Remote intelligent closed circuit television monitoring system

Abstract

The invention discloses a remote intelligent closed circuit television monitoring system, and belongs to the field of ship safety monitoring. The system comprises a switch which is used for being connected with each monitoring camera of a video acquisition end, receiving monitoring video data, sending the monitoring video data to a storage module for storage, and sending the monitoring video data to an AI calculation module for early warning monitoring identification; the AI calculation module is used for generating early warning information under the condition that the monitoring information meeting the early warning triggering condition is recognized, generating a control instruction according to a preset target display device corresponding to the early warning information, and sending the control instruction to the switch; the switch is used for sending the early warning information to the target display equipment; and after the target display equipment of the early warning display end receives the early warning information, performing early warning prompt. According to the technical scheme, intelligent early warning can be carried out timely and accurately, early warning monitoring covers all directions, the consumption of labor cost is reduced, and meanwhile the safety of ship operation is improved.

Description

Technical Field

[0001] The present invention relates to the field of ship design technology, and in particular to a remote intelligent closed-circuit television monitoring system. Background Art

[0002] With the rapid development of technology, industries such as maritime transportation have also experienced rapid growth and development. Currently, CCTV systems used on ships utilize a combination of cameras, system cabinets, and monitors for conventional local monitoring services. These monitors must be placed in locations where personnel are on duty, and the status of key locations on board is monitored manually. If an anomaly is detected, an early warning notification is issued via the ship's communication equipment. This form of manual monitoring can lead to delayed early warning notifications, resulting in delayed responses to emergency situations and potentially significant consequences. Furthermore, manual monitoring can lead to oversights, resulting in safety hazards that go unnoticed. Furthermore, manual monitoring requires staff to be on duty in shifts, which consumes significant human resources. Therefore, overcoming the many challenges associated with manual monitoring presents a pressing technical challenge in this field. Summary of the Invention

[0003] The present invention provides a remote intelligent CCTV monitoring system designed to address the problems of delayed warnings, missed warnings, and high human resource consumption associated with manual monitoring. This technical solution utilizes an AI-based CCTV monitoring system to efficiently identify surveillance video data. Upon identifying information that triggers a warning, a pre-established warning mechanism is used to generate a warning notification. This system provides timely and accurate warnings, and provides comprehensive monitoring coverage, reducing labor costs and improving the safety of vessel operations.

[0004] In a first aspect, an embodiment of the present application provides a remote intelligent closed-circuit television monitoring system, the system comprising a video acquisition terminal, a CCTV cabinet, and an early warning display terminal; The CCTV cabinet includes a switch, a storage module, and an AI computing module; the warning display terminal includes at least one ship-side display device and a shore-side display device; the shore-side display device is connected to the switch via satellite communication; The switch is used to connect to each surveillance camera of the video acquisition end, receive surveillance video data, and send the surveillance video data to the storage module for storage, and send it to the AI computing module for early warning monitoring and identification; The AI computing module is configured to generate warning information upon identifying monitoring information that meets the warning triggering condition, and generate a control instruction based on a preset target display device corresponding to the warning information, and send the control instruction to the switch; The switch is used to send the warning information to the target display device; After receiving the warning information, the target display device of the warning display terminal issues a warning prompt.

[0005] In a second aspect, an embodiment of the present application provides a remote intelligent closed-circuit television monitoring method, which includes being executed by the above-mentioned remote intelligent closed-circuit television monitoring system.

[0006] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the remote intelligent closed-circuit television monitoring method as described above.

[0007] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the remote intelligent closed-circuit television monitoring method as described above is implemented.

[0008] The remote intelligent closed-circuit television monitoring system provided in the embodiment of the present application automatically identifies warning information through the AI computing module and controls the sending of warning information, so that the system does not require manual supervision throughout the entire process, effectively solving the problems of delayed and easy omissions in traditional manual monitoring warnings, reducing human resource consumption, and at the same time, with the help of communication networks and satellite communications, realizing warnings on both ends of the ship and the shore, allowing managers to obtain warning information in a timely manner, and to understand and disseminate warning information remotely and respond quickly, thereby improving the intelligence level of ship monitoring and the safety of ship navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 This is a schematic diagram of the architecture of the remote intelligent closed-circuit television monitoring system provided in Example 1 of the present application; Figure 2 This is a schematic diagram of the architecture of the remote intelligent closed-circuit television monitoring system provided in Example 2 of the present application; Figure 3 This is a schematic diagram of the structure of the remote intelligent closed-circuit television monitoring system provided in Example 3 of the present application; Figure 4 This is a structural diagram of the electronic device provided in Example 5 of the present application. DETAILED DESCRIPTION

[0010] To further clarify the objectives, technical solutions, and advantages of this application, specific embodiments of this application are described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are intended only to illustrate this application and are not intended to limit it. It should also be noted that, for ease of description, the drawings only illustrate portions relevant to this application, not all of them. Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts depict the various operations (or steps) as sequential processes, many of the operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process may terminate upon completion of its operations, but may also include additional steps not shown in the accompanying drawings. The process may correspond to a method, function, procedure, subroutine, subprogram, and the like.

[0011] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0012] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0013] The remote intelligent closed-circuit television monitoring system provided by the embodiment of the present application is described in detail below through specific embodiments and application scenarios in conjunction with the accompanying drawings.

[0014] Example 1 Figure 1 This is a schematic diagram of the architecture of the remote intelligent closed-circuit television monitoring system provided in Example 1 of this application. Figure 1 As shown, the system includes a video acquisition terminal 10, a CCTV cabinet 20 and an early warning display terminal 30; The CCTV cabinet 20 includes a switch 201, a storage module 202, and an AI computing module 203; the warning display terminal 30 includes at least one ship-side display device and a shore-side display device; the shore-side display device is connected to the switch via satellite communication; The switch 201 is used to connect to each surveillance camera of the video acquisition terminal 10, receive surveillance video data, and send the surveillance video data to the storage module 202 for storage, and send it to the AI calculation module 203 for early warning monitoring and identification; The AI calculation module 203 is configured to generate warning information upon identifying monitoring information that meets the warning triggering condition, and generate a control instruction based on a preset target display device corresponding to the warning information, and send the control instruction to the switch 202; The switch 202 is configured to send the warning information to the target display device; After receiving the warning information, the target display device of the warning display terminal 30 issues a warning prompt.

[0015] The video acquisition terminal 10 consists of surveillance cameras distributed across different areas of the ship. Some or all of these cameras may have zoom and infrared fill-light capabilities, responsible for collecting real-time surveillance video data. The CCTV cabinet 20, which can be a physical cabinet, processes and distributes surveillance video data. The warning display terminal 30, including both ship-side and shore-side display devices, serves as a human-computer interface for receiving and displaying warning information. These two devices can be one or more.

[0016] Switch 201 is a multi-port data exchange device responsible for building an internal network and enabling data transmission between modules. Storage module 202 is a large-capacity hard disk array used for long-term storage of surveillance video data. AI computing module 203 can be a computing unit integrated with an AI chip, running deep learning algorithms to analyze video content.

[0017] Satellite communication connection refers to the communication link that uses satellite network to realize ship-to-shore data transmission, ensuring that ships can communicate with shore-based systems in all sea areas around the world.

[0018] Surveillance video data refers to the raw video information stream captured by cameras, including real-time monitoring images of the ship's interior and exterior. The switch establishes a physical connection with each surveillance camera through a network interface, forming a data transmission channel for the video stream. The switch continuously receives the video data stream from the camera and distributes the received video data simultaneously to the storage module and the AI computing module.

[0019] Warning trigger conditions are pre-set rules for identifying abnormal scenarios. For example, if a person is not on duty or the device temperature is too high, these conditions can be determined to have been met, and a warning message can be issued. The warning message can include data packets containing key information such as the abnormal event type, occurrence time, and location.

[0020] The control instruction refers to the signal generated by the AI computing module for controlling the transmission path of the warning information, such as executing the warning information to display the warning information on display device 1 and display device 3 in the ship-side display device.

[0021] In this solution, an AI algorithm analyzes video content in real time, comparing it against pre-set rules to determine if anomalies exist. When a scenario meeting the warning criteria is detected, an alert message and corresponding control instructions are automatically generated. The control instructions are then passed to the switch, instructing it on how to distribute the alert information. Based on the control instructions, the switch transmits the alert information to the target display device. The target display device can include only ship-side display devices, only shore-side display devices, or both.

[0022] After receiving warning information from the switch, the display device issues warning prompts, such as through sound and light alarms, screen pop-ups, etc., to remind managers to pay attention to abnormal events.

[0023] The remote intelligent CCTV monitoring system provided in this embodiment provides real-time intelligent warnings through a fully automated process encompassing data collection, transmission, analysis, and early warning. This system utilizes AI algorithms to replace manual real-time video monitoring, addressing the delays and omissions inherent in traditional manual monitoring. Furthermore, it enables collaborative ship-shore management, overcoming communication limitations through the use of satellite communications, allowing shore-based management personnel to intervene in vessel anomalies in real time. Automated monitoring reduces the need for human oversight, saving on monitoring personnel costs. Furthermore, this early warning method facilitates subsequent big data analysis, further enhancing vessel navigation safety.

[0024] Example 2 Figure 2 This is a schematic diagram of the remote intelligent closed-circuit television monitoring system architecture provided in Example 2 of this application. This embodiment has been further optimized, specifically as follows: the warning display terminal also includes a smart mobile device; the smart mobile device is connected to the AI computing module via a local area network; the AI computing module is also used to send the warning information to the smart mobile device via the local area network when the target display device corresponding to the warning information includes the smart mobile device. Figure 2 As shown: The warning display terminal 30 also includes a smart mobile device; The smart mobile device is connected to the AI computing module 203 via a local area network; The AI calculation module 203 is further configured to send the warning information to the smart mobile device via a local area network when the target display device corresponding to the warning information includes the smart mobile device.

[0025] Smart mobile devices can refer to portable terminals such as smartphones and tablets that are equipped with an operating system, installed with appropriate applets, or possess appropriate data processing capabilities. On ships, these devices are typically carried by crew members or management personnel and support the receipt of real-time warning information via the ship's local area network.

[0026] The local area network connection is a wireless communication network built inside the ship, such as Wi-Fi. It provides a data transmission channel between smart mobile devices and the AI computing module 203, enabling real-time communication between devices.

[0027] In this solution, the smart mobile device can be incorporated into the component of the warning display terminal 30. When the AI calculation module 203 determines that a warning is required to be issued to the smart mobile device, the warning data is pushed to the target device via the local area network.

[0028] The technical solution provided by this embodiment can achieve full-area coverage of early warning. As long as the crew is on board the ship and the early warning information notification function is enabled, they can receive early warning information in real time through their mobile devices at any location. Smart mobile devices support instant interaction and, combined with GPS positioning, can quickly dispatch the nearest personnel to the scene. Response efficiency can be significantly improved, especially in complex working conditions. The early warning system constructed by this embodiment can optimize human resource allocation while improving safety assurance capabilities.

[0029] Based on the above embodiments, optionally, the AI calculation module 203 is specifically configured to: Obtain the monitoring area corresponding to each monitoring video data; According to the warning logic corresponding to each monitoring area, the monitoring video data in each monitoring area is subjected to warning trigger identification; wherein, the warning logic includes identifying at least one of the following behaviors: looking out, answering and making phone calls, sleeping, smoking, absence from work, and not wearing a helmet, and generates warning information when the warning behavior is identified.

[0030] Among them, the monitoring area refers to a specific space range in the ship that has been pre-divided, such as the bridge, engine room, deck operation area, etc. Each area corresponds to different cameras and exclusive warning rules.

[0031] Early warning logic is a set of pre-set behavior recognition rules that includes recognition models for various abnormal behaviors. For example, lookout behavior recognition detects whether crew members are continuously observing the window or surveillance equipment, analyzing head posture and line of sight. Phone call recognition identifies characteristic movements, such as holding a phone close to the ear, and uses ambient audio analysis to assist in judgment. Sleeping behavior recognition uses posture detection, such as lowered head, closed eyes, and prolonged stillness. Smoking behavior recognition identifies features such as smoke, open flames, and handheld cigarettes, combined with smoke diffusion trajectory analysis. Absence recognition uses a presence detection algorithm to determine whether a specific position has been unattended for a specified period of time. Helmet-less identification uses key point detection on the human body and matching helmet color / shape features.

[0032] In this solution, feature extraction can be performed based on surveillance video data, and target detection can be performed on video frames to identify the position and posture of target objects such as people and equipment. Based on time-series video frames, the target's movement trajectory is analyzed and the extracted behavioral features are compared with the preset warning logic. For example, for lookout behavior, it is determined whether the head has not turned towards the porthole within 30 seconds; for smoking behavior, it is detected that an orange flame-like object is combined with hand movements, and so on. When a behavior that meets the warning conditions is identified, structured data containing the following elements can be encapsulated, such as: Event type: No lookout; Timestamp: 16:30:30; Location: Deck; Risk level: Level II; After sorting the above data, early warning information can be obtained and sent to the corresponding display device for display.

[0033] This solution, through real-time monitoring of factors such as personnel behavior, safety regulations, and on-duty personnel, can simultaneously identify various safety hazards with high accuracy, significantly reducing false alarm rates. This refined behavior recognition mechanism can accurately capture various safety hazards in complex ship environments, enabling real-time intelligent monitoring and improving the safety of ship operations.

[0034] Based on the above embodiments, optionally, the AI calculation module further obtains ship status information and time information through the system signal interface; The AI calculation module is specifically configured to determine, based on the ship status information and time information, a current warning logic that matches the current ship status information and time information; Based on the current warning logic, warning trigger identification is performed on the monitoring video data in each monitoring area.

[0035] Ship status information is the real-time operating status of the ship obtained through the system signal interface, such as the navigation status provided by the AIS system, such as data such as underway, anchored, docked in port, speed and heading.

[0036] Time information is the precise time input by the master clock system, which is used to determine whether the current moment belongs to the different operating periods of the ship, such as navigation period, loading and unloading period, and rest period.

[0037] The current warning logic is a set of warning rules dynamically selected by the AI computing module based on the real-time ship status and time. Different states and time periods correspond to different warning strategy combinations. This solution maps ship status information to pre-set status categories. Time information is used to determine which pre-set operating period the current state falls into. A pre-defined warning logic library is used to retrieve the rule combination that matches the current state and time period. For example, when underway and during working hours, high-priority warnings such as "lookout behavior" and "making or receiving phone calls" are enabled. When docked and during rest periods, only key warnings such as "fire smoke" and "illegal intrusion" are retained. Recognition of surveillance video data is then performed based on the current warning logic.

[0038] This technical solution uses AI algorithms to dynamically match ship status and time information to achieve intelligent recognition of behaviors such as lookout and smoking. Combined with multi-terminal warning push, it can improve the intelligence of monitoring and warning, avoid the generation and sending of invalid warning information, and improve the fit between warning information and real needs.

[0039] Based on the above embodiments, optionally, the ship status information is obtained based on an AIS signal; and the time information is obtained based on a master clock signal.

[0040] The acquisition of ship status information can be achieved by collecting ship dynamic data in real time through the ship Automatic Identification System (AIS) signal interface, including key parameters such as navigation status, position coordinates, speed, and heading, providing the system with the ship's current operating environment and spatial position information.

[0041] Time information acquisition relies on the master clock signal interface to access the ship's unified timing system to obtain a high-precision time reference, ensure time synchronization across the entire system, and provide a unified timeline reference for behavior analysis and early warning triggering.

[0042] This solution, through the deep integration of AIS and master clock signals, can perform more accurate intelligent monitoring and early warning, significantly improving the intelligence level of ship safety monitoring.

[0043] Based on the above embodiments, optionally, the ship status information includes navigation working status, anchoring operation status and port rest status.

[0044] When in the navigation working state, the AIS signal may indicate that the ship is underway. At this time, the system automatically activates the highest level of safety monitoring, focusing on detecting behaviors of bridge personnel that affect navigation safety, such as lookout behavior, making or receiving phone calls, etc., while strengthening visual monitoring of the operating status of key equipment.

[0045] In the anchoring operation state, when the ship is anchored and loading and unloading operations are underway, the system will monitor the center of gravity and shift it to the deck area to identify whether personnel are wearing safety helmets and complying with cargo handling regulations. At the same time, it will monitor the anchor chain status and the dynamics of surrounding ships to prevent collision risks.

[0046] In the rest state at port, when the ship is docked and has no operation plan, the system enters a low-power monitoring mode, retaining only abnormal intrusion and fire warnings in key areas. At the same time, it combines the master clock time to determine whether it is in a non-working period, and automatically reduces the frequency of detection of personnel behavior norms.

[0047] By dividing different states, this solution can perform different levels of monitoring and early warning for different states, improve the effectiveness of early warning information, and avoid the problem of low accuracy of early warning information caused by misidentification.

[0048] Based on the above embodiments, optionally, the AI computing module is further configured to: Determining the duration of the surveillance video associated with the warning information based on the warning triggering condition; The surveillance video data of the corresponding surveillance video duration is retrieved from the storage module.

[0049] The AI computing module automatically determines the duration of surveillance footage associated with the warning based on pre-set alert trigger conditions, such as neglect of lookout duties, smoking, and other specific violations. For example, for neglect of lookout duties, the system might rewind 30 seconds of footage to fully document the ongoing absence of lookouts; for smoking, it might retrieve a one-minute video, covering the entire process from lighting the cigarette to smoking. Once the duration is determined, the AI computing module accurately retrieves the surveillance video data for the corresponding time period from the storage module, eliminating the need for manual frame-by-frame searching and enabling rapid location and extraction of evidence of violations.

[0050] Through this intelligent video retrieval mechanism, this solution can automatically capture key video clips based on the characteristics of different warning events, completely retaining the relevant information before and after the violation, providing a clear chain of evidence for responsibility determination and event analysis, and avoiding the time-consuming and omission problems of manual retrieval of long-term videos, allowing managers to obtain concentrated key information in the first time, shortening the emergency response cycle.

[0051] Based on the above embodiments, optionally, the AI computing module is further configured to: When performing target recognition on the surveillance video data, if the target in the surveillance video is smaller than a set threshold, zoom information is generated and sent to the corresponding surveillance camera through the switch.

[0052] When identifying a target in a surveillance video, the AI computing module determines the target's size in real time. If the target's displayed size is smaller than a preset threshold, the AI computing module automatically generates a zoom command, including information such as the focal length and focus position to be adjusted. This command is transmitted via a switch to the corresponding surveillance camera, which automatically zooms in, magnifying the target to a clear size, allowing the AI computing module to accurately identify the target's behavior or status.

[0053] This solution, through the use of this intelligent zoom mechanism, automatically adjusts the camera's focus without manual intervention, magnifying target details within a recognizable range. Dynamic zoom also avoids image distortion and field of view limitations associated with full-scale magnification, maintaining the integrity of the surveillance range while ensuring accurate recognition. This solution is particularly suitable for scenarios requiring a balanced view of both the overall situation and details, such as ship decks and waterway observations. It reduces missed reports or misjudgments caused by blurred targets, ensuring safe vessel operation.

[0054] Based on the above embodiments, optionally, the AI computing module is configured in the following manner: Warning logic, setting warning trigger conditions for different time periods, setting warning trigger conditions for different navigation states, setting the target display device corresponding to the warning information, and setting the recording duration and clarity when the warning information is generated.

[0055] Among them, the early warning logic configuration is to preset recognition rules for specific behaviors such as lookout behavior, answering and making phone calls, smoking, etc., such as using computer vision algorithms to analyze the head posture of people to determine the lookout status, or detecting hand movements and facial features to identify answering and making phone calls.

[0056] Time-based warning configuration is to divide different time periods according to the ship's operating schedule and set corresponding trigger conditions. For example, the sailing period is 06:00-18:00 and the rest period is 23:00-06:00.

[0057] State-based warning configuration can dynamically adjust rules based on the vessel's navigation status acquired by AIS. For example, underway, the monitoring density of bridge personnel's operational specifications can be increased, while at anchor, the focus can be on checking the compliance of cargo loading and unloading on deck.

[0058] Alert push path configuration refers to pre-setting a list of receiving terminals for different types of alert events. For example, a fire alert is pushed simultaneously to all onboard displays, the captain's mobile phone, and the shore-based safety center. A vacancy alert is only notified to the corresponding post's smart mobile device.

[0059] Recording parameter configuration refers to associating specific recording duration and clarity with different warning events.

[0060] This technical solution enables the system to have scene adaptation capabilities through this multi-dimensional configuration mechanism, and realizes intelligent monitoring of ships by deeply binding warning rules with time, space, and behavior types.

[0061] Based on the above embodiments, optionally, the system further includes: A power supply box is used to supply power to the CCTV cabinet.

[0062] The power supply box is responsible for powering the system. Through internal transformers, rectifiers, and other circuit modules, it adjusts the power provided by the ship's power supply system to the voltage and current specifications of various devices within the cabinet, such as switches, storage modules, and AI computing modules, ensuring stable operation within rated parameters.

[0063] Example 3 Figure 3 This is a schematic diagram of the structure of the remote intelligent closed-circuit television monitoring system provided in Example 3 of this application. Figure 3 As shown, the system mainly consists of the following parts: 1. CCTV system hardware: 1. CCTV system camera; According to the needs of important equipment and important work areas on board, a sufficient number of waterproof / non-waterproof cameras are configured, including corresponding junction boxes for cameras, which are used to collect monitoring information, have zoom function, and are equipped with infrared fill light capability; the cameras are connected to the switch of the CCTV system host cabinet.

[0064] 2. CCTV system main cabinet; It is used to place necessary hardware including hard disk recorders, power boxes, switches, fiber optic transceivers, etc. The hard disk recorder is used to receive the video signal of the camera and compress and store the data. The power box is used for power distribution at the system terminal. The switch is used to transmit the video stream data collected by each camera to the AI computing module, and then transmit the data to the hard disk recorder and computer host after processing. The fiber optic transceiver is used to switch long-distance cameras.

[0065] 3. CCTV system substation; It includes CCTV display screen and computer host; CCTV display screen is used to display monitoring images, and computer host serves as information control station.

[0066] 2. AI part: 1. WIFI router, used for mobile devices to access the AI intelligent system; 2. AI computing module, used to meet AI computing power requirements, placed in the CCTV system host cabinet, processes video stream data and outputs it to the host; 3. AI intelligent software system for analyzing data stream information and deep learning.

[0067] 3. External signal interface: 1. Automatic Identification System (AIS) signal input, used to input the ship's navigation status (underway, anchored, in port) into the CCTV system, and view the current basic information of the ship; 2. Master clock time signal input, used to calibrate the time of the CCTV system.

[0068] 3. Ship LAN signal output, used to output CCTV real-time monitoring data and AI analysis results to the LAN, and transmit them to the shore management platform via the satellite network.

[0069] The configuration of AI algorithms is divided into 5 groups, namely: 1. Warning logic, including cameras, warning time period, warning duration, etc.; 2. Set the warning conditions for different time periods, for example, no warning will be generated during period 1, but a warning will be generated during period 2; 3. Set warning conditions for different navigation states, for example, generate warnings during navigation but not during loading and unloading; 4. Set the equipment that generates the warning, such as host computer and camera; 5. Set the recording duration and clarity when an early warning is generated.

[0070] At the same time, the AI computing module can set behavior recognition paths based on actual needs, such as: lookout, making or receiving phone calls, sleeping behavior, absence from work, not wearing a helmet, smoking, etc. The AI algorithm uses input from the AIS to determine the ship's navigation status and input from the master clock to determine the time. By combining information from the AIS and master clock, it will form different groups of work and rest time, such as underway working time, anchoring time, port rest time, etc., and based on the pre-entered information from the ship management manual, it will determine whether each grouped behavior in the behavior recognition path is a violation. If the initial recognition target is small, the AI computing module will automatically adjust the camera for zooming and secondary recognition to ensure the reliability of the recognition effect. After the secondary judgment, if it is a violation, an early warning will be issued at the workstation, and an early warning interface will pop up on the host. At the same time, a warning message will pop up on the mobile app to remind management personnel to check the current monitoring, achieving real-time early warning.

[0071] In addition to being connected to the mobile device on board via Wi-Fi, the video stream data processed by the AI computing module is also transmitted to the CCTV system switch. The switch transmits the ship-side line to the host, and the shore-side line is output to the V-SAT satellite network and transmitted to the shore-side management platform for real-time viewing by managers.

[0072] The present invention, by utilizing AI technology, has the following advantages compared to the prior art: 1. Automatically detect abnormal behavior and issue real-time alerts. Existing technologies rely primarily on manual observation, and abnormal events often require post-event review to detect. Personnel easily fatigue during long periods of monitoring, and their attention cannot always be focused on the surveillance video, which can lead to missed detections. This invention integrates AI algorithms to analyze video stream data in real time, extracting key information. It can automatically identify abnormal behavior, immediately trigger alerts, and record abnormal events, reducing manual intervention, improving response speed, and enhancing crew safety.

[0073] 2. Remote monitoring and real-time access to monitoring records. Existing technologies rely on local monitoring and cannot achieve remote real-time management. By integrating AI algorithms, this invention can proactively send warning information to onboard equipment and shore-based management platforms, reminding managers to check warning events in real time, eliminating the need for crew members to be on duty in front of the monitoring station for long periods of time.

[0074] 3. Real-time visibility of vessel status and time zone information. Existing technologies rely solely on manual time adjustment and are unable to obtain real-time vessel status through CCTV systems. This invention, by acquiring master clock signals and AIS signals and analyzing them using AI algorithms, enables real-time visibility of vessel status and time zone information, further facilitating the operation of the ship management platform.

[0075] Example 4 The present application also provides a remote intelligent CCTV monitoring method, which can be performed by the remote intelligent CCTV monitoring system described above. For example, the following steps are performed: Receive surveillance video data, and send the surveillance video data to the storage module for storage, and send it to the AI computing module for early warning monitoring and identification; When monitoring information that meets the warning triggering conditions is identified, a warning message is generated, and a control instruction is generated according to a target display device corresponding to the pre-set warning message and sent to the switch; Sending the warning information to the target display device; After receiving the warning information, the target display device of the warning display terminal issues a warning prompt.

[0076] Furthermore, the remote intelligent CCTV monitoring method can achieve the same technical effect, and will not be described here in detail to avoid repetition.

[0077] Example 5 Figure 4 This is a schematic diagram of the structure of the electronic device provided in Example 5 of this application. Figure 4 As shown, the embodiment of the present application further provides an electronic device 400, including a processor 401, a memory 402, and a program or instruction stored in the memory 402 and executable on the processor 401. When the program or instruction is executed by the processor 401, the various processes of the above-mentioned remote intelligent closed-circuit television monitoring method embodiment are implemented, and the same technical effects can be achieved. To avoid repetition, they are not described here.

[0078] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0079] Example 6 An embodiment of the present application further provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned remote intelligent closed-circuit television monitoring system embodiment are implemented, and the same technical effects can be achieved. To avoid repetition, they are not described here.

[0080] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0081] Example 7 An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned remote intelligent closed-circuit television monitoring system embodiment, and can achieve the same technical effects. To avoid repetition, they are not described here.

[0082] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0083] It should be noted that, in this article, the terms "comprises", "includes" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0084] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of this application, or the part that contributes to the existing technology, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of this application.

[0085] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

[0086] The above are only preferred embodiments of the present application and the technical principles employed. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that are possible for those skilled in the art will not depart from the scope of protection of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments and may include more other equivalent embodiments without departing from the concept of the present application. The scope of the present application is determined by the scope of the claims.

Claims

1. A remote intelligent closed-circuit television monitoring system, characterized in that: The system includes a video acquisition terminal, a CCTV cabinet and an early warning display terminal; The CCTV cabinet includes a switch, a storage module, and an AI computing module; the warning display terminal includes at least one ship-side display device and a shore-side display device; the shore-side display device is connected to the switch via satellite communication; The switch is used to connect to each surveillance camera of the video acquisition end, receive surveillance video data, and send the surveillance video data to the storage module for storage, and send it to the AI computing module for early warning monitoring and identification; The AI computing module is configured to generate warning information upon identifying monitoring information that meets the warning triggering condition, and generate a control instruction based on a preset target display device corresponding to the warning information, and send the control instruction to the switch; The switch is used to send the warning information to the target display device; After receiving the warning information, the target display device of the warning display terminal issues a warning prompt.

2. The remote intelligent closed-circuit television monitoring system according to claim 1, characterized in that: The warning display terminal also includes a smart mobile device; The smart mobile device is connected to the AI computing module via a local area network; The AI calculation module is further configured to send the warning information to the smart mobile device via a local area network when the target display device corresponding to the warning information includes the smart mobile device.

3. The remote intelligent closed-circuit television monitoring system according to claim 1, characterized in that: The AI computing module is specifically used to: Obtain the monitoring area corresponding to each monitoring video data; According to the warning logic corresponding to each monitoring area, the monitoring video data in each monitoring area is subjected to warning trigger identification; wherein, the warning logic includes identifying at least one of the following behaviors: looking out, answering and making phone calls, sleeping, smoking, absence from work, and not wearing a helmet, and generates warning information when the warning behavior is identified.

4. The remote intelligent closed-circuit television monitoring system according to claim 3, characterized in that: The AI calculation module also obtains ship status information and time information through the system signal interface; The AI calculation module is specifically configured to determine, based on the ship status information and time information, a current warning logic that matches the current ship status information and time information; Based on the current warning logic, warning trigger identification is performed on the monitoring video data in each monitoring area.

5. The remote intelligent closed-circuit television monitoring system according to claim 4, characterized in that: The ship status information is obtained based on the AIS signal; the time information is obtained based on the master clock signal.

6. The remote intelligent closed-circuit television monitoring system according to claim 5, characterized in that: The ship status information includes the navigation working state, the anchoring operation state and the port rest state.

7. The remote intelligent closed-circuit television monitoring system according to claim 1, characterized in that: The AI computing module is further used to: Determining the duration of the surveillance video associated with the warning information based on the warning triggering condition; The surveillance video data of the corresponding surveillance video duration is retrieved from the storage module.

8. The remote intelligent closed-circuit television monitoring system according to claim 1, characterized in that: The AI computing module is further used to: When performing target recognition on the surveillance video data, if the target in the surveillance video is smaller than a set threshold, zoom information is generated and sent to the corresponding surveillance camera through the switch.

9. The remote intelligent closed-circuit television monitoring system according to claim 1, characterized in that: The AI computing module is configured as follows: Warning logic, setting warning trigger conditions for different time periods, setting warning trigger conditions for different navigation states, setting the target display device corresponding to the warning information, and setting the recording duration and clarity when the warning information is generated.

10. The remote intelligent closed-circuit television monitoring system according to claim 1, characterized in that: The system further comprises: A power supply box is used to supply power to the CCTV cabinet.

Images