Waterway rescue method, system, and storage medium

Abstract

This application relates to the field of rescue technology and provides a water rescue method, system, and storage medium, including: performing a preliminary search based on a location to be searched to determine a target area, wherein the location to be searched is a suspected location where a rescue target may exist, and the target area is an area where the rescue target is preliminarily determined to exist; releasing an intelligent lifebuoy on an unmanned surface vessel (USV) in the target area, wherein the intelligent lifebuoy includes a camera device; receiving first video data transmitted by the intelligent lifebuoy, wherein the first video data is video data collected by the camera device of the intelligent lifebuoy; and transmitting the first video data to a rescue platform. This application can improve the accuracy and efficiency of water rescue.

Description

Technical Field

[0001] This application belongs to the field of rescue technology, and in particular relates to water rescue methods, systems, rescue equipment and computer-readable storage media. Background Technology

[0002] my country has abundant river basins and waterways, and in recent years, floods caused by extreme weather and other reasons have occurred frequently. In addition, with the increasing volume of ship traffic in my country, water traffic accidents have also occurred frequently, and various water disasters have made water rescue tasks increasingly arduous and difficult.

[0003] Currently, water rescue operations typically require professional rescue personnel to operate boats or helicopters for search and rescue, which results in low search and rescue efficiency and makes rescue operations difficult in extreme weather conditions. Summary of the Invention

[0004] This application provides a water rescue method, system, and storage medium, which can improve the accuracy and efficiency of water rescue.

[0005] In a first aspect, embodiments of this application provide a water rescue method applied to unmanned surface vessels, including:

[0006] A preliminary search is conducted based on the location to be searched to determine the target area. The location to be searched is a location where a rescue target is suspected to exist, and the target area is an area where the rescue target is preliminarily determined to exist.

[0007] Deploy the intelligent lifebuoy on the unmanned surface vessel in the target area; the intelligent lifebuoy includes a camera device.

[0008] The system receives first video data sent by the smart lifebuoy and sends the first video data to the rescue platform. The first video data is video data collected by the camera device of the smart lifebuoy.

[0009] Secondly, embodiments of this application provide a water rescue method applied to a rescue platform, comprising:

[0010] Target recognition is performed based on the received first video data to obtain the recognition result. The first video data is video data collected by the camera device on the smart lifebuoy in the target area.

[0011] If the identification result indicates that the rescue target exists in the target area, the target location of the existing rescue target is determined according to the location of the smart lifebuoy corresponding to the identification result, wherein the location of the smart lifebuoy is determined by the positioning device on the smart lifebuoy.

[0012] Thirdly, embodiments of this application provide a water rescue system, including a rescue platform, an unmanned boat, and an intelligent lifebuoy, wherein the intelligent lifebuoy includes a positioning device and a camera device;

[0013] The unmanned surface vessel is used to perform a preliminary search based on the location to be searched, determine the target area, and release a smart lifebuoy on the unmanned surface vessel in the target area. The location to be searched is a location where a rescue target is suspected to exist, and the target area is an area where the rescue target is preliminarily determined to exist.

[0014] The intelligent lifebuoy is used to collect first video data through the camera device and send the first video data to the unmanned surface vessel;

[0015] The unmanned surface vessel is also used to send the received first video data to the rescue platform;

[0016] The rescue platform is used to perform target recognition based on the first video data to obtain a recognition result. If the recognition result indicates that the rescue target exists in the target area, the target location of the existing rescue target is determined according to the location of the smart lifebuoy corresponding to the recognition result, wherein the location of the smart lifebuoy is determined by the positioning device.

[0017] Fourthly, embodiments of this application provide a rescue device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the water rescue method described in the first or second aspect above.

[0018] Fifthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the water rescue method described in the first or second aspect above.

[0019] Sixthly, embodiments of this application provide a computer program product that, when run on a rescue device, causes the rescue device to perform the water rescue method described in either the first aspect or the second aspect above.

[0020] The beneficial effects of the embodiments in this application compared with the prior art are:

[0021] In this embodiment, the target area is initially determined by the unmanned surface vessel (USV) based on the location of a suspected rescue target (i.e., the location to be searched). Since USVs can perform searches much faster than smart lifebuoys, the target area can be determined more quickly, thus improving search speed. Simultaneously, because smart lifebuoys search in target areas where the probability of a rescue target is higher, the accuracy of the smart lifebuoy search is improved.

[0022] Once the intelligent lifebuoy acquires initial video data of the target area using its onboard cameras, it transmits this data to the shore-based rescue platform. Because the lifebuoy is in direct contact with the water, its cameras can capture video data of the water's surface and underwater areas. This means the initial video data provides more information. Therefore, after the rescue platform performs a secondary assessment based on the initial video data, it can more accurately determine whether a rescue target exists in the target area, thus improving the accuracy of water rescues. Furthermore, since the secondary assessment is performed by the rescue platform based on the initial video data, rather than by the unmanned surface vessel (USV), the computational burden on the USV is reduced, and the computational speed is increased. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0024] Figure 1 This is a schematic flowchart of a water rescue method applied to an unmanned surface vessel, provided in an embodiment of this application;

[0025] Figure 2 This is a schematic flowchart of a water rescue method applied to an unmanned surface vessel, provided in an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of the structure of a water rescue device applied to an unmanned surface vessel provided in an embodiment of this application;

[0027] Figure 4 This is a schematic diagram of the structure of a water rescue device applied to a rescue platform, as provided in an embodiment of this application;

[0028] Figure 5 This is a schematic diagram of the structure of a water rescue system provided in an embodiment of this application;

[0029] Figure 6 This is a schematic diagram of the structure of a water rescue system provided in one embodiment of this application;

[0030] Figure 7This is a schematic diagram of the structure of the rescue equipment provided in the embodiments of this application. Detailed Implementation

[0031] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0032] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0033] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0034] Furthermore, in the description of this application and the appended claims, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0035] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized.

[0036] Example 1:

[0037] Figure 1 A schematic flowchart of a water rescue method applied to an unmanned surface vessel provided by an embodiment of the present invention is shown below:

[0038] Step S101: Perform a preliminary search based on the location to be searched to determine the target area. The location to be searched is the location where the rescue target is suspected to exist, and the target area is the area where the rescue target is preliminarily determined to exist.

[0039] The search locations mentioned above can be locations suspected of harboring rescue targets discovered during waterway patrols, such as locations determined by unmanned surface vessels during routine patrols according to preset routes. These search locations can also be locations identified based on personnel, vessels, etc. 、 The location determined by water alarm signals emitted by drones or shore-based water rescue platforms is not restricted here.

[0040] The aforementioned rescue targets refer to the targets of water rescue, which include at least people who have fallen into the water (not only people who have fallen into the water, but also people on floating planks, dangerous ships, or isolated islands in the water), and may also include important items.

[0041] Specifically, to improve the accuracy and efficiency of water rescue, after obtaining a suspected location for a rescue target, rescue operations are not initiated directly based on that location. Instead, a preliminary search is conducted to determine if a rescue target exists in the surrounding waters. Upon finding a target, the target area is then determined. For example, a search is performed within a 5-nautical-mile radius of the suspected location to determine if a rescue target exists within that area.

[0042] Optionally, since the location distribution of rescue targets is highly correlated for the same water area emergency, and they are usually distributed in close proximity, in this embodiment of the application, to improve the accuracy of water rescue, after a rescue target is found based on the location to be searched, a target area can be defined with the location of the found rescue target as the center and a predetermined length as the radius, so that other rescue targets can be searched for in the target area. When multiple rescue targets are initially found based on the location to be searched, a target area corresponding to each rescue target can be determined separately, resulting in multiple target areas.

[0043] For example, suppose there is a location to be searched: A. A search is conducted on the waters within a radius of 5 nautical miles centered on the location to be searched. A rescue target is found, and the location corresponding to the rescue target is B. When determining the target area based on the rescue target, the waters within a radius of 3 nautical miles centered on location B will be taken as the target area corresponding to the rescue target.

[0044] In this embodiment, to improve the accuracy and efficiency of water rescue, an unmanned surface vessel (USV) first searches for locations suspected of harboring rescue targets to determine if such targets exist. Then, upon determining the presence of a rescue target, the target area containing the target is identified, rather than directly conducting rescue operations based on the search location. Furthermore, since the distribution of rescue targets in water emergencies caused by the same incident exhibits significant correlation, determining the target area based on the identified rescue targets allows for further analysis of whether and which rescue targets actually exist within that area, thereby improving the efficiency of water rescue.

[0045] Step S102: Deploy the smart lifebuoy on the unmanned vessel in the target area. The smart lifebuoy includes a camera device.

[0046] The aforementioned camera equipment can be panoramic cameras, dome cameras, binocular cameras, or other devices capable of recording video. Optionally, the camera equipment on the smart lifebuoy may include at least two cameras, of which at least one camera is used for underwater filming.

[0047] Specifically, due to the complex conditions of lakes, oceans, and other bodies of water, simple searches may lead to misjudgments. To improve the accuracy of rescue information, after initially determining the waters where a rescue target exists and identifying the target area, intelligent lifebuoys carried on the unmanned surface vessel (USV) are released into the target area. Cameras mounted on the lifebuoys then conduct further searches of the target area. Optionally, the USV carries multiple intelligent lifebuoys. When releasing these lifebuoys in the target area, the release method can be determined based on the size of the target area, either releasing one lifebuoy for searching or releasing multiple lifebuoys for coordinated searching.

[0048] In this embodiment, because the intelligent lifebuoy can directly contact the water area, its onboard camera can effectively capture images of the area near the water surface and underwater. That is, releasing the intelligent lifebuoy carried on the unmanned surface vessel into the target area and using this lifebuoy to further search the target area improves the accuracy of water area searches.

[0049] Step S103: Receive the first video data sent by the smart lifebuoy and send the first video data to the rescue platform. The first video data is the video data collected by the camera device of the smart lifebuoy.

[0050] Specifically, since video data typically contains a large number of images, and determining rescue targets based on video data requires high computing power from the equipment, and since the equipment that can be installed in a smart lifebuoy is limited, in order to minimize the load on the smart lifebuoy, in this embodiment of the application, the smart lifebuoy needs to send the collected first video data to the unmanned surface vessel (USV). At the same time, in order to improve the computing speed, after receiving the first video data sent by the smart lifebuoy, the USV sends the first video data to the shore-based rescue platform. The shore-based rescue platform then determines whether there is a rescue target in the target area based on the first video data.

[0051] Optionally, dedicated network communication equipment can be installed on the intelligent lifebuoy and the unmanned surface vessel (USV) to enable communication between them. The dedicated network communication is a communication network built to provide emergency communication, command and dispatch, and daily work communication services to specific departments or groups. The dedicated network communication equipment refers to the equipment required to implement dedicated network communication, such as vehicle-mounted terminals and data transmission terminals.

[0052] In this embodiment, since video data processing requires high computing power from the device, in order to speed up the processing and reduce the load on the smart lifebuoy and the unmanned surface vessel (USV), after receiving the first video data sent by the smart lifebuoy, the USV sends the first video data to the rescue platform. The rescue platform set up on the shore makes a judgment based on the first video data, which can reduce the computing load on the USV while speeding up the computing speed, thereby improving the rescue efficiency.

[0053] In this embodiment, the location to be searched is a suspected location where a rescue target may exist. First, an unmanned surface vessel (USV) with relatively fast search speed is used to initially determine the area where a rescue target may exist (this area is the target area). Since USVs can perform searches much faster than smart lifebuoys, the target area can be determined more quickly, improving search speed. Simultaneously, because a further search is conducted on the target area where a rescue target is more likely to exist using a smart lifebuoy, the accuracy of the smart lifebuoy search can be improved.

[0054] Once the intelligent lifebuoy acquires initial video data of the target area using its onboard camera, it transmits this data to the shore-based rescue platform. Because the intelligent lifebuoy is equipped with a camera that is in direct contact with the water, it can capture video data of the underwater areas. This allows the initial video data to reflect more information. Therefore, the rescue platform, after making a secondary assessment based on the initial video data, can more accurately determine whether the target area is indeed a rescue target, thus improving the accuracy of water rescues. Furthermore, since the secondary assessment is performed by the rescue platform based on the initial video data, rather than by the unmanned surface vessel (USV), the computational burden on the USV is reduced, and the computational speed is increased.

[0055] In some embodiments, prior to step S102 described above, the method further includes:

[0056] A1. Based on the target area mentioned above, determine the number of smart lifebuoys that need to be released to obtain the target number.

[0057] A2. Determine the search areas corresponding to the aforementioned smart lifebuoys that need to be released, as well as the search routes corresponding to each of the aforementioned search areas.

[0058] A3. Send the above search area and the corresponding search route to the corresponding smart lifebuoy.

[0059] Correspondingly, step S102 above includes:

[0060] The aforementioned number of intelligent lifebuoys on the aforementioned unmanned surface vessel are released in the aforementioned target area. The intelligent lifebuoys are used to collect the aforementioned first video data in their corresponding search areas.

[0061] Specifically, the initial assessment indicates that the target area containing the rescue target is relatively large, and searching this area with smart lifebuoys may take a considerable amount of time. To improve search efficiency, in this embodiment, before releasing the smart lifebuoys, the number of smart lifebuoys to be released can be determined based on the size of the target area, thus obtaining the target number. The smart lifebuoys corresponding to the target number are then released to search the target area. Simultaneously, to enable each smart lifebuoy to search more effectively and further improve rescue efficiency, a search area corresponding to each smart lifebuoy and a corresponding search route are determined for each search area. This route, where the smart lifebuoys search within their respective search areas, ensures that the released smart lifebuoys can search systematically according to the search routes, thereby improving search efficiency. There is a one-to-one correspondence between the search areas and the smart lifebuoys; that is, the number of determined search areas matches the number of targets.

[0062] Optionally, due to the complex and changeable aquatic environment, changes in water conditions can have a certain impact on the movement of the intelligent lifebuoy in the water. Therefore, when determining the search route corresponding to each search area, the search route of the intelligent lifebuoy in the search area can be determined according to the water conditions of the search area, so as to avoid areas in the water with rapid currents and whirlpools that are not conducive to the intelligent lifebuoy's search, so that the intelligent lifebuoy can better collect the first video data in the search area and improve the image quality of the obtained first video data.

[0063] In some embodiments, when determining the search areas corresponding to the smart lifebuoys to be released and the search routes corresponding to each search area, to improve efficiency, the unmanned surface vessel (USV) can directly analyze and determine the search areas corresponding to each smart lifebuoy to be released and the search routes corresponding to each search area, and then send the determined search areas and their search routes to the corresponding smart lifebuoys. Alternatively, to reduce the computing power requirements and load on the USV, the rescue platform can determine a corresponding number of specific search areas based on the number of targets, then analyze and determine the search routes corresponding to each search area, and then send each search area and its corresponding search route to the USV. The USV parses the received information to extract each search area and its corresponding search route, and determines the correspondence between each search area, its corresponding search route, and the smart lifebuoy based on the extracted search areas and their corresponding search routes. Then, based on this correspondence, the USV sends the search areas and their corresponding search routes to the corresponding smart lifebuoys.

[0064] In this embodiment, when the target area is large, searching the entire area with a single smart lifebuoy takes a considerable amount of time. Therefore, to improve search efficiency and ensure rescue efficiency, the number of smart lifebuoys to be released can be determined based on the target area. Simultaneously, due to the complex water conditions, the search for smart lifebuoys can be easily affected, reducing search efficiency. Therefore, the search area corresponding to each smart lifebuoy to be released is determined, and the search route corresponding to each search area is determined based on the water conditions of the search area. This allows the smart lifebuoys to perform a better search within their respective search areas according to the corresponding search routes, thus improving search efficiency.

[0065] In some embodiments, the unmanned surface vessel (USV) includes navigation equipment and environmental data acquisition equipment. During water rescue operations, the USV further includes:

[0066] The location of the unmanned surface vessel is obtained through the navigation device and the environmental image is acquired through the environmental acquisition device to obtain the environmental image corresponding to the location of the unmanned surface vessel.

[0067] The location of the unmanned surface vessel and the environmental images were sent to the rescue platform.

[0068] Specifically, in order to enable rescuers to better understand the real-time situation of the target area and conduct rescue operations when necessary, in some embodiments, the unmanned surface vessel (USV) is also equipped with navigation equipment (such as inertial navigation systems, global positioning systems, etc.) and environmental acquisition equipment (such as lidar, visual sensors, etc.). During its navigation in the water, the USV obtains its current location (i.e., the USV's position) through its navigation equipment and acquires surrounding images of the USV's position through its onboard environmental acquisition equipment, obtaining the environmental image corresponding to the USV's position. Then, the acquired USV position and its corresponding environmental image are sent to the rescue platform, so that the rescue platform can construct a map of the scene where the USV is located based on the USV's acquired position and environmental image. This allows rescuers to further understand the scene situation based on the constructed map and conduct rescue operations more effectively.

[0069] In some embodiments, the navigation equipment installed on the unmanned surface vessel (USV) is an inertial navigation system, and its environmental acquisition equipment includes lidar and / or visual sensors. This environmental acquisition equipment acquires images of the USV's location. As an example, when the USV acquires its position during navigation, its inertial navigation system can obtain the USV's real-time position according to a preset acquisition frequency (e.g., once every 0.2 nautical miles, once every 30 seconds, etc.). Then, the environmental acquisition equipment, including lidar, acquires a point cloud image corresponding to the USV's real-time position, obtaining an environmental image corresponding to that real-time position. This real-time position and its corresponding environmental image are then sent together to a rescue platform. The rescue platform can then perform SLAM (Simultaneous Localization and Mapping) based on the received real-time position and environmental image to construct a real-time 3D map, thereby gaining a comprehensive understanding of the situation at the USV's location and improving rescue efficiency.

[0070] Optionally, the unmanned surface vessel (USV) also receives a constructed map sent by the rescue platform, enabling the USV to understand the conditions of the waters it is in based on the map, thereby avoiding obstacles and conducting a better search.

[0071] In some embodiments, the aforementioned unmanned surface vessel (USV) communicates with the rescue platform via a relay communication device installed on the USV.

[0072] The aforementioned relay communication equipment refers to devices installed on the UAV to forward communication data between the unmanned surface vessel (USV) and the rescue platform, such as repeaters, wireless communication equipment, and private network communication equipment. Optionally, since private network communication is a communication network built for emergency communication, command and dispatch, and daily work communication services provided by specific departments or groups, and the communication is relatively stable and efficient, private network communication equipment can be used as relay communication equipment on the UAV to improve the communication efficiency between the USV and the rescue platform, thereby improving the efficiency of water rescue.

[0073] Specifically, since communication signals are usually poor in large bodies of water such as lakes and oceans, a relay communication device can be set up on the drone to ensure stable communication between the unmanned surface vessel (USV) and the rescue platform. During the water rescue, the drone is also in the target area. When the USV and the rescue platform communicate, the USV can first send the messages and data that need to be communicated to the drone in the air, and then the drone will forward the communication data to the rescue platform.

[0074] In this embodiment of the application, since the UAV is located in the air, it is less affected by signal interference and can better transmit communication data. Therefore, the relay communication device installed on the UAV is used as a communication relay between the UAV and the rescue center. Based on the relay communication device, communication between the UAV and the rescue center is carried out to ensure stable transmission of communication data and improve transmission efficiency, thereby ensuring the efficiency of water rescue.

[0075] Corresponding to the above-mentioned water rescue methods applied to unmanned surface vessels, Figure 2 A flowchart illustrating a water rescue method applied to a rescue platform according to an embodiment of this application is shown below:

[0076] Step S201: Target recognition is performed based on the received first video data to obtain the recognition result. The first video data is the video data collected by the camera device on the smart lifebuoy in the target area.

[0077] The aforementioned target areas are areas where rescue targets are initially identified, such as areas where rescue targets are initially determined based on waterway alarm signals, waterway patrols, etc.

[0078] The aforementioned camera equipment can be panoramic cameras, dome cameras, binocular cameras, or other devices capable of recording video. Optionally, the camera equipment on the smart lifebuoy may include at least two cameras, of which at least one camera is used for underwater filming.

[0079] Specifically, to improve the efficiency of water rescue, after receiving the first video data, the rescue center can use a trained model to perform target recognition on the received video data and obtain the corresponding recognition results. The rescue targets include people who have fallen into the water; in some embodiments, the rescue targets also include important items.

[0080] Optionally, since the video data contains a large number of images, the time and computational load required to recognize each image are substantial. Therefore, to accelerate the recognition speed of the first video data, a portion of the images corresponding to the first video data can be extracted according to preset rules (e.g., extracting 5 images every 1 second of video data, extracting one image every 2 images, etc.) for target recognition. In some embodiments, when performing target recognition on the first video data, a trained target recognition model can be directly used to perform target recognition on the extracted images. Alternatively, a trained classification model can be used to first classify the images to obtain images containing target categories (such as human bodies), and then the target device model can be used to recognize the images containing target categories to further confirm whether the images containing target categories contain the target requiring rescue, thereby improving recognition efficiency.

[0081] In this embodiment, since the first video data is video data collected by the camera device on the smart lifebuoy in the target area, and the smart lifebuoy can directly contact the water, thereby better collecting video data of the underwater area in the water, target identification is performed based on the first video data that can reflect more information, so as to make a secondary judgment on whether there is a rescue target in the target area suspected of having a rescue target, which can improve the accuracy of water rescue.

[0082] Step S202: If the above identification result indicates that the above rescue target exists in the target area, then the target location of the above rescue target is determined according to the location of the smart lifebuoy corresponding to the above identification result.

[0083] The location of the aforementioned smart lifebuoy is determined by a positioning device on the smart lifebuoy. This positioning device can be GPS (Global Positioning System) or INS (Inertial Navigation System), etc.

[0084] Specifically, if the identification result obtained from the first video data indicates that a rescue target does indeed exist in the target area, then the smart lifebuoy that collected the first video data is identified based on the first video data corresponding to the identification result. Then, the location of the smart lifebuoy is obtained based on its position when the first video data was collected. Finally, the location information of the existing rescue target is determined based on the location of the smart lifebuoy, thus obtaining the target location. Since the smart lifebuoy is equipped with a positioning device, its location can be determined using this device when acquiring its position.

[0085] Optionally, when determining the target location of the rescue target based on the location of the smart lifebuoy, since the rescue target is present in the first video data collected at that location, it indicates that the existing rescue target is relatively close to the smart lifebuoy's current location. Therefore, the determined location of the smart lifebuoy can be directly used as the target location of the rescue target. Alternatively, to further improve rescue accuracy, a more detailed target location can be determined based on the location of the smart lifebuoy and the azimuth distance of the identified rescue target relative to the smart lifebuoy. Optionally, the target location can be the specific latitude and longitude of the rescue target, or it can be the relative azimuth based on the location of the smart lifebuoy.

[0086] In this embodiment of the application, after determining that a rescue target exists in the target area based on the first video data, the target location of the existing rescue target is determined based on the location of the smart lifebuoy that collected the first video data. This allows the specific location of the rescue target in the target area to be determined, thereby enabling better rescue operations based on the target location and improving the efficiency of water rescue.

[0087] In this embodiment, since the smart lifebuoy is in close contact with the water and can capture underwater scene images, reflecting more information about the water, the presence of a rescue target in the target area can be determined based on the first video data collected by the smart lifebuoy in the target area. This allows for a more accurate assessment of the presence of a rescue target in the target area and improves the accuracy of water rescue.

[0088] In some embodiments, after step S202 described above, the method further includes:

[0089] Based on the aforementioned target location, determine at least one of the aforementioned smart lifebuoys and the rescue route for the aforementioned smart lifebuoys.

[0090] Send a rescue command, including the aforementioned rescue route, to the aforementioned smart lifebuoy.

[0091] Specifically, when the target location is far from the rescuers, it takes time for the rescuers to reach the target and carry out the rescue. Therefore, in order to ensure the safety of the target and carry out the rescue in a timely manner, at least one smart lifebuoy can be determined for the rescue based on the target location and the locations of each smart lifebuoy. The corresponding rescue route for the smart lifebuoy can also be determined. Then, a rescue command can be sent to the smart lifebuoy so that it can move to the target location according to the rescue route in the rescue command, so that the target can climb onto the smart lifebuoy and thus ensure the safety of the target.

[0092] Optionally, when determining at least one smart lifebuoy based on the target location, the smart lifebuoy closest to the target location can be selected as the one used to rescue the target, based on the distance between each smart lifebuoy and the target location. Alternatively, multiple smart lifebuoys close to the target location can be selected as the same smart lifebuoys for coordinated rescue of the target. Alternatively, the smart lifebuoy with the shortest rescue route among the multiple smart lifebuoys can be selected as the final smart lifebuoy, and the target can be rescued using this smart lifebuoy, further ensuring the success rate of water rescue.

[0093] Optionally, the rescue route can be determined by analyzing the water conditions between the smart lifebuoy and the target location to find the safest or fastest route. Furthermore, an evacuation route is also determined after the smart lifebuoy reaches the target location and rescues the target. This evacuation route instructs the smart lifebuoy to move from the target location to the destination (unmanned surface vessel or land, such as the nearest shore), allowing the target to safely await rescue personnel. When determining the evacuation route, the safest route can be chosen based on the water conditions between the target location and the destination, maximizing the safety of rescue personnel. Correspondingly, the rescue command sent by the rescue center to the smart lifebuoy also includes this evacuation route.

[0094] In this embodiment of the application, after determining the target location of the rescue target in the target area, in order to carry out timely rescue of the rescue target and maximize the safety of the rescue target, at least one smart lifebuoy is determined according to the target location of the rescue target. The smart lifebuoy is moved to the target location through a rescue command, thereby realizing automatic rescue of the rescue target, so that the rescue target can wait for the arrival of rescuers in a relatively safe manner.

[0095] In some embodiments, due to poor communication signals in water areas, communication between the rescue platform and intelligent lifebuoys, unmanned boats, etc., is not stable enough, and data transmission efficiency is low. Therefore, in some embodiments, the rescue platform communicates with intelligent lifebuoys and unmanned boats through relay communication equipment (such as dedicated network communication equipment) installed on the drone. The drone is located in the airspace and acts as a communication relay station. Communication data is first sent to the drone, which then receives the communication data based on the relay communication equipment and sends it to the rescue platform. Communication between the rescue platform and intelligent lifebuoys and unmanned boats is achieved through the relay communication equipment on the drone. This method is less affected by signal interference, improves communication stability, ensures stable transmission of communication data, and thus ensures the timeliness and reliability of water rescue.

[0096] In some embodiments, prior to step S201 described above, the method further includes:

[0097] Receive water area alarm signals and send the alarm location from the water area alarm signals to the drone.

[0098] The system receives second video data sent by the drone, which is video data collected by the drone's camera equipment in the water area corresponding to the alarm location.

[0099] The location to be searched is determined based on the second video data mentioned above, and the location to be searched is sent to the unmanned surface vessel.

[0100] The alarm location in the above-mentioned water area alarm signal is the location where the water area accident occurred (such as latitude and longitude, address, etc.). The above-mentioned water area alarm signal can be an alarm signal sent autonomously by personnel, or an alarm signal automatically generated by a vessel or other vessel when it detects a water area accident (such as vessel malfunction, water ingress, etc.), or an alarm signal sent by other vessels or drones when they detect a water area accident during patrol, etc. There are no restrictions here.

[0101] Specifically, to further improve the efficiency of water rescue, when the rescue platform receives a water alarm signal, it sends the alarm location from the alarm signal to a drone. After arriving at the water area corresponding to the alarm location, the drone uses its onboard camera to collect surrounding video data, obtaining second video data, which is then sent to the rescue platform. The rescue platform receives the second video data from the drone and performs target identification based on it (e.g., using a trained target recognition model) to confirm the existence of any suspected rescue targets. If a suspected rescue target is found, the platform determines its location (e.g., the specific location where the drone collected the second video data) based on the second video data corresponding to that suspected target, thus obtaining the search location.

[0102] After obtaining the search location, the rescue platform sends it to the unmanned surface vessel (USV). Since this search location is determined based on the alarm location and is close to it, the rescue platform simultaneously sends the alarm location to the USV along with the USV. This allows the USV to also travel to the alarm location, enabling it to quickly reach the nearby search location after receiving the search location from the rescue platform and conduct an initial search to determine the target area. The USV then deploys a smart lifebuoy in the target area to acquire initial video data, which is then sent to the rescue platform. The rescue platform can then perform target identification based on the video data collected by the smart lifebuoy and obtain the identification result.

[0103] In some embodiments, the overall process of water rescue using rescue platforms and drones is as follows:

[0104] The rescue platform receives a water area alarm signal and transmits the alarm location from the alarm signal to the unmanned surface vessel (USV) and drone, coordinating the USV and drone to simultaneously proceed to the alarm location. The rescue platform also receives second video data transmitted by the drone, which is video data collected by the drone's onboard camera during a rapid aerial search after reaching the alarm location.

[0105] After receiving the second video data, the rescue platform can determine the search location of the suspected rescue target based on the second video data collected by the drone, and then send the search location to the unmanned boat located at the alarm position.

[0106] Since the unmanned surface vessel (USV) has already headed to the alarm location while the rescue platform is determining the location to be searched, and the location to be searched is determined based on the alarm location and is close to the alarm location, the USV can quickly obtain the location to be searched after receiving the location to be searched. It can then conduct a preliminary search of the more precise location to be searched relative to the alarm location to determine the target area. This target area is the area where the rescue target is initially judged to exist.

[0107] After determining the target location, the unmanned surface vessel (USV) deploys its intelligent lifebuoy within the target area. It then receives the first video data transmitted from the lifebuoy and forwards it to the rescue platform. This first video data is the video data captured by the lifebuoy's camera.

[0108] Then, the rescue platform receives the first video data, identifies the target based on the first video data, confirms whether there is a rescue target in the target area, and determines the target location of the existing rescue target if there is a rescue target, so as to carry out rescue on the rescue target.

[0109] Throughout the water rescue operation, the rescue platform coordinated drones and unmanned surface vessels (USVs) to simultaneously proceed to the alarm location. After confirming the search area based on second video data collected by the drones, the USVs conducted a search and preliminary assessment of the area to determine the target region where the rescue target might be located. Then, intelligent lifebuoys were deployed to collect first video data within the target region. Finally, the rescue platform further determined whether the target region contained the rescue target based on the first video data. Through collaborative operations and multiple searches and assessments, the efficiency and accuracy of water rescue operations were significantly improved.

[0110] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0111] Example 2:

[0112] Corresponding to the water rescue method described in the above embodiments, Figure 3 The diagram shows a structural block diagram of a water rescue device for unmanned surface vessels provided in an embodiment of this application. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0113] Reference Figure 3 The device includes: a target area determination module 31, a lifebuoy release module 32, and a receiving module 33. Among them,

[0114] The target area determination module 31 is used to perform a preliminary search based on the location to be searched to determine the target area, wherein the location to be searched is a location where a rescue target is suspected to exist, and the target area is an area where the rescue target is preliminarily determined to exist.

[0115] The lifebuoy release module 32 is used to release the intelligent lifebuoy on the unmanned surface vessel in the target area. The intelligent lifebuoy includes a camera device.

[0116] The receiving module 33 is used to receive the first video data sent by the smart lifebuoy and send the first video to the rescue platform. The first video data is the video data collected by the camera device of the smart lifebuoy.

[0117] In this embodiment, the location to be searched is a suspected location where a rescue target may exist. First, an unmanned surface vessel (USV) with relatively fast search speed is used to initially determine the area where a rescue target may exist (this area is the target area). Since USVs can perform searches much faster than smart lifebuoys, the target area can be determined more quickly, improving search speed. Simultaneously, because a further search is conducted on the target area where a rescue target is more likely to exist using a smart lifebuoy, the accuracy of the smart lifebuoy search can be improved.

[0118] Once the intelligent lifebuoy acquires initial video data of the target area using its onboard camera, it transmits this data to the shore-based rescue platform. Because the intelligent lifebuoy is equipped with a camera that is in direct contact with the water, it can capture video data of the underwater areas. This allows the initial video data to reflect more information. Therefore, the rescue platform, after making a secondary assessment based on the initial video data, can more accurately determine whether the target area is indeed a rescue target, thus improving the accuracy of water rescues. Furthermore, since the secondary assessment is performed by the rescue platform based on the initial video data, rather than by the unmanned surface vessel (USV), the computational burden on the USV is reduced, and the computational speed is increased.

[0119] In some embodiments, the above-mentioned water rescue device further includes:

[0120] The target quantity determination module is used to determine the number of smart lifebuoys that need to be released based on the target area, thus obtaining the target quantity.

[0121] The search area and route determination module is used to determine the search area corresponding to the smart lifebuoy to be released and the search route corresponding to each of the search areas.

[0122] The first sending module is used to send the search area and the search route corresponding to the search area to the corresponding smart lifebuoy.

[0123] Correspondingly, the lifebuoy release module 32 is used to release the target number of smart lifebuoys on the unmanned surface vessel in the target area, and the smart lifebuoys are used to collect the first video data in their corresponding search areas.

[0124] In some embodiments, the above-mentioned water rescue device further includes:

[0125] In some embodiments, the unmanned surface vessel further includes navigation equipment and environmental data collection equipment, and the water rescue device further includes:

[0126] The environmental image acquisition module is used to obtain the position of the unmanned surface vessel through the navigation device and to acquire images through the environmental acquisition device to obtain the environmental image corresponding to the position of the unmanned surface vessel.

[0127] The second transmitting module is used to transmit the location of the unmanned surface vessel and the environmental images to the rescue platform.

[0128] Corresponding to the water rescue method described in the above embodiments, Figure 4The diagram shows a structural block diagram of a water rescue device applied to a rescue platform according to an embodiment of this application. For ease of explanation, only the parts related to the embodiment of this application are shown.

[0129] Reference Figure 4 The device includes a target recognition module 41 and a target location determination module 42. Among them,

[0130] The target recognition module 41 is used to perform target recognition based on the received first video data and obtain the recognition result. The first video data is the video data collected by the camera device on the smart lifebuoy in the target area.

[0131] The target location determination module 42 is used to determine the target location of the rescue target if the above identification result indicates that the rescue target exists in the target area, based on the location of the smart lifebuoy corresponding to the above identification result, wherein the location of the smart lifebuoy is determined by the positioning device on the smart lifebuoy.

[0132] In this embodiment, since the smart lifebuoy is in close contact with the water and can capture underwater scene images, reflecting more information about the water, the presence of a rescue target in the target area can be determined based on the first video data collected by the smart lifebuoy in the target area. This allows for a more accurate assessment of the presence of a rescue target in the target area and improves the accuracy of water rescue.

[0133] In some embodiments, the above-mentioned water rescue device further includes:

[0134] The rescue route determination module is used to determine at least one of the aforementioned smart lifebuoys and the rescue route for the aforementioned smart lifebuoys based on the aforementioned target location.

[0135] The command sending module is used to send rescue commands, including the rescue route, to the aforementioned smart lifebuoy.

[0136] It should be noted that the information interaction and execution process between the above modules / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0137] Example 3:

[0138] Corresponding to the water rescue method described in the above embodiments, Figure 5 A structural block diagram of the water rescue system provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0139] Reference Figure 5The system includes: an unmanned surface vessel 50, an intelligent lifebuoy 51, and a rescue platform 52. The intelligent lifebuoy 51 includes a camera device 511 and a positioning device 512.

[0140] The aforementioned unmanned surface vessel 50 is used to conduct a preliminary search based on the location to be searched, determine the target area, and release the intelligent lifebuoy 51 on the unmanned surface vessel 50 in the target area. The location to be searched is a location where a rescue target is suspected to exist, and the target area is an area where the rescue target is preliminarily determined to exist.

[0141] The aforementioned rescue targets refer to those in the water that require rescue, including at least people who have fallen into the water, and may also include important items.

[0142] Specifically, upon obtaining a suspected location for a rescue target, an unmanned surface vessel (USV) 50 conducts a preliminary search based on that location. If the preliminary search confirms the existence of a rescue target, the area containing that target is determined, thus obtaining the target area. Since the USV 50's initial assessment of the target location is based on the location itself, to further confirm the presence of a rescue target within the target area, intelligent lifebuoys 51 carried on the USV 50 are released within the confirmed target area. This allows for more precise assessment using the intelligent lifebuoys 51, improving the accuracy of water rescue operations. The USV 50 carries one or more intelligent lifebuoys 51.

[0143] The aforementioned intelligent lifebuoy 51 is used to collect first video data through the aforementioned camera device 511 and send the first video data to the aforementioned unmanned surface vessel 50.

[0144] The camera device 511 of the aforementioned intelligent lifebuoy 51 can be a panoramic camera, a dome camera, a binocular camera, or other camera capable of recording images. Optionally, the camera device on the intelligent lifebuoy may include at least two cameras, wherein at least one camera is used for underwater filming.

[0145] Specifically, after the intelligent lifebuoy 51 lands in the water, its onboard camera 511 collects data about the surrounding environment, obtaining first video data, which is then transmitted back to the unmanned surface vessel 50. Optionally, the intelligent lifebuoy 51 may be equipped with a communication device (such as a wireless communication device) to send the collected first video data to the unmanned surface vessel 50.

[0146] The aforementioned unmanned surface vessel 50 is also used to send the received first video data to the aforementioned rescue platform 52.

[0147] Specifically, in order to reduce the computational burden on the unmanned surface vessel 50 and thus reduce its load, after receiving the first video data sent by the intelligent lifebuoy 51, the unmanned surface vessel 50 sends the first video data to the shore-based rescue platform 52, which then makes a secondary judgment on the rescue target based on the first video data.

[0148] The rescue platform 52 is used to perform target recognition based on the first video data and obtain recognition results. If the recognition results indicate that the rescue target exists in the target area, the target location of the rescue target is determined based on the location of the smart lifebuoy 51 corresponding to the recognition results. The location of the smart lifebuoy 51 is determined by the positioning device 512.

[0149] The positioning device 512 of the aforementioned intelligent lifebuoy 51 can be a GPS (Global Positioning System) or an INS (Inertial Navigation System) positioning device.

[0150] Specifically, after receiving the first video data, the rescue platform 52 performs target recognition on the first video data to confirm whether a rescue target exists in the image of the first video data, thereby obtaining a recognition result. If the recognition result indicates the presence of a rescue target in the image of the first video data, i.e., a rescue target exists in the target area, the target location of the rescue target is determined based on the position of the smart lifebuoy 51 corresponding to the first video data. Optionally, when the smart lifebuoy 51 collects the first video data, it can simultaneously collect its current position through its positioning device 512, associating the collected first video data with its corresponding collection position one-to-one. The position of the smart lifebuoy 51 corresponding to the first video data is the collection position corresponding to the first video data.

[0151] In this embodiment, since the intelligent lifebuoy 51 is in direct contact with the water, its camera device 511 can better capture images of the underwater area, allowing the obtained first video data to reflect more information. Therefore, by performing a secondary judgment based on the first video data collected by the intelligent lifebuoy 51, it is possible to more accurately determine whether the target area is a rescue target, thereby improving the accuracy and efficiency of water rescue. Simultaneously, the unmanned surface vessel 50 sends the first video data to the rescue platform 52, which performs a secondary judgment on the first video data, reducing the computational burden on the unmanned surface vessel and increasing its computational speed, thereby further improving the efficiency of water rescue.

[0152] In some embodiments, the above-described water rescue system further includes a drone 53, which is equipped with a camera device 531 and a navigation device 532.

[0153] The aforementioned rescue platform 52 is also used to receive water area alarm signals and send the alarm location in the water area alarm signals to the drone.

[0154] The aforementioned drone 53 is used to receive the alarm location, collect second video data of the water area corresponding to the alarm location through the aforementioned camera device 531, and send the aforementioned second video data to the aforementioned rescue platform 52.

[0155] The rescue platform 52 is also used to receive the second video data sent by the drone 53, determine the search location based on the second video data, and send the search location to the unmanned surface vessel 50.

[0156] Specifically, the rescue platform 52 is also used to receive water area alarm signals, which include an alarm location indicating the location of the water accident. The rescue platform 52 can simultaneously send the alarm location to the unmanned surface vessel 50 and the drone 53. The unmanned surface vessel 50 can first reach the water area corresponding to the alarm location, while the drone 53 reaches the corresponding water area based on the alarm location to search and capture images using camera equipment 531, obtaining second video data. The collected second video data is then sent to the rescue platform 52. The rescue platform 52 judges based on the received second video data to determine possible rescue targets, and if a rescue target is suspected to exist, determines the location of the suspected rescue target, thus obtaining the search location.

[0157] After obtaining the location to be searched, the rescue platform 52 sends the location to the unmanned surface vessel 50. Since the location to be searched is determined based on the alarm location and is close to the alarm location, and the unmanned surface vessel 50 also goes to the alarm location while the rescue platform 52 is determining the location to be searched, the unmanned surface vessel 50 can quickly reach the location to be searched and conduct a preliminary search after receiving the location to be searched from the rescue platform.

[0158] After receiving the alarm location, the rescue platform 52 coordinates the unmanned surface vessel 50 and the drone 53 to go to the alarm location simultaneously. The drone 53 first quickly searches and collects second video data in the air to determine the location to be searched. Then, the nearby unmanned surface vessel 50 conducts a preliminary search for the location to be searched, which is more accurate than the alarm location, further improving the efficiency and accuracy of water rescue.

[0159] In some embodiments, the aforementioned drone 53 also includes a relay communication device 533, through which the rescue platform 52 communicates with the unmanned surface vessel 50 and the intelligent lifebuoy 51.

[0160] In some embodiments, in order to enable rescuers to better understand the real-time situation of the target area and to better carry out rescue operations when needed, the unmanned surface vessel 50 includes a navigation device 501 and an environmental acquisition device 502 (such as lidar). During navigation in the water, the unmanned surface vessel 50 obtains its current position through its navigation device 501 and acquires surrounding images corresponding to its position through the onboard environmental acquisition device 502 to obtain an environmental image corresponding to the position of the unmanned surface vessel. Then, a map of the water area where the unmanned surface vessel 50 is located is generated based on the acquired position of the unmanned surface vessel and its corresponding environmental image. Alternatively, the acquired position of the unmanned surface vessel and its corresponding environmental image are sent to the rescue platform 52, and the rescue platform 52 generates a map of the water area where the unmanned surface vessel 50 is located based on the received position of the unmanned surface vessel and its corresponding environmental image.

[0161] It should be noted that the information interaction and execution process between the various parts of the above system are based on the same concept as the method embodiment of this application. For details on their specific functions and technical effects, please refer to the method embodiment section, and they will not be repeated here.

[0162] Example 4:

[0163] Figure 7 This is a schematic diagram of the structure of a rescue device provided in one embodiment of this application. Figure 7 As shown, the rescue device 7 of this embodiment includes: at least one processor 70 ( Figure 7 The diagram shows only one processor, a memory 71, and a computer program 72 stored in the memory 71 and executable on the at least one processor 70, which, when executed, performs the steps in any of the above-described method embodiments.

[0164] The rescue device 7 can be a desktop computer, laptop, handheld computer, or cloud server, etc. This rescue device may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will understand that... Figure 7 This is merely an example of rescue device 7 and does not constitute a limitation on rescue device 7. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0165] The processor 70 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0166] In some embodiments, the memory 71 may be an internal storage unit of the rescue device 7, such as a hard drive or memory of the rescue device 7. In other embodiments, the memory 71 may be an external storage device of the rescue device 7, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the rescue device 7. Furthermore, the memory 71 may include both internal and external storage units of the rescue device 7. The memory 71 is used to store operating systems, applications, bootloaders, data, and other programs, such as the program code of computer programs. The memory 71 can also be used to temporarily store data that has been output or will be output.

[0167] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0168] This application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the steps in any of the above method embodiments.

[0169] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0170] This application provides a computer program product that, when run on a rescue device, enables the rescue device to perform the steps described in the above-described method embodiments.

[0171] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a photographic device / rescue equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0172] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0173] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0174] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0175] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0176] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A water rescue method, characterized in that, An unmanned surface vessel (USV) is used in a water rescue system, which also includes a rescue platform and a drone; the method includes: The system receives a search location sent by the rescue platform. The search location is determined by the rescue platform after receiving a water area alarm signal and sending the alarm location in the water area alarm signal to the drone, based on the second video data sent by the drone. The second video data is video data collected by the drone's camera device in the water area corresponding to the alarm location. A preliminary search is performed based on the location to be searched to determine the target area. The location to be searched is the location where a rescue target is suspected to exist. The target area is the area where the rescue target is preliminarily determined to exist. The target area is the water area with a preset length as the radius and the location of the rescue target as the center. When multiple rescue targets are found, the target area corresponding to each rescue target is determined separately. The number of smart lifebuoys to be released is determined based on the size of the target area, thus obtaining the target number; Determine the search area corresponding to the smart lifebuoy that needs to be released and the search route corresponding to each search area; The target number of smart lifebuoys on the unmanned surface vessel are released in the target area. The smart lifebuoys include camera equipment for collecting first video data in the corresponding search area. The system receives first video data sent by the smart lifebuoy and sends the first video data to the rescue platform. The first video data is video data collected by the camera device of the smart lifebuoy.

2. The water rescue method as described in claim 1, characterized in that, The unmanned surface vessel (USV) includes navigation equipment and environmental data collection equipment. During water rescue operations, the USV also includes: The location of the unmanned surface vessel is obtained through the navigation device, and an environmental image is obtained by the environmental acquisition device to obtain the environmental image corresponding to the location of the unmanned surface vessel. The location of the unmanned surface vessel and the environmental images are sent to the rescue platform.

3. The water rescue method as described in any one of claims 1 to 2, characterized in that, The unmanned surface vessel (USV) communicates with the rescue platform via a relay communication device installed on the USV.

4. A water rescue method, characterized in that, A rescue platform applied to a water rescue system, the water rescue system also including unmanned surface vessels and drones, the method comprising: Receives a water area alarm signal and sends the alarm location from the water area alarm signal to the drone; Receive the second video data sent by the drone, wherein the second video data is video data collected by the drone's camera device in the water area corresponding to the alarm location; The location to be searched is determined based on the second video data, and the location to be searched is sent to the unmanned surface vessel. Target identification is performed based on the received first video data to obtain an identification result, wherein the first video data is obtained according to the water rescue method as described in any one of claims 1 to 3; If the identification result indicates that a rescue target exists in the target area, the target location of the existing rescue target is determined according to the location of the smart lifebuoy corresponding to the identification result, wherein the location of the smart lifebuoy is determined by the positioning device on the smart lifebuoy.

5. The water rescue method as described in claim 4, characterized in that, After determining the target location of the existing rescue target based on the location of the smart lifebuoy corresponding to the identification result, the method further includes: Determine at least one of the smart lifebuoys and the rescue route for the smart lifebuoys based on the target location; Send a rescue command, including the rescue route, to the smart lifebuoy.

6. A water rescue system, characterized in that, It includes a rescue platform, drones, unmanned boats, and intelligent lifebuoys. The drones are equipped with camera equipment, and the intelligent lifebuoys include positioning equipment and camera equipment. The rescue platform is used to receive water area alarm signals and send the alarm location in the water area alarm signals to the drone; The drone is used to collect second video data of the water area corresponding to the alarm location through the camera device, and send the second video data to the rescue platform; The rescue platform is also used to determine the location to be searched based on the second video data and send the location to be searched to the unmanned surface vessel; The unmanned surface vessel (USV) is used to perform a preliminary search based on the location to be searched, determine a target area, and release smart lifebuoys from the USV within the target area. The location to be searched is a suspected location where a rescue target may exist, and the target area is an area where the rescue target is preliminarily determined to exist. The target area is defined as the water area centered on the location of the rescue target and with a preset radius. When multiple rescue targets are found, a target area is determined for each rescue target. The number of smart lifebuoys to be released is determined based on the size of the target area, thus obtaining the target number. The search area corresponding to each smart lifebuoy to be released and the search route corresponding to each search area are determined. The target number of smart lifebuoys from the USV are released within the target area. The intelligent lifebuoy is used to collect first video data in the corresponding search area through the camera device, and send the first video data to the unmanned surface vessel; The unmanned surface vessel is also used to send the received first video data to the rescue platform; The rescue platform is used to perform target recognition based on the first video data to obtain a recognition result. If the recognition result indicates that the rescue target exists in the target area, the target location of the existing rescue target is determined according to the location of the smart lifebuoy corresponding to the recognition result, wherein the location of the smart lifebuoy is determined by the positioning device.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 3 or claims 4 to 5.

Images