KR20210055904A - Apparatus for electronic surveillance of voyage - Google Patents

Abstract

Disclosed is an electronic device for monitoring voyage, which uses an image of the surrounding of a ship taken to distinguish and detect an obstacle and a suspicious object around a ship, and accurately determine a risk of collision with the ship. The electronic device for monitoring voyage according to an embodiment of the present invention comprises: an image photographing unit for photographing the surrounding of a ship; and an object detecting unit for detecting an object corresponding to a marine object in the image. The object detecting unit includes: a first object detecting unit for detecting a first object from the image by a semantic segmentation-based deep learning model which finds meaning by a pixel unit; a second object detecting unit for detecting a second object from the image by an area-based object detecting deep learning model which detects a box-shaped object; and a determining unit for distinguishing and determining an obstacle and a suspicious object from the image, based on the first object and the second object.

Description

Electronic navigation monitoring device {APPARATUS FOR ELECTRONIC SURVEILLANCE OF VOYAGE}

The present invention relates to an electronic navigation monitoring device, and more particularly, an electronic navigation monitoring capable of distinguishing and detecting an obstacle and a suspicious object around the vessel using an image captured around the vessel and accurately determining the risk of a vessel collision. It relates to the device.

In the case of a ship's operation, the navigator performs the watch-to-see service in preparation for a crash accident, and is supported by radar and electronic chart equipment. However, it takes a lot of time to manually check a number of navigational equipment and quickly respond to a dangerous situation until the collision situation is initially identified and the evasion maneuver is performed. In order to prevent ship collision accidents in advance, there is a need for a system that supports effective identification of collision situations with dozens of ships around the ship in a short time.

Conventionally, there has been a system that prevents a ship from colliding using an AIS (Automatic Identification System) or a radar, but the conventional ship collision avoidance system does not detect ships that are not registered in AIS, or even if it detects unregistered ships, the ship's predictions There is a problem in that the navigator judges the risk of a collision of the ship through background knowledge and experience because the location of the collision and the path of movement of other ships could not be provided.

An object of the present invention is to provide an electronic navigation monitoring device capable of distinguishing and detecting an obstacle and a suspicious object around a ship by using an image captured around a ship and accurately determining the risk of a ship collision.

The problem to be solved by the present invention is not limited to the problems mentioned above. Other technical problems not mentioned will be clearly understood by those of ordinary skill in the art from the following description.

An electronic navigation monitoring device according to an embodiment of the present invention includes an image photographing unit for photographing an image around a ship; And an object detection unit that detects an object corresponding to a marine object in the image. The object detector may include: a first object detector configured to detect a first object from the image by means of a semantic division-based deep learning model that finds a meaning in a pixel unit; A second object detection unit detecting a second object from the image by using a region-based object detection deep learning model that detects a box-shaped object; And a determination unit that distinguishes and determines an obstacle and a suspicious object in the image based on the first object and the second object.

The determining unit determines an object commonly included in the first object and the second object as the obstacle; In addition, an object included in only one of the first object and the second object may be determined as the suspicious object.

The image capturing unit may include a visible light camera for capturing a visible image and a thermal camera for capturing a thermal image. The object detector may be configured to detect the first object and the second object from an image obtained by combining the visible image and the thermal image.

The electronic navigation monitoring apparatus according to an embodiment of the present invention may further include a monitoring control unit for controlling the image photographing unit and the object detection unit. The object detection unit may further include an analysis unit that calculates the center position and size of the suspicious object.

The monitoring control unit controls the image capture unit to generate an enlarged image of the suspect object by applying a zoom function to the size of the suspect object according to a center position and size, and extracts the suspect object from the enlarged image to determine whether there is an obstacle. Can be judged.

Electronic navigation monitoring device according to an embodiment of the present invention includes a three-axis driving unit for controlling the photographing direction of the image photographing unit in the three-axis direction; And a stability control unit driving the three-axis drive unit to maintain the direction angle indicated by the monitoring control unit.

The object detection unit may further include a marine object extraction unit excluding an object within a land area from among the objects extracted from the image.

The monitoring control unit may compare an obstacle detected by a radar with an obstacle detected from the image, and display a case where both the radar and the image are detected as obstacles and an obstacle detected only in the image.

An electronic navigation monitoring apparatus according to an embodiment of the present invention includes: a collision prediction unit for predicting a collision with an obstacle of the ship based on the image; And a display unit that displays a collision prediction result of the collision prediction unit.

The collision prediction unit may include a second line extraction unit for extracting at least one other line from the image; A movement path detector configured to detect a movement path and speed of the other ship; And a collision risk prediction unit predicting a collision risk between the ship and the other ship based on the moving path and speed of the other ship.

The collision risk prediction unit calculates the angular velocity of the other ship using the moving path and speed of the other ship, predicts the future movement path of the other ship using the speed and angular speed of the other ship, and The collision probability and collision time between the other ship and the ship may be calculated by using the future movement path of the ship.

According to an embodiment of the present invention, there is provided an electronic navigation monitoring device capable of distinguishing and detecting an obstacle and a suspicious object around a ship using an image captured around a ship, and accurately determining the risk of a ship collision.

The effects of the present invention are not limited to the above-described effects. Effects not mentioned will be clearly understood by those of ordinary skill in the art from the present specification and the accompanying drawings.

1 is a block diagram of an electronic navigation monitoring device according to an embodiment of the present invention.
2 is an exemplary view of an image photographing unit constituting an electronic navigation monitoring device according to an embodiment of the present invention.
3 is a block diagram of an object detection unit constituting an electronic navigation monitoring device according to an embodiment of the present invention.
4 is a conceptual diagram illustrating a function of an object detection unit constituting an electronic navigation monitoring device according to an embodiment of the present invention.
5 is a flowchart illustrating an operation of an electronic navigation monitoring device according to an embodiment of the present invention.
6 to 8 are exemplary views for explaining the operation of the electronic navigation monitoring device according to an embodiment of the present invention.
9 is a block diagram of a collision prediction unit constituting an electronic navigation monitoring device according to an embodiment of the present invention.
10 is an exemplary diagram of information displayed by a display unit constituting an electronic navigation monitoring device according to an embodiment of the present invention.
11 is an exemplary view of a screen displayed by a display unit constituting an electronic navigation monitoring device according to an embodiment of the present invention.

Other advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments to be described later in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, and the present invention is only defined by the scope of the claims. Even if not defined, all terms (including technical or scientific terms) used herein have the same meaning as commonly accepted by universal technology in the prior art to which this invention belongs. A general description of known configurations may be omitted so as not to obscure the subject matter of the present invention.

1 is a block diagram of an electronic navigation monitoring device according to an embodiment of the present invention. Referring to FIG. 1, an electronic navigation monitoring device 100 according to an embodiment of the present invention includes an image capture unit 110, an object detection unit 120, a collision prediction unit 130, a monitoring control unit 140, and a display unit ( 150), may include a stability control unit 160 and a three-axis drive unit 170.

2 is an exemplary view of an image photographing unit constituting an electronic navigation monitoring device according to an embodiment of the present invention. Referring to FIGS. 1 and 2, the image photographing unit 110 may be installed on a ship to capture images around the ship from the front, side, and rear of the ship.

The image capture unit 110 is provided with three or more cameras installed in the front, side, and rear of the ship, or one or two or more wide-angle cameras provided in one or two or more directions of the front, side, and rear of the ship. Can be provided. The image capturing unit 110 may be provided with a single 360° camera or a VR camera provided at a specific location of the ship.

The image capturing unit 110 may include a visual camera 112 for capturing a visible image and a thermal camera 114 for capturing a thermal image. For example, the visible light camera 112 may be a Complementary Metal Oxide Semiconductor (CMOS) camera or a Charge Coupled Device (CCD) camera.

3 is a block diagram of an object detection unit constituting an electronic navigation monitoring device according to an embodiment of the present invention. 4 is a conceptual diagram illustrating a function of an object detection unit constituting an electronic navigation monitoring device according to an embodiment of the present invention.

1, 3, and 4, the object detection unit 120 may detect an object corresponding to a marine object from an image captured by the image capture unit 110. The object detection unit 120 may include a first object detection unit 121, a second object detection unit 122, a marine object extraction unit 123, a determination unit 124, and an analysis unit 125.

The first object detector 121 may detect a first object from an image by using a semantic segmentation-based deep learning model (eg, SEGNET) to find a meaning in a pixel unit. The first object detector 121 may detect first objects from an image obtained by combining the visible image 10 and the thermal image 20.

The second object detection unit 122 detects a box-shaped object corresponding to a box of a specific location and size by using a region-based object detection deep learning model (eg, YOLO). Can be detected. The second object detector 122 may detect second objects from an image obtained by combining the visible image 10 and the thermal image 20.

In an embodiment, in order to accurately detect marine objects even at night, marine objects may be detected using an image that is a combination of three 2D visible images and 2D thermal images. The marine object extraction unit 123 may extract marine objects by excluding objects in the land area from among the objects extracted from the image.

The determination unit 124 is based on the first objects 30 detected by the first object detection unit 121 and the second objects 40 detected by the second object detection unit 122. Obstacle) and Suspect Object can be distinguished and judged.

The determination unit 124 determines objects commonly included in the first objects 30 detected by the first object detection unit 121 and the second objects 40 detected by the second object detection unit 122. It can be determined as an obstacle 50.

The determination unit 124 may determine an object included in only one of the first object and the second object as the suspicious object 60. The analysis unit 125 may calculate the center position and size of the suspect object 60.

That is, the determination unit 124 detects an obstacle through an area corresponding to the intersection of the first objects detected by the first object detection unit 121 and the second objects detected by the second object detection unit 122 However, even if the two detection techniques, semantic division-based object detection and area-based object detection, do not determine that the object is a sea object in common, the area detected as an obstacle by either semantic division-based object detection or area-based object detection can be detected as a suspicious object. I can.

The monitoring control unit 140 may display a monitoring situation on the display unit 150, perform a function of receiving a user's command, and control the image capture unit 110 and the object detection unit 120 for maritime monitoring. .

The monitoring control unit 140 may control the image capturing unit 110 to generate an enlarged image of the suspicious object by applying a zoom function according to the center position and size of the suspicious object detected by the object detection unit 120. The monitoring control unit 140 may accurately determine whether there is an obstacle by extracting a suspicious object from the enlarged image.

The three-axis driving unit 170 may control the photographing direction of the image capturing unit 110 in the three-axis direction. The three-axis driving unit 170 may include at least three motors. The stability control unit 160 may drive the three-axis drive unit to maintain the direction angle indicated by the monitoring control unit 140.

The stability control unit 160 may include one or more inertial measurement units, and control the three-axis driving unit 170 to obtain an image without shaking a horizontal line or a specific object even when a ship movement occurs.

The stability control unit 160 reads the current angular velocity from the inertial measurement unit (IMU) mounted on the camera to minimize the motion of the image capture unit 110, and maintains a specific direction angle on a fixed coordinate system indicated by the monitoring control unit. The direction of (110) can be controlled.

The monitoring control unit 140 compares the obstacle detected by the radar and the obstacle detected from the image, and distinguishes between the case detected as an obstacle from the radar and the image and the obstacle detected only in the image, and displays it on the display unit 150. I can.

The collision prediction unit 130 may predict a collision with an obstacle of the ship based on the image captured by the image capture unit 110. The display unit 150 may display a collision prediction result of the collision prediction unit 130.

5 is a flowchart illustrating an operation of an electronic navigation monitoring device according to an embodiment of the present invention. 6 to 8 are exemplary views for explaining the operation of the electronic navigation monitoring device according to an embodiment of the present invention.

1, 5 to 8, the monitoring control unit 140, the object detection unit 120 to perform the specimen detection again using the zoom function of the image capturing unit 110 in order to check the uncertain information related to the suspicious object. ) Can be controlled.

In an embodiment, when a monitoring function is commanded by the monitoring control unit 140, an omnidirectional image is acquired along the horizontal line in the forward direction by a panoramic scan of the image capturing unit 110, and the obstacles O1 , O2) and suspicious objects (SO1, SO2, SO3) are detected (S10, S20).

Thereafter, when the scan direction of the image photographing unit 110 is changed and returned to the reverse direction, the camera zoom function of the image photographing unit 110 is used based on the center of the suspicious object (S01, S02, S03) and the size of the suspicious object. An additional obstacle O3 can be detected through a large enlarged image (S30, S40, S50).

As for the obstacle information, a probability of an obstacle in a future collision prediction system may be applied as 100%, and a probability of a suspicious object being an obstacle may be set to a value less than 100%. According to an embodiment of the present invention, not only an obstacle but also a suspicious object can be utilized for predicting a collision of a ship.

According to an embodiment of the present invention, by providing information on visible maritime conditions, it is possible to improve safety and reduce ship operating costs, and to reduce the dependence of observers to prevent accidents due to human error.

In addition, according to an embodiment of the present invention, information provided by various navigation equipment (Inertial Navigation System, AIS, Radar), as well as current and past visible and thermal image information and collision prediction information about the situation around the ship in all directions. Can provide.

9 is a block diagram of a collision prediction unit constituting an electronic navigation monitoring device according to an embodiment of the present invention. Referring to FIGS. 1 and 9, the collision prediction unit 130 may include another ship extraction unit 132, a movement path detection unit 134, and a collision risk prediction unit 136.

The other line extracting unit 132 may extract at least one other line (an obstacle or a suspicious object) from the image acquired by the image capturing unit 110.

The movement path detection unit 134 may detect the movement path and speed of the other ship extracted from the image. In an embodiment, the movement path detection unit 134 may be implemented with a Kanade-Lucas-Tomasi algorithm or the like.

The collision risk prediction unit 136 may predict a collision risk between a ship and another ship based on the moving path and speed of the other ship.

Specifically, the collision risk prediction unit 136 may calculate the angular velocity of the other ship using the moving path and speed of the other ship, and predict the future movement path of the other ship using the speed and angular velocity of the other ship.

In addition, the collision risk prediction unit 136 may calculate the angular velocity of the vessel using the moving path and speed of the vessel (own vessel), and predict the future moving path of the vessel using the velocity and angular velocity of the vessel.

The collision risk prediction unit 136 may calculate a collision probability and a collision time between the other ship and the ship by using the predicted future movement path of the other ship and the future movement path of the ship. In this case, the collision risk prediction unit 136 may determine that the collision probability between the other ship and the ship decreases as the collision time between the other ship and the ship is delayed.

According to an embodiment of the present invention, a collision of a ship can be predicted using information on a ship selected by a radar sensor, and roll, pith, and yaw information obtained through the ship's inertial navigation device is used. Thus, it is possible to detect the inclined state of the ship.

In addition, according to an embodiment of the present invention, an obstacle and a suspicious object are detected using an object detection or semantic segmentation technology based on an image acquired by the image capturing unit 110, and The location and size can be detected using feature-based detection technologies (SIFT, SURF, HOG, Ferns, LBP, etc.).

In addition, object tracking technology may be used to determine the state change of other ships identified in the image. As the object tracking technology, an algorithm such as the Kanade-Lucas-Tomasi method may be used. For example, by detecting image similarity between other lines detected in an image and other lines detected in a previous image, the other line with the highest similarity can be associated. If multiple images are used, information on how a specific other line has moved over time. Can be obtained. In addition, in order to prevent a case where the other line that has not been detected at a specific time point exists in the image before or after the position movement is interrupted, a Kalman filter technique that estimates the location of the other line may be used. In this way, tracking information of other ships extracted from the image may be used to predict a future path. Specifically, the other ship is assumed to exist only when it moves forward or moves to the port or starboard. The future travel path can be predicted through the past travel path.

In addition, the estimated location of other ships has inherent uncertainty, and this uncertainty may increase in magnitude over time. Specifically, if the speed of the other ship is high, it may be located further forward in the direction of the other ship's travel than the estimated position of the other ship, and if the speed of the other ship is low, it may be located further in the direction of travel of the other ship than the estimated position of the other ship have. In addition, the uncertainty may be located to the left or right of the estimated position of the other ship according to the angular speed of the other ship. When all positions due to uncertainty are considered when estimating the position of other ships, the processing speed may be slowed due to a large amount of calculation, and thus the processing may be replaced with an approximation function. In addition, the probability of the predicted position of the other ship may have 100% from the estimated position and may decrease as the distance from the estimated position increases. Since the uncertainty increases over time in estimating the location of other ships, the standard deviation may increase as the distance from the current point increases.

The collision probability can be calculated by using the position distribution of the other ships and the position distribution of the own ship over time. Specifically, a maximum value of a result of multiplying the position distribution of each other ship and the position distribution of the own ship at a specific time point may be a collision probability at the time point. In addition, the largest value among the collision probability of each other ship according to time may be set as the collision probability of the other ship. In addition, if all other ships are arranged in the order of the high collision probability, the expected collisions can be prioritized based on the speeds and angular speeds of the own ship and other ships at the current point in time.

The display unit 150 may display a result of determination of the collision prediction unit 130. For example, the display unit 150 may be implemented as an LCD monitor installed on a ship to display a collision probability and a collision time between another ship and the ship determined by the collision prediction unit 130. In addition, the display unit 150 may display a maritime map in which the surrounding environment of the ship is displayed.

The display unit 150 displays the movement path of the other ship and the ship determined by the collision prediction unit 130 and the future movement path on the maritime map, and displays the predicted position of collision between the other ship and the ship on the maritime map, and The collision probability and collision time of other ships and ships can be displayed at the predicted position of collision.

The electronic navigation monitoring device 100 may further include a communication unit (not shown). The communication unit may receive AIS information from the outside. The communication unit may be implemented as a wireless communication module or the like, and may be, for example, a Wi-Fi module. However, the present invention is not limited thereto, and may be implemented with various wireless communication modules or wired communication modules.

The other line extraction unit 132 may extract other lines not registered in the AIS information by comparing the AIS information received from the communication unit with the image obtained by the image capturing unit 110. In addition, the movement path detection unit 134 can detect the movement path and speed of other ships not registered in AIS information, and the collision risk prediction unit 136 is based on the movement path and speed of other ships not registered in AIS information. Thus, it is possible to predict the collision between the ship and other ships not registered in the AIS information.

In the case of other ships not registered in the AIS information, it is difficult to predict the collision with the ship. However, according to the electronic navigation monitoring device 100 of the present invention, it is possible to predict the collision between the ships and other ships not registered in the AIS information. Accordingly, a collision between a ship and another ship registered through AIS is prevented, and a collision between a ship not registered in AIS by the electronic navigation monitoring device 100 of the present invention is prevented, and a ship collision prevention system using AIS Can be supplemented.

10 is an exemplary diagram of information displayed by a display unit constituting an electronic navigation monitoring device according to an embodiment of the present invention. 1 and 10, the display unit 150 may display a display screen as shown in FIG. 10. For example, a future movement path of a ship (ownership) may be displayed in blue, and a future movement path of another ship may be displayed in black or purple. Among other ships, other ships that have a risk of collision with the ship may be marked in purple, and other ships that do not have a risk of collision may be marked in black. In addition, the predicted position of collision between the other ship and the ship may be displayed in red, and the probability of collision between the other ship and the ship and the collision time may be displayed at the corresponding position. In addition, for efficient information transmission, the identified collision information may be overlaid on an image and displayed.

11 is an exemplary view of a screen displayed by a display unit constituting an electronic navigation monitoring device according to an embodiment of the present invention. 1 and 11, a panoramic view portion 151 displays a panoramic image obtained by rotating the image capturing unit 110 by 360°. The panoramic image may be displayed based on a direction such as the heading of the ship or the direction of the forward north.

In the embodiment of FIG. 11, the detected object 152 is displayed as a dotted line in the panoramic view, and predicted distance information and AIS information may be additionally displayed. In addition, by showing the capture status 154 currently being scanned in real time, a past image and a current image can be distinguished. In the panoramic view, the measured image may be corrected and displayed using an image stitching technique so that the horizontal line is parallel to the horizontal of the image. The portion 153 indicated by a mouse, joystick, or the like on the panoramic view may be enlarged and displayed in the zoom view portion 155.

The collision prediction chart part 156 may provide collision information of a ship. Obstacle detection information (157, 158, 159) compares obstacles detected by AIS and Radar (other ships) and obstacles detected based on image vision. Cases and cases detected only in image vision may be displayed separately.

The zoom view part 155 is selected when selecting the image being photographed according to the zoom mode at the bottom, the part where the cursor is located in the panorama, the image of the cursor position on the collision prediction chart, and the detected obstacle. You can display an enlarged image of the content. When using the cursor position, zoomed images can be displayed using the function of the mouse wheel or joystick button.

Panoramic view and capture view can be selected from a visible image alone, a thermal image alone, or an overlay of a thermal image on a visible image. When selecting the Historic Run mode, it is also possible to check the past situation by calling the past image information and collision prediction information according to the time slide bar at the bottom. Therefore, it is also possible to check the image and collision prediction information stored in the past.

Conventional ship collision prevention system using AIS or radar to prevent collision of ships has a problem in that it is difficult to identify ships not registered in AIS, or it is not possible to provide a collision predicted position or movement path of the ship, but the present invention According to an embodiment, an image of the periphery of a ship is acquired by an image pickup unit installed on a ship, and accordingly, a collision of a ship is predicted to provide a ship collision probability and a ship collision time. Accordingly, according to the electronic navigation monitoring device according to the present invention, it is possible to effectively prevent a collision of a ship, and to provide information on the surrounding situation of the ship in real time. According to various embodiments of the present invention as described above, information on the movement path and the predicted position of collision of other ships is accurately provided, and the risk of collision can be determined even for other ships not registered in the AIS, so that the collision of ships can be more effectively prevented. I can.

At least some of the methods according to the embodiments of the present invention may be written in a program that can be executed on a computer, and may be implemented in a general-purpose digital computer that operates the program using a computer-readable recording medium. Computer-readable recording media include volatile memories such as SRAM (Static RAM), DRAM (Dynamic RAM), SDRAM (Synchronous DRAM), Read Only Memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Nonvolatile memory such as Electrically Erasable and Programmable ROM (EEPROM), flash memory device, phase-change RAM (PRAM), magnetic RAM (MRAM), resistive RAM (RRAM), ferroelectric RAM (FRAM), floppy disk, hard disk, or The optical reading medium may be, for example, a storage medium such as a CD-ROM or a DVD, but is not limited thereto.

It should be understood that the above embodiments have been presented to aid the understanding of the present invention, and do not limit the scope of the present invention, and various deformable embodiments are also within the scope of the present invention. The scope of protection of the present invention should be determined by the technical spirit of the claims, and the scope of protection of the present invention is not limited to the literal description of the claims itself, but the technical value extends to the invention of an equal scope. It should be understood that it will be.

10: visible image 20: thermal image
110: image capture unit 112: visible light camera
114: thermal imaging camera 120: object detection unit
121: first object detection unit 122: second object detection unit
123: marine object extraction unit 124: determination unit
125: analysis unit 130: collision prediction unit
132: other ship extraction unit 134: moving path detection unit
136: collision risk prediction unit 140: monitoring control unit
150: display unit 160: stability control unit
170: 3-axis drive unit

Claims (10)

An image photographing unit for photographing images around the ship; And
Including an object detection unit for detecting an object corresponding to the marine object in the image,
The object detection unit,
A first object detection unit that detects a first object from the image by means of a semantic division-based deep learning model that finds meaning in units of pixels;
A second object detection unit detecting a second object from the image by using a region-based object detection deep learning model that detects a box-shaped object; And
Electronic navigation monitoring apparatus comprising a determination unit for determining by classifying an obstacle and a suspicious object in the image based on the first object and the second object. The method of claim 1,
The determination unit,
Determining an object commonly included in the first object and the second object as the obstacle; And
An electronic navigation monitoring device that determines an object included in only one of the first object and the second object as the suspicious object. The method of claim 1,
The image capturing unit includes a visible light camera for capturing a visible image and a thermal camera for capturing a thermal image,
The object detection unit is configured to detect the first object and the second object in an image obtained by combining the visible image and the thermal image. The method of claim 1,
Further comprising a monitoring control unit for controlling the image capturing unit and the object detection unit,
The object detection unit further includes an analysis unit that calculates the center position and size of the suspicious object,
The monitoring control unit controls the image capture unit to generate an enlarged image of the suspect object by applying a zoom function to the size of the suspect object according to a center position and size, and extracts the suspect object from the enlarged image to determine whether there is an obstacle. Electronic navigation monitoring device to determine the. The method of claim 1,
A three-axis driving unit for controlling a photographing direction of the image capturing unit in a three-axis direction; And
Electronic navigation monitoring device further comprising a stability control unit for driving the three-axis driving unit to maintain the direction angle indicated by the monitoring control unit. The method of claim 1,
The object detection unit further comprises a marine object extraction unit excluding objects in the land area from among the objects extracted from the image. The method of claim 1,
The monitoring control unit compares the obstacle detected by the radar with the obstacle detected from the image, and displays a case where both the radar and the image are detected as obstacles and the obstacle detected only in the image. . The method of claim 1,
A collision prediction unit for predicting a collision with an obstacle of the ship based on the image; And
Electronic navigation monitoring device further comprising a display unit for displaying the collision prediction result of the collision prediction unit. The method of claim 8,
The collision prediction unit,
Another line extraction unit for extracting at least one other line from the image;
A movement path detector configured to detect a movement path and speed of the other ship; And
Electronic navigation monitoring apparatus comprising a collision risk prediction unit for predicting the risk of collision between the ship and the other ship based on the moving path and speed of the other ship. The method of claim 9,
The collision risk prediction unit,
The angular velocity of the other ship is calculated using the moving path and speed of the other ship, and the future movement path of the other ship is predicted using the speed and angular velocity of the other ship,
An electronic navigation monitoring device that calculates a collision probability and a collision time between the other ship and the ship by using the future movement path of the other ship and the future movement path of the ship.

Images