on second viewpoint transformation information used to convert an image having the first view property into an image having a third view property different from the first view property and the second view property. and generating a display image having the third view property from the harbor image having the first view property.

Here, the harbor monitoring method may further include outputting the display image and the eyepiece guide information.

Here, the outputting may include: transmitting the display image and the eyepiece guide information to a terminal to display the display image and the eyepiece guide information using a remotely located terminal; or displaying the display image and the eyepiece guide information;

Here, the artificial neural network may be trained in consideration of a difference between an output image output by inputting a training image to the artificial neural network and a labeling image in which information about the type of object included in the training image is reflected.

Here, the second view may be a view looking down at the sea level from a direction perpendicular to the sea level.

According to another aspect of the present invention, in a method for monitoring the vicinity of a ship performed by a computing means, obtaining a maritime image including an obstacle object corresponding to an obstacle around the ship and a sea object corresponding to the sea having a first view attribute step; generating a segmentation image corresponding to the resolution image and having the first view attribute by performing image segmentation using an artificial neural network trained to output information about a type of an object included in the input image from an input image; The segmentation image includes a first pixel labeled to correspond to the obstacle object and a second pixel labeled to correspond to the sea object -; From the segmentation image having the first view attribute based on first view conversion information used to convert the image having the first view attribute into an image having a second view attribute different from the first view attribute, generating a transform segmentation image having a 2-view attribute; and calculating navigation guide information of the ship based on the transformed segmentation image - the navigation guide information is at least one of information about a distance of the ship to the obstacle and information about an approaching speed of the ship to the obstacle. Including one - including ;, wherein the generating of the transformed segmentation image comprises: obtaining sea level height information reflecting the height of the sea level; updating the first viewpoint conversion information by reflecting the sea level height information; and generating a transformed segmentation image having the second view property from the segmentation image having the first view property based on the updated first view property transformation information. .

Here, the sea level height information may reflect a height from the sea level of a camera installed in the ship.

Here, the acquiring of the sea level height information may include receiving the sea level height information from a sensor installed in the ship to measure the sea level height information.

According to another aspect of the present invention, in a harbor monitoring method performed by a computing means, obtaining a first image having a first view and including a ship object corresponding to a ship and a sea object corresponding to the sea; generating a second image having a top view different from the first view by projecting the first image onto a first plane parallel to the sea level; Calculating berthing guide information based on the second image - The berthing guide information includes at least one of information about a distance to the quay wall of the ship and information about an approach speed of the ship to the quay wall - ; obtaining sea level height information corresponding to a height of a second plane formed at a height different from the first plane and parallel to the first plane; and correcting the calculated eyepiece guide information by reflecting a height difference between the first plane and the second plane.

Here, the height of the second plane may be characterized in that the height of the sea level.

According to another aspect of the present invention, in a harbor monitoring method performed by a computing means, obtaining a first image having a first view and including a ship object corresponding to a ship and a sea object corresponding to the sea; obtaining sea level height information reflecting the height of sea level; In order to project the first image onto a first plane formed parallel to the sea level and parallel to the sea level, viewpoint conversion information for projecting the image onto a second plane parallel to the sea level but formed at a different height from the sea level is used as the sea level height information. Updating based on; converting the first image into a second image having a top view different from the first view by using the updated viewpoint conversion information; And calculating berthing guide information based on the second image - the berthing guide information includes at least one of information about a distance to the quay wall of the ship and information about an approach speed of the ship to the quay wall A port monitoring method comprising -; may be provided.

Hereinafter, a port and vessel monitoring method and apparatus considering sea level will be described.

In this specification, monitoring means not only monitoring, observing, and sensing a certain area or a specific object using various sensors, but also providing the result to the user or providing additional information through calculation based on the result. should be interpreted broadly to include

In the present specification, the port and ship monitoring device is a device for performing port and ship monitoring, and a detailed configuration thereof will be described later.

1 is a diagram of a port monitoring method considering sea level according to an embodiment. Referring to FIG. 1 , the harbor monitoring method may include a harbor image acquisition step (S100), a segmentation image generation step (S200), and a berth guide information acquisition step (S300).

The harbor image acquisition step (S100) may refer to a step in which the monitoring device acquires a harbor image. The segmentation image generation step ( S200 ) may refer to a step of generating a segmentation image from a harbor image by performing image segmentation by the monitoring device. Details of image segmentation will be described later. The eyepiece guide information acquisition step (S300) may refer to a step in which the monitoring device acquires eyepiece guide information based on the segmentation image. Here, the monitoring device may obtain berthing guide information in consideration of sea level, such as sea level height. If the sea level is considered, the accuracy of berthing guide information can be improved. Details of the step of obtaining berthing guide information will be described later.

In the present specification, berthing guide information may be used for berthing of a ship and may refer to information for assisting or guiding users such as a pilot or a captain to berth. For example, the berthing guide information may include the distance from the ship's wharf wall, the approach speed of the ship to the wharf wall, the distance between the ship and other ships, the relative speed between the ship and other ships, the harbor image, and the like. may, but is not limited thereto.

2 is a diagram of a monitoring device according to an embodiment. Referring to FIG. 2 , the monitoring device 10 may include a sensor module 100 , a control module 200 and a communication module 300 .

The sensor module 100 may acquire or sense information about a ship or a ship's surroundings and a port. The sensor module 100 may include an automatic identification system (AIS), an image generation unit, a position measurement unit, a posture measurement unit, a casing/case, and the like.

The image generating unit may generate an image. Images for harbor and vessel monitoring will generally include objects such as the sea, ships, buoys, obstacles, terrain, harbors, sky, and buildings. The image generating unit may include a camera, lidar, radar, ultrasonic detector, and the like. Examples of cameras include, but are not limited to, monocular cameras, binocular cameras, visible light cameras, IR cameras, and depth cameras. Hereinafter, a method of analyzing and monitoring an image acquired through a visible ray camera will be mainly described, but is not limited thereto.

Depending on the image generating unit, a field of view (FOV) and a depth of field (DOF) may vary. The viewing angle may refer to an extent to which the left and right or top and bottom ranges are included in the image, and are generally expressed as angles (degrees). The meaning of having a larger viewing angle may mean generating an image including an area with a wider width horizontally or vertically. The depth of field may mean a distance range recognized as being in focus, and the depth of field may mean that the distance range recognized as being in focus is wide. Hereinafter, the area included in the image is referred to as the imaging area, and the area recognized as being in focus is referred to as the effective area. Since it may be performed based on a part of the area, the area used to perform monitoring is referred to as a monitoring area.

An example of a camera with a large field of view and shallow depth of field is a wide-angle camera. Examples of a camera with a small field of view and a deep depth of field include a high-magnification camera and a zoom camera.

The position measurement unit may measure the position of a component included in a sensor module, such as a sensor module or an image generating unit. For example, the location measurement unit may be a Global Positioning System (GPS). In particular, RTK-GPS (Real-Time Kinematic GPS) may be used to improve the accuracy of position measurement.

The location measurement unit may obtain location information at predetermined time intervals. Here, the time interval may vary depending on the installation location of the sensor module. For example, when the sensor module is installed on a moving object such as a ship, the position measurement unit may obtain position information at short time intervals. On the other hand, when the sensor module is installed in a fixed body such as a port, the position measurement unit may acquire position information at every long time interval. A time interval for acquiring location information of the location measurement unit may be changed.

The posture measurement unit may measure the posture of a component included in a sensor module, such as a sensor module or an image generating unit. For example, the posture measurement unit may be an inertial measurement unit (IMU).

The posture measuring unit may obtain posture information at every predetermined time interval. Here, the time interval may vary depending on the installation location of the sensor module. For example, when the sensor module is installed on a moving object such as a ship, the attitude measurement unit may acquire attitude information at short time intervals. On the other hand, when the sensor module is installed in a fixed body such as a port, the attitude measurement unit may acquire attitude information at every long time interval. A time interval for acquiring attitude information of the attitude measuring unit may be changed.

The casing may protect sensor modules such as an image generating unit, a position measurement unit, and a posture measurement unit.

At least one of an image generating unit, a position measurement unit, and a posture measurement unit may be present inside the casing. The casing can prevent equipment, such as an image generating unit, from being corroded by salt water. Alternatively, the casing may protect the equipment existing therein by preventing or mitigating impact applied thereto.

A cavity may be formed inside the casing to contain an image generating unit or the like therein. For example, the casing may have a hollow rectangular parallelepiped shape, but is not limited thereto and may be provided in various shapes in which an image generating unit or the like may be disposed.

When the image generating unit is disposed inside the casing, an opening may be formed in one region of the casing or a transparent material such as glass may be formed in one region of the casing to secure the field of view of the image generating unit. The image generating unit may capture an image of the ship's periphery and the harbor through the opening or the transparent area.

The casing may be made of a strong material to protect the image generating unit from external impact. Alternatively, the casing may be made of a material such as an alloy for seawater to prevent corrosion due to salt.

The casing may include equipment for removing foreign substances from the image generating unit. For example, foreign substances adhering to the surface of the image generating unit may be physically removed through a wiper included in the casing. Here, the wiper may be provided in a linear or plate shape having the same or similar curvature as the surface so as to be in close contact with the surface to remove foreign substances. As another example, foreign substances may be removed by applying water or washer fluid through a liquid spray included in the casing, or foreign substances may be physically removed using a wiper after application.

The foreign matter removal equipment may be operated manually, but may also be operated automatically. For example, the foreign material removal equipment may be operated at predetermined time intervals. Alternatively, the foreign material removal equipment may be operated using a sensor that detects whether or not a foreign material is attached to the image generating unit. Alternatively, after determining whether a foreign material is captured in the image using the image captured by the image generating unit, the foreign material removing device may be operated when it is determined that the foreign material exists. Here, whether a foreign substance is captured in the image may be determined through an artificial neural network.

One sensor module 100 may include a plurality of identical equipment, such as two or more identical cameras.

The sensor module may be installed without limitation in its position or attitude, such as a lighting tower, crane, ship, etc. in a port, and there is no limit to the number thereof. However, the installation location or number may vary depending on the type and performance of the sensor module. For example, a camera may be installed at an altitude of 15 m or more from the surface of the water for efficient monitoring, or a plurality of cameras may be installed to have different imaging areas. In addition, the position and posture of the sensor module may be manually or automatically adjusted during or after installation.

3 and 4 are diagrams for explaining an installation position of a sensor module according to an embodiment. Referring to FIGS. 3 and 4 , the sensor module 100 may be installed in a fixed location such as a port or land, or may be installed in a moving object such as a ship. Here, when the sensor module 100 is installed on a ship, it can be installed on a ship (hereinafter referred to as a “target ship”) to be monitored as shown in FIG. 4, and berthing or unloading the target ship as shown in FIG. It can also be installed on a third vessel that is not subject to monitoring, such as an auxiliary tugboat. In addition to this, the sensor module may be installed in a drone or the like to monitor a target ship.

Other components of the monitoring device may be installed together with the sensor module or in a separate location.

The control module 200 may perform image segmentation or determine eyepiece guide information. In addition, an operation of receiving various data through the sensor module 100, an operation of outputting various outputs through an output device, an operation of storing various data in a memory or acquiring various data from a memory, and the like are of the control module 200. It can be done by control.

Examples of the control module 200 include a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a Digital Signal Processor (DSP), a state machine, and an on-demand Semiconductors (Application Specific Integrated Circuits, ASICs), radio-frequency integrated circuits (Radio-Frequency Integrated Circuits, RFICs), and combinations thereof may be used.

The communication module 300 may transmit information from the device 10 to the outside or receive information from the outside. The communication module 300 may perform wired or wireless communication. The communication module 300 may perform bi-directional or unidirectional communication. For example, the device 10 may transfer information to an external output device through the communication module 300 and output a control result performed by the control module 200 through the external output device.

The sensor module 100, the control module 200, and the communication module 300 may include a control unit. The control unit may process and calculate various types of information within the module, and may control other components constituting the module. The controller may be physically provided in the form of an electronic circuit that processes electrical signals. A module may physically include only a single control unit, but may also include a plurality of control units. For example, the control unit may be one or a plurality of processors mounted on one computing means. As another example, the control unit may be provided as processors that are mounted on physically separated servers and terminals and collaborate through communication. Examples of the control unit include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a state machine, and an application specific semiconductor (Application Specific Integrated Circuit (ASIC), Radio-Frequency Integrated Circuit (RFIC), and combinations thereof. Hereinafter, various operations or steps disclosed as embodiments of this specification may be interpreted as being performed by the control module 200 or the control unit or under the control of the control module 200 or the control unit unless otherwise stated. .

The sensor module 100, the control module 200, and the communication module 300 may include a communication unit. The modules may transmit and receive information through a communication unit. For example, the sensor module 100 may transmit information acquired from the outside through the communication unit, and the control module 200 may receive the information transmitted by the sensor module 100 through the communication unit. The communication unit may perform wired or wireless communication. The communication unit may perform bi-directional or unidirectional communication.

The sensor module 100, the control module 200, and the communication module 300 may include a memory. The memory may store various processing programs, parameters for performing program processing, or such processing result data. For example, the memory may store data necessary for learning and/or reasoning, learning is in progress or a learned artificial neural network, and the like. Memory is a non-volatile semiconductor memory, hard disk, flash memory, RAM (Random Access Memory), ROM (Read Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), or any other tangible non-volatile recording medium. etc. can be implemented.

The monitoring device may include a plurality of identical modules, such as including two or more sensor modules. For example, one device may include two sensor modules, and each sensor module may further include two cameras.

5 and 6 are diagrams of an embodiment of a monitoring device according to an embodiment.

Referring to FIG. 5 , the monitoring device may include a sensor module 100 and a control module 200 . The sensor module 100 may generate an image through the camera 130 and transmit the image to the control module 200 through the communication unit 110 . In addition, the controller 120 of the sensor module 100 may change the viewpoint of the image by performing a viewpoint conversion to be described later. The control module 200 may receive an image from the sensor module 100 through the communication unit 210, and may perform eyepiece guide information determination and image matching, which will be described later, through the control unit 220. In addition, the control module 200 may transmit analysis results such as eyepiece guide information and matched images to the cloud server through the communication unit 210 . The cloud server may transmit the analysis result received from the control module 200 to a user terminal such as a smartphone, tablet, or PC, or may receive an instruction from the user terminal.

Referring to FIG. 6 , the monitoring device may include the sensor module 100 . The sensor module 100 may generate an image through the camera 130 and transmit the image to a cloud server through the communication unit 110 . In addition, the controller 120 of the sensor module 100 may change the viewpoint of the image by performing a viewpoint conversion to be described later. The cloud server may receive an image from the sensor module 100 and perform eyepiece guide information determination and image matching, which will be described later. In addition, the cloud server may transmit analysis results such as eyepiece guide information and matched images to a user terminal such as a smartphone, tablet, or PC, or may receive an instruction from the user terminal.

The devices shown in FIGS. 2 to 6 are only examples, and the configuration of the devices is not limited thereto.

As an example, the device may include an output module. The output module may output a result of an operation performed by the control module and the like. For example, the output module may output analysis results. The output module may be, for example, a display, a speaker, a signal output circuit, etc., but is not limited thereto. In this case, the information may be output through an output module, in addition to transferring the information to an external output device such as a user terminal and outputting the information by the external output device.

As another example, a device may not include a sensor module. In this case, the control module may perform a monitoring operation such as receiving information from an external sensor device and calculating eyepiece guide information. For example, the control module may determine berthing guide information by receiving information from an AIS, camera, lidar, radar, etc. already installed in a ship or port.

In addition, the steps performed by each component of FIGS. 2 to 6 are not necessarily performed by the corresponding component, but may be performed by other components. For example, in FIG. 5 above, it is described that the controller 120 of the sensor module 100 performs the viewpoint conversion, but the controller 220 of the control module 200 or the cloud server may perform the viewpoint conversion. will be.

Hereinafter, each step and configuration of port and vessel monitoring will be examined in more detail.

As described above, the monitoring method may include a harbor image acquisition step, and the harbor image acquisition step may mean a step in which a monitoring device acquires a harbor image. The harbor image may be generated by an image generating unit included in the monitoring device. Alternatively, the monitoring device may receive a harbor image from the outside. Here, the type of image may be various such as an RGB image, an IR image, a depth image, a lidar image, and a radar image, and is not limited thereto. In addition, not only 2D images but also 3D images are possible.

As described above, the monitoring method may include generating a segmentation image. Segmentation may mean allocating/labeling/matching a characteristic or attribute corresponding to each pixel for each pixel of an image. For example, when a segmented image is generated from an original image by performing segmentation, it can be seen that each pixel of the segmented image is assigned an identification value reflecting the characteristics/attributes of the corresponding pixel on the original image. As a result, the segmented image may be viewed in the form of a matrix to which identification values are assigned. Examples of characteristics/attributes include, but are not limited to, information about the type, location, coordinates, distance, direction, and speed of an object corresponding to a corresponding pixel.

7 is a diagram for describing image segmentation according to an exemplary embodiment. FIG. 7(a) is an image captured by a camera, and FIG. 7(b) is a segmented image generated based on image segmentation (or an image obtained by visualizing the segmented image).

Specifically, based on the segmentation performed using the image of FIG. 7 (a), a segmented image as shown in (b) of FIG. 7 may be generated. In (b) of FIG. 7 , the first pixel area P1 is an area on the image of a pixel corresponding to a ship, and the second pixel area P2 is water (eg, sea, river, lake, etc.), The 3-pixel area P3 is the harbor wall, the 4th pixel area P4 is the topography (eg, mountain, land, etc.), and the 5th pixel area P5 is the area on the image of the pixel corresponding to the sky. Different identification values may be assigned to different pixel regions of the segmented image. For example, an identification value corresponding to a ship may be assigned to the first pixel region P1, and an identification value corresponding to water may be assigned to the second pixel region P2, and other pixel regions may be the same.

In (b) of FIG. 7, it is illustrated that information about the type of object corresponding to each pixel on an image is calculated by performing segmentation, but as described above, information that can be obtained through segmentation is not limited thereto. In this case, different characteristics/attributes may be expressed independently, such as being assigned as separate identification values, or may be reflected and expressed simultaneously, such as being assigned as one identification value.

8 is a table related to allocation of identification values in which information on object types and distances are simultaneously reflected according to an exemplary embodiment. Referring to FIG. 8 , classes may be set in consideration of object type and distance information, and an identification value may be assigned to each class. For example, identification value 2 may be assigned by considering both topography, which is information about the type of object, and short distance, which is information about distance. 8 is an example of a case in which information on type and information on distance are considered together, and other information such as direction information, obstacle movement direction, speed, and navigational aid may also be considered together. In addition, all identification values do not have to include a plurality of pieces of information, nor do they have to include the same type of information. For example, in some cases, a specific identification value includes only type information (for example, identification value 1 does not include information about distance) and other identification values include information about type and distance. It can be expressed in various ways.

Segmentation may be performed using an artificial neural network. Segmentation may be performed through one artificial neural network, or each artificial neural network may perform segmentation using a plurality of artificial neural networks, and a final result may be calculated by combining the results.

An artificial neural network is a type of algorithm modeled after the structure of a human neural network, and may include one or more layers including one or more nodes or neurons, and each node may be connected through a synapse. Data (input data) input to the artificial neural network may be output (output data) through nodes through synapses, through which information may be obtained.

Types of artificial neural networks include a convolution neural network (CNN) that extracts features using a filter and a recurrent neural network (RNN) that has a structure in which the output of a node is fed back to an input. Various structures such as restricted Boltzmann machine (RBM), deep belief network (DBN), generative adversarial network (GAN), and relational networks (RN) can be applied, and there are limitations. It is not.

Before using an artificial neural network, a training step is required. Alternatively, it may be trained using an artificial neural network. Hereinafter, the step of learning the artificial neural network will be expressed as a learning step, and the step of using it as an inference step.

The artificial neural network may be trained through various methods such as supervised learning, unsupervised learning, reinforcement learning, and imitation learning.

9 is a diagram of a learning step and an inference step of an artificial neural network according to an embodiment.

Figure 9 (a) is an embodiment of the learning step of the artificial neural network, in which the untrained artificial neural network receives learning data or training data and outputs output data, and outputs the output data and labeling data. ) can be compared and the artificial neural network can be trained through backpropagation of the error. Training data, output data, and labeling data may be images. Labeling data may include ground truth. Alternatively, the labeling data may be data generated by a user or program.

9(b) is an example of an artificial neural network inference step, in which the trained artificial neural network receives input data and outputs output data. Information that can be inferred in the inference step may vary depending on the information of the learning data in the learning step. In addition, the accuracy of output data may vary according to the degree of learning of the artificial neural network.

As described above, the monitoring method may include obtaining eyepiece guide information. The berthing guide information acquisition step may refer to a step in which the monitoring device acquires berthing guide information based on the segmentation image, but the monitoring method does not necessarily include a segmentation image generation step, and berthing guide information may be obtained directly from the harbor image. It could be.

The berthing guide information may be used for berthing of a ship and may refer to information for assisting or guiding a user such as a pilot or a captain in berthing.

Eyepiece guide information may include information on distance/velocity. Examples of information on distance/velocity include, but are not limited to, an absolute position such as coordinates, a relative position from a specific reference point, a distance from an arbitrary point, a distance range, a direction, an absolute speed, a relative speed, and a speed.

Information on distance/velocity may be estimated based on a predetermined area or point. For example, the distance between the ship and the quay may be estimated by calculating the distance between one point of the ship and one point of the quay, or may be estimated by calculating the shortest distance between one point of the ship and the quay. As another example, the distance between ships may be estimated by calculating the distance between one point of the first ship and one point of the second ship. One point of the ship may correspond to a point of the ship in contact with the sea or may correspond to the bow or stern of the ship, but is not limited thereto.

Information on distance/speed may be expressed as a predetermined distance value, direction value, and speed value. For example, distance information may be expressed as 1m, 2m, etc., direction information may be expressed as 10°, 20°, etc., and speed information may be expressed as 5cm/s, 10cm/s, etc.

Information on distance/speed may be expressed as an index corresponding to a plurality of categories having a certain range. For example, distance information may be expressed as short distance, medium distance, and long distance, direction information may be expressed as left direction, front direction, and right direction, and speed information may be expressed as low speed, medium speed, and high speed. there is. It will also be possible to combine these and express them as left near distance, right far distance, and the like.

10 is a diagram for explaining eyepiece guide information according to an embodiment. Referring to (a) of FIG. 10, berthing guide information is berthing guide information (f ₁ , f ₂ ) between the ship (OBJ1) and the quay (OBJ2) and between the ship (OBJ1) and other ships (OBJ3, OBJ4). Eyepiece guide information (f ₃ , f ₄ ) may be included. Specifically, the berthing guide information (f ₁ , f ₂ ) between the ship (OBJ1) and the quay wall (OBJ2) may include information on the distance/velocity of the ship (OBJ1) to the quay wall (OBJ2), and the ship ( The berthing guide information (f ₃ , f ₄ ) between OBJ1) and other ships OBJ3 and OBJ4 may include information about the distance/velocity of the ship OBJ1 to the other ships OBJ3 and OBJ4. Referring to (b) of FIG. 10, berthing guide information (f ₁ , f ₂ ) between the ship OBJ1 and the quay wall OBJ2 is a boundary region corresponding to the region in contact with the sea surface of the ship OBJ1 and the quay wall. (OBJ2). The boundary area may include not only a line or a point where the ship and the sea surface meet, but also a certain area near the line or point. In addition, the berthing guide information between the ship (OBJ1) and the other ships (OBJ3, OBJ4) may be information between a predetermined area corresponding to the bow / stern of the vessel (OBJ1, OBJ3, OBJ4), where the predetermined area may mean not only the bow/stern points of the ships OBJ1, OBJ3, and OBJ4, but also a certain area near them.

The berthing guide information (f ₁ , f ₂ ) between the ship (OBJ1) and the quay wall (OBJ2) may include two berthing guide information as shown in FIG. 10, but is not limited thereto, and one berthing guide information or Three or more eyepiece guide information may be included. In addition, the berthing guide information (f ₃ , f ₄ ) between the ship (OBJ1) and the other ships (OBJ3, OBJ4) may include one berthing guide information between the two ships as shown in FIG. 10, but is limited thereto It is not possible to include information on two or more berthing guides between two ships. The above-described information may be referred to as unloading guide information when used for unloading of a ship.

11 is a diagram for explaining berthing guide information between a ship and a quay according to an embodiment.

The berthing guide information may be sea level height/sea level information. For example, the berthing guide information f ₅ may include information about the distance/velocity between the ship OBJ1 and the quay wall OBJ2 at sea level.

The eyepiece guide information may be information at ground level (or quay wall level). For example, the berthing guide information f ₆ may include information on the distance/velocity between the ship OBJ1 and the quay wall OBJ2 at the height of the quay wall OBJ2.

The eyepiece guide information may be information at a predetermined height. Here, the predetermined height may be between the height of the sea level and the height of the quay, as in the berthing guide information (f ₇ ) shown in FIG. 11, but is not limited thereto.

The berthing guide information between the ship and the quay may be information (f ₈ ) between the fender and OBJ6 installed on the ship (OBJ1) and the quay (OBJ2). Since the ship (OBJ1) collides with the insect repellent (OBJ6) when berthing or comes into contact with the insect repellent (OBJ6) when anchored, obtaining information (f ₈ ) on the distance / speed between the ship (OBJ1) and the insect repellent (OBJ6) that can be advantageous. In FIG. 11, although the insect repellent OBJ6 is shown as being installed at a higher position than the sea level, at least a portion of the insect repellent OBJ6 may be installed so as to be submerged in the sea OBJ5. In this case, the berthing guide information is at the sea level. It may include information on the distance/velocity between the vessel and the insect repellent.

The berthing guide information between the ship and the other ship may include information about the distance/velocity between the ship and the other ship at sea level. The berthing guide information between the ship and the other ship may include information about the distance/velocity between the ship and the other ship at a predetermined height. Here, the predetermined height may be determined in consideration of the shape of the hull. For example, the predetermined height may be the height of a region where a ship protrudes in a direction of another ship. In this case, it may be advantageous to the berthing guide by more accurately grasping the possibility of collision between ships.

Eyepiece guide information may be calculated based on the image. Here, the image may be an image generated by an image generating unit such as a camera or an image processed through image segmentation therefrom. For example, information on the distance/speed of a ship is calculated based on an image including a ship, sea, and land as objects, or information on the distance/speed of a ship based on a segmentation image generated through segmentation from the image. can be calculated. Examples of objects may include ships, seas, and lands as well as harbors, quay walls, buoys, terrain, sky, buildings, people, and animals.

Hereinafter, an object for estimating eyepiece guide information is referred to as a target object. For example, in the above example, a ship may be a target object. Also, the number of target objects may be plural. For example, when estimating the distance or speed of each of a plurality of ships included in the image, the plurality of ships may be the target object.

Eyepiece guide information may be calculated based on image pixels. As described above, when eyepiece guide information is calculated based on a point, a point on an image may correspond to a pixel. Thus, eyepiece guide information can be calculated based on the spacing between image pixels.

Information on the distance between points may be calculated based on the spacing between pixels. For example, a predetermined distance may be assigned to each pixel interval and a distance between points may be calculated in proportion to the interval between pixels. As another example, distances between pixels may be calculated based on coordinate values of pixels on an image, and distances between points may be calculated based on the distances between pixels.

Information about the speed between points may be calculated based on changes in information about the distance between points. In this case, movement information may be calculated based on a plurality of images or video frames. For example, information on speed between points may be calculated based on a distance between points in a previous frame, a distance between points in a current frame, and a time interval between frames.

12 is a diagram for explaining a method of acquiring eyepiece guide information according to an embodiment. Obtaining eyepiece guide information is a step of acquiring an image generated by an image generating unit such as a camera (FIG. 12(a)), performing image segmentation on the image to obtain a segmented image (or an image obtained by visualizing the segmented image) Generating (Fig. 12 (b)), finding a point for calculating eyepiece guide information based on the segmentation image (Fig. 12 (c)), and calculating eyepiece guide information corresponding to the point can include Although a method of calculating eyepiece guide information from a segmentation image has been described in FIG. 12, this is only an embodiment, and it is possible to find a point based on an image generated by an image generating unit and calculate eyepiece guide information without generating a segmentation image. There will be.

Obtaining eyepiece guide information may include converting a viewpoint of an image. For example, the obtaining of the eyepiece guide information includes obtaining an image generated by an image generating unit, performing viewpoint transformation on the image, and segmenting the viewpoint-converted image to obtain a segmented image. Eyepiece guide information may be calculated for the segmentation image converted from the viewpoint through the step of generating the segmentation image or performing viewpoint conversion on the segmentation image after the step of generating the segmentation image. Hereinafter, viewpoint conversion will be described.

In general, an image generated by an image generating unit such as a camera may appear as a perspective view. Converting this to a top view (planar viewpoint), a side view, or another perspective viewpoint may be referred to as viewpoint conversion. Of course, a top view or side view image may be converted to another view, and the image generating unit may generate a top view image or a side view image, etc. In this case, the view conversion may not need to be performed.

13 is a diagram related to viewpoint conversion according to an exemplary embodiment. Referring to (a) of FIG. 13 , another near perspective image may be acquired through conversion of a perspective view image. Here, the viewpoint conversion may be performed so that the pier OBJ2 is positioned along the horizontal direction (left-right direction on the image) on the image. Referring to (b) of FIG. 13 , a top view image may be obtained through conversion of a perspective view image of a perspective view image. Here, the top view image may be a view looking down at the sea level from a direction perpendicular to the sea level. In addition, as in (a) of FIG. 13 , viewpoint conversion may be performed so that the pier OBJ2 is positioned along the horizontal direction on the image.

Convenience, convenience, and accuracy can be improved when calculating eyepiece guide information through viewpoint conversion. For example, in the case of pixel-based distance calculation, if a top-view image is used, a distance corresponding to an interval between pixels may be the same for the entire image or at least a partial area.

As an example of viewpoint transformation, inverse projective mapping (IPM) may be performed. A 2D image is generated when light reflected from a subject in a 3D space is incident on an image sensor through a lens of a camera, and the relationship between 2D and 3D depends on the image sensor and lens. For example, as shown in Equation 1 can be expressed

[Equation 1]

Here, the matrix on the left side denotes 2D image coordinates, the first matrix on the right side denotes intrinsic parameters, the second matrix denotes extrinsic parameters, and the third matrix denotes 3D coordinates. Specifically, f _x and f _y are focal lengths, c _x and c _y are principal points, and r and t are rotation and translation parameters, respectively.

A viewpoint can be changed by projecting a 2D image onto an arbitrary 3D plane through back-projection transformation. For example, a perspective view image may be converted into a top view image through back projection transformation, or may be converted into another perspective view image.

Internal parameters may be required for viewpoint conversion. As an example of a method for obtaining internal parameters, the Zhang method may be used. The Zhang method is a kind of polynomial model, which acquires internal parameters by taking pictures of a grid having a known grid size from various angles and distances.

Information on the position and/or attitude of the image generating unit/sensor module that captured the image may be required for viewpoint conversion. This information may be obtained from the position measurement unit and the attitude measurement unit.

Alternatively, information on the position and/or posture may be obtained based on the position of the fixed body included in the image. For example, the image generating unit may generate a first image including a target fixture, which is a fixed object such as a terrain or a building, disposed in a first position and/or a first posture at a first viewpoint. Then, at a second viewpoint, the image generation unit may generate a second image including the target fixture. The position of the target fixture on the first image and the position of the target fixture on the second image are compared to calculate the second position and/or the second posture, which is the position and/or posture of the image generating unit at the second viewpoint. can do.

Acquisition of information on a position and/or posture for viewpoint conversion may be performed at predetermined time intervals. Here, the time interval may depend on the installation location of the image generating unit/sensor module. For example, when the image generating unit/sensor module is installed on a mobile body such as a ship, there may be a need to acquire position and/or attitude information at short time intervals. On the other hand, when the image generating unit/sensor module is installed in a fixed body such as a port, information on the position and/or attitude may be obtained at a relatively long time interval or initially obtained only once. When movement and fixation are repeated, such as in a crane, it may be implemented in a manner in which information on position and/or attitude is obtained only after movement. In addition, the time interval for acquiring information on the location and/or posture may be changed.

The above-described viewpoint conversion method is only an example, and viewpoint conversion may be performed in a different way, and the viewpoint conversion information is used for viewpoint conversion, such as the matrix of Equation 1, parameters, coordinates, position and/or posture information, etc. Include the necessary information.

Berthing guide information may be calculated in consideration of sea level height information reflecting the height of sea level.

In this specification, the sea level height information is information related to the height of the sea level, not only the absolute height of the sea level, but also the distance between the sea level and the ground, the distance between the sea level and the quay, and between the sea level and the monitoring device (eg, an image generating unit). It means various information that can change according to the change in the height of the sea level, such as the distance of the object and the length of the object exposed above the sea level.

14 to 20 are views for explaining acquisition of berthing guide information in consideration of sea level height information according to an embodiment. FIGS. 14 and 15 do not include a viewpoint conversion step, and FIGS. 16 to 20 convert viewpoints. It is a drawing for explaining a case including steps.

Referring to FIG. 14 , the step of obtaining berthing guide information according to an embodiment includes correcting the segmentation image generated in the segmentation image generation step (S200) in consideration of sea level height information (S331) and based on the corrected segmentation image It may include calculating eyepiece guide information (S332). Referring to FIG. 15, the step of obtaining berthing guide information according to an embodiment includes calculating berthing guide information based on a segmentation image (S341) and correcting the calculated berthing guide information in consideration of sea level height information (S342). steps may be included.

Referring to FIG. 16 , the step of obtaining berth guide information according to an embodiment is the step of converting the viewpoint of the segmentation image generated in the segmentation image generation step (S200) in consideration of the sea level height information (S301) and based on the converted segmentation image. It may include the step of calculating (S302) eyepiece guide information. In the viewpoint conversion step, the converted image may vary according to the setting of the reference plane/reference height. 17 is a view related to conversion of viewpoints at different reference planes/reference heights. Even in the same image, images converted according to criteria of viewpoint conversion may be different. For example, the left images in (b) and (c) of FIG. 17 are the same, but the images converted according to the criterion at the time of converting the viewpoint are ships for the quay as shown in the right images in (b) and (c) of FIG. 17, respectively. The relative position of may appear different. In this case, since berthing guide information of the target ship is also different, it may be important to set the reference plane/reference height in order to calculate accurate berthing guide information, and this reference plane/reference height may depend on the sea level height. Therefore, the accuracy of the berthing guide information can be increased if the viewpoint conversion is performed in consideration of the sea level height information.

As shown in FIG. 17, the reference plane may be a plane parallel to the sea level, but is not limited thereto.

Viewpoint conversion may be performed by updating viewpoint conversion information according to sea level height information whenever berthing guide information is calculated to consider sea level height information. Alternatively, the viewpoint conversion information may be updated by reflecting sea level height information according to a predetermined time interval. Here, it is not necessary to update all parameters of the view conversion information, but only some of them may be updated.

Referring to FIG. 18, the step of obtaining eyepiece guide information according to an embodiment is the step of correcting the converted segmentation image generated in the viewpoint conversion step (S311) in consideration of sea level height information (S312) and based on the corrected converted segmentation image. and calculating eyepiece guide information (S313). 19 is a view related to image correction for calculation of berthing guide information on sea level/sea level according to an embodiment, wherein a segmentation image is converted from a viewpoint to a reference plane/reference height, and sea level height information is converted into the converted segmentation image. It is to calculate the berthing guide information after taking into account and correcting it. The greater the difference between the sea level height and the reference height, the greater the difference between images before and after correction.

Referring to FIG. 20 , obtaining berthing guide information according to an embodiment includes converting a viewpoint of a segmentation image (S321), calculating berthing guide information based on the converted segmentation image (S322), and sea level information. It may include a step (S323) of correcting the eyepiece guide information calculated in consideration of.

The sea level information considerations of FIGS. 16, 18 and 20 may be merged and performed. 16, 18, and 20 show that the sea level height information is considered only in the viewpoint conversion step (S301), the conversion segmentation image correction step (S312), and the eyepiece guide information correction step (S323), respectively, but the sea level height information is converted to the viewpoint It may be considered in at least one or more steps among the step, transformation segmentation image correction step, and eyepiece guide information correction step. For example, considering the sea level information, the viewpoint conversion step is performed, berthing guide information is calculated therefrom, and then the berthing guide information is corrected by considering the sea level height information again. and will be able to use it.

16 to 20 have been described as obtaining berthing guide information based on the segmentation image, but berthing guide information acquisition is not limited thereto, and berthing guide information may be obtained from a harbor image without generating a segmentation image.

In order to calculate the berthing guide information in consideration of the sea level information, it may be necessary to obtain sea level information beforehand. 21 to 23 are diagrams for examples of obtaining sea level height information according to an embodiment. Hereinafter, various embodiments of sea level height information acquisition will be described based on FIGS. 21 to 23, but sea level height information The acquisition method is not limited thereto.

Sea level height information may be obtained based on characteristics (eg, length, area, etc.) of an object exposed above the sea level. For example, referring to (a) of FIG. 21 , sea level height information may be calculated based on the exposure length h ₁ of the quay wall OBJ2 exposed above the sea OBJ5. If the exposure length (h ₁ ) increases, it can be seen _as a decrease in sea level height, and if it decreases, it can be seen as an increase in sea level height. will be able to derive As another example, referring to (b) and (c) of FIG. 21 , sea level height information may be calculated based on the exposure lengths h ₂ and h ₃ of the object OBJ9 exposed above the sea OBJ5. Here, the height measuring object OBJ9, which is an object OBJ9 necessary for calculating the sea level height information, is not limited to an object such as a pole installed for this purpose as well as an object whose length exposed above the sea changes according to a change in sea level height. As the sea level changes, the exposure length increases from h ₂ to h ₃ or decreases from h ₃ to h ₂ , and by measuring this length, the degree of increase or decrease in sea level can be calculated.

Sea level height information based on the characteristics of the height measurement object may be obtained using an image. If the image includes a height measurement object, it is analyzed to obtain characteristics such as a length of the height measurement object, and based on this, sea level height information may be calculated.

For example, sea level height information may be calculated according to the number of pixels corresponding to the height measurement object. If the number of pixels increases, it can be seen that the height of the sea level decreases because the length of the height measurement object exposed above the sea level is long. Here, a pixel corresponding to the height measurement object may be determined through image segmentation, but is not limited thereto.

The sea level height information may be calculated based on a shaded area corresponding to an invisible sea occluded by a quay wall. For example, when the image generating unit is installed on the quay wall and is disposed facing the sea, the sea area close to the quay wall is blocked by the quay wall and cannot be monitored by the image generating unit. Sea level height information may be obtained based on the characteristics (eg, length, area, etc.) of the shaded area.

22 (a) is a diagram of a shaded area SA1 when the sea level is relatively high, and (b) is a diagram related to a shaded area SA2 when the sea level is relatively low. As the sea level decreases, the area of the shaded area increases, and sea level information can be calculated by measuring it.

The sea level height information may be calculated based on a plurality of images generated by the same type of image generation unit. For example, the sea level height information may be calculated based on a plurality of images generated by a plurality of cameras or based on a plurality of images generated by a single camera.

The sea level height information may be calculated based on an overlap area, which is an overlapping monitoring area between a plurality of images. For example, when the monitoring device includes a plurality of sensor modules/image generating units, a plurality of images may be acquired, and sea level height information may be obtained based on characteristics such as an area of an overlapping region between the plurality of images. can Alternatively, when a plurality of images having different monitoring areas are generated due to rotation of one sensor module/image generating unit, sea level height information may be obtained based on characteristics of an overlapping area between the plurality of images. .

Referring to FIG. 23 , monitoring areas MA1 and MA2 corresponding to the two cameras OBJ7 and OBJ8 exist, and an overlap area OA may exist depending on the installation location or direction of the cameras OBJ7 and OBJ8. there is. As the sea level increases, the area of the overlap area decreases, and as the sea level decreases, the area of the overlap area may increase. Therefore, sea level height information can be calculated by measuring the area of the overlap area.

The overlap area may be determined based on feature points. For example, feature points may be extracted from the first image and the second image, and an overlapping area of the first image and the second image may be determined through matching of the feature points.

The sea level height information may be calculated based on a plurality of images generated by different types of image generating units. For example, the sea level height information may be calculated based on a camera image generated by a camera and a lidar image generated by a lidar, or may be calculated based on a camera image and a radar image generated by a radar, but is not limited thereto. Hereinafter, for convenience of description, images generated by different types of image generating units are referred to as a first type image and a second type image, respectively.

Sea level height information may be calculated through matching between the first type image and the second type image. For example, the location/distance/height of one or more points on the first type image may be obtained based on the second type image to calculate sea level height information.

As a specific example, looking at the case where each of the first type image and the second type image is a camera image and a lidar image, the position/distance/height of one or more points on the camera image is obtained based on the lidar image, and then the camera image Sea level height information can be calculated by fusing with pixel information such as the number of pixels on the image. For example, after finding a pixel on a camera image corresponding to a specific point in a point cloud of a lidar image and calculating the location/distance/height of the pixel based on the lidar image, the pixel and the sea level on the camera image Sea level height information may be calculated by considering the number of pixels between the pixels. In this case, the pixel may be a pixel located higher than the sea level. In addition, the camera image may be an image captured by a camera or an image processed through a viewpoint transformation therefrom.

In the above, a method for calculating sea level height information based on two different types of images has been described, but sea level height information may be calculated based on three or more types of images.

The monitoring device may receive sea level height information from the outside. The monitoring device may receive sea level height information from an external device having sea level height information.

The external device having sea level height information may be a sensor capable of measuring the sea level height. In this case, the monitoring device may receive sea level height information from a separate sensor capable of measuring the sea level height. For example, sea level height information may be calculated by measuring the water depth at a predetermined location with a sensor capable of measuring the water depth, such as an ultrasonic detector. (For example, it would be seen that the sea level increased as the water depth increased.)

An external device having sea level height information may be a vessel traffic service system (VTS system). In this case, the monitoring device may receive sea level height information from the marine traffic control system.

Sea level height information can be calculated by considering the tide. Sea level information can also be calculated since the sea level in a given area can change between high tide and ebb tide and can be predicted over time. For example, if at least one of region and time is input, a function that outputs sea level height information may be set.

The monitoring method may include steps other than the steps described above.

The monitoring method may include a pre-processing step. Preprocessing refers to all kinds of processing performed on images, such as image normalization, image equalization, histogram equalization, image resize, and upscaling to change the resolution/size of the image. and downscaling, cropping, denoising, and the like. Here, noise may include fog, rain, water droplets, sea fog, fine dust, direct sunlight, salt, and combinations thereof, and removing noise means removing or reducing noise components included in an image. can include

Looking at normalization as an example of preprocessing, normalization may mean obtaining an average of RGB values of all pixels of an RGB image and subtracting the average from the RGB image.

Looking at defogging as another example of preprocessing, defogging may mean converting an image of a foggy area to look like an image of a clear area through preprocessing. 24 is a view related to fog removal according to an embodiment. Referring to FIG. 24 , through fog removal, an image of a foggy region as shown in FIG. 24 (a) may be converted into a fog-free image as shown in FIG. 24 (b).

Looking at the removal of water droplets as another example of pre-processing, the removal of water droplets may mean converting an image of water droplets formed on the front of a camera to appear as if the water droplets have been removed through pre-processing.

A pre-processing step may be performed after the image acquisition step. For example, the monitoring method may sequentially include an image acquisition step, a preprocessing step, and a segmentation image generation step, or may sequentially include an image acquisition step, a preprocessing step, and a viewpoint conversion step, but is not limited thereto. Through image preprocessing, acquisition of eyepiece guide information may be facilitated or accuracy of eyepiece guide information may be improved.

The pre-processing step may be performed through an artificial neural network. For example, an image containing noise can be input to an artificial neural network to obtain a denoised image, such as inputting an image of a foggy area into an artificial neural network and converting it to look like an image of a sunny area. can Examples of artificial neural networks include, but are not limited to, GANs.

Alternatively, the preprocessing step may be performed using an image mask. For example, an image of a foggy area can be converted to look like an image of a clear area by applying an image mask. Here, examples of the image mask include a deconvolution filter, a sharpen filter, and the like, and the image mask may be generated through an artificial neural network such as GAN, but is not limited thereto.

The monitoring method may include outputting eyepiece guide information. 25 is a diagram for explaining an eyepiece guide information output step according to an embodiment. Referring to FIG. 25 , the monitoring method may include outputting the eyepiece guide information calculated through the eyepiece guide information acquisition step (S300) (S400).

Eyepiece guide information may be visually output. For example, eyepiece guide information may be output through an output module such as a display.

The step of outputting the eyepiece guide information may include displaying an image acquired using the image generating unit in the image acquisition step. In addition, the step of outputting eyepiece guide information may include displaying various images related to monitoring, such as an image after preprocessing, an image after segmentation, and an image after converting a viewpoint.

26 is a diagram related to an eyepiece guide information output step according to an embodiment. Referring to FIG. 26 , an image and distance/velocity information may be displayed together. As shown in FIG. 26 , the displayed distance/speed information may include the distance and speed between the bow and stern of the target ship and the quay, and the distance between the target ship and other ships.

The step of outputting eyepiece guide information may include providing information to the user in a different way, such as outputting sound or vibration, in addition to a visual display. For example, if there is a risk of collision of the target ship with a quay, other ships, obstacles, etc., or if the approaching speed to the quay at the time of berthing exceeds a standard speed, a warning sound can be output when the ship deviated from its course and navigated.

In the above, the monitoring method based on a single image has been mainly described, but monitoring may be performed based on a plurality of images. When monitoring is performed based on a plurality of images, the total monitoring area of the monitoring device may be increased or the accuracy of monitoring may be improved.

A monitoring method based on a plurality of images may include registering the plurality of images. For example, one matching image may be generated by matching the first image and the second image, and eyepiece guide information may be obtained based on the matching image.

The image matching step may be performed before or after the segmentation image generation step. For example, after generating a matched image by matching a plurality of port images, image segmentation may be performed, or after performing segmentation on each of a plurality of port images, the plurality of segmented images may be matched.

The image matching step may be performed before or after the viewpoint conversion step. For example, a plurality of viewport images may be matched to generate a matched image, and then view conversion may be performed, or view transformation may be performed on each of the plurality of view images, and then the plurality of view converted images may be matched.

The sea level height information may be considered before or after registration of the plurality of images, or both before and after registration. For example, a plurality of images may be corrected in consideration of sea level height information and then matched, or a registered image may be generated by matching a plurality of images and then the registered image may be corrected in consideration of sea level height information.

Image matching may be performed through feature point matching. For example, a matched image may be generated by extracting feature points of the first image and the second image and matching them. In this case, matching information may include feature points and information necessary for feature point matching.

A homography matrix may be required for image matching. In this case, matching information may include a homography matrix. Homography is matching between two arbitrary images on the same plane, and the homography matrix can be expressed as Equation 2.

[Equation 2]

Here, the 3x1 matrices on the left and right sides represent the coordinates of the image, and the 3x3 matrix on the right side represents the homography matrix. A matched image may be generated by calculating a homography matrix between a plurality of images and then performing image matching using the homography matrix.

The above image matching method is only an example, and image matching may be performed by other methods.

In the above, monitoring has been mainly described when the ship is docked, but this can be applied also when the ship is unloaded or when the ship is operating. For example, to assist or guide the safe navigation of a ship, such as detecting another ship or obstacles around the ship, warning of a collision using the distance to them, and their moving speed, or recommending/creating a route, etc. One method can be applied. Alternatively, autonomous navigation may be performed based on such information. In addition, although it has been described that guide information is acquired in consideration of the sea level, it should be widely understood that the surface is not limited to the sea level and the water surface is considered. The above-mentioned berthing guide information may be referred to as unloading guide information when the ship is unloaded and operation guide information when the ship is operating. The step of obtaining berth guide information/obtaining navigation guide information may include the above-described step of obtaining berthing guide information.

27 is a diagram for explaining navigation guide information according to an exemplary embodiment. Referring to FIG. 27, the operation guide information acquisition step may include calculating operation guide information (f ₉ , f ₁₀ ) with another vessel (OBJ3) or an obstacle (OBJ10) such as a buoy during the operation of the target vessel (OBJ1). can

When the monitoring device is installed on a ship, its installation height may change according to the operation of the ship. If the monitoring device is installed in a place where the height does not change, such as a port, the height of the device will be constant unless it is intentionally changed, so the distance from the sea level to the device can be predicted if only the height of the sea level is known. However, if the monitoring device is installed in a place where the height changes, such as a ship, even if the height of the sea level is known, if the draft of the ship cannot be known, it will not be possible to accurately predict the distance from the sea level to the device. For example, if a monitoring device is installed in a port, the distance between the device and the sea level decreases when the height of the sea level increases. might increase. Therefore, in this case, the relative distance between the device and the sea level should be obtained rather than the height of the sea level, and in order to obtain guide information from the monitoring device installed on the ship, the sea level height information needs to be determined by reflecting the draft of the ship. This point of view may also be applied to the case of acquiring eyepiece guide information.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computing means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

In the above, the configuration and characteristics of the present invention have been described based on the examples, but the present invention is not limited thereto, and various changes or modifications can be made within the spirit and scope of the present invention to those skilled in the art. It is obvious, and therefore such changes or modifications are intended to fall within the scope of the appended claims.

10: monitoring device
100: sensor module
110: communication department
120: control unit
130: camera
200: control module
210: communication department
220: control unit
300: communication module

Claims (16)

In the ship surroundings monitoring method performed by a computing means,
obtaining a first image having a first view;
obtaining sea level information reflecting sea level;
In order to project the first image on a first plane formed parallel to the sea level at a height of the sea level, viewpoint conversion information for projecting an image on a second plane formed at a height different from the height of the sea level but parallel to the sea level Updating based on the sea level height information;
converting the first image into a second image having a second view different from the first view by using the updated viewpoint conversion information; and
Calculating surrounding monitoring information based on the second image, wherein the surrounding monitoring information includes at least one of information about a distance of the vessel to neighboring vessels and information about a moving speed of the neighboring vessels; including
How to monitor the ship's perimeter. According to claim 1,
The sea level height information reflects the height from the sea level of the camera installed in the ship.
How to monitor the ship's perimeter. According to claim 1,
The sea level height information reflects the draft of the ship
How to monitor the ship's perimeter. According to claim 1,
The obtaining of the sea level height information includes receiving the sea level height information from a sensor installed in the ship to measure the sea level height information.
How to monitor the ship's perimeter. According to claim 1,
The surrounding monitoring information is calculated based on a border area, which is an area in contact with the sea level of the surrounding vessel.
How to monitor the ship's perimeter. According to claim 5,
The information on the distance to the neighboring vessel corresponds to the distance to the vessel in the boundary area,
The information on the moving speed of the surrounding vessels corresponds to the moving speed of the boundary area.
How to monitor the ship's perimeter. According to claim 5,
The surrounding monitoring information is based on a first point corresponding to the bow of the neighboring vessel and a second point corresponding to the stern of the neighboring vessel, wherein the first point and the second point are included in the boundary area. produced
How to monitor the ship's perimeter. According to claim 7,
The information on the distance to the neighboring vessel corresponds to the distance of the first point and the second point to the vessel,
The information on the moving speed of the neighboring vessel corresponds to the moving speed of the first point and the second point.
How to monitor the ship's perimeter. According to claim 1,
The acquiring of the sea level height information may include calculating the sea level height information based on an area where a height measurement object included in the first image is exposed above the sea level.
How to monitor the ship's perimeter. According to claim 1,
The obtaining of the sea level height information includes receiving the sea level height information from a vessel traffic service system (VTS system).
How to monitor the ship's perimeter. According to claim 1,
Converting the viewpoint of the first image using second viewpoint conversion information used to convert the image having the first view attribute into an image having a third view attribute different from the first view attribute and the second view attribute Generating a display image having the third view property through
How to monitor the ship's perimeter. According to claim 11,
Outputting the display image and the surrounding monitoring information; further comprising
How to monitor the ship's perimeter. According to claim 12,
The outputting step is
transmitting the display image and the surrounding monitoring information to a terminal to display the display image and the surrounding monitoring information using a remotely located terminal; and
displaying the display image and the surrounding monitoring information; containing at least one of
How to monitor the ship's perimeter. According to claim 1,
Characterized in that the second view is a view looking down at the sea level in a direction perpendicular to the sea level
How to monitor the ship's perimeter. In the ship surroundings monitoring method performed by a computing means,
obtaining a first image having a first view;
generating a second image having a second view different from the first view by projecting the first image onto a first plane parallel to the sea level;
Calculating surrounding monitoring information based on the second image, wherein the surrounding monitoring information includes at least one of information about a distance of the vessel to neighboring vessels and information about a moving speed of the neighboring vessels;
obtaining sea level height information corresponding to a height of the sea level formed at a height different from the first plane; and
Comprising the step of correcting the calculated surrounding monitoring information by reflecting the height difference between the first plane and the sea level,
How to monitor the ship's perimeter. A computer-readable recording medium recording a program for executing the method according to any one of claims 1 to 15 in a computer.

Images