System and method for maritime boundary monitoring based on video analysis and electronic charts

Abstract

The present invention relates to a system and method for maritime boundary monitoring. Generally, surveillance personnel monitor images captured by fixed cameras installed on land 24 hours a day, which makes the acquisition and utilization of image information inefficient and limited. As a result, a large number of maritime boundary surveillance personnel are required, and there are concerns about blind spots due to the accumulated fatigue of each surveillance personnel. Furthermore, when an unidentified vessel appears, the surveillance personnel must be dispatched to the site to conduct a face-to-face investigation, which is inefficient in terms of personnel and costs. To solve these problems, the present invention provides a maritime boundary monitoring system and method based on video analysis and electronic nautical charts that can be operated efficiently at low cost by automatically analyzing camera and radar images to minimize the intervention of maritime boundary surveillance personnel, and when an unidentified vessel appears, by using unmanned vessels and drones to obtain images of the vessel and identifying it using visual search methods, thereby reducing the need for on-site dispatch and face-to-face investigation.

Description

[Technical Field]

[0001] The present invention relates to a system and method for maritime boundary monitoring. More specifically, the present invention relates to a system and method for maritime boundary monitoring based on video analysis and electronic charts. This system solves the problems of conventional maritime boundary monitoring systems and methods, which generally require observers to monitor images obtained from fixed cameras installed on land 24 hours a day, resulting in inefficient and limited acquisition and utilization of image information. As a result, a large number of maritime boundary monitors are required, and there are concerns about blind spots due to fatigue among observers. In addition, when an unidentified vessel appears, the observer must be dispatched to the site to conduct a face-to-face investigation, which is inefficient in terms of personnel and costs. To solve these problems, the present invention relates to a maritime boundary monitoring system and method based on video analysis and electronic charts, which automatically analyzes camera and radar images to minimize the intervention of maritime boundary monitors, and when an unidentified vessel appears, uses unmanned vessels and drones to obtain images of the vessel and identifies it using visual search methods, thereby reducing the need for on-site dispatch and face-to-face investigation, thereby enabling more efficient operation.

[0002] Furthermore, in order to solve the problems of the conventional marine boundary monitoring system and method, which are configured such that observers monitor the images obtained through the cameras as described above, there is a concern of blind spots, and in addition, when an unidentified vessel appears, it is necessary to dispatch to the scene and check it in person, which is inefficient. The present invention provides an area monitoring unit that uses a camera to perform a process of overviewing the entire monitored area, a regional monitoring unit that uses a camera to perform a process of analyzing in detail a part of the monitored area or an object of interest, an image analysis unit that analyzes camera and radar images and combines information received from various sensors and monitoring equipment (camera, radar, AIS, V-pass, e-Nav, etc.) to automatically detect and track objects, and an electronic nautical chart that displays information about the monitored area and The system includes an electronic chart monitoring unit that performs processing to overlay and display information from various sensors and monitoring devices, sensor fusion information from the video analysis unit, and object identification results, and an unmanned vessel and drone control unit that, if an object cannot be identified in the object identification results, uses an unmanned vessel or drone to take close-up video of the unidentified object and performs processing to make it identifiable. This system automatically analyzes camera and radar images to minimize the intervention of maritime boundary monitors, and if an unidentified vessel appears, uses an unmanned vessel or drone to obtain video and identifies it using visual search methods, thereby reducing the need for on-site dispatches and face-to-face confirmation and enabling more efficient operation. [Background technology]

[0003] Traditionally, marine surveillance has generally been carried out by large vessels such as fisheries guidance vessels and coast guard vessels, or by observers monitoring camera footage 24 hours a day to identify vessels suspected of illegal activity or in emergency situations.

[0004] In this case, when observers monitor the footage captured by the camera, they must manually identify the ship by comparing the ship's position received through the Automatic Identification System (AIS) with the ship's position captured by the camera, which makes it difficult to perform the identification process quickly.Furthermore, since it relies on the observer's subjective judgment, the accuracy of the identification results cannot be guaranteed.

[0005] In other words, conventional maritime boundary monitoring systems and methods are configured so that observers monitor images obtained through fixed cameras installed on land 24 hours a day, which makes the acquisition and utilization of image information inefficient and limited. As a result, a large number of maritime boundary monitors are required, and there is a concern that blind spots will occur due to fatigue of each observer.

[0006] Furthermore, conventional maritime boundary monitoring systems and methods have limitations in terms of manpower and costs, as they require a person to go to the scene and check in person when an unidentified vessel is encountered.

[0007] Therefore, in order to overcome the limitations of the above-mentioned conventional maritime boundary monitoring systems and methods, it is desirable to propose a new maritime boundary monitoring system and method that automatically analyzes camera and radar images, minimizes the intervention of maritime boundary monitors, reduces on-site dispatches and face-to-face confirmation when an unidentified vessel is encountered, and enables more efficient operation. However, at present, no device or method that meets all of these requirements has been proposed. Summary of the Invention [Problem to be solved by the invention]

[0008] The present invention seeks to solve the problems of the prior art, and therefore, an object of the present invention is to propose a maritime boundary monitoring system and method based on video analysis and electronic charts that automatically analyzes camera and radar images to minimize the intervention of maritime boundary monitors, and, when an unidentified vessel appears, uses unmanned vessels and drones to obtain video of the vessel and identify it using visual search methods, thereby reducing the need for on-site dispatches and face-to-face confirmation and enabling more efficient operation. This aims to solve the problems of the prior art maritime boundary monitoring system and method, which generally require observers to monitor images obtained from fixed cameras installed on land 24 hours a day, making the acquisition and utilization of video information inefficient and limited, resulting in the need for a large number of maritime boundary monitors and concerns about blind spots due to fatigue among observers. In addition, when an unidentified vessel appears, the observer must dispatch to the scene and conduct a face-to-face confirmation, which is inefficient in terms of manpower and costs. This system and method can automatically analyze camera and radar images to minimize the intervention of maritime boundary monitors, and, when an unidentified vessel appears, uses unmanned vessels and drones to obtain video of the vessel and identify it using visual search methods, thereby reducing the need for on-site dispatches and face-to-face confirmation and enabling more efficient operation.

[0009] Another object of the present invention is to solve the problems of the conventional marine boundary monitoring system and method, which are configured such that observers monitor the images obtained through cameras as described above, and which have limitations in efficiency, such as the need to dispatch an observer to the scene for face-to-face confirmation when an unidentified vessel appears, and which comprise an area monitoring unit that performs processing to overview the entire monitored area using a camera, a regional monitoring unit that performs processing to analyze in detail a part of the monitored area or an object of interest using a camera, an image analysis unit that analyzes camera and radar images and combines information received from various sensors and monitoring equipment (camera, radar, AIS, V-pass, e-Nav, etc.) to automatically detect and track objects, and an electronic nautical chart that displays information about the monitored area and The system is configured to include an electronic chart monitoring unit that performs processing to overlay and display information from various sensors and monitoring equipment, sensor fusion information from the video analysis unit, and object identification results, and an unmanned ship and drone control unit that, if there is an object that cannot be identified in the object identification results, uses an unmanned ship or drone to capture close-up video of the unidentified object and performs processing to make it identifiable.The system aims to propose a maritime boundary monitoring system and method based on video analysis and electronic charts that automatically analyzes camera and radar video to minimize the intervention of maritime boundary monitors, and in the event of an unidentified vessel, uses an unmanned ship or drone to obtain video and identifies it using visual search methods, thereby reducing the need for on-site dispatches and face-to-face confirmation and enabling more efficient operation. [Means for solving the problem]

[0010] In order to achieve the above object, according to the present invention, in a marine boundary monitoring system based on image analysis and electronic nautical charts, there is provided a system including an all-area monitoring unit that includes a panoramic camera for capturing an image of the entire pre-defined boundary monitoring target area and is configured to execute a process of monitoring the entire boundary monitoring target area; a local monitoring unit that includes a local camera for capturing detailed images of a part of the boundary monitoring target area or an object of interest and is configured to execute a process of monitoring a specific area or object based on a pre-defined setting or a user's input; and a system that monitors the images received through the all-area camera and the local camera and the images received from radar, various sensors, and monitoring equipment previously installed for maritime monitoring. A maritime boundary monitoring system based on video analysis and electronic nautical charts is provided, which includes: a video analysis unit configured to perform a process of fusing video and various information and automatically detecting and tracking objects through video analysis; an electronic nautical chart monitoring unit configured to perform a process of displaying various information received from each sensor and monitoring device along with the sensor fusion information and object identification results of the video analysis unit on an electronic nautical chart according to a predetermined setting; and an unmanned ship and drone control unit configured to perform a process of taking close-range video of the unidentified object using an unmanned ship or drone if there is an object not identified in the object identification results of the video analysis unit.

[0011] Here, the system further includes an output unit configured to execute a process of displaying various information including the processing contents and processing results processed through the system on a display; a communication unit configured to execute a process of transmitting and receiving various data including information received from various sensors and monitoring devices and object identification results via either wired or wireless communication with external devices including a server; and a control unit configured to execute a process of controlling the overall operation of the system.

[0012] The entire area monitoring unit includes at least one camera and is configured to capture an image of the entire boundary monitoring area that has been set in advance, and to transmit the captured image to the image analysis unit.

[0013] In this case, the full-area monitoring unit includes two or more cameras, and is configured to perform a process of displaying each camera image in a panoramic format through image stitching and controlling each camera to operate in cooperation and synchronously through PTZ (Pan-Tilt-Zoom) control.

[0014] Furthermore, the area monitoring unit includes at least one camera and is configured to capture detailed images of a part of the boundary monitoring area or an object of interest designated by a user based on the detection and tracking results of the image analysis unit, and to transmit the captured images to the image analysis unit.

[0015] Furthermore, the video analysis unit is configured to use a deep learning or machine learning-based artificial intelligence (AI) object recognition model trained to enable visual search, combine camera and radar images with information from various sensors and monitoring devices, automatically detect and track objects according to predetermined settings, and transmit the generated sensor fusion information to the overall area monitoring unit, the regional monitoring unit, and the electronic chart monitoring unit, respectively.

[0016] In addition, the video analysis unit is configured to identify unidentified objects photographed using close-range video and meta information received through the unmanned ship and drone control unit, and to perform a process of transferring the identification results of the unidentified objects to the overall area monitoring unit, the regional monitoring unit, and the electronic chart monitoring unit, respectively.

[0017] Furthermore, the electronic chart monitoring unit is configured to execute a process of overlaying and displaying various data, including information about the boundary monitoring area, images from each of the panoramic cameras and local cameras, information about various sensors and monitoring equipment including radar, AIS, V-pass, and e-Nav, sensor fusion information from the image analysis unit, and object identification results, on an electronic chart according to predetermined settings.

[0018] Furthermore, the electronic chart monitoring unit is configured to, when an unidentified object is present, generate route plans and control information for unmanned ships and drones to acquire footage of the unidentified ship based on information received from the global monitoring unit and the regional monitoring unit, and transmit the information to the unmanned ship and drone control unit.

[0019] Furthermore, the unmanned ships and drones are characterized in that they are configured to include an optical camera and be capable of capturing video, or in addition to the optical camera, they are further configured to include a thermal imaging camera, LiDAR, searchlight, and flash.

[0020] Furthermore, according to the present invention, in the maritime boundary monitoring method using the above-described maritime boundary monitoring system, there are provided a monitoring step in which an image of a predetermined boundary monitoring area is captured by an overall monitoring unit and a regional monitoring unit of the maritime boundary monitoring system; a detection step in which an image analysis unit of the maritime boundary monitoring system integrates the image collected in real time in the monitoring step with images and various information received from radars, various sensors, and monitoring devices previously installed for maritime monitoring, and automatically detects and tracks an object through image analysis; and an electronic nautical chart of the maritime boundary monitoring system. A maritime boundary monitoring method based on image analysis and an electronic nautical chart is provided, which includes a display step in which a monitoring unit performs processing to display, on an electronic nautical chart, the sensor integration information of the image analysis unit, the object identification result, and various data received from various sensors and monitoring devices based on a predetermined setting; and a redetection step in which, if an unidentified object is found based on the object identification result of the analysis step, an unmanned ship or a drone is used to capture a close-up image of the unidentified object, and the image analysis unit performs processing to re-identify the unidentified object based on the close-up image, through an unmanned ship and drone control unit of the maritime boundary monitoring system. [Effects of the Invention]

[0021] As described above, according to the present invention, there are provided an all-area monitoring unit that uses a camera to perform a process of overviewing the entire boundary monitoring area, a regional monitoring unit that uses a camera to perform a process of analyzing in detail a part of the boundary monitoring area or an object of interest, an image analysis unit that analyzes camera and radar images and combines information received from various sensors and monitoring devices (cameras, radar, AIS, V-pass, e-Nav, etc.) to automatically detect and track objects, and an electronic chart monitoring unit that overlays and displays information about the monitoring area, information about various sensors and monitoring devices, sensor fusion information from the image analysis unit, and object identification results on an electronic chart. Furthermore, if an object cannot be identified as a result of the object identification, a maritime boundary monitoring system and method based on image analysis and electronic nautical charts is provided, which includes an unmanned vessel and drone control unit that uses an unmanned vessel or drone to capture close-range video of the unidentified object and performs processing to make it identifiable.This system and method automatically analyzes camera and radar video to minimize the intervention of maritime boundary monitors, and when an unidentified vessel occurs, unmanned vessels and drones are used to obtain video and identify it using a visual search method, thereby reducing the need for on-site dispatch and face-to-face confirmation, thereby making maritime boundary monitoring more effective and efficient.

[0022] In addition, the present invention provides a maritime boundary monitoring system and method based on image analysis and electronic nautical charts that automatically analyzes camera and radar images to minimize the intervention of maritime boundary monitors, and when an unidentified vessel appears, uses unmanned vessels and drones to obtain video of the vessel and identifies it using a visual search method, thereby reducing the need for on-site dispatches and face-to-face confirmation, enabling more effective and efficient operation.This solves the problems of conventional maritime boundary monitoring systems and methods, which are typically configured to have observers monitor video images obtained from fixed cameras installed on land 24 hours a day, resulting in inefficient and limited acquisition and use of video information, requiring a large number of maritime boundary monitors and the risk of blind spots due to the accumulation of observer fatigue, and requiring on-site face-to-face confirmation when an unidentified vessel appears, which is inefficient in terms of human resources and costs. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a block diagram showing a schematic overall configuration of a maritime boundary monitoring system based on video analysis and electronic charts according to an embodiment of the present invention;

[0024] [Figure 2] FIG. 2 is a diagram illustrating the overall processing flow of the maritime boundary surveillance system based on video analysis and electronic charts according to the embodiment of the present invention shown in FIG. 1.

[0025] [Figure 3] 2 is a conceptual diagram illustrating a maritime boundary monitoring system based on video analysis and electronic charts according to the embodiment of the present invention shown in FIG. 1.

[0022] FIG. DETAILED DESCRIPTION OF THE INVENTION

[0026] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a specific embodiment of a system and method for maritime boundary monitoring based on image analysis and electronic charts according to the present invention will be described with reference to the accompanying drawings.

[0027] It should be noted that the content described below is merely one embodiment for carrying out the present invention, and the present invention is not limited to the content of the embodiment described below.

[0028] In addition, in the following description of the embodiments of the present invention, it should be noted that detailed descriptions of parts that are identical or similar to the contents of the prior art or that are deemed to be easily understood and implemented by a person skilled in the art have been omitted in order to simplify the description.

[0029] Next, the specific contents of the maritime boundary monitoring system and method based on image analysis and electronic charts according to the present invention will be described with reference to the drawings.

[0030] More specifically, first, referring to Figures 1 and 2, Figure 1 is a block diagram that schematically illustrates the overall configuration of a maritime boundary monitoring system (10) based on video analysis and electronic nautical charts according to an embodiment of the present invention, and Figure 2 is a diagram that schematically illustrates the overall processing flow of the maritime boundary monitoring system (10) based on video analysis and electronic nautical charts according to the embodiment of the present invention shown in Figure 1.

[0031] In FIG. 2, blue characters indicate information transmitted from left to right, and green characters indicate information transmitted from left to right.

[0032] As shown in Figures 1 and 2, a maritime boundary monitoring system (10) based on video analysis and electronic charts according to an embodiment of the present invention is broadly composed of an overall area monitoring unit (11) that uses a camera to take general images of the entire boundary monitoring area, a regional monitoring unit (12) that uses a camera to take detailed images of a part of the boundary monitoring area or objects of interest, a video analysis unit (13) that analyzes camera and radar images and combines information received from various sensors and monitoring equipment (cameras, radar, AIS, V-pass, e-Nav, etc.) to automatically detect and track objects, an electronic chart monitoring unit (14) that overlays and displays information about the monitoring area, various sensor and monitoring equipment information, sensor fusion information from the video analysis unit, and object identification results on an electronic chart, and an unmanned ship and drone control unit (15) that, if an object that could not be identified in the object identification results exists, uses an unmanned ship or drone to take close-range images of the unidentified object to make it identifiable.

[0033] Here, the above system (10) further includes an output unit that performs processing to display various information related to the overall operation of the system (10) via a display device or the like, a communication unit that performs processing to send and receive various data including information received from various sensors and monitoring devices and target identification results via either wired or wireless communication with an external device such as a server, and a control unit that performs processing to control the above units and the overall operation of the system (10).

[0034] More specifically, the whole area monitoring unit (11) can be configured to include one or more cameras and serve to capture and overview the whole area to be monitored.

[0035] Here, when two or more cameras are used, the boundaries between the cameras can be displayed in a natural panoramic format through image stitching, and all cameras can be configured to operate in sync through PTZ (Pan-Tilt-Zoom) control of the cameras.

[0036] In this case, if excessive zooming in results in no overlapping area between camera images, the stitching function may be configured not to operate.

[0037] In addition, the all-area monitoring unit (11) can be configured to perform a process of overlaying and displaying the sensor fusion information and object identification results received from the image analysis unit (13) on the camera image in an augmented reality (AR) format.

[0038] Furthermore, the area monitoring unit (12) is configured to include one or more cameras and to take detailed photographs of parts of the boundary monitoring area or objects of interest, and to achieve this, information about the target area to be investigated in detail can be specified by the user through the overall area monitoring unit (11) or the electronic chart monitoring unit (14) and transmitted as a camera control signal.

[0039] Here, if the object of investigation is an object, the detection and tracking results of the video analysis unit (13) can be configured to be transmitted as a camera control signal, that is, each local camera can operate independently, and if no specific area or object is designated, it can be configured to repeat the operation of automatically moving along a predefined monitoring route.

[0040] Furthermore, the regional monitoring unit (12), like the above-mentioned global monitoring unit (11), can be configured to receive sensor fusion information and object identification results from the video analysis unit (13) and display them as an overlay on the camera image in an augmented reality (AR) format.

[0041] Next, the image analysis unit (13) can be configured to analyze camera and radar images to automatically detect and track targets, and further to more accurately detect and track targets by combining information from various sensors and monitoring devices.

[0042] More specifically, the image analysis unit (13) can be configured to combine information between objects that are presumed to be the same object to identify and distinguish ships, and to transmit the sensor fusion information generated in this process to the overall area monitoring unit (11), the regional monitoring unit (12), the electronic chart monitoring unit (14), etc., and provide it to users.

[0043] In addition, the above-mentioned video analysis unit (13) can be configured to use the captured video and meta information transmitted through the unmanned ship and drone control unit (15) to identify which object (ship) is being photographed, and transmit the object identification results to the global monitoring unit (11), the regional monitoring unit (12), the electronic chart monitoring unit (14), etc.

[0044] Here, the object identification function can be configured using an artificial intelligence (AI) object recognition model based on deep learning or machine learning that is trained to enable visual search, and this model can be configured to be continuously updated as unidentified objects are identified.

[0045] Here, it should be noted that the process of identifying ships using an artificial intelligence algorithm that has been trained in advance to enable visual search as described above is something that a person skilled in the art could appropriately configure by referring to conventional data processing methods and artificial intelligence object recognition algorithms. Therefore, in order to simplify the explanation, the present invention omits detailed explanations of parts that would be obvious to a person skilled in the art from the content of the conventional art as described above or parts that a person skilled in the art could easily understand and implement by referring to conventional literature.

[0046] Furthermore, the electronic chart monitoring unit (14) can be configured to overlay and display information about the monitoring area, information about various sensors and monitoring devices such as cameras, radar, AIS, V-pass, and e-Nav, sensor fusion information and target identification results from the image analysis unit (13) on a two-dimensional electronic chart.

[0047] Furthermore, the electronic chart monitoring unit (14) can be configured to automatically receive input from the user of the monitoring route along which the camera will move if no specific area or target is designated for the local camera, and furthermore, if it is difficult to identify the target (ship) even through the local camera, it can be configured to transmit route plans for the unmanned ships and drones, and generate and transmit control information based on the operation information of the unmanned ships and drones, so that the unmanned ships and drones can move and obtain footage of the ships that could not be identified.

[0048] In other words, the unmanned ship and drone control unit (15) can be configured to perform processing to capture close-range images of the unidentified object using the unmanned ship and drone, so that if an object cannot be identified even after identifying it by combining information from various sensors and monitoring devices, the unmanned ship and drone can be used to capture close-range images of the unidentified object, making it possible to identify it.

[0049] At this time, the route planning and control information for the unmanned vessel and drone is generated and transmitted by the electronic chart monitoring unit (14) based on the selected target information of the global monitoring unit (11) and the regional monitoring unit (12), thereby enabling automatic video capture of unidentified targets.

[0050] Furthermore, unmanned vessels and drones are operated appropriately taking into consideration the weather conditions at sea, the time of day, the distance to the object to be identified, etc., and can be configured to use infrared cameras, LIDAR, searchlights, flashes, etc. in addition to optical cameras. It should be noted that the present invention can be appropriately modified and altered as necessary by those skilled in the art within the scope that does not deviate from the spirit and essence of the invention.

[0051] As described above, the maritime boundary monitoring system (10) and method based on video analysis and electronic charts according to the present invention can be easily implemented. That is, referring to FIG. 3, FIG. 3 is a conceptual diagram illustrating how maritime boundary monitoring is performed using the maritime boundary monitoring system (10) based on video analysis and electronic charts according to the embodiment of the present invention shown in FIG. 1.

[0052] As shown in Figure 3, according to the present invention, a series of processes can be configured to collect various data related to ships to build a database for learning an artificial intelligence algorithm, learn an AI model based on the built database, identify ships based on video and various surveillance information collected in real time using the AI ​​model learned in this way, display the identification information, and transmit it to the outside according to predetermined settings.

[0053] In addition, if an unidentified ship is encountered that cannot be identified through the AI ​​model, a request for deployment can be sent to a drone or unmanned ship, which will then move to the location of the unidentified ship, and the unidentified ship can be re-identified using footage of the unidentified ship captured by the drone or unmanned ship.

[0054] Based on the above configuration, the present invention can automatically identify ships by analyzing camera and radar images using a visual search method that utilizes artificial intelligence, thereby minimizing the intervention of maritime boundary monitors. In the event of an unidentified ship, unmanned ships and drones can be used to obtain close-up images of the unidentified ship and identify it through a visual search method, significantly reducing the need for on-site dispatch and face-to-face confirmation. This allows for effective and efficient maritime boundary monitoring with a simpler configuration and lower cost than the conventional method in which observers monitor images obtained from fixed cameras installed on land 24 hours a day.

[0055] Thus, a video analytics and electronic chart based maritime boundary surveillance system and method according to the present invention can be implemented as described above.

[0056] Although the details of the maritime boundary monitoring system and method based on image analysis and electronic nautical charts according to the present invention have been described above, the present invention is not limited to the contents described in the above embodiments. Therefore, it is apparent that various modifications, changes, combinations and substitutions can be made to the present invention by those skilled in the art based on design needs and various other factors. [Explanation of symbols]

[0057] 10. Maritime Boundary Monitoring System Based on Image Analysis and Electronic Charts 11. Global Surveillance Department 12. Community Surveillance Department 13. Video Analysis Section 14. Electronic Chart Monitoring Department 15. Unmanned Vessel and Drone Control Units

Claims

1. In maritime boundary monitoring systems based on video analysis and electronic charts, an all-area monitoring unit including an all-area camera for capturing an image of an entire predetermined boundary monitoring target area, the all-area monitoring unit being configured to execute a process of monitoring the entire boundary monitoring target area; an area monitoring unit including an area camera for taking detailed images of a part of the boundary monitoring area or an object of interest, configured to perform a process of monitoring a specific area or object based on a predetermined setting or user input; a video analysis unit configured to combine the video received through the panoramic camera and the local camera with the video and various information received from radars, various sensors, and monitoring devices pre-installed for maritime surveillance, and to automatically detect and track objects through video analysis; an electronic chart monitoring unit configured to execute a process of displaying on an electronic chart various information received from each sensor and monitoring device together with the sensor fusion information and object identification results of the image analysis unit according to a predetermined setting; and A maritime boundary monitoring system based on image analysis and electronic nautical charts, including an unmanned ship and drone control unit configured to perform a process of capturing close-range video of the unidentified object using an unmanned ship or drone if there is an unidentified object in the object identification result of the image analysis unit.

2. The system comprises: an output unit configured to execute a process of displaying various information including the processing contents and processing results processed through the system on a display; A communication unit configured to execute a process of transmitting and receiving various data including information received from various sensors and monitoring devices and object identification results to and from external devices including a server via at least one of wired and wireless communication methods; and The video analytics and electronic chart based maritime boundary surveillance system of claim 1 , further comprising a control unit configured to execute a process for controlling the overall operation of the system.

3. The entire area monitoring unit 2. The maritime boundary monitoring system based on image analysis and electronic nautical charts as described in claim 1, characterized in that it includes at least one camera, and is configured to capture an image of the entire predetermined boundary monitoring area and transfer the captured image to the image analysis unit.

4. The entire area monitoring unit In the case of a configuration including two or more cameras, images from each camera are displayed in a panoramic format through image stitching. The maritime boundary monitoring system based on video analysis and electronic charts according to claim 3, characterized in that it is configured to execute a process of controlling each camera to operate in coordination and synchronization through PTZ (Pan-Tilt-Zoom) control.

5. The regional monitoring unit 2. The maritime boundary monitoring system according to claim 1, further comprising at least one camera, configured to capture detailed images of a part of the boundary monitoring area or an object of interest designated by a user based on the detection and tracking results of the image analysis unit, and to transmit the captured images to the image analysis unit.

6. The video analysis unit It uses an AI object recognition model based on deep learning or machine learning, which is trained to enable visual search, to combine camera and radar images with information from various sensors and surveillance devices, and automatically detect and track objects according to pre-defined settings.

2. The image analysis and electronic chart-based maritime boundary monitoring system of claim 1, further comprising a process for transmitting the generated sensor fusion information to the entire area monitoring unit, the regional monitoring unit, and the electronic chart monitoring unit, respectively.

7. The video analysis unit 7. The image analysis and electronic chart-based maritime boundary monitoring system of claim 6, wherein the system is configured to perform a process of identifying unidentified objects photographed using close-range video and meta information received through the unmanned vessel and drone control unit, and transmitting the identification results of the unidentified objects to the entire area monitoring unit, the regional monitoring unit, and the electronic chart monitoring unit, respectively.

8. The electronic chart monitoring unit includes:

2. The maritime boundary monitoring system based on image analysis and electronic nautical chart according to claim 1, wherein the system is configured to execute a process of overlaying and displaying various data, including information about the boundary monitoring area, images from each of the panoramic camera and the local camera, information about various sensors and monitoring devices including radar, AIS, V-pass, and e-Nav, sensor fusion information from the image analysis unit, and object identification results, on an electronic nautical chart according to a predetermined setting.

9. The electronic map monitoring unit 2. The maritime boundary monitoring system based on image analysis and electronic maps as claimed in claim 1, wherein, when an unidentified object is present, a process is executed to generate route planning and control information for unmanned ships and drones to acquire video of the unidentified ship based on information received from the all-area monitoring unit and the local monitoring unit, and transmit the route planning and control information to the unmanned ship and drone control unit.

10. The unmanned ship and the drone are It is configured to be capable of video shooting including optical cameras, Alternatively, the maritime boundary monitoring system based on image analysis and electronic maps according to claim 1 is configured to further include a thermal imaging camera, a lidar, a searchlight and a flash in addition to the optical camera.

11. A maritime boundary monitoring method using the maritime boundary monitoring system according to any one of claims 1 to 10, a monitoring step in which a process of capturing an image of a predetermined border monitoring area is performed through the global monitoring unit and the regional monitoring unit of the maritime border monitoring system; a detection step in which the image analysis unit of the maritime boundary monitoring system integrates the images collected in real time in the monitoring step with images and various information received from radars, various sensors, and monitoring devices previously installed for maritime monitoring, and automatically detects and tracks the object through image analysis; a display step in which the electronic chart monitoring unit of the maritime boundary monitoring system displays the sensor integration information of the image analysis unit, the object identification result, and various data received from various sensors and monitoring devices on an electronic chart based on a predetermined setting; and A maritime boundary monitoring method based on image analysis and electronic nautical charts, including a redetection step in which, if an unidentified object is found to exist as a result of the object identification in the analysis step through an unmanned ship and drone control unit of the maritime boundary monitoring system, a close-range video of the unidentified object is taken using an unmanned ship or drone, and a process of re-identifying the unidentified object based on the close-range video is performed through an image analysis unit.

Images