Method and apparatus for detecting leakage of ammonia

Abstract

According to one embodiment of the present invention, a method for detecting leakage of ammonia may be provided, the method comprising the steps of: obtaining at least one first image captured by at least one camera capturing images along a preset path in each of zones; identifying a specific zone in which ammonia has leaked among the respective zones on the basis of the obtained first image; obtaining at least one second image by controlling at least one camera installed in the specific zone or a zone adjacent to the specific zone; and monitoring the safety of a passenger on the basis of the obtained second image.

Description

Method and device for detecting ammonia leaks

[0001] The present disclosure relates to a method and device for detecting ammonia leaks.

[0002] The engine used to propel a vessel may be installed in the vessel's engine room. More specifically, if ammonia is used as fuel, an ammonia-powered engine may be installed in the vessel's engine room. The engine room may be equipped with a number of piping systems, including a supply pipe used to supply ammonia to the engine and a drain pipe used to recover ammonia from the engine.

[0003] Meanwhile, if ammonia leaks and exposes the human body, its toxicity can cause respiratory irritation, skin burns, and other problems, posing a problem. Furthermore, leaked ammonia can cause secondary accidents such as fires and explosions. Therefore, a method for detecting ammonia leaks is urgently needed to prevent various accidents that can occur due to ammonia leaks.

[0004] The background technology described above is technical information that the inventor possessed for the purpose of deriving the present invention or acquired in the process of deriving the present invention, and cannot necessarily be considered as publicly known technology disclosed to the general public prior to the application for the present invention.

[0005] The technical problem that the present disclosure seeks to solve is to provide a method and device for detecting ammonia leakage.

[0006] The problems to be solved by this disclosure are not limited to those mentioned above. Other problems and advantages of this disclosure not mentioned above can be understood through the following description and will be more clearly understood through the embodiments of this disclosure. Furthermore, it will be appreciated that the problems and advantages to be solved by this disclosure can be realized by the means and combinations thereof set forth in the claims.

[0007] As a technical means for achieving the above-described technical task, a first aspect of the present disclosure may provide a method for detecting an ammonia leak, including: a step of acquiring at least one first image captured by at least one camera that performs shooting along a preset path within each zone; a step of identifying a specific zone in which ammonia is leaked among each zone based on the acquired first image; a step of controlling at least one camera installed in the specific zone or in a surrounding zone of the specific zone to acquire at least one second image; and a step of monitoring the safety of passengers based on the acquired second image.

[0008] A second aspect of the present disclosure provides a device for detecting an ammonia leak, comprising: a memory having at least one program stored therein; and a processor for performing an operation by executing the at least one program, wherein the processor acquires at least one first image captured by at least one camera that performs shooting along a preset path within each zone, detects an ammonia leak occurring in a specific zone among the zones based on the first image, provides a notification based on the detection of the leak, controls at least one camera installed in the specific zone and at least one camera installed in a surrounding zone of the specific zone, acquires at least one second image captured by the controlled camera, and monitors the safety of passengers based on the acquired second image.

[0009] A third aspect of the present disclosure can provide a computer-readable recording medium having recorded thereon a program for executing the method of the first aspect of the present disclosure on a computer.

[0010] Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims and detailed description of the invention.

[0011] According to the problem solving means of the present disclosure described above, damage to passengers caused by ammonia leakage can be minimized through a method and device for detecting ammonia leakage.

[0012] FIG. 1 is a drawing illustrating an ammonia leak in a ship that can be detected by a device according to one embodiment.

[0013] Figure 2 is a block diagram of a device according to one embodiment.

[0014] FIG. 3 is a flowchart illustrating a method for detecting ammonia leaks by a device according to one embodiment.

[0015] FIG. 4 is a drawing for explaining a method for a device according to one embodiment to acquire a first image.

[0016] FIG. 5 is a diagram illustrating a method for a device according to one embodiment to identify a specific area where ammonia has leaked.

[0017] FIG. 6 is a diagram illustrating a method for a device according to one embodiment to acquire a second image.

[0018] FIG. 7 is a drawing illustrating an example of a device monitoring the safety of passengers according to one embodiment.

[0019] FIG. 8 is a drawing illustrating another example of a device monitoring the safety of passengers according to one embodiment.

[0020] A first aspect of the present disclosure may provide a method for detecting an ammonia leak, comprising: acquiring at least one first image captured by at least one camera that performs shooting along a preset path within each zone; identifying a specific zone in which ammonia is leaked among each zone based on the acquired first image; controlling at least one camera installed in the specific zone or in a surrounding zone of the specific zone to acquire at least one second image; and monitoring the safety of passengers based on the acquired second image.

[0021] The present disclosure is capable of various modifications and embodiments. Specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present disclosure, as well as methods for achieving them, will become clearer with reference to the embodiments described in detail below, along with the drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various forms.

[0022] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings. When describing with reference to the drawings, identical or corresponding components are given the same reference numerals and redundant descriptions thereof will be omitted.

[0023] In the examples below, the terms first, second, etc. are not used in a limiting sense, but are used for the purpose of distinguishing one component from another.

[0024] The phrases "in one embodiment," "according to one embodiment," "relating to one embodiment," or "according to an implementation of one embodiment" used in this specification do not necessarily all refer to the same embodiment. Furthermore, the term "embodiment" throughout this specification is an arbitrary distinction used to facilitate the description of the present disclosure, and each embodiment is not necessarily exclusive of the others. For example, the configurations mentioned for the description of one embodiment may be applied and / or implemented in other embodiments, and may be modified and applied and / or implemented without departing from the scope of the present disclosure.

[0025] In the examples below, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0026] In the following examples, terms such as “include” or “have” mean that a feature or component described in the specification is present, and do not preclude the possibility that at least one other feature or component may be added.

[0027] Some embodiments of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented by various hardware and / or software components that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by at least one microprocessor or by circuit configurations for a given function.

[0028] For example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks may be implemented as algorithms that run on at least one processor. In addition, the present disclosure may employ conventional techniques for electronic environment settings, signal processing, and / or data processing. Terms such as "mechanism," "element," "means," and "configuration" may be used broadly and are not limited to mechanical and physical configurations. In addition, terms such as "- part," "- module," etc. refer to a unit that processes at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software.

[0029] Additionally, some components in the drawings may be depicted with somewhat exaggerated sizes or proportions. Additionally, components depicted in one drawing may not be depicted in another drawing.

[0030] The present disclosure will be described in detail with reference to the attached drawings below.

[0031] FIG. 1 is a drawing illustrating an ammonia leak in a ship that can be detected by a device according to one embodiment.

[0032] Referring to Figure 1, a vessel capable of experiencing an ammonia leak is illustrated. For example, the vessel illustrated in Figure 1 may be a vessel that uses ammonia as fuel. As an example, the vessel illustrated in Figure 1 may be equipped with an engine that uses ammonia as fuel.

[0033] For example, the vessel of FIG. 1 may include an engine room. The engine room may be equipped with an engine that uses ammonia as fuel. Furthermore, the engine room may be equipped with a number of piping systems, including a supply pipe used to supply ammonia to the engine and a drain pipe used to recover ammonia from the engine.

[0034] Piping can refer to equipment used to transport fluids, including pipes, valves, and flanges. Here, a pipe can refer to a hollow cylindrical tube used to transport fluids. A valve can also refer to a component used to control the flow of fluids. A flange can also refer to a component used to connect multiple components.

[0035] For example, ammonia leaks can occur at the flange joints of pipes installed on vessels using ammonia as fuel. Furthermore, ammonia leaks inside a vessel can cause various damages, posing a serious problem.

[0036] For example, if passengers are exposed to leaked ammonia, accidents such as suffocation can occur. Furthermore, the leaked ammonia can cause secondary accidents such as fires and explosions.

[0037] Therefore, in order to prevent various accidents that may occur due to ammonia leakage, a method for detecting ammonia leakage is required.

[0038] Figure 2 is a block diagram of a device according to one embodiment.

[0039] The device (200) according to the present disclosure may be a device for detecting ammonia leaks. For example, the device (200) may detect ammonia leaks that may occur in the vessel described above with reference to FIG. 1.

[0040] Referring to FIG. 2, the device (200) may include a processor (210) and a memory (220).

[0041] The memory (220) is hardware that stores various data processed within the device (200), and can store a program for processing and controlling the processor (210).

[0042] The memory (220) may include random access memory (RAM) such as dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), CD-ROM, Blu-ray or other optical disk storage, hard disk drive (HDD), solid state drive (SSD), or flash memory.

[0043] The processor (210) controls the overall operation of the device (200). For example, the processor (210) can control the memory (220) and the like by executing programs stored in the memory (220).

[0044] The processor (210) can control the operation of the device (200) by executing programs stored in the memory (220). The processor (210) can control at least a part of the operation of the device (200).

[0045] In one embodiment, the processor (210) may acquire at least one first image captured by at least one camera that performs shooting along a preset path within each zone, identify a specific zone in each zone where ammonia has leaked based on the acquired first image, control at least one camera installed in the specific zone or in a surrounding area of ​​the specific zone to acquire at least one second image, and monitor the safety of passengers based on the acquired second image.

[0046] In one embodiment, the first image and the second image may be distinguished based on a specific point in time. For example, an image acquired by the processor (210) before a specific point in time may be referred to as a first image, and an image acquired after a specific point in time may be referred to as a second image. In this case, the specific point in time may be the point in time when the processor (210) identifies a specific area where ammonia has leaked.

[0047] In one embodiment, a zone may refer to each area designated to monitor a space where ammonia leakage may occur. For example, a zone may be each area designated to monitor an engine room where ammonia leakage may occur.

[0048] In one embodiment, the first image may be captured by at least one camera that performs shooting along a preset path. The cameras may be installed within each zone. Furthermore, at least one camera may be installed in each zone.

[0049] In one embodiment, the camera may be a PTZ camera in which the direction and magnification of the lens can be adjusted.

[0050] A PTZ camera may be a camera that provides a pan function in which the direction of the lens is adjusted horizontally, a tilt function in which the direction of the lens is adjusted vertically, and a zoom function in which the magnification of the lens is adjusted.

[0051] A camera according to one embodiment may capture a first image based on a preset set to capture a preset path. The preset may include at least one predefined setting value among pan, tilt, and zoom.

[0052] For example, the camera can capture a specific point along a preset path by adjusting at least one of the pan, tilt, and zoom settings according to a preset. As an example, the camera can sequentially capture images according to multiple presets, thereby sequentially acquiring first images captured at each specific point along the preset path.

[0053] At this time, the preset path may be a shooting path set for efficient area monitoring. According to one embodiment, the camera can sequentially monitor specific points within the area where the camera is installed by sequentially calling multiple presets along the preset path.

[0054] In one embodiment, the processor (210) may acquire at least one first image including at least one of the leak detection tape and piping installed within each zone.

[0055] In one embodiment, the first image may be an image captured by at least one camera installed within each zone, capturing at least one of the leak detection tape and the pipe installed within each zone. In this case, the first image may include a portion of the leak detection tape and / or a portion of the pipe.

[0056] For example, the first image may include an image of the leak detection tape captured by at least one camera installed within each zone. In another example, the first image may include an image of the pipe captured by at least one camera installed within each zone.

[0057] In another example, the first image may include images of the pipe and leak detection tape taken by at least one camera installed within each zone.

[0058] In one embodiment, the leak detection tape may be a film-type sensor tape used to detect ammonia leaks. For example, the leak detection tape may be a tape that changes color when in contact with ammonia.

[0059] In one embodiment, the leak detection tape may be installed at an ammonia leak-prone portion of the pipe. In one embodiment, the ammonia leak-prone portion may include a flange fastening portion of the pipe.

[0060] For example, leak detection tape may be installed at the flange joints of a pipe. As an example, leak detection tape may be installed at each of a plurality of flange joints included in the pipe.

[0061] In one embodiment, the processor (210) can determine whether at least one first image includes at least one of icing and discoloration of the leak detection tape.

[0062] In one embodiment, icing may refer to the formation of ice on the surface of a pipe due to an ammonia leak. When an ammonia leak occurs, the high heat of vaporization of the ammonia causes a rapid drop in the surrounding temperature, causing moisture in the air to condense and freeze, resulting in the formation of ice on the surface of the pipe, known as icing.

[0063] In one embodiment, the processor (210) may use an icing detection model to determine whether at least one first image contains icing based on the first image.

[0064] According to one embodiment, the icing detection model may be a machine learning model used to detect icing. In the following, the machine learning model may include a machine learning model based on an artificial neural network architecture, such as a convolutional neural network (CNN).

[0065] For example, an icing detection model may be a machine learning model based on the YOLO (You Only Look Once) algorithm. Meanwhile, machine learning models that can be used as icing detection models may include various object detection models, and the specific types of models are not limited by the aforementioned criteria.

[0066] In one embodiment, the processor (210) may use various image processing techniques to determine whether at least one first image contains discoloration of the leak detection tape based on the first image. For example, the processor (210) may use a color masking technique to determine whether at least one first image contains discoloration of the leak detection tape.

[0067] Meanwhile, a detailed description of various image processing techniques used by the processor (210) to determine whether the first image includes discoloration of the leak detection tape will be described later with reference to FIG. 3.

[0068] In one embodiment, the processor (210) may switch the leak detection camera that captured the first image related to the ammonia leak among at least one camera installed in a specific area to a fixed mode, and switch the cameras other than the leak detection camera among at least one camera installed in the specific area to a safety monitoring mode.

[0069] In one embodiment, a leak detection camera may be a camera that captures a first image associated with an ammonia leak. In this case, the first image associated with the ammonia leak may be a first image that includes at least one of icing and discoloration of the leak detection tape.

[0070] In one embodiment, a fixed mode may be a mode in which the camera's pan, tilt, and zoom settings remain unchanged. For example, the camera may maintain its pan, tilt, and zoom settings without changing them based on the camera's fixed mode.

[0071] In one embodiment, the processor (210) can control the leak detection camera that has captured the first image related to the ammonia leak to be switched to a fixed mode so that the camera continuously captures the point where the leak occurred.

[0072] In one embodiment, the safety monitoring mode may be a mode for detecting rescue targets within a specific area. For example, a camera switched to safety monitoring mode may perform shooting based on multiple presets set to detect rescue targets within a specific area.

[0073] As an example, a camera switched to safety monitoring mode can acquire images of the entire specific area by sequentially shooting according to multiple presets set to detect a rescue target within a specific area.

[0074] In one embodiment, the processor (210) may switch at least one of the cameras installed in the surrounding area to a passage surveillance mode.

[0075] In one embodiment, the aisle surveillance mode may be a mode for detecting passengers within an aisle leading to a specific area. For example, a camera switched to aisle surveillance mode may perform photography based on multiple presets set to detect passengers within an aisle leading to a specific area.

[0076] Here, a corridor can refer to a physical connection between one area and another. For example, a camera switched to corridor surveillance mode can sequentially capture images according to multiple presets to acquire images of the physical connection leading to a specific area.

[0077] In one embodiment, the processor (210) may detect a target person within a specific area based on at least one second image captured by at least one camera installed in the specific area. In this case, the second image may include an image captured by a camera switched to safety monitoring mode.

[0078] According to one embodiment, the processor (210) may use a structure target detection model to detect a structure target included in at least one second image based on the second image. In this case, the structure target may refer to a passenger requiring rescue, such as a collapsed person within a specific space.

[0079] According to one embodiment, the target person detection model may be a machine learning model used to detect the target person. For example, the target person detection model may be a machine learning model based on the YOLO algorithm.

[0080] Meanwhile, machine learning models that can be used as structural target detection models may include various object detection models, and the specific types of models are not limited by the above.

[0081] In one embodiment, the processor (210) may detect a passenger approaching a specific area based on at least one second image captured by at least one camera installed in the surrounding area. The second image may include an image captured by a camera switched to aisle surveillance mode.

[0082] According to one embodiment, the processor (210) can use a passenger detection model to detect a passenger approaching a specific area included in at least one second image based on the second image.

[0083] According to one embodiment, a passenger detection model may be a machine learning model used to detect passengers approaching a specific area. For example, the passenger detection model may be a machine learning model based on the YOLO algorithm.

[0084] Meanwhile, machine learning models that can be used as passenger detection models may include various object detection models, and the specific types of models are not limited by the above.

[0085] In one embodiment, when a rescue target is detected, the processor (210) can switch the camera capturing the rescue target within a specific area to fixed mode. This allows the processor (210) to control the camera capturing the rescue target within the specific area to continuously capture the rescue target.

[0086] In one embodiment, the processor (210) may provide a leak notification based on the identification of a specific area. For example, the processor (210) may provide a leak notification to the control room based on the identification of a specific area where an ammonia leak has occurred. The leak notification may include information regarding the location of the specific area where the ammonia leak has occurred, etc.

[0087] In one embodiment, the processor (210) may provide a risk alert based on the results of monitoring. For example, the processor (210) may provide a risk alert to the control room based on the detection of at least one of a rescue target and a passenger approaching a specific area. The risk alert may include information regarding the location of the rescue target and / or the passenger approaching the specific area.

[0088] A detailed description of the various operations of the device (200) that can be performed by the processor (210) will be described later with reference to FIGS. 3 to 8.

[0089] The processor (210) may be implemented using at least one of application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors (210), and other electrical units for performing functions.

[0090] FIG. 3 is a flowchart illustrating a method for detecting ammonia leaks by a device according to one embodiment.

[0091] In step 310, the processor (210) can acquire at least one first image captured by at least one camera that performs shooting along a preset path within each zone.

[0092] As described above with reference to FIG. 2, the first image according to one embodiment may be an image acquired before the processor (210) identifies a specific area where ammonia has leaked. In this case, the first image may be used to detect an ammonia leak.

[0093] Meanwhile, a detailed description of at least one camera that performs shooting according to a preset path is omitted as it has been described above with reference to FIG. 2.

[0094] According to one embodiment, each camera can transmit at least one first image it has captured in real time using various wired / wireless communications. At this time, the processor (210) can receive at least one first image transmitted by the camera.

[0095] According to one embodiment, the processor (210) can obtain a first image including at least one of the leak detection tape and pipe installed within each zone.

[0096] For example, the processor (210) may obtain a first image including a leak detection tape installed in each zone and obtain a first image including a pipe installed in each zone.

[0097] At this time, the first image including the leak detection tape installed in each area may be an image captured by enlarging an area of ​​interest within at least one specific point included in a preset path.

[0098] As an example, at least one camera that acquires a first image may sequentially perform shooting according to a preset to zoom in and shoot a region of interest within at least one specific point included in a preset path to acquire a first image including leak detection tape installed within each area. In this case, the region of interest may be an area where leak detection tape is installed.

[0099] In one embodiment, a leak detection tape may be installed at an ammonia leak-prone portion of the pipe. As described above with reference to FIG. 2, the leak detection tape may be installed at a flange connection portion of the pipe.

[0100] In step 320, the processor (210) can identify a specific area where a hazardous gas has leaked among each area based on the acquired first image.

[0101] In one embodiment, the processor (210) can determine whether at least one first image includes at least one of icing and discoloration of the leak detection tape.

[0102] According to one embodiment, a processor (210) may use an icing detection model to determine whether at least one first image contains icing based on the first image. In this case, the first image may include at least a portion of the pipes installed in each zone.

[0103] As described above with reference to FIG. 2, the icing detection model according to one embodiment may be a machine learning model used to detect icing. Meanwhile, a detailed description of the icing detection model is omitted as it has been described above with reference to FIG. 2.

[0104] For example, the processor (210) can determine whether at least one first image contains icing by using the first image that has undergone a preprocessing process and the icing detection model.

[0105] As an example, the preprocessing process may include an HSV color space conversion process and a saturation adjustment process. In this case, the HSV color space conversion process may refer to a process of converting a first image in RGB format into an HSV format that can be expressed as a hue (H) value, a saturation (S) value, and a brightness (V) value. In addition, the saturation adjustment process may refer to a process of adjusting the saturation (S) of the image to emphasize the color.

[0106] In one embodiment, the processor (210) may use various image processing techniques to determine whether discoloration of the leak detection tape is included in the first image. The first image may be an enlarged image of a region of interest within at least one specific point included in a preset path. Additionally, the first image may include at least a portion of the leak detection tape.

[0107] For example, the processor (210) can determine whether at least one first image includes discoloration of the leak detection tape by using a first image that has undergone a preprocessing process and various image processing techniques.

[0108] As an example, the preprocessing process may include an HSV color space conversion process and a saturation adjustment process. Meanwhile, a detailed description of the HSV color space conversion process and the saturation adjustment process has been described above, so they will be omitted.

[0109] According to one embodiment, the processor (210) may determine whether discoloration of the leak detection tape is included in the first image using a color masking technique. The color masking technique may refer to a technique for extracting only a region of a specific color from a specific image by masking only pixels having a color (H) value included in a specific color (H) range.

[0110] For example, the processor (210) may mask only pixels having a color (H) value that falls within a specific color (H) range that has been discolored due to ammonia leakage. As an example, the processor (210) may mask only pixels having a color (H) value that falls within a blue range.

[0111] According to one embodiment, a processor (210) can remove noise by applying a morphological transform to a first image masked using a color masking technique.

[0112] Morphological operations can refer to techniques for removing noise by applying operations such as erosion and dilation to a masked image. Erosion can refer to a technique for shrinking white areas, while dilation can refer to a technique for expanding white areas.

[0113] According to one embodiment, the processor (210) may determine that the first image includes discoloration of the leak detection tape if the area of ​​the masked area within the first image is greater than a preset threshold using the first image from which noise has been removed.

[0114] In one embodiment, the processor (210) can identify as a specific area an area where a first image was captured that includes at least one of icing and discoloration of the leak detection tape.

[0115] For example, if the processor (210) determines that a specific first image includes at least one of icing and discoloration of the leak detection tape, the processor (210) may identify the area where the camera that captured the first image is installed as a specific area.

[0116] In one embodiment, the processor (210) may provide a leak notification based on the identification of a specific area. For example, the processor (210) may provide a leak notification to the control room based on the identification of a specific area where an ammonia leak has occurred. The leak notification may include information regarding the location of the specific area where the ammonia leak has occurred, etc.

[0117] In step 330, the processor (210) can control at least one camera installed in a specific area or in a surrounding area of ​​the specific area to obtain at least one second image.

[0118] As described above with reference to FIG. 2, the second image according to one embodiment may be an image acquired after the processor (210) identifies a specific area where ammonia has leaked.

[0119] In one embodiment, the processor (210) may switch the leak detection camera that captured the first image related to the ammonia leak among at least one camera installed in a specific area to a fixed mode, and switch the cameras other than the leak detection camera among at least one camera installed in the specific area to a safety monitoring mode.

[0120] At this time, the first image related to the leak may be a first image including at least one of icing and discoloration of the leak detection tape.

[0121] For example, the processor (210) may switch a leak detection camera, which has captured a first image containing at least one of icing and discoloration of the leak detection tape, among at least one camera installed in a specific area where an ammonia leak has occurred, to a fixed mode. In one embodiment, the processor (210) may acquire the image captured by the leak detection camera switched to the fixed mode as a second image.

[0122] A fixed mode according to one embodiment may be a mode in which the settings of the pan, tilt and zoom of the camera are not changed.

[0123] As an example, the processor (210) may control the settings of the pan, tilt, and zoom of a leak detection camera installed in a specific area where ammonia has leaked to not change the settings of the camera that captured the first image containing at least one of icing and discoloration of the leak detection tape.

[0124] At this time, the mode of the leak detection camera may be switched from the basic mode of performing shooting according to a preset path to the fixed mode.

[0125] By switching the mode of the leak detection camera according to one embodiment from the basic mode to the fixed mode, the processor (210) can continuously acquire a second image capturing a location where at least one of icing and discoloration of the leak detection tape has occurred.

[0126] In one embodiment, the processor (210) may switch at least one camera installed in a specific area, excluding the leak detection camera, to safety monitoring mode. For example, the processor (210) may switch a camera installed in a specific area that did not capture the first image related to a leak to safety monitoring mode.

[0127] According to one embodiment, the processor (210) can acquire an image captured by a camera switched to a safety monitoring mode as a second image.

[0128] A safety monitoring mode according to one embodiment may be a mode for detecting a rescue target within a specific area. For example, the processor (210) may control at least one camera installed in a specific area, excluding a leak detection camera, to perform photography based on multiple presets set to detect a rescue target within the specific area.

[0129] At this time, the mode of the camera, excluding the leak detection camera among at least one camera installed in a specific area, may be switched from the basic mode of performing filming according to a preset path to the safety monitoring mode.

[0130] Meanwhile, a camera switched to safety monitoring mode can acquire images of the entire specific area by sequentially shooting according to multiple presets set to detect rescue targets within a specific area.

[0131] In one embodiment, the processor (210) may switch at least one camera among the cameras installed in the surrounding area to passage surveillance mode. For example, the processor (210) may switch the camera installed in the surrounding area closest to a specific area to passage surveillance mode.

[0132] According to one embodiment, a processor (210) may acquire an image captured by a camera switched to a passage surveillance mode as a second image. At this time, the mode of the camera may be switched from a basic mode that performs shooting along a preset path to a passage surveillance mode.

[0133] A passageway surveillance mode according to one embodiment may be a mode for detecting passengers within a passageway leading to a specific area. For example, the processor (210) may control the camera closest to a specific area among the cameras installed in the surrounding area to perform filming according to multiple presets set to detect passengers within the passageway leading to the specific area.

[0134] For example, a camera switched to passage surveillance mode can perform recording based on multiple presets set to capture a predetermined area around a passage leading to a specific area. The predetermined area can be set to, for example, an area within a 1-meter radius around the passage leading to the specific area.

[0135] For example, a camera switched to passage surveillance mode can sequentially photograph multiple points within a 1m radius around a passage leading to a specific area by performing shooting according to multiple presets.

[0136] At step 340, the processor (210) can monitor the safety of the passenger based on the acquired second image.

[0137] In one embodiment, the processor (210) can detect a target person within a specific area based on at least one second image captured by at least one camera installed in the specific area.

[0138] For example, the processor (210) may use a structure target detection model to detect a structure target included in a second image based on the second image. In this case, the structure target detection model may be a machine learning model based on the YOLO algorithm.

[0139] Meanwhile, a detailed description of the structural target detection model is omitted as it has been described above with reference to Fig. 2.

[0140] In one embodiment, the processor (210) may detect a passenger approaching a specific area based on at least one second image captured by at least one camera installed in the surrounding area.

[0141] For example, the processor (210) may use a passenger detection model to detect a passenger approaching a specific area included in a second image based on the second image. In this case, the passenger detection model may be a machine learning model based on the YOLO algorithm.

[0142] Meanwhile, a detailed description of the passenger detection model is omitted as it has been described above with reference to Fig. 2.

[0143] In one embodiment, when a rescue target is detected, the processor (210) can switch the camera capturing the rescue target within a specific area to fixed mode. This allows the processor (210) to control the camera capturing the rescue target to continuously capture the rescue target.

[0144] Meanwhile, a detailed description of the fixed mode is omitted as it has been described above with reference to FIGS. 2 and 3.

[0145] In one embodiment, the processor (210) may provide a risk alert based on the results of monitoring. For example, the processor (210) may provide a risk alert to the control room based on the detection of at least one of a rescue target and a passenger approaching a specific area. The risk alert may include information regarding the location of the rescue target and / or the passenger approaching the specific area.

[0146] FIG. 4 is a drawing for explaining a method for a device according to one embodiment to acquire a first image.

[0147] Referring to Figure 4, multiple zones, 'Zone 1', 'Zone 2', 'Zone 3', and 'Zone 4', are illustrated. Figure 4 also illustrates passageways leading from each zone to another zone.

[0148] At this time, each zone may be a separate area set up by dividing the engine room to monitor the engine room where ammonia leakage may occur.

[0149] Meanwhile, at least one camera may be installed in each zone. As illustrated in FIG. 4, a 1-1 camera (411) and a 1-2 camera (412) may be installed in 'Zone 1', a 2-1 camera (421) and a 2-2 camera (422) may be installed in 'Zone 2', a 3-1 camera (431) and a 3-2 camera (432) may be installed in 'Zone 3', and a 4-1 camera (441) and a 4-2 camera (442) may be installed in 'Zone 4'.

[0150] At this time, each camera (411, 412, 421, 422, 431, 432, 441, 442) installed in each zone can perform shooting according to a preset path. In addition, the processor (210) can obtain at least one first image captured by at least one camera performing shooting according to the preset path.

[0151] Meanwhile, a detailed description of the cameras (411, 412, 421, 422, 431, 432, 441, 442) that perform shooting according to a preset path and the first image is omitted as it has been described above with reference to FIGS. 2 and 3.

[0152] FIG. 5 is a diagram illustrating a method for a device according to one embodiment to identify a specific area where ammonia has leaked.

[0153] Referring to FIG. 5, 'Zone 3', which is a specific zone (500) where ammonia leaked, is illustrated. At this time, a 3-1 camera (510) and a 3-2 camera (520) may be installed in 'Zone 3'.

[0154] Meanwhile, the 3-1 camera (510) and the 3-2 camera (520) of FIG. 5 may correspond to the 3-1 camera (431) and the 3-2 camera (432) of FIG. 4, respectively. In addition, the 'zone 3' illustrated in FIG. 5 may correspond to the 'zone 3' illustrated in FIG. 4.

[0155] In one embodiment, the processor (210) may identify a specific zone (500) from which ammonia has leaked among a plurality of zones based on the acquired first image. For example, the processor (210) may identify 'Zone 3' as the specific zone (500) based on the acquired first image.

[0156] For example, the processor (210) may identify 'Zone 3' as a specific zone (500) based on the inclusion of at least one of icing and discoloration of the leak detection tape in the first image captured by the 3-1 camera (510) installed in 'Zone 3'.

[0157] In one embodiment, the processor (210) can determine whether at least one first image includes at least one of icing and discoloration of the leak detection tape.

[0158] For example, the processor (210) may use an icing detection model to determine whether at least one first image contains icing based on the first image. In another example, the processor (210) may use various image processing techniques to determine whether at least one first image contains discoloration of the leak detection tape based on the first image.

[0159] Meanwhile, a detailed description of a method for determining whether icing is included in at least one first image using an icing detection model and a method for determining whether discoloration of a leak detection tape is included in at least one first image using various image processing techniques is omitted as it has been described above with reference to FIGS. 2 and 3.

[0160] In one embodiment, the processor (210) may provide a leak notification based on the identification of a specific area (500).

[0161] For example, the processor (210) may provide a leak notification to the control room, including information about the location of ‘Zone 3’, which is a specific zone (500) where an ammonia leak has occurred, based on the identification of ‘Zone 3’ as a specific zone (500).

[0162] In another example, the processor (210) may provide a leak notification, such as a siren sound, to a specific zone (500) where an ammonia leak has occurred, that is, 'Zone 3'.

[0163] Meanwhile, if a specific area (500) is not identified, the processor (210) may repeatedly perform the processes of steps 310 and 320 described above with reference to FIG. 3 until the specific area (500) is identified.

[0164] In one embodiment, the processor (210) can control at least one camera (510, 520) installed in a specific area (500).

[0165] According to one embodiment, the processor (210) may switch the leak detection camera (510) that has captured the first image related to the ammonia leak among at least one camera (510, 520) installed in a specific area (500) to a fixed mode, and switch the camera (520) other than the leak detection camera among at least one camera (510, 520) installed in the specific area to a safety monitoring mode.

[0166] For example, the processor (210) can switch the 3-1 camera (510), which corresponds to the leak detection camera (510), to a fixed mode, and switch the 3-2 camera (520), excluding the 3-1 camera (510), to a safety monitoring mode.

[0167] Meanwhile, detailed descriptions of the fixed mode and safety monitoring mode are omitted as they have been described above with reference to FIGS. 2 and 3.

[0168] FIG. 6 is a diagram illustrating a method for a device according to one embodiment to acquire a second image.

[0169] Referring to Figure 6, multiple zones are depicted as 'Zone 1', 'Zone 2', 'Zone 3', and 'Zone 4'.

[0170] As illustrated in FIG. 6, the 1-1 camera (611) and the 1-2 camera may be installed in 'Zone 1', which is a peripheral zone (610) of a specific zone (600), the 4-1 camera (621) and the 4-2 camera may be installed in 'Zone 4', which is another peripheral zone (620) of the specific zone (600), and the 3-1 camera and the 3-2 camera may be installed in 'Zone 3', which is a specific zone (600).

[0171] Meanwhile, each camera including the 1-1 camera (611) and the 4-1 camera (621) illustrated in FIG. 6 may correspond to each camera described above with reference to FIG. 4. In addition, 'Zone 1' to 'Zone 4' illustrated in FIG. 6 may correspond to 'Zone 1' to 'Zone 4' illustrated in FIG. 4, respectively.

[0172] In one embodiment, the processor (210) can control at least one camera installed in a peripheral area (610, 620) of a specific area (600) to obtain at least one second image.

[0173] According to one embodiment, the processor (210) can switch at least one of the cameras installed in the surrounding area (610, 620) to a passage surveillance mode.

[0174] For example, the processor (210) can switch the 1-1 camera (611) installed in 'Zone 1', which is a peripheral zone (610), and the 4-1 camera (621) installed in 'Zone 4', which is another peripheral zone (620), to passage surveillance mode. At this time, the 1-1 camera (611) may be the camera that is closest to a specific zone (600) among the cameras installed in 'Zone 1', which is a peripheral zone (610), and the 4-1 camera (621) may be the camera that is closest to a specific zone (600) among the cameras installed in 'Zone 4', which is another peripheral zone (620).

[0175] Additionally, the processor (210) can acquire images captured by the 1-1 camera (611) and the 4-1 camera (621) switched to the passage surveillance mode as second images.

[0176] Meanwhile, a detailed description of the passage surveillance mode is omitted as it has been described above with reference to FIGS. 2 and 3.

[0177] According to one embodiment, the processor (210) may switch the leak detection camera that has captured the first image related to the ammonia leak among at least one camera installed in a specific area (600) to a fixed mode, and switch the cameras other than the leak detection camera among at least one camera installed in the specific area to a safety monitoring mode.

[0178] At this time, the processor (210) can acquire an image captured by a camera switched to fixed mode or safety monitoring mode as a second image.

[0179] Meanwhile, a detailed description of an embodiment in which a processor (210) controls at least one camera installed in a specific area (600) is omitted as it has been described above with reference to FIG. 5.

[0180] FIG. 7 is a drawing illustrating an example of a device monitoring the safety of passengers according to one embodiment.

[0181] Referring to FIG. 7, multiple zones are depicted as 'Zone 1', 'Zone 2', 'Zone 3', and 'Zone 4'. As depicted in FIG. 7, multiple cameras, including a 3-2 camera (710), may be installed in 'Zone 3', which is a specific zone (700).

[0182] Meanwhile, each camera including the 3-2 camera (710) illustrated in FIG. 7 may correspond to each camera illustrated in FIG. 4. In addition, 'Zone 1' to 'Zone 4' illustrated in FIG. 7 may correspond to 'Zone 1' to 'Zone 4' illustrated in FIG. 4, respectively.

[0183] In one embodiment, the processor (210) can detect a rescue target (715) within a specific area (700) based on at least one second image captured by at least one camera installed in the specific area (700). For example, the processor (210) can detect a rescue target (715) within a specific area (700) based on at least one second image captured by a 3-2 camera (710) installed in the specific area (700).

[0184] At this time, the 3-2 camera (710) may be the 3-2 camera (520) described above with reference to FIG. 5. As described above with reference to FIG. 5, the 3-2 camera (520) may be a camera switched to a safety monitoring mode.

[0185] In one embodiment, the processor (210) may provide a risk alert based on the results of the monitoring.

[0186] For example, the processor (210) may provide a danger notification to the control room based on the detection of a rescue target (715). At this time, the danger notification may include information regarding the location of the rescue target (715), etc. As an example, the processor (210) may provide information that the rescue target (715) is located in 'Zone 3' as part of the danger notification.

[0187] FIG. 8 is a drawing illustrating another example of a device monitoring the safety of passengers according to one embodiment.

[0188] Referring to FIG. 8, multiple zones are illustrated as 'Zone 1', 'Zone 2', 'Zone 3', and 'Zone 4'. As illustrated in FIG. 8, multiple cameras including the 4-1 camera (820) may be installed in 'Zone 4' (810), which is one of the surrounding zones of a specific zone (800).

[0189] In one embodiment, the processor (210) may detect a passenger (825) approaching a specific area (800) based on at least one second image captured by at least one camera installed in the surrounding area.

[0190] Referring to FIG. 8, a passenger (825) located in 'Zone 4' (810), which is one of the surrounding zones, is shown approaching 'Zone 3', which is a specific zone (800). For example, the processor (210) can detect a passenger (825) approaching a specific zone (800) based on at least one second image captured by the 4-1 camera (820).

[0191] At this time, the 4-1 camera (820) may be the 4-1 camera (621) described above with reference to FIG. 6. As described above with reference to FIG. 6, the 4-1 camera (820) may be a camera switched to passage surveillance mode.

[0192] In one embodiment, the processor (210) may provide a risk alert based on the results of the monitoring.

[0193] For example, the processor (210) may provide a danger alert to the control room based on the detection of a passenger (825) approaching a specific zone (800). At this time, the danger alert may include information regarding the location of the passenger (825) approaching the specific zone (800). As an example, the processor (210) may provide, as part of the danger alert, that the passenger (825) approaching the specific zone (800) is located in 'Zone 4' (810).

[0194] If an ammonia leak is detected, the ship's onboard fire suppression system may be activated. For example, ammonia is classified as a hazardous gas and can pose a risk to passengers. To protect passengers, a fire suppression system may be installed onboard. This system may include sprinklers or air circulation systems to remove the leaked ammonia gas.

[0195] When an ammonia leak is detected, the processor (210) can guide the leaked ammonia through an air circulation device to an ammonia treatment device (e.g., a scrubber, an absorption tank, etc.) and circulate it.

[0196] For example, if the processor (210) identifies a specific area (500) where ammonia has leaked among a plurality of areas based on the first image, or detects a person to be rescued within the specific area based on the second image, the processor (210) may activate an ammonia gas disaster prevention device within the ship.

[0197] The embodiments of the present disclosure described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. In this case, the medium may include a magnetic medium such as a hard disk, a floppy disk, and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a hardware device specifically configured to store and execute program instructions, such as a ROM, a RAM, a flash memory, etc.

[0198] Meanwhile, the computer program may be specifically designed and configured for the present disclosure, or may be known and available to those skilled in the computer software field. Examples of computer programs may include not only machine language code, such as that generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

[0199] The specific implementations described in this disclosure are merely exemplary embodiments and do not limit the scope of the present disclosure in any way. For the sake of brevity, descriptions of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the lines connecting or connecting members between components depicted in the drawings are merely exemplary functional connections and / or physical or circuit connections, and may be replaced or represented as various additional functional connections, physical connections, or circuit connections in an actual device. Furthermore, unless specifically stated as "essential," "important," or the like, a component may not be absolutely necessary for the application of the present disclosure.

[0200] The use of the term "above" and similar referential terms in the specification of this disclosure (especially in the claims) may refer to both the singular and the plural. Furthermore, if a range is described in this disclosure, it includes disclosures applying individual values ​​within the range (unless otherwise stated), and is equivalent to describing each individual value constituting the range in the detailed description of the invention. Finally, unless the order of the steps constituting the method according to this disclosure is explicitly stated or otherwise stated to the contrary, the steps may be performed in any suitable order. The disclosure is not necessarily limited by the order in which the steps are described. Any use of examples or exemplary terms (e.g., "for example," etc.) in this disclosure is merely intended to further illustrate the disclosure, and the scope of the disclosure is not limited by the examples or exemplary terms, unless otherwise defined by the claims. Furthermore, those skilled in the art will appreciate that various modifications, combinations, and variations may be made within the scope of the appended claims or their equivalents, depending on design conditions and factors.

Claims

1. A step of acquiring at least one first image captured by at least one camera that performs shooting along a preset path within each zone; A step of identifying a specific area where ammonia has leaked among each of the areas based on the first image acquired above; A step of controlling at least one camera installed in the specific area or in a surrounding area of ​​the specific area to acquire at least one second image; and A step of monitoring the safety of passengers based on the second image acquired above; including; How to detect ammonia leaks.

2. In paragraph 1, The step of obtaining the first image is as follows: comprising the step of acquiring at least one first image including at least one of the leak detection tapes and pipes installed within each of the above zones; method.

3. In paragraph 1, The step of identifying the above specific area is: A step of determining whether at least one of icing and discoloration of the leak detection tape is included in the at least one first image; method.

4. In paragraph 1, The above controlling step is, A step of switching a leak detection camera, which has captured a first image related to the ammonia leak among at least one camera installed in the specific area, to a fixed mode; and A step of switching a camera, excluding the leak detection camera, among at least one camera installed in the specific area, to a safety monitoring mode; method.

5. In paragraph 1, The above controlling step is, A step of switching at least one camera among the cameras installed in the above surrounding area to a passage surveillance mode; method.

6. In paragraph 1, The above monitoring steps are: A step of detecting a person to be rescued within the specific area based on at least one second image captured by at least one camera installed in the specific area; method.

7. In paragraph 1, The above monitoring steps are: A step of detecting a passenger approaching the specific area based on the at least one second image captured by at least one camera installed in the surrounding area; method.

8. In paragraph 6, The above monitoring steps are: If the above rescue target is detected, the step of switching the camera that captured the rescue target within the specific area to a fixed mode is further included. method.

9. In paragraph 1, The above method, further comprising a step of providing a leak notification based on the identification of said specific area; method.

10. In paragraph 1, The above method, Further comprising a step of providing a risk notification based on the results of performing the above monitoring; method.

11. In paragraph 1, The above method, If a specific area where ammonia has leaked is identified based on the first image acquired above, a step of operating a fire prevention system within the ship is further included. method.

12. In paragraph 6, The above method, Further comprising a step of detecting a rescue target within the specific area based on one second image, and then operating a disaster prevention system within the specific area; method.

13. In paragraph 2, The above leak detection tape, Installed in the ammonia leakage vulnerable part of the above pipe, method.

14. Memory in which at least one program is stored; and By executing at least one program, a processor is included that performs an operation, The above processor, Acquire at least one first image captured by at least one camera that performs shooting along a preset path within each zone, Detecting ammonia leakage occurring in a specific area among each of the above areas based on the above first image, Providing a notification based on the detection of the above leak, controlling at least one camera installed in the specific area and at least one camera installed in the surrounding area of ​​the specific area, Obtaining at least one second image captured by the above-described controlled camera, and monitoring the safety of passengers based on the obtained second image. A device for detecting ammonia leaks.

15. A computer-readable recording medium storing a program for executing the method according to paragraph 1.

Images