Object observation system and method applied to ship and electronic equipment

Abstract

The invention relates to the field of ships, and provides a navigation obstruction observation system and method applied to a ship and electronic equipment, and the system comprises a shipborne system and a shore-based system; the shipborne system comprises: an information acquisition unit for acquiring environmental information of a ship; the navigation obstruction identification unit is used for identifying the environment information based on a navigation obstruction identification model and obtaining an identification result, and the navigation obstruction identification model is obtained through pre-training of a shore-based system; the early warning unit is used for carrying out early warning based on the identification result; and the shore-based system is used for acquiring the environmental information of the ship and training and updating the navigation obstruction identification model based on the environmental information. The method and the device are used for solving the defects that the navigation obstacles on the sea surface cannot be accurately recognized by a navigation obstacle recognition method in the related technology, and the safety of ship navigation cannot be guaranteed, the navigation obstacles on the sea surface can be recognized based on a recognition model obtained through pre-training, and the safety of ship navigation can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ships, and in particular to a navigation obstruction observation system and method, and electronic equipment applied to ships. Background Art

[0002] With the rapid development of offshore aquaculture, marine ranching, offshore wind power, and marine leisure tourism, the number of lost fishing nets, obstructing floating objects, and small boats has continued to increase, posing not only a huge threat to the safety of ship navigation, but also bringing huge challenges to the management of navigation order.

[0003] In the current relevant technology, seafaring vessels are all equipped with active detection equipment such as radar. However, since the electromagnetic reflection cross-section of obstructing floating objects and small boats is very small, it is difficult for radar to detect them. Even if the ship's crew strengthens their lookout, due to the limitation of human visual range, they are often too close to maneuver the ship to avoid them by the time they find them, which in turn causes safety accidents. In addition, some obstructions that are difficult to find are often more likely to cause major accidents. For example, floating fishing nets on the sea are extremely difficult to find. Once a ship's propeller thruster is entangled in the fishing nets, it is not only difficult to clean it, but in serious cases it may also cause the ship to lose power, which can easily lead to major maritime accidents.

[0004] There are also methods of using neural networks to identify obstacles in related technologies, but such algorithms in related technologies cannot identify obstacles on the sea surface in real time, and the safety of ship navigation cannot be guaranteed. Summary of the invention

[0005] The present invention provides an obstruction lookout system and method, and electronic equipment applied to ships, so as to solve the defect that the obstruction identification method in the related art cannot accurately identify the obstructions on the sea surface, and the safety of the ship's navigation cannot be guaranteed. In the scheme of the present application, the obstructions on the sea surface can be identified based on the recognition model obtained by pre-training, so that the ship itself can identify the obstructions based on the recognition model, and the real-time performance of the obstruction identification can be improved compared with the navigation radar and personnel lookout. Moreover, the recognition model can be continuously updated during the use process, and the recognition accuracy can be continuously improved, which can effectively improve the safety of the ship's navigation.

[0006] The present invention provides a navigation obstruction observation system applied to ships, comprising a ship-borne system arranged on the ship and a shore-based system arranged on a shore, wherein the ship-borne system and the shore-based system are wirelessly connected;

[0007] The shipboard system comprises:

[0008] An information acquisition unit, used to acquire environmental information of the ship, wherein the environmental information represents the surrounding environment in the direction of the ship's travel;

[0009] an obstacle recognition unit, used to recognize the environmental information based on an obstacle recognition model and obtain a recognition result, wherein the obstacle recognition model is pre-trained by the shore-based system;

[0010] An early warning unit, used for issuing an early warning based on the recognition result;

[0011] The shore-based system is used to obtain environmental information of the ship and train and update the obstacle recognition model based on the environmental information.

[0012] According to the obstruction observation system for ships provided by the present invention, the shore-based system is communicatively connected with the ship-borne system, and the ship-borne system is arranged in the corresponding ship;

[0013] The shipborne system is used to send the environmental information of the corresponding ship to the shore-based system, and the shore-based system is used to train the navigation obstacle identification standard model based on the environmental information of the corresponding ship acquired by the shipborne system, and the navigation obstacle identification standard model is stored in the shore-based system;

[0014] The shore-based system is also used to update the obstacle recognition model of the shipborne system based on the trained obstacle recognition standard model.

[0015] According to the obstacle observation system for ships provided by the present invention, the shore-based system updates the obstacle recognition model of the shipborne system based on the trained obstacle recognition standard model according to a preset update rule.

[0016] According to the obstacle observation system for ships provided by the present invention, the shore-based system is also used to send remote control instructions to the ship-borne system, and the remote control instructions include instructions for obtaining camera control rights of the ship-borne system to obtain video information of the sea area where the ship is located.

[0017] According to the obstruction observation system for ships provided by the present invention, the shipborne system also includes a first communication management unit, which is used to automatically select a communication mode based on the status information of the ship, the status information of the ship includes the signal strength of 700M 5G and 5G communication networks, and the communication mode includes 700M 5G, 5G communication and satellite communication.

[0018] According to the obstruction observation system for ships provided by the present invention, the shore-based system includes a second communication management unit, which is used to determine the availability of the communication link based on the communication importance level and the economic efficiency of the communication cost, and the communication link includes 700M 5G, 5G communication network and satellite communication.

[0019] According to the obstruction lookout system for ships provided by the present invention, the early warning unit is also used to classify the recognition results into early warning levels, and determine the notification method and notification personnel of the early warning information based on a preset early warning plan and the early warning level, and the notification method includes a system client, WeChat applet, and text message.

[0020] According to the obstruction observation system applied to a ship provided by the present invention, the environmental information of the ship includes image information;

[0021] The obstacle recognition unit is further used to pre-process the acquired image information, and the pre-processing is used to improve the clarity of the image information.

[0022] The preprocessing includes extracting features from the image information and eliminating background noise.

[0023] The present invention also provides a method for observing obstructions to ships, which is executed by a ship-borne system and includes:

[0024] Acquiring environmental information of the ship, wherein the environmental information represents the surrounding environment in the direction of the ship's travel;

[0025] Identify the environmental information based on an obstacle recognition model and obtain a recognition result, the obstacle recognition model is pre-trained, and the recognition result represents obstacles around the channel in the forward direction of the ship;

[0026] An early warning is issued based on the identification result.

[0027] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, any of the above-mentioned methods for observing obstructions to ships is implemented.

[0028] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program implements any of the above-mentioned methods for observing obstructions to ships.

[0029] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for observing obstructions to ships.

[0030] The obstruction lookout system for ships provided in the present application includes a ship-borne system respectively arranged on the ship and a shore-based system arranged on the shore, wherein the ship-borne system is equipped with an obstruction recognition model, so that the ship itself can identify obstacles based on the recognition model, which can improve the real-time nature of obstacle recognition compared with navigation radar and personnel lookout. The obstruction recognition model can identify obstacles in real time based on the acquired information about the surrounding environment in the direction of travel. If an obstruction is identified, a timely warning can be issued to improve the safety of ship navigation. At the same time, the shore-based system can also obtain the environmental information of the ship. The environmental information of the ship obtained by the shore-based system is used to continuously train and update the obstruction recognition model. In this way, with the use of the obstruction lookout system, the accuracy of the obstruction recognition model will become higher and higher, further improving the safety of ship navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 Schematic diagram of the structure of the navigation obstruction observation system provided by the embodiment of the present invention;

[0033] Figure 2 This is one of the flow charts of the method for observing obstructions to navigation provided by an embodiment of the present invention;

[0034] Figure 3 This is a second flow chart of the method for observing obstructions to navigation provided by an embodiment of the present invention;

[0035] Figure 4 It is a schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Figure 1 It is a schematic diagram of the structure of a navigation obstruction observation system provided by an embodiment of the present invention.

[0038] like Figure 1As shown, this embodiment provides a navigation obstruction observation system applied to ships, including a ship-borne system arranged on the ship and a shore-based system arranged on the shore, wherein the ship-borne system and the shore-based system are wirelessly connected;

[0039] The shipboard system comprises:

[0040] An information acquisition unit, used to acquire environmental information of the ship, wherein the environmental information represents the surrounding environment in the direction of the ship's travel;

[0041] an obstacle recognition unit, used to recognize the environmental information based on an obstacle recognition model and obtain a recognition result, wherein the obstacle recognition model is pre-trained by the shore-based system;

[0042] An early warning unit, used for issuing an early warning based on the recognition result;

[0043] The shore-based system is used to obtain environmental information of the ship and train and update the obstacle recognition model based on the environmental information.

[0044] In actual applications, the shore-based system is equivalent to a fixed server, and the ship-borne system is equivalent to a mobile terminal. The shore-based system acting as a server can be connected to multiple ship-borne systems at the same time.

[0045] In practical applications, after the obstacle recognition unit identifies obstacles around the ship, it can automatically load the obstacle annotations into the acquired environmental data and generate corresponding alarm information to provide data services for the alarm management and visualization sharing management units. After that, the early warning unit can apply the target tracking algorithm to highlight the marked obstacles on the display end to improve the recognition efficiency of the drivers and passengers and avoid navigation risks in time. The target tracking algorithm can include existing tracking algorithms such as the TLD (Tracking-Learning-Detection) algorithm and the optical flow algorithm.

[0046] During implementation, the obstacle recognition model in the obstacle recognition unit of the shipborne system can be pre-trained by the shore-based system and transmitted to the shipborne system. At the same time, the shore-based system stores the obstacle recognition standard model, that is, the backup of the obstacle recognition model. While the shipborne system recognizes obstacles based on the obstacle recognition model, the shore-based system can also synchronously train and optimize the obstacle recognition standard model. In practical applications, the shore-based system can use the YOLO detection algorithm and the SSD detection algorithm as the basis of the model, and use the image or video data of the obstruction under the actual sea conditions as the training set. Through a large number of detailed classification and positioning training, a large number of multi-scale feature maps of obstacles such as fishing net floats, harmful floating objects, and ships under different sea conditions are constructed, and finally the standard model for identifying marine obstacles is trained. In the first training, the data of the training set can be obtained from the test ship and the network. Later, as the use progresses, the standard model for identifying obstructions can be further deeply trained based on the environmental information of the ship during actual navigation. In addition, the detailed classification and positioning training of the training set refers to distinguishing the obstructions in the training set according to their types, such as reefs, ships, and harmful floating objects. After that, the obstruction recognition model can be trained separately according to different categories. In this way, the recognition accuracy of the trained obstruction recognition model for each type of obstruction can be improved, and the actually detected obstructions can be accurately divided into corresponding categories, which is convenient for evaluating the safety level of the obstruction.

[0047] In this embodiment, the shipborne system can independently complete all functions of obstruction observation, including data acquisition, obstacle identification, and early warning. The obstruction here can include any object on the sea surface that hinders the navigation of the current ship, including naturally existing reefs, other ships, fishing nets on the sea surface, and other garbage that may affect the navigation of the ship. In actual applications, the shipborne system can identify almost all obstructions on the sea surface based on the obstruction identification model. Of course, different levels are also distinguished among obstructions, and different obstacles may have different effects on the navigation of the ship. On this basis, the early warning unit of the shipborne system can also divide different safety levels based on different obstacles when issuing an early warning based on the identification result, and issue different forms of early warning according to different safety levels. For example, if the obstruction identification unit identifies that there are reefs or other ships ahead of the ship, the highest level of early warning can be issued. If the obstruction identification unit identifies that there are obstructions that do not endanger navigation safety ahead of the ship, a low level of early warning can be issued.

[0048] In actual applications, the shore-based system can obtain environmental information about the ship's surroundings through the shipborne system. Specifically, after the shipborne system obtains the ship's environmental information through the information acquisition unit, it can upload it to the shore-based system in real time. The shore-based system can also send instructions to the shipborne system to obtain real-time environmental information in a specified time period. The ship's environmental information may include images captured by the ship's camera and videos taken.

[0049] The obstruction lookout system applied to ships provided in this embodiment includes a ship-borne system respectively arranged on the ship and a shore-based system arranged on the shore, wherein the ship-borne system is equipped with an obstruction recognition model, so that the ship itself can identify the obstruction based on the recognition model, which can improve the real-time performance of the obstruction recognition compared to transmitting data to the server for remote decision-making. The obstruction recognition model can identify the obstruction in the surrounding environment of the ship in real time based on the acquired environmental information. If the obstruction is identified, a timely warning can be issued to improve the safety of the ship's navigation. At the same time, the shore-based system can also obtain the environmental information of the ship. The shore-based system obtains the environmental information of the ship for continuous training and updating of the obstruction recognition model. In this way, with the use of the obstruction lookout system, the accuracy of the obstruction recognition model will become higher and higher, further improving the safety of the ship's navigation.

[0050] In an exemplary embodiment, the shore-based system is communicatively connected to the ship-borne system, and the ship-borne system is disposed in a corresponding ship;

[0051] The shipborne system is used to send the environmental information of the corresponding ship to the shore-based system, and the shore-based system is used to train the navigation obstacle identification standard model based on the environmental information of the corresponding ship acquired by the shipborne system, and the navigation obstacle identification standard model is stored in the shore-based system;

[0052] The shore-based system is also used to update the obstacle recognition model of the shipborne system based on the trained obstacle recognition standard model.

[0053] In implementation, as described in the above embodiment, after the shore-based system obtains the obstacle recognition model through the first training, the obstacle recognition model is sent to the ship-borne system for actual use. The shore-based system itself retains a backup of the obstacle recognition model, that is, the obstacle recognition standard model. In actual applications, the shore-based system can be connected to multiple ship-borne systems. As the ship-borne system actually works in the ship, each ship equipped with the ship-borne system can obtain a large amount of training set data containing obstacles on the sea surface. At the same time, the training set data obtained by all ships can be sent to the shore-based system. The shore-based system then continuously trains and updates the obstacle recognition standard model based on this continuous and huge training set. After the shore-based system trains and updates the obstacle recognition standard model, it can also update the obstacle recognition model given in the shipborne systems of all connected ships based on the updated obstacle recognition standard model. That is, the updating of the obstacle recognition model in the shipborne system is not linear, but step-by-step, providing technical support for improving the obstacle recognition efficiency and accuracy of the shipborne AI video obstacle observation system.

[0054] In this embodiment, the shore-based system can uniformly train the obstacle recognition model based on the training set data collected by all ships in the connected system. Compared with the targeted training for each obstacle recognition model, the training set data is more sufficient, and the obstacle recognition model trained in this way is consistent in each ship-borne model. A unified obstacle recognition model can adapt to various working conditions and has sufficiently accurate recognition capabilities for various obstacles.

[0055] In an exemplary embodiment, the shore-based system updates the obstacle recognition model of the shipborne system based on the trained obstacle recognition standard model according to a preset update rule.

[0056] In practical applications, the preset update rule may be to update the obstacle recognition model of the shipborne system at set intervals. For example, the set time may be 10 days. During implementation, the shore-based system may also set a training phase, that is, set a training target. When the obstacle recognition standard model in the shore-based system reaches a training phase, or completes a training target, the obstacle recognition model of the shipborne system is updated.

[0057] In an exemplary embodiment, the shore-based system is also used to send remote control instructions to the shipborne system, and the remote control instructions include instructions for obtaining camera control rights of the shipborne system to obtain video information of the sea area where the ship is located.

[0058] In actual applications, the shore-based system includes a data sharing unit, which is used to build a shore-based marine video data sharing platform. It uses broadband Internet to provide technical support for relevant agencies to instantly receive obstruction avoidance alarm information and view real-time and historical marine video data according to preset marine video and alarm information sub-plans.

[0059] Specifically, although the shipborne system is wirelessly connected to the shore-based system, the shipborne system has a very large degree of autonomy. During the normal navigation of the ship, all obstacles encountered can basically be independently identified and warned by the shipborne system. However, it should be noted that when the ship discovers special circumstances such as a shipwreck or other suspicious objects during navigation, it can notify the shore-based system. The shore-based system will send remote control commands to the shipborne system to obtain control of the camera, extend the visual range of the shore-based system, and provide intuitive visual information support for shipwreck rescue and suspicious object identification.

[0060] In addition, when the shore-based system completes the training of the obstacle identification standard model and hopes to update the obstacle identification model of the ship-borne system based on the trained obstacle identification standard model, a remote control command for updating the system can also be sent to the ship-borne system of each ship in the system. After receiving the remote control command, the ship-borne system can receive the updated obstacle identification standard model from the shore-based system and update the obstacle identification model loaded on itself.

[0061] In an exemplary embodiment, the shipborne system also includes a first communication management unit, which is used to automatically select a communication mode based on the status information of the ship, the status information of the ship includes the signal strength of 700M 5G and 5G communications, and the communication mode includes 700M 5G, 5G communication links and satellite communication links.

[0062] In an exemplary embodiment, the shore-based system includes a second communication management unit, which is used to determine the availability of communication links based on the communication importance level and the economic efficiency of communication costs. The communication links include 700M 5G, 5G communication networks and satellite communications.

[0063] In practical applications, the shore-based system and the ship-borne system can communicate with each other through a variety of communication methods. In implementation, the shore-based system can communicate with the ship-borne system through a data communication unit. The data communication unit can be combined with a variety of communication modules such as 700M5G, 5G, satellite, and Beidou satellite SMS. That is to say, the shore-based system can include 700M 5G, 5G, satellite communication, Beidou satellite SMS and other communication methods. In practical applications, the most suitable communication method can be flexibly selected based on the different ship-borne systems. Specifically, in this embodiment, before the shore-based system communicates with a certain ship-borne system, it can first determine the status information of the ship, specifically including the configuration, working status and communication conditions of the communication equipment loaded on the ship, and comprehensively determine the optimal communication method, communication link and communication time, etc. Among them, the standard for selecting the communication method can include selecting the method with the lowest economic cost, selecting the method with the highest communication security, selecting the method with the fastest information transmission, etc., and the communication method can be selected according to actual needs. For example, when it is necessary to update the obstacle identification model, due to the high data communication capacity of the obstacle identification model, 700M can be selected. 5G and 5G broadband communication methods. When encountering emergencies such as shipwrecks and suspicious objects, you can choose Weixin communication and Beidou SMS methods, without geographical restrictions, and establish a communication connection with the shore-based system in the fastest way of information transmission.

[0064] In this embodiment, through the communication management unit of the shipborne system and the communication management unit of the shore-based system, the obstruction observation system forms a configurable, multi-channel, intelligent ship-shore communication system, providing technical support for the full-time, efficient and economical information exchange between the ship and the shore, and realizing efficient and economical interconnection of ship-shore video and alarm information.

[0065] In an exemplary embodiment, the warning unit is also used to classify the recognition results into warning levels, and determine the notification method and notification personnel of the warning information based on a preset warning plan and the warning level. The notification methods include system client, WeChat applet, and text message.

[0066] In actual applications, after the shipborne system identifies obstacles in the surrounding environment of the ship based on the obstacle identification unit, it can make corresponding warnings based on the pre-set notification and announcement management plan. Specifically, according to different identification results, different responsible persons on the ship can be warned. The warning method can include providing a human-computer interaction window for the relevant responsible persons to instantly receive and view information such as obstacle avoidance alarms, shore-based remote control and telemetering notifications, etc. The relevant responsible persons can obtain the warning information of the obstacles based on the human-computer interaction window, and the human-computer interaction window can also provide corresponding processing methods, and the relevant responsible persons can perform corresponding processing based on this.

[0067] In an exemplary embodiment, the environmental information of the vessel includes image information;

[0068] The obstacle recognition unit is further used to pre-process the acquired image information, and the pre-processing is used to improve the clarity of the image information.

[0069] The preprocessing includes extracting features from the image information and eliminating background noise.

[0070] Specifically, an adaptive noise elimination algorithm may be used to eliminate ocean background noise. The adaptive noise elimination algorithm may use existing technology, such as an LMS algorithm or an RLS algorithm, etc., which is not limited in this embodiment.

[0071] After the preprocessing is completed, the combined data of video frames, camera latitude and longitude coordinates, compass, illumination, etc. can be formed and stored based on time. These combined data can be stored in the shipborne system and the shore-based system to provide data services for the ship's AI video obstacle observation system to display video information with high quality.

[0072] The following is a description of the method for observing obstructions applied to ships provided by the present invention. The method for observing obstructions applied to ships described below and the system for observing obstructions applied to ships described above can be referred to in correspondence with each other.

[0073] Figure 2 This is one of the flow charts of the method for observing navigation obstacles provided by an embodiment of the present invention.

[0074] like Figure 2 As shown, the method for observing obstacles to ships provided in this embodiment is executed by a ship-borne system and includes:

[0075] Step 201, obtaining environmental information of the ship, wherein the environmental information represents the surrounding environment in the direction of the ship's travel;

[0076] Step 202, identifying the environmental information based on an obstacle recognition model and obtaining a recognition result, wherein the obstacle recognition model is pre-trained, and the recognition result represents obstacles around the ship;

[0077] Step 203: issuing an early warning based on the identification result.

[0078] Figure 3 This is the second flow chart of the method for observing obstructions to navigation provided by the embodiment of the present invention.

[0079] Combine the following Figure 3 The method for observing obstructions to navigation provided in this application is described.

[0080] First, the environmental information around the ship's sailing direction can be collected based on the high-definition over-the-horizon cameras and environmental sensors installed on the ship. The shipboard system integrates and caches the collected environmental information and removes the ocean background noise. After that, the obstacles in the data can be identified based on the obstacle recognition model, and an alarm can be issued based on the recognition result. At the same time, the alarm data can also be stored for future application.

[0081] The specific implementation method of the obstruction observation method provided in this embodiment can be implemented with reference to the above embodiment and will not be repeated here.

[0082] In summary, the obstruction observation system for ships provided by the present application has the following beneficial effects:

[0083] (1) The shore-based system collects and stores a large amount of video and obstruction alarm data uploaded by the ship-borne AI video obstruction observation system, accumulates training materials under various weather and sea conditions for in-depth training of the standard model for marine obstruction identification. The YOLO detection algorithm and the SSD detection algorithm are used as the basis for the accumulated video data of obstructions under the actual sea conditions. Through a large amount of detailed classification and positioning training, multi-scale feature maps of obstructions such as fishing net floats, hazardous floating objects, and small ships are constructed to form a standard model database for marine obstruction identification. This provides a standard model update service for marine obstruction identification to improve the ship-borne AI video obstruction observation system, thereby maximizing the efficiency and accuracy of obstruction identification.

[0084] (2) The shipboard system uses a high-definition, high-viewing-range video camera system and AI video recognition technology to efficiently detect and identify obstacles while extending the ship's personnel's field of vision. This is used to make up for the blind spot of shipborne radar in detecting small obstacles, improve personnel's field of vision and efficiency, and provide technical support for timely reminding crew members to identify potential navigation safety risks, take scientific ship operation measures in a timely manner, and avoid maritime accidents;

[0085] (3) The shipborne system can also receive remote control and telesignaling commands from the shore-based marine AI video obstruction observation system, connect and share real-time and historical marine video data and obstruction alarm data in a manageable state, and use the ship as a carrier for the high-definition camera system to make up for the lack of deep-sea visualization range, and provide information support for improving the management of navigation order in the sea area, maritime search and rescue, marine environmental protection, and marine national defense security control capabilities.

[0086] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the obstruction observation method applied to the ship, and the method includes:

[0087] Acquiring environmental information of the ship, wherein the environmental information represents the surrounding environment of the ship;

[0088] Identifying the environmental information based on an obstacle recognition model and obtaining a recognition result, wherein the obstacle recognition model is pre-trained;

[0089] An early warning is issued based on the identification result.

[0090] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), disk or optical disk, etc. Various media that can store program codes.

[0091] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the obstruction observation method applied to a ship provided by the above methods, the method includes:

[0092] Acquiring environmental information of the ship, wherein the environmental information represents the surrounding environment in the direction of the ship's travel;

[0093] Identifying the environmental information based on an obstacle recognition model and obtaining a recognition result, wherein the obstacle recognition model is pre-trained;

[0094] An early warning is issued based on the identification result.

[0095] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the obstruction observation method for ships provided by the above methods, the method comprising:

[0096] Acquiring environmental information of the ship, wherein the environmental information represents the surrounding environment in the direction of the ship's travel;

[0097] Identifying the environmental information based on an obstacle recognition model and obtaining a recognition result, wherein the obstacle recognition model is pre-trained;

[0098] An early warning is issued based on the identification result.

[0099] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0100] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The obstruction observation system applied to ships is characterized by: It includes a ship-borne system arranged on a ship and a shore-based system arranged on a shore, wherein the ship-borne system and the shore-based system are wirelessly connected; The shipboard system comprises: An information acquisition unit, used to acquire environmental information of the ship, wherein the environmental information represents the surrounding environment in the direction of the ship's travel; an obstacle recognition unit, used to recognize the environmental information based on an obstacle recognition model and obtain a recognition result, wherein the obstacle recognition model is pre-trained by the shore-based system; An early warning unit, used for issuing an early warning based on the recognition result; The shore-based system is used to obtain environmental information of the ship and train and update the obstacle recognition model based on the environmental information.

2. The navigation obstruction observation system for ships according to claim 1, characterized in that: The shore-based system is communicatively connected with the ship-borne system, and the ship-borne system is arranged in a corresponding ship; The shipborne system is used to send the environmental information of the corresponding ship to the shore-based system, and the shore-based system is used to train the navigation obstacle identification standard model based on the environmental information of the corresponding ship acquired by the shipborne system, and the navigation obstacle identification standard model is stored in the shore-based system; The shore-based system is also used to update the obstacle recognition model of the shipborne system based on the trained obstacle recognition standard model.

3. The navigation obstruction observation system for ships according to claim 2, characterized in that: The shore-based system updates the obstacle recognition model of the shipborne system based on the trained obstacle recognition standard model according to the preset update rules.

4. The navigation obstruction observation system for ships according to claim 2, characterized in that: The shore-based system is also used to send remote control instructions to the ship-borne system, and the remote control instructions include instructions for obtaining camera control rights of the ship-borne system to obtain video information of the sea area where the ship is located.

5. The navigation obstruction observation system for ships according to claim 1, characterized in that: The shipborne system also includes a first communication management unit, which is used to automatically select a communication mode based on the status information of the ship, the status information of the ship includes the signal strength of the marine 700M 5G and 5G communication networks, and the communication modes include 700M 5G, 5G communication and satellite communication.

6. The navigation obstruction observation system for ships according to claim 1, characterized in that: The shore-based system includes a second communication management unit, which is used to determine the availability of communication links based on the communication importance level and the economic efficiency of communication costs. The communication links include 700M 5G, 5G communication networks and satellite communications.

7. The navigation obstruction observation system for ships according to claim 1, characterized in that: The warning unit is also used to classify the recognition results into warning levels, and determine the notification method and notification personnel of the warning information based on a preset warning plan and the warning level. The notification methods include system client, WeChat applet, and text message.

8. The navigation obstruction observation system for ships according to claim 1, characterized in that: The environmental information of the ship includes image information; The obstacle recognition unit is further used to pre-process the acquired image information, and the pre-processing is used to improve the clarity of the image information. The preprocessing includes extracting features from the image information and eliminating background noise.

9. A method for observing obstructions applied to ships, executed by a ship-borne system, characterized in that: include: Acquiring environmental information of the ship, wherein the environmental information represents the surrounding environment in the direction of the ship's travel; Identify the environmental information based on an obstacle recognition model and obtain a recognition result, the obstacle recognition model is pre-trained, and the recognition result represents obstacles around the channel in the forward direction of the ship; An early warning is issued based on the identification result.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for observing obstacles to ships as claimed in claim 9 is implemented.

Images