Emergency search and rescue method, system and equipment for sea area around island reef and medium
Through the collaborative control technology of multiple drones, the flight strategy is dynamically adjusted and the location of the distressed person is quickly identified, solving the problems of long response time and small search range in maritime search and rescue, and achieving efficient and fast search and rescue operations.
Patent Information
- Application Number
- CN202411000087.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-08
AI Technical Summary
Existing drones respond long and costly in maritime search and rescue, and it is difficult to improve search and rescue efficiency in severe weather and complex sea conditions. Especially in the case of people in distress, they may be in danger without support, and the drone is equipped with rescue materials. The battery life will be affected and the search range will be small.
Adopt the collaborative control technology of multiple drones, and dynamically adjust the flight strategy by obtaining the collected data and video data of each drone, optimize the search coverage, and use particle swarm optimization algorithm to determine the optimal position and flight route to quickly identify dangers. The drone with rescue materials can be controlled to quickly reach the target location for delivery.
It improves the search and rescue efficiency and success rate, shortens the rescue response time, expands the search range, ensures that those in distress can receive timely support, and reduces the search and rescue costs.
Smart Images

Figure CN118907351A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of cooperative control of unmanned aerial vehicles, and in particular to an emergency search and rescue method, system, equipment and medium in sea areas around islands and reefs. Background Art
[0002] In recent years, with the global population growth and the increasing scarcity of land resources, the pace of development and utilization of marine resources has gradually accelerated, human marine activities have gradually increased, and the importance of maritime emergency search and rescue and disposal has also increased. In traditional maritime search and rescue, ships and helicopters are often relied on. Although these methods are effective, they have problems such as long response time, high cost, and great influence by weather and sea conditions. The development of drone technology has provided a new solution for maritime search and rescue.
[0003] However, currently drones are only used for video footage collection. The location of the person in distress is determined through video footage analysis, and then rescue personnel are notified to go to the location of the person in distress for rescue. This process takes a long time, and the person in distress is likely to be in danger without support. If each drone is to carry rescue supplies for search, the drone's battery life will be affected, resulting in a very small search range and the inability to improve search and rescue efficiency. Summary of the invention
[0004] The embodiment of the present invention provides an emergency search and rescue method, system, device and medium for the sea area around islands and reefs to solve the problems existing in the related technologies. The technical solution is as follows:
[0005] In a first aspect, an embodiment of the present invention provides an emergency search and rescue method in the sea area around islands and reefs, comprising:
[0006] Acquire collected data obtained by multiple first drones searching a designated area, and dynamically adjust the flight strategy of each first drone according to each collected data;
[0007] Obtaining video data obtained when each first unmanned aerial vehicle executes its corresponding flight strategy, and determining the target location of the person in distress according to the video data and the collected data;
[0008] The current position of the second UAV flying in the specified area is obtained, and the second UAV is a UAV carrying rescue supplies; the current position of each second UAV is compared with the target position, and the second UAV closest to the target position is marked as the target UAV. A dispatch instruction is generated according to the target position and sent to the target UAV to control the target UAV to perform the rescue delivery mission.
[0009] In one embodiment, the collected data is collected by an onboard device on the first drone, and the collected data includes the drone position and the drone speed.
[0010] In one embodiment, dynamically adjusting the flight strategy of each first UAV according to each collected data includes:
[0011] Divide the designated area equally into multiple search grids in advance;
[0012] Determine the time interval between two scans of each search grid by any first UAV according to each collected data;
[0013] Determine an objective function according to the time interval, and optimize the optimal position of each first UAV according to the objective function based on a particle swarm optimization algorithm;
[0014] The flight route and flight speed of each first UAV are determined based on the optimal position, and a flight strategy is generated in combination with the flight route and flight speed.
[0015] In one implementation, determining the target location of the person in distress based on the video data and the collected data includes:
[0016] Perform environmental feature analysis on the video data. If the video image shows that there is an offshore area, perform color analysis on the offshore area to obtain the area where the floating objects are located.
[0017] Based on the motion detection algorithm, the area where the floating objects are located is identified to obtain the suspected area;
[0018] The suspected area is analyzed by using a pre-trained first learning model. When it is found that there is a person in distress in the suspected area, the target location of the person in distress is determined based on the collected data.
[0019] In one implementation, determining the target location of the person in distress based on the video data and the collected data includes:
[0020] Performing environmental feature analysis on the video data, and if the analysis shows that there is a land area in the video screen, performing human outline recognition on the land area, and marking the suspected human outline in the video screen as the first designated area;
[0021] Acquire infrared detection data, and identify a second designated area having a temperature within a preset range based on the infrared detection data;
[0022] The video image is analyzed based on the pre-trained second learning model to determine whether there is a person in distress in the first designated area and the second designated area. If there is a person in distress in the first designated area and / or the second designated area, the target location of the person in distress is determined based on the collected data.
[0023] In one embodiment, controlling the target drone to perform a rescue delivery mission includes:
[0024] Obtain the current position of the target UAV, simulate the shortest flight route based on the difference between the current position and the target position, and control the target UAV to fly to the target position along the shortest flight route;
[0025] Based on the falling motion equation, the optimal delivery height and optimal delivery time of the target UAV are calculated, the target UAV is controlled to fly to the optimal delivery height and the materials mounted on the target UAV are delivered at the optimal delivery time.
[0026] In one implementation, energy data corresponding to each drone in the drone group is obtained, the energy data is monitored, and a recall instruction is issued to abnormal drones whose energy data is lower than a preset limit value;
[0027] Obtain the response command time corresponding to each drone in the drone group, and issue a recall command to abnormal drones whose response command time exceeds the preset time value.
[0028] In a second aspect, an embodiment of the present invention provides an emergency search and rescue system for waters around islands and reefs, which executes the emergency search and rescue method for waters around islands and reefs as described above.
[0029] In a third aspect, an embodiment of the present invention provides an electronic device, the device comprising: a memory and a processor. The memory and the processor communicate with each other through an internal connection path, the memory is used to store instructions, the processor is used to execute the instructions stored in the memory, and when the processor executes the instructions stored in the memory, the processor executes the method in any one of the above-mentioned embodiments.
[0030] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a computer, the method in any one of the above-mentioned embodiments is executed.
[0031] The advantages or beneficial effects of the above technical solution include at least:
[0032] The present invention optimizes the optimal position of each first drone through the collected data of multiple first drones, dynamically adjusts the flight strategy of each first drone, optimizes the search coverage, and improves the search and rescue efficiency; determines the target position of the person in distress based on the video data and collected data collected by each first drone, controls the second drone closest to the target position and equipped with rescue supplies to go to the target position to deliver the rescue supplies to the person in distress, thereby improving the rescue response speed and further improving the search and rescue efficiency.
[0033] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in the present invention and should not be regarded as limiting the scope of the present invention.
[0035] Figure 1 It is a schematic diagram of the process of the emergency search and rescue method for the sea areas around islands and reefs of the present invention;
[0036] Figure 2 This is a schematic diagram of the module composition of the emergency search and rescue system for sea areas around islands and reefs of the present invention;
[0037] Figure 3 The structure block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0038] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.
[0039] In recent years, with the global population growth and the increasing scarcity of land resources, the pace of development and utilization of marine resources has gradually accelerated, human marine activities have gradually increased, and the importance of maritime emergency search and rescue and disposal has also increased. In traditional maritime search and rescue, ships and helicopters are often relied on. Although these methods are effective, they have problems such as long response time, high cost, and great influence by weather and sea conditions. The development of drone technology has provided a new solution for maritime search and rescue.
[0040] However, currently drones are only used for video footage collection. The location of the person in distress is determined through video footage analysis, and then rescue personnel are notified to go to the location of the person in distress for rescue. This process takes a long time, and the person in distress is likely to be in danger without support. If each drone is to carry rescue supplies for search, the drone's battery life will be affected, resulting in a very small search range, and the search and rescue efficiency and success rate cannot be improved.
[0041] In order to solve the above problems, this embodiment provides an emergency search and rescue method in the waters around islands and reefs, which can perform long-term, high-precision search tasks in severe weather and complex sea conditions, promptly discover accidents and quickly deliver rescue supplies to people in distress, greatly improving the search and rescue efficiency and success rate.
[0042] The emergency search and rescue method for the sea area around the islands and reefs of this embodiment can be performed by a central control system connected to the entire drone group signal, such as Figure 1 , Figure 2 As shown, perform the following steps:
[0043] Step S1: Acquire collected data obtained by multiple first drones searching a designated area, and dynamically adjust the flight strategy of each first drone according to each collected data.
[0044] The scope of the designated area may be pre-divided according to the endurance of the first UAV, and the designated area may be a sea area, a land area, or a sea island area.
[0045] The drone group flying in the designated area includes a plurality of first drones and a plurality of second drones. In this embodiment, the drones carrying rescue materials are referred to as second drones, and the drones equipped with airborne detection equipment are referred to as first drones for distinction.
[0046] Each first drone is equipped with airborne detection equipment, including but not limited to high-definition cameras, GPS locators, and infrared sensors. During the flight, the first drone uses the airborne detection equipment to scan the designated area, collect terrain and thermal imaging data, and obtain the drone position and drone speed of each first drone, thereby obtaining the collected data. Among them, the first drone uses its ADS-B (Automatic Dependent Surveillance-Broadcast) communication system to identify signals with surrounding aircraft, report location and heading information, and avoid collisions between the drone and other aircraft.
[0047] The method for adjusting the flight strategy of each first UAV in this embodiment is:
[0048] Step S11: gridding the designated search area in advance, that is, dividing the designated search area into multiple search grids.
[0049] Step S12: Determine the time interval between two scans of each search grid by any first UAV according to each collected data.
[0050] For each grid, T iIt is defined as the time interval between two scans of this grid by the drone. Whenever a drone scans grid i, let T i =0.
[0051] Step S13: determining an objective function according to the time interval, and optimizing the optimal position of each first UAV according to the objective function based on a particle swarm optimization algorithm.
[0052] For a drone swarm, at a specific moment, the objective function is expressed as:
[0053]
[0054] Based on the particle swarm optimization algorithm, the value of the objective function is used to evaluate whether the position of the particle is close to the global optimal solution. When the objective function value of all particles in the particle swarm reaches a certain threshold or there is no significant improvement within a certain number of iterations, the algorithm can stop searching. Specifically, each first UAV adjusts its flight speed and position according to the value of the objective function, and the particle swarm optimization algorithm is used to find the optimal position of each first UAV.
[0055] When dealing with the optimization problem of a drone swarm, in order to avoid the algorithm finding only a local optimal solution (i.e., the scanning interval of a certain drone is extremely large, resulting in the minimum total time interval of the entire swarm, but this is not the global optimal solution), this embodiment adopts the following strategy:
[0056] Restrictions on individuals: In order to avoid the occurrence of a single first UAV with a very large scanning interval, it is necessary to represent the first UAV’s scanning interval dataset {T i The purpose is to ensure that the scanning interval distribution of the drone group is more uniform and avoid the occurrence of extreme values. The specific limit value is determined by the actual situation as σ lt d, then the expression of the standard deviation of the scanning interval of the drone group is:
[0057]
[0058] And σ T ≤σ ltd ;
[0059] When the above conditions are met, it means that the standard deviation σ of the scanning interval of the drone group T Cannot exceed the limit value σ ltd , at this time, the position of the drone group is the current optimal position of the group; the position of the individual drone in the drone group is the current optimal position of the individual drone.
[0060] Step S14: determining the flight path and flight speed of each first UAV based on the optimal position, and generating a flight strategy based on the flight path and flight speed.
[0061] When the individual optimal position is determined, the position of each first UAV is updated, and the global optimal position is updated, so as to assign the latest flight mission to each first UAV, that is, the flight route is determined according to the current position and optimal position of each first UAV, and the flight speed of each first UAV is calculated in combination with the speed update formula:
[0062]
[0063] in,
[0064] The speed of drone i at time t+1;
[0065] ω: Inertia weight, which controls how much of the previous velocity is retained;
[0066] The speed of drone i at time t;
[0067] c1 and c2: acceleration coefficients, representing the weights of random items;
[0068] r1 and r2: random values between 0 and 1, introducing randomness in the drone’s motion;
[0069] The optimal position found by particle i up to time t;
[0070] The current position of particle i at time t;
[0071] The best position found by the entire drone swarm up to time t.
[0072] The central control system dynamically adjusts the flight path of the drone and assigns new search tasks based on real-time data and algorithm analysis results to improve search coverage and reduce search time. It also updates the tasks of each drone in real time to ensure maximum search efficiency and prevent task overlap.
[0073] Step S2: Obtain video data obtained when each first unmanned aerial vehicle executes its corresponding flight strategy, and determine the target location of the person in distress based on the video data and the collected data.
[0074] Each first unmanned aerial vehicle takes a photo of the area it flies through during the flight according to the flight speed and flight route corresponding to its flight mission to obtain video data.
[0075] First, during the flight, the drone may scan and photograph the sea area, or it may scan and photograph the island land area. Therefore, after obtaining the video data, it is necessary to analyze the environmental characteristics of the video data. After the analysis determines the area type corresponding to the video image, it is then determined whether there are people in distress in the video image.
[0076] Specifically, the video data is analyzed for environmental characteristics. When there is a large area of open water in the video screen and there are features such as waves and reflections on the water surface, it can be considered that there is a sea area in the video screen. When the analysis shows that there is a sea area in the video screen, color analysis is performed on the sea area. The color filter is used to identify whether there are objects of specified colors in the sea area of the video screen. In this embodiment, the specified color is orange or yellow, representing the color of a life jacket. If objects of specified colors are detected in the sea area, it can be preliminarily considered that there are floating objects on the sea, and the area where the floating objects are located in the video screen is marked.
[0077] Afterwards, the area where the floating objects are located is identified based on the motion detection algorithm to determine whether there are moving objects in the sea area. If there are moving objects, the area where the moving objects are located is also marked as a suspected area. Among them, the motion detection algorithm can use optical flow method or background subtraction method to detect moving objects in the sea area and eliminate the interference of waves.
[0078] The video images analyzed as above are imported into the pre-trained first learning model to analyze all suspected areas. When the analysis shows that there are people in distress in the suspected areas, the target location of the people in distress is determined in combination with the GPS information in the collected data.
[0079] The training method of the first learning model is to use a large number of image samples marked with suspected areas as training inputs, and the conclusion on whether there are people in distress in the suspected areas as training outputs, and train deep learning models such as SSD to obtain the first learning model. In the early stage of this embodiment, the first learning model is trained and corrected using existing data such as completed rescue videos. In the early stage of applying the first learning model to actual rescue, manual review is used as an insurance measure to avoid missing out on identifying people in distress and gradually improve the recognition accuracy of the first learning model. Later, case data is extracted in proportion for manual review to ensure that the first learning model does not deviate. This embodiment uses a pre-trained first learning model for transfer learning to improve recognition accuracy in a marine environment.
[0080] In addition, during the process of analyzing the environmental characteristics of video data, when there are complex terrain features, including vegetation, beaches and rocks, or when the lighting conditions vary greatly and there are shadow features, it can be considered that there is an island in the video screen. When the analysis shows that there is an island land area in the video screen, human outline recognition is performed on the island land area, and the suspected human outline in the video screen is marked as the first designated area; among them, the background subtraction method can be used to separate the foreground (person in distress) and the background (terrain), and the edge detection and contour detection can be used to identify the human outline on the ground.
[0081] At the same time, an infrared thermal imaging camera is used to detect human body heat to obtain infrared detection data. Based on the infrared detection data, people in distress who are partially blocked by vegetation or other obstacles can be identified. In order to detect more accurately, when the object temperature is detected to be within the preset range corresponding to normal human body heat, the current object can be judged to be a person in distress. At this time, the area where the person in distress is located is marked as the second designated area.
[0082] The video images after the above marking are analyzed based on the pre-trained second learning model, and the human outline on the ground is identified by training a special deep learning model. At the same time, a multi-task learning model is used to identify the victims in different postures and partially occluded, and further accurately determine whether there are victims in the first designated area and the second designated area in the video image. When there are victims in the first designated area and / or the second designated area, the target location of the victims is determined based on the collected data. Among them, the training method of the second learning model is similar to the training method of the first training model. In the early stage, the second learning model is also trained and corrected using existing data such as completed rescue videos. In the early stage of applying the second learning model to actual rescue, manual review is used as an insurance measure to avoid missing the identification of victims and gradually improve the recognition accuracy of the second learning model. In the later stage, case data is extracted in proportion for manual review to ensure that the second learning model does not deviate.
[0083] When it is determined that there is a person in distress in the sea area or island land area in the video screen, the target location of the person in distress is determined in combination with the GPS information in the collected data.
[0084] Step S3: Obtain the current position of the second UAV flying in the designated area, where the second UAV is a UAV carrying rescue supplies; compare the current position of each second UAV with the target position, mark the second UAV closest to the target position as the target UAV, generate a dispatch instruction based on the target position and send it to the target UAV to control the target UAV to perform the rescue delivery mission.
[0085] Among them, the second drone can be equipped with airborne detection equipment and mounted with rescue supplies, and join the drone swarm of the first drone to jointly find the best flight route through the particle swarm optimization algorithm for flight.
[0086] In addition, the second drone may not be equipped with airborne detection equipment such as cameras and infrared detection, but only with GPS equipment and rescue supplies, which reduces the weight of the second drone and increases the endurance of the second drone; all second drones fly in a designated area as an independent drone group, and their flight routes can also be found through the particle swarm optimization algorithm to find the optimal or approximately optimal flight path, or they can be randomly scattered in different locations within the search area of the first drone. When determining the target location of the person in distress, the current location of each second drone is obtained, and the current location of each second drone is compared with the target location of the person in distress, and the second drone closest to the person in distress is determined as the target drone.
[0087] The current position of the target UAV is obtained, and the shortest flight route is simulated according to the difference between the current position and the target position to generate a dispatch instruction, which is sent to the target UAV to control the target UAV to fly quickly to the target position along the shortest flight route.
[0088] At the same time, the optimal delivery height and optimal delivery time of the target UAV are calculated based on the falling motion equation, the target UAV is controlled to fly to the optimal delivery height, and the materials mounted on the target UAV are delivered at the optimal delivery time.
[0089] Assuming that the material is only affected by gravity and air resistance during the falling process, the falling motion equation of the material can be expressed as:
[0090]
[0091] in:
[0092] m is the mass of the material;
[0093] g is the acceleration due to gravity, about 9.81 m / s 2 ;
[0094] k is the air resistance coefficient;
[0095] v is the speed of the material movement.
[0096] From the above differential equation, we can get the equation of the change of material speed with time can be expressed as:
[0097]
[0098] The change in the position of the material over time can be obtained by integrating the velocity equation:
[0099]
[0100] When the material falls on the sea level, h(t) = 0. According to the above equation, the release time t is:
[0101]
[0102] In order to ensure that the materials reach the ground accurately, the optimal delivery height h op It needs to be adjusted according to the height and wind speed of the second drone. Assuming the drone flight height is H, the wind speed is w, and the release time is t, the optimal release height can be expressed as:
[0103]
[0104] While the second UAV is performing the rescue material delivery operation, a rescue instruction is generated based on the target location of the person in distress and sent to the command center, which then dispatches rescue personnel to the target location to rescue the person in distress.
[0105] The central control system collects and analyzes all search data to evaluate the search efficiency and prepare improvement strategies for future search and rescue missions; the data and results of the entire mission are used for subsequent training and algorithm optimization to improve the response speed and success rate of future missions. In addition, the central control system can also obtain the energy data corresponding to each drone in the drone group (including the first drone and the second drone), monitor the energy data of each drone, and obtain the remaining power of the drone based on the energy data. If the remaining power of a drone is lower than the preset limit value, the drone is marked as an abnormal drone, and a recall command is issued to the abnormal drone to let the abnormal drone fly back to avoid loss. Alternatively, each drone will generate a feedback message and return it to the central control system when receiving any command issued by the central control system. The response command time of each drone in the drone group to return the feedback message after receiving the command is counted. If the central control system has not received the feedback message returned by the drone after the preset time value after issuing a command to any drone, the drone can be considered as an abnormal drone. At this time, a recall command is issued to the abnormal drone to control the abnormal drone to fly back, or the positioning information of the abnormal drone is directly obtained, and the drone is manually retrieved based on the positioning information.
[0106] Another embodiment of the present invention provides an emergency search and rescue system for sea areas around islands and reefs based on drones, which implements the emergency search and rescue method for sea areas around islands and reefs as described above. The functions of each module in the system of the embodiment of the present invention can be referred to the corresponding description in the above method, and will not be repeated here.
[0107] Another embodiment of the present invention provides an electronic device, Figure 3 FIG. 2 shows a structural block diagram of an electronic device according to an embodiment of the present invention. Figure 3As shown, the electronic device includes: a memory 100 and a processor 200, wherein the memory 100 stores a computer program that can be run on the processor 200. When the processor 200 executes the computer program, the emergency search and rescue method for the sea area around the islands and reefs in the above embodiment is implemented. The number of the memory 100 and the processor 200 can be one or more.
[0108] The electronic device also includes:
[0109] The communication interface 300 is used to communicate with external devices and perform data exchange transmission.
[0110] If the memory 100, the processor 200 and the communication interface 300 are implemented independently, the memory 100, the processor 200 and the communication interface 300 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0111] Optionally, in a specific implementation, if the memory 100, the processor 200 and the communication interface 300 are integrated on a chip, the memory 100, the processor 200 and the communication interface 300 can communicate with each other through an internal interface.
[0112] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present invention when executed by a processor.
[0113] An embodiment of the present invention further provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present invention.
[0114] An embodiment of the present invention also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided by the embodiment of the invention.
[0115] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced RISC machines (ARM) architecture.
[0116] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM).
[0117] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
[0118] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.
[0119] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.
[0120] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of various changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
Claims
1. An emergency search and rescue method for sea areas around islands and reefs, characterized in that: include: Acquire collected data obtained by multiple first drones searching a designated area, and dynamically adjust a flight strategy of each of the first drones according to each of the collected data; Acquire video data obtained when each of the first drones executes the corresponding flight strategy, and determine the target location of the person in distress according to the video data and the collected data; The current position of the second UAV flying in the designated area is obtained, where the second UAV is a UAV carrying rescue supplies; the current position of each of the second UAVs is compared with the target position, the second UAV closest to the target position is marked as the target UAV, and a dispatch instruction is generated according to the target position and sent to the target UAV to control the target UAV to perform the rescue delivery mission.
2. The method for emergency search and rescue in the sea area around islands and reefs according to claim 1, characterized in that: The collected data is collected by an onboard device on the first UAV, and the collected data includes the UAV position and the UAV speed.
3. The emergency search and rescue method for sea areas around islands and reefs according to claim 1 is characterized in that: The dynamically adjusting the flight strategy of each of the first UAVs according to each of the collected data includes: Dividing the designated area equally into a plurality of search grids in advance; Determine, according to each of the collected data, a time interval between two scans of each of the search grids by any of the first drones; Determine an objective function according to the time interval, and optimize the optimal position of each of the first UAVs according to the objective function based on a particle swarm optimization algorithm; The flight route and the flight speed of each of the first UAVs are determined based on the optimal position, and the flight strategy is generated in combination with the flight route and the flight speed.
4. The emergency search and rescue method for sea areas around islands and reefs according to claim 1 is characterized in that: The step of determining the target location of the person in distress according to the video data and the collected data includes: Performing environmental feature analysis on the video data, and when it is found that the video screen corresponding to the video data exists in an offshore area, performing color analysis on the offshore area to obtain an area where the floating object is located; Identify the area where the floating object is located based on a motion detection algorithm to obtain a suspected area; The suspected area is analyzed by using a pre-trained first learning model, and when it is found through the analysis that the person in distress exists in the suspected area, the target position where the person in distress is located is determined based on the collected data.
5. The emergency search and rescue method for sea areas around islands and reefs according to claim 1 is characterized in that: The step of determining the target location of the person in distress according to the video data and the collected data includes: Performing environmental feature analysis on the video data, and if the analysis shows that a land area exists in the video screen corresponding to the video data, performing human outline recognition on the land area, and marking the suspected human outline in the video screen as a first designated area; Acquire infrared detection data, and identify a second designated area having a temperature within a preset range based on the infrared detection data; The video image is analyzed based on a pre-trained second learning model to determine whether the person in distress exists in the first designated area and the second designated area. If the person in distress exists in the first designated area and / or the second designated area, the target location of the person in distress is determined based on the collected data.
6. The method for emergency search and rescue in the sea area around islands and reefs according to claim 5, characterized in that: The controlling the target UAV to perform the rescue delivery mission includes: Acquire the current position of the target UAV, and simulate the shortest flight route according to the difference between the current position and the target position, so as to control the target UAV to fly to the target position along the shortest flight route; The optimal delivery height and the optimal delivery time of the target UAV are calculated based on the falling motion equation, the target UAV is controlled to fly to the optimal delivery height, and the materials mounted on the target UAV are delivered at the optimal delivery time.
7. The method for emergency search and rescue in the sea area around islands and reefs according to claim 1, characterized in that: Also includes: Obtain energy data corresponding to each drone in the drone group, monitor the energy data, and issue a recall command to abnormal drones whose energy data is lower than a preset limit value; The response instruction time corresponding to each drone in the drone group is obtained, and a recall instruction is issued to the abnormal drone whose response instruction time exceeds a preset time value.
8. An emergency search and rescue system for sea areas around islands and reefs, characterized in that: Execute the emergency search and rescue method for sea areas around islands and reefs as described in any one of claims 1 to 7.
9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the emergency search and rescue method for the sea area around islands and reefs as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method for emergency search and rescue in the waters around islands and reefs as claimed in any one of claims 1 to 7 is implemented.
