Method, device, equipment and medium for searching for distressed targets on water

Abstract

The present disclosure relates to a method, device, equipment and medium for searching for targets in distress on the water. By using the environmental prediction information corresponding to the preset spatial range around the drift position of the target in distress on the water at the target time point, and the drift speed of the target in distress on the water before the target time point, the drift speed of the target in distress on the water at the target time point is intelligently predicted, and then the drift position, drift trajectory and search range of the target in distress on the water are predicted, and finally a collaborative search is performed within the search range through available search equipment. Since the environmental prediction information is spatial information and the drift speed is temporal information, and considering the nonlinear effect of the environmental prediction information, the drift speed of the target in distress on the water can be accurately predicted based on the combination of spatial information and temporal information, and a precise search range can be obtained, and then the search equipment can be used to search for the target in distress on the water in a timely and accurate manner, thereby improving the search efficiency and success rate of the target in distress on the water.

Description

Technical Field

[0001] The present disclosure relates to the field of maritime technology, and in particular to a method, device, equipment and medium for searching for a target in distress on water. Background Art

[0002] When searching for targets in distress on the water, drift prediction is required (i.e., predicting the target's future drift speed, drift position, drift trajectory, and search range based on the water environment). However, current drift speed prediction accuracy is low, which in turn leads to inaccurate search range prediction, resulting in low efficiency and success rate in searching for targets in distress on the water. Summary of the Invention

[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a method, device, equipment and medium for searching for distressed targets on water, so as to search for distressed targets on water in a timely and accurate manner, thereby improving the search efficiency and success rate of distressed targets on water.

[0004] In a first aspect, an embodiment of the present disclosure provides a method for searching for a target in distress on water, the method comprising:

[0005] Obtaining a starting position and a starting time for drift prediction of a target in distress on water, wherein the drift prediction includes prediction of drift speed, drift position, drift trajectory, and search range;

[0006] Obtaining environmental prediction information corresponding to the starting time within a preset spatial range around the starting position;

[0007] generating a plurality of initial positions for the drift prediction based on the starting position, generating a plurality of initial times for the drift prediction based on the starting time, generating a plurality of initial environmental information for the drift prediction based on environmental prediction information corresponding to the starting time, and constructing a plurality of sets of initial conditions based on the plurality of initial positions, the plurality of initial times, and the plurality of initial environmental information, each set of initial conditions including any initial position, any initial time, and any initial environmental information;

[0008] predicting, based on each set of initial conditions, a drift speed and a drift position of the target in distress at a plurality of target time points after any of the initial times, wherein the drift speed of the target in distress at each target time point is obtained based on environmental prediction information corresponding to a preset spatial range around the drift position of the target in distress at the target time point, and the drift speed of the target in distress before the target time point, and the drift positions of the target in distress at the plurality of target time points forming a drift trajectory;

[0009] predicting a search range for the target in distress on the water based on an end point of each drift trajectory in the plurality of drift trajectories corresponding to the plurality of sets of initial conditions;

[0010] A collaborative search is performed for the target in distress on the water within the search range using available search equipment.

[0011] In a second aspect, an embodiment of the present disclosure provides a device for searching for a target in distress on water, the device comprising:

[0012] A first acquisition module is used to obtain a starting position and a starting time for drift prediction of a target in distress on water, wherein the drift prediction includes prediction of drift speed, drift position, drift trajectory, and search range;

[0013] A second acquisition module is used to obtain environmental prediction information corresponding to the starting time within a preset spatial range around the starting position;

[0014] a generating module, configured to generate a plurality of initial positions for the drift prediction according to the starting position, generate a plurality of initial times for the drift prediction according to the starting time, and generate a plurality of initial environmental information for the drift prediction according to the environmental prediction information corresponding to the starting time;

[0015] A first constructing module is configured to construct multiple groups of initial conditions based on the multiple initial positions, the multiple initial times, and the multiple initial environmental information, each group of initial conditions including any initial position, any initial time, and any initial environmental information;

[0016] a prediction module for predicting, based on each set of initial conditions, the drift speed and drift position of the target in distress at a plurality of target time points after any of the initial times, wherein the drift speed of the target in distress at each target time point is obtained based on environmental prediction information corresponding to a preset spatial range around the drift position of the target in distress at the target time point, and the drift speed of the target in distress before the target time point, and the drift positions of the target in distress at the plurality of target time points constitute a drift trajectory; and predicting a search range for the target in distress based on the endpoint of each of the plurality of drift trajectories corresponding to the plurality of sets of initial conditions;

[0017] The collaborative search module is used to perform a collaborative search for the distressed target on the water within the search range by using available search equipment.

[0018] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:

[0019] Memory;

[0020] processor; and

[0021] computer programs;

[0022] The computer program is stored in the memory and is configured to be executed by the processor to implement the method as described in the first aspect.

[0023] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method described in the first aspect.

[0024] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, comprising a computer program, which implements the method described in the first aspect when executed by a processor.

[0025] The method, device, equipment and medium for searching for a target in distress on the water provided by the embodiments of the present disclosure obtain the starting position, starting time and environmental prediction information for drift prediction of the target in distress on the water, and then generate multiple initial positions based on the starting position, generate multiple initial times based on the starting time, and generate multiple initial environmental information based on the environmental prediction information corresponding to the starting time. Further, multiple groups of initial conditions are constructed based on the multiple initial positions, the multiple initial times and the multiple initial environmental information. For each target time point after any initial time included in each group of initial conditions in the multiple groups of initial conditions, the drift speed of the target in distress on the water at the target time point is intelligently predicted based on the environmental prediction information corresponding to the preset spatial range around the drift position of the target in distress on the water at the target time point, and the drift speed of the target in distress on the water before the target time point, thereby predicting the search range of the target in distress on the water, and finally performing a collaborative search within the search range through available search equipment. Since the environmental prediction information is spatial information and the drift speed of the target in distress on the water before the target time point is time information, and considering the nonlinear effect of the environmental prediction information, the drift speed of the target in distress on the water at the target time point can be accurately predicted based on the combination of spatial information and time information, thereby accurately predicting the drift position of the target in distress on the water at each target time point, obtaining a precise drift trajectory and search range, and then using available search equipment to search for the target in distress on the water in a timely and accurate manner, thereby improving the search efficiency and success rate of the target in distress on the water.

[0026] Furthermore, by constructing a pre-trained intelligent drift speed prediction model, the AI model fully considers the nonlinear interactions of environmental information such as wind, waves, and currents, as well as the nonlinear effects on the drift speed of distressed targets on the water, thereby improving drift prediction accuracy. Furthermore, by combining remote sensing satellite observation data, the prediction results such as the drift speed, drift trajectory, and search range of distressed targets on the water observed by remote sensing satellites are updated. The drift speed, drift trajectory, and search range of other unobserved distressed targets are also corrected and updated, simultaneously improving the drift prediction accuracy of distressed targets on the water, both observable and unobservable by satellite remote sensing. Furthermore, based on deep reinforcement learning, a joint search model using drones and unmanned boats is proposed, which improves the efficiency and success rate of searching for distressed targets on the water. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0028] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0029] Figure 1 A flow chart of a method for searching for a target in distress on water provided in an embodiment of the present disclosure;

[0030] Figure 2 A schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0031] Figure 3 A schematic diagram of a preset spatial range provided in an embodiment of the present disclosure;

[0032] Figure 4 A schematic diagram of the probability distribution within the search range provided by an embodiment of the present disclosure;

[0033] Figure 5 A schematic diagram of the probability distribution within the search range provided by an embodiment of the present disclosure;

[0034] Figure 6 A flow chart of a method for searching for a target in distress on water provided in an embodiment of the present disclosure;

[0035] Figure 7 A flow chart of a method for searching for a target in distress on water provided in an embodiment of the present disclosure;

[0036] Figure 8 A schematic diagram of a drift speed intelligent prediction model provided by an embodiment of the present disclosure;

[0037] Figure 9 A flow chart of a method for searching for a target in distress on water provided in an embodiment of the present disclosure;

[0038] Figure 10 A flow chart of a method for searching for a target in distress on water provided in an embodiment of the present disclosure;

[0039] Figure 11 A schematic diagram of a method for predicting a small target search range according to an embodiment of the present disclosure;

[0040] Figure 12 A flow chart of a method for searching for a target in distress on water provided in an embodiment of the present disclosure;

[0041] Figure 13 A schematic diagram of an object detection model provided in an embodiment of the present disclosure;

[0042] Figure 14 A schematic diagram of a spatial-spectral dual attention module provided in an embodiment of the present disclosure;

[0043] Figure 15 A flow chart of a method for searching for a target in distress on water provided in an embodiment of the present disclosure;

[0044] Figure 16 A schematic diagram of the spectral attention mechanism provided for an embodiment of the present disclosure;

[0045] Figure 17 A schematic diagram of a spatial-spectral dual attention module provided in an embodiment of the present disclosure;

[0046] Figure 18 A schematic diagram of a spatial attention mechanism provided for an embodiment of the present disclosure;

[0047] Figure 19 A schematic diagram of the structure of a device for searching for a target in distress on water provided by an embodiment of the present disclosure;

[0048] Figure 20 A schematic structural diagram of an electronic device embodiment provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0049] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that, in the absence of conflict, the embodiments of the present disclosure and the features therein can be combined with each other.

[0050] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0051] The current drift velocity prediction accuracy is low, which leads to inaccurate search range prediction, resulting in low efficiency and low success rate in searching for distressed targets on the water. To address this problem, the present disclosure provides a method for searching for distressed targets on the water, which involves the following terminology:

[0052] Targets in distress: people in distress at sea or on water, ships (such as fishing boats, yachts, cargo ships, etc.), life rafts at sea, etc.

[0053] Remote sensing identification: Identification of distressed targets based on remote sensing technology, such as identifying the type and location information of distressed targets.

[0054] Drift prediction: Based on environmental information at sea or on water (such as wind field, wave field, current field), the drift speed, drift position, drift trajectory and search range of distressed targets at sea or on water are predicted over a period of time in the future.

[0055] Search range: The possible distribution range of the distressed target in the future after the distress.

[0056] Collaborative search: Based on the predicted search range, drones, unmanned boats, etc. are used to jointly search for targets in distress.

[0057] Figure 1 A flow chart of a method for searching for targets in distress on water provided in an embodiment of the present disclosure. Specifically, the method can be executed by a device for searching for targets in distress on water, which can be implemented in software and / or hardware, and can be configured on a server, a server cluster, or a terminal device. Among them, a server cluster can be a plurality of servers brought together to perform the same service, which appears to the client as if there is only one server. A server cluster can utilize multiple computers for parallel computing to obtain a higher computing speed, and can also use multiple computers for backup, so that the entire system can still operate normally after any machine breaks down. Terminal devices are, for example, mobile phones, PDAs, tablet computers, wearable devices with displays, desktop computers, laptop computers, all-in-one computers, smart home devices, etc. Figure 2The schematic diagram of an application scenario applicable to an embodiment of the present disclosure is shown. After a remote sensing satellite 21 observes the sea area or water area where a distressed target 20 is located and obtains a remote sensing image, it transmits the remote sensing image to a server 22. Server 22 processes the remote sensing image to determine whether a distressed target is present. If a distressed target is present in the remote sensing image, server 22 can further identify the type of distressed target and its location information in the remote sensing image based on the remote sensing image. Based on the location information of the distressed target in the remote sensing image, server 22 can calculate the geographic coordinates of the distressed target, i.e., the remote sensing observation location, thereby achieving remote sensing identification. Alternatively, after a remote sensing satellite 21 observes the sea area or water area where a distressed target 20 is located and obtains a remote sensing image, it first determines whether a distressed target is present in the remote sensing image. If a distressed target is present in the remote sensing image, server 21 transmits the remote sensing image to server 22. The server 22 processes the remote sensing image to determine the type of the target in distress on the water and the location information of the target in distress on the water in the remote sensing image, and calculates the geographical coordinates of the target in distress on the water, i.e., the remote sensing observation position, based on the location information of the target in distress on the water in the remote sensing image. The remote sensing observation position can be used as the actual location of the target in distress on the water. The following is an introduction to the method for searching for targets in distress on the water provided by the embodiment of the present disclosure with reference to the figures. Figure 1 As shown, the specific steps of this method are as follows:

[0058] S101. Obtaining a starting position and a starting time for drift prediction of a target in distress on water, wherein the drift prediction includes prediction of drift speed, drift position, drift trajectory, and search range.

[0059] like Figure 2As shown, the position of the distressed target 20 may change in real time, resulting in the remote sensing satellite 21 not always being able to observe the distressed target 20 in real time. Therefore, the server 22 may not always be able to obtain the actual position of the distressed target 20 in real time. Assuming that at a certain moment, such as time t1, the remote sensing satellite 21 observes the distressed target 20, time t1 is recorded as the remote sensing observation time point. In this case, the remote sensing observation position of the distressed target 20 is used as the starting position for drift prediction of the distressed target 20, and the remote sensing observation time point is used as the starting time for drift prediction of the distressed target 20. Specifically, drift prediction includes predictions of drift speed, drift position, drift trajectory, and search range. It should be understood that the starting position and starting time for drift prediction of the distressed target 20 are not limited to the remote sensing observation position and remote sensing observation time point. For example, if another ship traveling in the same sea area or waters observes the distress target 20, the ship may send the time of its observation of the distress target 20, the position of the distress target 20 relative to the ship at the time of observation, and the ship's positioning information at the time of observation to the server 22. The server 22 determines the position of the distress target 20 at the time of observation based on the position of the distress target 20 relative to the ship at the time of observation and the ship's positioning information at the time of observation, and uses this position as the starting position for drift prediction of the distress target 20. The time when the ship observed the distress target 20 is used as the starting time for drift prediction of the distress target 20. Alternatively, the starting position for drift prediction of the distress target 20 may be the position of the distress target 20 at the time of distress, and the starting time for drift prediction of the distress target 20 may be the time when the distress target 20 was in distress. That is, the starting position and starting time that can be used for drift prediction of the target 20 in distress on the water are the actual position and time of the target 20 in distress on the water, for example, the actual position and time of the target 20 in distress on the water that the server 22 obtained most recently.

[0060] S102: Obtain environmental prediction information corresponding to the starting time within a preset spatial range around the starting position.

[0061] For example, after determining the starting position and starting time for drift prediction of the target 20 in distress on water, the server 22 further obtains the environmental prediction information corresponding to the starting time within the preset spatial range around the starting position. Figure 3 As shown, water area 30 represents the water area where the target 20 in distress on water is located, position 31 represents the starting position, and preset spatial range 32 represents the preset spatial range around the starting position. The preset spatial range can be a spatial range with a longitude range of lon1 to lon2 and a latitude range of lat1 to lat2 centered on the starting position.

[0062] Specifically, the environmental prediction information corresponding to the preset spatial range at the starting time may be the wind field forecast result, wave field forecast result, and flow field forecast result at a height of 10 meters above the water surface within the preset spatial range. The wind field forecast result includes wind speed and direction. The wave field forecast result includes wave height, wave direction, wavelength, wave period, etc. The flow field forecast result includes flow velocity and direction. For example, when the preset spatial range is divided into multiple high-resolution grids (e.g., with a high resolution of the order of ten meters), the wind field forecast result, wave field forecast result, and flow field forecast result at a height of 10 meters above the water surface within the preset spatial range are, respectively, the wind field forecast result, wave field forecast result, and flow field forecast result at a height of 10 meters at each high-resolution grid vertex (or center point) within the preset spatial range. It is understandable that the wind field forecast result, wave field forecast result, and flow field forecast result at a height of 10 meters at the same high-resolution grid vertex will change over time.

[0063] S103. Generate multiple initial positions for the drift prediction based on the starting position, generate multiple initial times for the drift prediction based on the starting time, generate multiple initial environmental information for the drift prediction based on the environmental prediction information corresponding to the starting time, and construct multiple groups of initial conditions based on the multiple initial positions, the multiple initial times and the multiple initial environmental information, each group of initial conditions including any initial position, any initial time and any initial environmental information.

[0064] For example, a random error of normal distribution is added to the starting position to obtain multiple initial positions, which constitute a set representing the uncertainty of the spatial position of the distress target on the water. The set is recorded as Adding a normal distribution of random errors to the starting time, we get multiple initial times, which constitute a set of uncertainties in the time and position of the target in distress on the water. This set is recorded as . Adding normally distributed random errors to the environmental prediction information corresponding to the starting time, a plurality of initial environmental information is obtained. For example, the environmental prediction information corresponding to the starting time includes wind field forecast results, wave field forecast results, and flow field forecast results. Further, adding normally distributed random errors to the wind field forecast results, the wave field forecast results, and the flow field forecast results, respectively, obtains a plurality of wind field disturbance results (i.e., the result of the wind field forecast result after multiple disturbances), a plurality of wave field disturbance results (i.e., the result of the wave field forecast result after multiple disturbances), and a plurality of flow field disturbance results (i.e., the result of the flow field forecast result after multiple disturbances). Furthermore, the wind field forecast result and the plurality of wind field disturbance results constitute a set that characterizes the uncertainty of the final wind field forecast result, and the set is recorded as The wave field prediction result and the multiple wave field disturbance results constitute a set that characterizes the uncertainty of the final wave field prediction result, and the set is recorded as The flow field prediction result and the multiple flow field disturbance results constitute a set that characterizes the uncertainty of the final flow field prediction result, which is recorded as Each initial environment information as described above includes Any element in (such as the wind field forecast result or any wind field disturbance result), Any element in (such as the wave field forecast result or any wave field disturbance result), and Any element in (such as the flow field prediction result or any flow field disturbance result).

[0065] In getting 、 、 、 、 After these sets are collected, a multivariate random forest sampling method is used to randomly extract an element from each set to form a combination. This combination is recorded as a set of initial conditions. In other words, each set of initial conditions includes any initial position, any initial time, and any initial environment information. For example, N random samplings are performed to obtain N sets of initial conditions.

[0066] S104. Predicting, based on each set of initial conditions, the drift speed and drift position of the target in distress on the water at multiple target time points after any of the initial times, wherein the drift speed of the target in distress on the water at each target time point is obtained based on environmental prediction information corresponding to a preset spatial range around the drift position of the target in distress on the water at the target time point, and the drift speed of the target in distress on the water before the target time point, and the drift positions of the target in distress on the water at the multiple target time points constitute a drift trajectory.

[0067] For example, for each of the N groups of initial conditions, the group of initial conditions includes any initial position, any initial time, and any initial environmental information. Based on the any initial environmental information, the drift speed of the target 20 in distress on the water at the any initial time is calculated. Assume that what is to be predicted here is the drift trajectory of the target 20 in distress on the water from the any initial time to a certain moment in the future, for example, the drift trajectory of the subsequent M hours starting from the any initial time. There are M target time points after the any initial time, and the first target time point of the M target time points is 1 hour away from the any initial time, and the interval between each two subsequent adjacent target time points is 1 hour. Further, based on the drift speed at the any initial time and the time interval between the first target time point and the any initial time, that is, 1 hour, the drift position of the target 20 in distress on the water at the first target time point can be calculated. Furthermore, the drift speed of the target 20 in distress at the first target time point is calculated based on the environmental prediction information (e.g., wind field prediction results, wave field prediction results, current field prediction results) for a preset spatial range surrounding the drift position of the target 20 in distress at the first target time point, as well as the drift speed of the target 20 in distress at any initial time point. Similarly, the drift position of the target 20 in distress at the second target time point can be calculated based on the drift speed of the target 20 in distress at the first target time point and the time interval of one hour between the first target time point and the second target time point. Similarly, the drift speed of the target 20 in distress at the second target time point is calculated based on the environmental prediction information for a preset spatial range surrounding the drift position of the target 20 in distress at the second target time point, as well as the drift speed of the target 20 in distress at any initial time point and the drift speed of the target 20 in distress at the first target time point. In other words, the drift speed of the object 20 in distress at each target time point is determined based on the environmental prediction information corresponding to that target time point and the drift speed of the object 20 in distress before that target time point. Furthermore, the drift positions of the object 20 in distress at each of the M target time points constitute a drift trajectory.

[0068] S105 , predicting a search range for the target in distress on the water according to an end point of each drift trajectory in the multiple drift trajectories corresponding to the multiple sets of initial conditions.

[0069] For example, a drift trajectory can be generated according to each set of initial conditions as described above, and therefore, N drift trajectories can be generated according to the N sets of initial conditions. Further, according to the end point of each drift trajectory in the N drift trajectories, that is, according to the N end points, the search range of the target 20 in distress on the water is predicted, and the search range can be a range containing the N end points. For example, according to the N end points, the minimum envelope rectangle is determined, and the minimum envelope rectangle is recorded as the prediction result of the search range. In addition, in some embodiments, the probability distribution within the search range can also be calculated based on the number of end points contained in different sub-areas in the search range. Figure 4 As shown, range 40 represents the search range, which includes 4 sub-areas. The number of endpoints contained in each sub-area divided by the total number of endpoints in the search range can be used to obtain the proportion of endpoints in the sub-area. The proportions corresponding to the four sub-areas constitute the probability distribution within the search range. It is understood that this embodiment does not limit the shape of the search range and the shape of each sub-area. For example, in other embodiments, the shape of the search range and the shape of each sub-area can be circular. Figure 5 As shown, range 50 represents the search range, and sub-areas 51 and 52 represent sub-areas within the search range. Similarly, based on the proportion of endpoints within each sub-area, the probability distribution within the search range can be obtained. In addition, this embodiment does not limit the number of sub-areas within the search range.

[0070] S106: Conduct a collaborative search for the target in distress on the water within the search range using available search equipment.

[0071] For example, available search equipment includes unmanned aerial vehicles (UAVs) and unmanned boats. Based on the search range of the target 20 in distress on the water, a joint search is conducted for the target 20 in distress on the water using the UAVs and unmanned boats within the search range.

[0072] The embodiment of the present disclosure obtains the starting position, starting time and environmental prediction information for drift prediction of the target in distress on the water, and then generates multiple initial positions based on the starting position, generates multiple initial times based on the starting time, and generates multiple initial environmental information based on the environmental prediction information corresponding to the starting time. Furthermore, multiple groups of initial conditions are constructed based on the multiple initial positions, the multiple initial times and the multiple initial environmental information. For each target time point after any initial time included in each group of initial conditions in the multiple groups of initial conditions, the drift speed of the target in distress on the water at the target time point is intelligently predicted based on the environmental prediction information corresponding to the preset spatial range around the drift position of the target in distress on the water at the target time point, and the drift speed of the target in distress on the water before the target time point, thereby predicting the search range of the target in distress on the water, and finally performing a collaborative search within the search range through available search equipment. Since the environmental prediction information is spatial information and the drift speed of the target in distress on the water before the target time point is time information, and considering the nonlinear effect of the environmental prediction information, the drift speed of the target in distress on the water at the target time point can be accurately predicted based on the combination of spatial information and time information, thereby accurately predicting the drift position of the target in distress on the water at each target time point, obtaining a precise drift trajectory and search range, and then using available search equipment to search for the target in distress on the water in a timely and accurate manner, thereby improving the search efficiency and success rate of the target in distress on the water.

[0073] Optionally, obtaining environmental prediction information corresponding to the preset spatial range around the starting position at the starting time includes: inputting the position information corresponding to multiple first-resolution grids contained in the preset spatial range around the starting position, the environmental prediction information corresponding to the multiple first-resolution grids at the starting time, and the position information corresponding to multiple second-resolution grids contained in the preset spatial range into the downscaling deep learning model, and using the environmental prediction information corresponding to the multiple second-resolution grids output by the downscaling deep learning model at the starting time as the environmental prediction information corresponding to the preset spatial range around the starting position at the starting time, wherein the second resolution is greater than the first resolution.

[0074] Specifically, the embodiment of the present disclosure uses the first resolution grid as the low resolution grid and the second resolution grid as the high resolution grid. Figure 3Taking the preset spatial range 32 around the starting point as an example, this preset spatial range 32 can be divided into multiple low-resolution grids or multiple high-resolution grids. The number of high-resolution grids into which this preset spatial range 32 is divided is greater than the number of low-resolution grids. Because the number of low-resolution grids within this preset spatial range 32 is smaller than the number of high-resolution grids, the storage space required to store the location information of the low-resolution grids (e.g., the longitude and latitude of the low-resolution grid vertices) and the environmental prediction information corresponding to the low-resolution grids (e.g., the wind field forecast results, wave field forecast results, and flow field forecast results at a height of 10 meters at the low-resolution grid vertices) is smaller, and the computation time required to predict the environmental prediction information corresponding to the low-resolution grids is shorter. The environmental prediction information corresponding to the high-resolution grid (e.g., wind field forecast results, wave field forecast results, and flow field forecast results at a height of 10 meters at the high-resolution grid vertex) is more detailed than the environmental prediction information corresponding to the low-resolution grid. Therefore, when a distress incident occurs at sea or on water, the environmental prediction information corresponding to the high-resolution grid can be predicted based on the environmental prediction information corresponding to the low-resolution grid and the position information of the low-resolution grid. Thus, the drift prediction of the distressed target on water can be performed based on the environmental prediction information corresponding to the high-resolution grid. Specifically, the position information corresponding to the multiple low-resolution grids within the preset spatial range 32, the environmental prediction information corresponding to the multiple low-resolution grids at the starting time, and the position information corresponding to the multiple high-resolution grids within the preset spatial range 32 (e.g., the latitude and longitude of the high-resolution grid vertices) are input into the downscaling deep learning model. The downscaling deep learning model outputs the environmental prediction information corresponding to the multiple high-resolution grids at the starting time. Here, the environmental prediction information corresponding to the multiple high-resolution grids at the starting time output by the downscaling deep learning model is used as the environmental prediction information corresponding to the preset spatial range 32 around the starting position at the starting time. That is to say, after an accident occurs at sea or on water, when subsequent drift prediction is needed, the downscaling deep learning model is used to quickly and intelligently downscale the low-resolution environmental prediction information within the required time period to obtain high-resolution wind field forecast results, wave field forecast results, and flow field forecast results at a height of 10 meters above the water surface within the required time period.

[0075] Optionally, the environmental prediction information corresponding to a preset spatial range around the drift position of the target in distress on the water at the target time point is obtained according to the following method: the position information corresponding to multiple first resolution grids contained in the preset spatial range around the drift position of the target in distress on the water at the target time point, the environmental prediction information corresponding to the multiple first resolution grids at the target time point, and the position information corresponding to multiple second resolution grids contained in the preset spatial range are input into the downscaling deep learning model, and the environmental prediction information corresponding to the multiple second resolution grids at the target time point output by the downscaling deep learning model is used as the environmental prediction information corresponding to the preset spatial range around the drift position of the target in distress on the water at the target time point, wherein the second resolution is greater than the first resolution.

[0076] For example, the position information corresponding to multiple low-resolution grids contained in a preset spatial range around the drift position of the water distress target 20 at any target time point, the environmental prediction information corresponding to the multiple low-resolution grids at the target time point, and the position information corresponding to multiple high-resolution grids contained in the preset spatial range (for example, the longitude and latitude of the high-resolution grid vertices) are input into the downscaling deep learning model, and the downscaling deep learning model outputs the environmental prediction information corresponding to the multiple high-resolution grids at the target time point. Here, the environmental prediction information corresponding to the multiple high-resolution grids at the target time point output by the downscaling deep learning model is used as the environmental prediction information corresponding to the preset spatial range around the drift position of the water distress target 20 at the target time point.

[0077] Optionally, the environmental prediction information includes wind field forecast results, wave field forecast results, and flow field forecast results; in the embodiment of the present disclosure, the downscaling deep learning model can specifically be a wind-wave-current coupled downscaling deep learning model based on a physical information constrained convolutional long short-term memory network. Specifically, the process of constructing a convolutional long short-term memory network can be the following process: constructing an encoder-decoder network, the encoder extracts features of low-resolution input data, and the decoder generates high-resolution output. Convolutional layers (Conv2D) are used in the encoder and decoder to extract spatial features, and transposed convolutional layers (Conv2DTranspose) are used in the decoder to upsample features and generate high-resolution outputs. A convolutional long short-term memory (ConvLSTM) module is added to the encoder-decoder structure to capture the dependencies between adjacent time solutions in the time series. The downscaling deep learning model is based on the following: Figure 6 The steps shown are trained as follows:

[0078] S601. Calculate environmental prediction information of multiple first-resolution grids in the target water area at preset time intervals within a preset future time period based on a wind-wave-current coupling prediction model, wherein the wind-wave-current coupling prediction model is a coupling model of an atmospheric numerical model, a wave numerical model, and a hydrodynamic numerical model.

[0079] In the disclosed embodiments, the atmospheric numerical model can output wind field forecast results, the wave numerical model can output wave field forecast results, and the hydrodynamic numerical model can output flow field forecast results. Specifically, the atmospheric numerical model can be the Weather Research & Forecasting Model (WRF). The hydrodynamic numerical model can be a finite-volume community ocean model (FVCOM) or a regional ocean model (ROMS). The wave numerical model can be a nonlinear random wave numerical model (SWAN) or a wind and wave simulation framework (WAVEWATCH). In the disclosed embodiments, the atmospheric numerical model, the wave numerical model, and the hydrodynamic numerical model can be coupled via a coupler to produce a wind-wave-current coupled forecast model, allowing the atmospheric numerical model, the wave numerical model, and the hydrodynamic numerical model to exchange relevant variables. For example, the atmospheric numerical model provides the wave numerical model and the hydrodynamic numerical model with the wind field and pressure field at a height of 10 meters above the water. The wave numerical model provides the effective wave height, wave direction, wavelength, and spectrum peak period to the hydrodynamic numerical model. The hydrodynamic numerical model provides the flow velocity and water level to the wave numerical model.

[0080] Specifically, according to the wind-wave-current coupled prediction model, simulation is carried out to obtain environmental prediction information of multiple low-resolution grids in the target water area at preset time intervals within the future preset time period. For example, at a fixed time every day, environmental prediction information of each low-resolution grid in the target water area is obtained every hour in the next 7 days. The environmental prediction information is recorded as the first simulation result, and the first simulation result is recorded as The wind field forecast result included in the first simulation result is recorded as The wave field forecast result included in the first simulation result is recorded as The flow field prediction result included in the first simulation result is recorded as .

[0081] S602: Calculate, based on the wind-wave-current coupling prediction model, environmental prediction information of a plurality of second-resolution grids in the target waters at preset time intervals within the future preset time period.

[0082] For example, the wind-wave-current coupled forecast model can also be used to calculate the environmental forecast information of each high-resolution grid in the target waters every hour in the next 7 days. The environmental forecast information is recorded as the second simulation result, and the second simulation result is recorded as The wind field forecast result included in the second simulation result is recorded as The wave field forecast result included in the second simulation result is recorded as The flow field prediction result included in the second simulation result is recorded as It is understandable that the time granularity corresponding to the second simulation result is the same as that of the first simulation result, except that the second simulation result has more spatial environmental prediction information than the first simulation result.

[0083] S603. Input the position information corresponding to the multiple first-resolution grids, the environmental prediction information of the multiple first-resolution grids at preset time intervals within the future preset time period, and the position information corresponding to the multiple second-resolution grids into the downscaling deep learning model to be trained, and the downscaling deep learning model outputs the environmental prediction information of the multiple second-resolution grids at preset time intervals within the future preset time period.

[0084] For example, the position information corresponding to the multiple low-resolution grids contained in the target water area, the environmental prediction information of the multiple low-resolution grids every hour in the next 7 days, and the position information corresponding to the multiple high-resolution grids contained in the target water area are input into the downscaling deep learning model to be trained, so that the downscaling deep learning model outputs the environmental prediction information of the multiple high-resolution grids every hour in the next 7 days.

[0085] S604. Train the downscaling deep learning model based on the environmental prediction information of the multiple second-resolution grids output by the downscaling deep learning model at preset time intervals within the future preset time period, and the environmental prediction information of the multiple second-resolution grids calculated by the wind-wave-current coupling forecast model at preset time intervals within the future preset time period.

[0086] For example, the multiple high-resolution grids output by the downscaling deep learning model are respectively the environmental forecast information and The difference between In addition, the cost function terms of the control equations of the atmospheric numerical model, the hydrodynamic numerical model, and the wave numerical model are respectively recorded as 、 、 . 、 、 It is used to constrain the downscaled wind field forecast results, wave field forecast results, and flow field forecast results to meet physical constraints. Further, the loss function is constructed. , and according to the loss function The downscaling deep learning model is trained. The loss function It is expressed as the following formula (1):

[0087] (1)

[0088] in, 、 、 Represent the coefficients respectively.

[0089] In addition, in some other embodiments, The wind field forecast results, wave field forecast results, and flow field forecast results at a height of 10 meters above the water surface, as well as the longitude and latitude of the low-resolution grid vertices, time information, and the longitude and latitude of the high-resolution grid vertices are used as inputs to the downscaling deep learning model, so that the downscaling deep learning model outputs the environmental prediction information corresponding to the high-resolution grid. Further, based on the environmental prediction information corresponding to the high-resolution grid output by the downscaling deep learning model and the time information corresponding to the high-resolution grid, the downscaling deep learning model is used to calculate the environmental prediction information corresponding to the high-resolution grid. The downscaling deep learning model is trained based on the difference between them.

[0090] Optionally, based on each set of initial conditions, the drift speed and drift position of the target in distress on water at multiple target time points after any initial time are predicted, including: Figure 7 The following steps are shown:

[0091] S701. Input any of the initial environmental information into a drift speed intelligent prediction model corresponding to the target in distress on the water, and the drift speed intelligent prediction model outputs the drift speed of the target in distress on the water at any of the initial times.

[0092] For example, for each of the N groups of initial conditions described above, the group of initial conditions includes any initial position, any initial time, and any initial environmental information. The any initial environmental information can be regarded as environmental prediction information corresponding to the preset spatial range around the any initial position at the any initial time. The any initial environmental information is input into the drift speed intelligent prediction model corresponding to the distress target 20 on the water, and the drift speed intelligent prediction model outputs the drift speed of the distress target 20 on the water at the any initial time. The drift speed intelligent prediction model corresponding to the distress target 20 on the water can be a drift speed intelligent prediction model corresponding to the type of the distress target 20 on the water. For example, when the distress target 20 on the water is a ship, the drift speed intelligent prediction model corresponding to the distress target 20 on the water is the drift speed intelligent prediction model of the ship.

[0093] S702. For each target time point after any initial time, calculate the drift position of the target in distress on the water at the target time point based on the drift speed and drift position of the target in distress on the water at the previous target time point.

[0094] For example, there are M target time points after the initial time. The first of the M target time points is one hour away from the initial time, and each subsequent target time point is one hour away from each other. Based on the drift speed of the object 20 in distress at the initial time and the one-hour interval between the first target time point and the initial time, the displacement of the object 20 in distress within the one-hour period can be calculated. Furthermore, based on any initial position included in the set of initial conditions (i.e., the drift position of the object 20 in distress at the initial time) and the displacement, the drift position of the object 20 in distress at the first target time point can be calculated.

[0095] S703. Input the environmental prediction information corresponding to the preset spatial range around the drift position of the target in distress on the water at the target time point, and the drift speed of the target in distress on the water before the target time point into the drift speed intelligent prediction model, and the drift speed intelligent prediction model outputs the drift speed of the target in distress on the water at the target time point.

[0096] For example, the environmental prediction information corresponding to a preset spatial range around the drift position of the target 20 in distress at a first target time point, as well as the drift speed of the target 20 in distress at any initial time point, is input into the drift speed intelligent prediction model. The drift speed intelligent prediction model outputs the drift speed of the target 20 in distress at the first target time point. Similarly, the drift position of the target 20 in distress at the second target time point is calculated based on the drift speed and drift position of the target 20 in distress at the first target time point, as well as the time interval of one hour between the first target time point and the second target time point. Further, the environmental prediction information corresponding to a preset spatial range around the drift position of the target 20 in distress at the second target time point, as well as the drift speed of the target 20 in distress at any initial time point and the drift speed of the target 20 in distress at the first target time point, is input into the drift speed intelligent prediction model. The drift speed intelligent prediction model outputs the drift speed of the target 20 in distress at the second target time point, and so on. That is, for each target time point after the initial time, the environmental prediction information corresponding to the preset spatial range around the drift position of the target 20 in distress at the target time point, as well as the drift speed of the target 20 in distress prior to the target time point, is input into the drift speed intelligent prediction model, and the drift speed intelligent prediction model outputs the drift speed of the target 20 in distress at the target time point. That is, after inputting the environmental prediction information corresponding to the preset spatial range around the drift position of the target 20 in distress at the current moment, as well as the historical drift speed of the target 20 in distress at the current moment, into the drift speed intelligent prediction model, the drift speed intelligent prediction model can output the drift speed of the target 20 in distress at the current moment.

[0097] For example, the drift speed of the target 20 in distress on the water at any initial time is recorded as V(0), and the drift speed of the target 20 in distress on the water at the kth target time point after the initial time is recorded as V(k). Figure 8As shown, the environmental prediction information corresponding to the preset spatial range around the drift position of the target 20 in distress on the water at the kth target time point, and the drift speed of the target 20 in distress on the water before the kth target time point, namely V(0), V(1), ..., V(k-1), are input into the drift speed intelligent prediction model, and the drift speed intelligent prediction model outputs the component of V(k) in the east-west direction and the component of V(k) in the north-south direction. Among them, V(0), V(1), ..., V(k-1) can be recorded as the time series of historical drift speeds. For each drift speed in V(0), V(1), ..., V(k-1), the drift speed obtained by dividing the remote sensing observation displacement by the remote sensing observation time interval is preferably used. If there is no corresponding remote sensing observation displacement, the speed predicted by the drift speed intelligent prediction model is used. For example, if a remote sensing satellite observes a distressed target 20 at the k-1th target time point and the kth target time point, respectively, then the remotely sensed observed position of the distressed target 20 at the k-1th target time point and the remotely sensed observed position of the distressed target 20 at the k-1th target time point and the remotely sensed observed position of the distressed target 20 at the k-kth target time point are used to obtain the remotely sensed observed displacement of the distressed target 20 between the k-1th target time point and the kth target time point. Furthermore, this remotely sensed observed displacement is divided by the remotely sensed observation time interval (i.e., the time interval between the k-1th target time point and the kth target time point) to obtain V(k-1). If there are no corresponding remotely sensed observed positions at the k-1th target time point and the kth target time point, V(k-1) is the velocity predicted by the drift velocity intelligent prediction model. Similarly, when the drift speed intelligent prediction model predicts V(k-1), the input of the drift speed intelligent prediction model is the environmental prediction information corresponding to the preset spatial range around the drift position of the target 20 in distress on the water at the k-1th target time point, and the drift speeds of the target 20 in distress on the water before the k-1th target time point, namely V(0), V(1), ..., V(k-2). In addition, in other embodiments, the number of historical drift speeds input to the drift speed intelligent prediction model can also be limited to no more than a preset number, such as 3. For example, the environmental prediction information corresponding to the preset spatial range around the drift position of the target 20 in distress on the water at the kth target time point, and the three drift speeds of the target 20 in distress on the water before the kth target time point, namely V(k-3), V(k-2), and V(k-1), are input into the drift speed intelligent prediction model, and the drift speed intelligent prediction model outputs the component of V(k) in the east-west direction and the component of V(k) in the north-south direction. Furthermore, V(k) is obtained based on the east-west component and the north-south component.

[0098] Specifically, the drift speed intelligent prediction model can be one that combines a convolutional neural network (CNN) with spatiotemporal features. Specifically, the model is based on a convolutional neural network (CNN), which consists of an input layer, a convolutional layer, an activation function, a pooling layer, a fully connected layer, and an output layer. The input layer contains the environmental prediction information fed into the drift speed intelligent prediction model. This information is spatially distributed in two dimensions. The convolutional layer convolves this environmental prediction information with a convolution kernel to obtain its spatial features. Furthermore, the convolutional layer can include residual connections to address vanishing gradient and degradation issues. Furthermore, the convolutional layer output is nonlinearly transformed using multiple activation functions, such as rectified linear units (ReLUs), sigmoids, and hyperbolic tangent functions (tanh), to reflect the nonlinear interactions between wind, flow, and wave fields. In addition, the pooling layer reduces the size of spatial features, thereby enhancing the robustness and generalization capabilities of the drift speed intelligent prediction model. The drift speed of the distressed target since the distress, i.e., the time series of historical drift speeds described above, is introduced before the fully connected layer of the CNN. Furthermore, the spatial features of this environmental prediction information and the time series of historical drift speeds are used as inputs to the fully connected layer, allowing the drift speed intelligent prediction model to predict the current drift speed component in the east-west direction and the north-south direction.

[0099] Optionally, the intelligent prediction model for the drift speed corresponding to the target in distress on water is trained according to the following steps shown in 9:

[0100] S901. Obtain, through the Beidou positioning system, drift positions of an experimental target representing the target in distress on water corresponding to a plurality of preset time points during its free drift in the target water area.

[0101] The intelligent drift velocity prediction model for distressed aquatic targets described above is trained using data from aquatic drift experiments. In these experiments, a representative target (e.g., a life raft, lifeboat, dummy, or debris) is dropped into the target waters and allowed to drift freely. If the target is a ship, the ship's power is shut down, allowing it to drift freely. During the experiment, the Beidou positioning system is used to obtain the target's drift position during the free drift process. For example, the drift position corresponding to multiple preset time points during the free drift process is obtained.

[0102] S902: Calculate the drift speeds of the experimental target corresponding to the plurality of preset time points according to the drift positions corresponding to the plurality of preset time points.

[0103] For example, the drift speeds of the experimental target corresponding to the multiple preset time points are calculated based on the drift positions of the experimental target corresponding to the multiple preset time points and the time interval between every two adjacent preset time points.

[0104] S903. For each preset time point among the multiple preset time points, the environmental prediction information corresponding to the preset spatial range around the drift position corresponding to the preset time point of the experimental target and the drift speed of the experimental target before the preset time point are input into the drift speed intelligent prediction model, and the drift speed intelligent prediction model outputs the drift speed of the experimental target corresponding to the preset time point.

[0105] For example, for each of the multiple preset time points, the environmental prediction information corresponding to the preset spatial range around the drift position corresponding to the preset time point of the experimental target, and the drift speed of the experimental target before the preset time point are input into the drift speed intelligent prediction model to be trained, and the drift speed intelligent prediction model outputs the drift speed corresponding to the preset time point of the experimental target.

[0106] S904. Training the drift speed intelligent prediction model according to the calculated drift speed corresponding to the experimental target at the preset time point and the drift speed corresponding to the experimental target at the preset time point output by the drift speed intelligent prediction model.

[0107] For example, for each of the multiple preset time points, the difference between the drift speed of the experimental target at the preset time point output by the drift speed intelligent prediction model and the drift speed of the experimental target at the preset time point calculated in the above S902 is calculated, and the drift speed intelligent prediction model is trained based on the difference.

[0108] In the disclosed embodiments, for each type of distressed aquatic target, an on-water drift experiment is conducted. Using the on-water drift experiment data, a specific intelligent drift speed prediction model corresponding to that distressed aquatic target is trained. Examples include intelligent drift speed prediction models for ships, people overboard, life rafts, and wreckage. Unless otherwise specified, these models are collectively referred to as intelligent drift speed prediction models corresponding to distressed aquatic targets.

[0109] Since the embodiment of the present disclosure inputs the environmental prediction information within a certain spatial range around the location of the experimental target (i.e., the output of the downscaled deep learning model) into the drift speed intelligent prediction model to be trained, rather than inputting the actual data such as the wind field, wave field, flow field, etc. at the location of the experimental target into the drift speed intelligent prediction model to be trained. Therefore, compared with the traditional water drift experiment, the water drift experiment described in the embodiment of the present disclosure does not require synchronous follow-up observation of the actual data such as the wind field, wave field, flow field, etc. at the location of the experimental target, thereby greatly reducing the experimental cost. In addition, since there is no need to synchronously follow-up observation of the actual data such as the wind field, wave field, flow field, etc. at the location of the experimental target, the number of experiments and experimental data can be increased when conducting water drift experiments in bad weather. In addition, since the embodiment of the present disclosure uses the output of the downscaled deep learning model as part of the input of the drift speed intelligent prediction model to be trained, the system error of the downscaled deep learning model can be optimized during the training of the drift speed intelligent prediction model, so that the trained drift speed intelligent prediction model does not need to consider the impact of the system error of the downscaled deep learning model in the subsequent reasoning process or application process, that is, when predicting the drift of actual water distress targets, thereby improving the accuracy of drift prediction, that is, improving the prediction accuracy of the drift trajectory and search range of the water distress targets.

[0110] Optionally, after predicting the search range of the target in distress on water, the method further includes: guiding the remote sensing satellite to observe within the search range.

[0111] For example, if a remote sensing satellite fails to observe a distressed target on the water, the search range of the distressed target can be used as a reference area for remote sensing satellite observation, thereby guiding the remote sensing satellite to conduct on-site observations within this search range. Furthermore, since the search range represents an area where the distressed target on the water may arrive in the future, if there are multiple remote sensing satellites, server 22 can query remote sensing satellite 21 to determine whether it can reach the search range within the future. If remote sensing satellite 21 can arrive on time, remote sensing satellite 21 can be guided to conduct on-site observations within the search range. If remote sensing satellite 21 cannot arrive on time, other remote sensing satellites that can arrive on time can be guided to conduct on-site observations within the search range.

[0112] Optionally, the method further includes: when the remote sensing satellite observes the distressed target on the water, based on the remote sensing observation position and remote sensing observation time point of the distressed target on the water, using the drift speed intelligent prediction model corresponding to the distressed target on the water to perform a re-drift prediction on the distressed target on the water, to obtain a new search range of the distressed target on the water, the remote sensing observation position is the starting position for the re-drift prediction, and the remote sensing observation time point is the starting time for the re-drift prediction.

[0113] For example, when the remote sensing satellite 21 observes the distress target 20 on the water within the search range, the remote sensing observation position and remote sensing observation time point of the remote sensing satellite 21 on the distress target 20 on the water are recorded. Further, the remote sensing observation position is used as the starting position for re-drift prediction of the distress target 20 on the water, and the remote sensing observation time point is used as the starting time for re-drift prediction of the distress target 20 on the water, and the drift prediction of the distress target 20 on the water is performed again. That is, the remote sensing observation position of the distress target 20 on the water by the remote sensing satellite 21 is used as the precise position of the distress target 20 on the water at the remote sensing observation time point, and the remote sensing observation position and the remote sensing observation time point are used as the starting position and starting time for the next drift prediction of the drift speed intelligent prediction model respectively. The process of re-drift prediction refers to the process of drift prediction described above and will not be repeated here.

[0114] Optionally, the method further comprises: Figure 10 The following steps are shown:

[0115] S1001. When the remote sensing satellite observes the distress target on the water within the search range, a preset number of end points are selected around the distress target on the water within the search range.

[0116] For example, there are 6 groups of initial conditions for drift prediction of the distress target 20 on the water, which are sequentially recorded as initial condition 1, initial condition 2, ..., initial condition 6. The initial positions included in initial condition 1, initial condition 2, ..., initial condition 6 are as follows: Figure 11 The initial positions 1, 2, ..., and 6 are shown in FIG. 6 . Based on the 6 sets of initial conditions, 6 drift trajectories can be generated, thereby obtaining 6 end points. The 6 end points are as follows: Figure 11 Endpoints 7 to 12 are shown. Based on Endpoints 7 to 12, a search range 110 for the distress target 20 is obtained. Assume that the remote sensing satellite observes the distress target 20 within search range 110. Furthermore, a preset number of endpoints are selected around the distress target 20 within search range 110. For example, three endpoints are selected around the distress target 20, namely Endpoints 7 to 9. Alternatively, endpoints within a preset range 111 around the distress target 20 are selected, such as Endpoints 7 to 9.

[0117] S1002. Predicting the drift speed, drift position, drift trajectory, and search range of other targets in distress based on the initial conditions corresponding to the preset number of endpoints and the drift speed intelligent prediction model corresponding to other targets in distress at the same time as the target in distress on the water, where the size of the other targets in distress is smaller than the size of the target in distress on the water.

[0118] For example Figure 11 As shown, based on endpoints 7, 8, and 9, the initial conditions corresponding to endpoints 7, 8, and 9 are traced back, such as initial conditions 1, initial conditions 2, and initial conditions 3. Furthermore, based on initial conditions 1, initial conditions 2, and initial conditions 3, as well as the drift velocity intelligent prediction model corresponding to other distressed targets simultaneously with the distressed target 20 on the water, the drift trajectory and search range of the other distressed targets are predicted. The specific prediction process refers to the prediction process described in the above embodiment and will not be repeated here. For example, the distressed target 20 on the water is a large-sized distressed target such as a fishing boat, yacht, or cargo ship that is easily observed by remote sensing satellites. Other distressed targets are smaller-sized distressed targets such as people and wreckage that are not easily observed by remote sensing satellites.

[0119] For example, the predicted drift trajectory of the other distressed target based on initial condition 1 is b, the predicted drift trajectory of the other distressed target based on initial condition 2 is a, and the predicted drift trajectory of the other distressed target based on initial condition 3 is c. End point 14 is the end point of drift trajectory a, end point 13 is the end point of drift trajectory b, and end point 15 is the end point of drift trajectory c. Furthermore, based on end points 13, 14, and 15, a search range for other distressed targets is obtained, such as search range 112.

[0120] In water distress incidents, medium-to-large targets such as ships and life rafts, as well as smaller targets such as people and debris, are often present simultaneously. However, medium-to-large targets may be identified and located by remote sensing satellites, while small targets may not. The disclosed embodiments not only predict the search range for larger water distress targets, but also, based on the remote sensing observation position of the water distress target within the search range, infer the drift trajectories and search ranges of other smaller distress targets that were in distress at the same time as the water distress target. This overcomes the problem of small targets being unable to be identified by remote sensing satellites and improves the timeliness and accuracy of small target searches.

[0121] In the embodiment of the present disclosure, the server 22 receives the remote sensing image sent by the remote sensing satellite 21, and the process of the server 22 performing remote sensing recognition on the distressed target on the water according to the remote sensing image can be as follows: Figure 12 The following steps are shown:

[0122] S1201. Input the remote sensing image captured by the remote sensing satellite into a target detection model. The target detection model includes a backbone network, a spatial-spectral dual attention module and a detection head. The backbone network is used to extract features from the remote sensing image to obtain a feature map.

[0123] For example, a target detection model is deployed on the server 22, and the target detection model 130 is as follows: Figure 13As shown. Specifically, the target detection model includes a backbone network, a spatial-spectral dual attention module and a detection head. Among them, the backbone network can be a high-performance real-time target detector (YOLOX). The server 22 inputs the remote sensing image it receives into the target detection model. The target detection model first extracts features from the remote sensing image through the backbone network to obtain a feature map. For example, the backbone network includes multiple feature layers that sequentially extract features from the remote sensing image, and each feature layer outputs a feature map. For example, the backbone network includes 5 feature layers, and the output of the previous feature layer is the input of the next feature layer. For example Figure 13 The feature map 131 shown is the output of the first feature layer, the feature map 132 is the output of the second feature layer, the feature map 133 is the output of the third feature layer, the feature map 134 is the output of the fourth feature layer, and the feature map 135 is the output of the fifth feature layer.

[0124] S1202. The feature map is processed by the spatial-spectral dual attention module, and the detection head is used to predict the type of the distressed water target in the remote sensing image and the location information of the distressed water target in the remote sensing image based on the output information of the spatial-spectral dual attention module.

[0125] For example, the result obtained after feature map 135 is processed by the spatial-spectral dual attention module is fused with feature map 134 to obtain feature map 136. The result obtained after feature map 136 is processed by the spatial-spectral dual attention module is fused with feature map 133 to obtain feature map 137. The result obtained after feature map 137 is processed by the spatial-spectral dual attention module is fused with feature map 136 to obtain feature map 138. The result obtained after feature map 138 is processed by the spatial-spectral dual attention module is fused with feature map 135 to obtain feature map 139. Then, feature map 137 is input into detection head 1310, feature map 138 is input into detection head 1311, and feature map 139 is input into detection head 1312. Detection head 1310 outputs the type of distressed water target in the remote sensing image, such as a ship, fishing boat, etc. Detection head 1311 outputs the location information of the distressed water target in the remote sensing image. The detection head 1312 outputs the confidence of the first two results, which may be the confidence corresponding to the first two results respectively, or may be the total confidence calculated based on the confidence corresponding to the first two results respectively.

[0126] S1203: Determine the remote sensing observation position of the target in distress on the water according to the position information of the target in distress on the water in the remote sensing image.

[0127] Since each pixel in a remote sensing image corresponds to a geographic coordinate, the geographic coordinates of the target in distress on the water, ie, the remote sensing observation position, can be determined based on the position information of the target in distress on the water in the remote sensing image.

[0128] Optionally, the spatial-spectral dual attention module includes a spectral attention mechanism and a spatial attention mechanism. Figure 14 As shown, the feature map 140 represents the feature map input to the spatial-spectral dual attention module, and the spectral attention mechanism and the spatial attention mechanism are connected in series. The spatial-spectral dual attention module processes the feature map as follows: Figure 15 The following steps are shown:

[0129] S1501. Extract spectral features from the feature map using the spectral attention mechanism to obtain a one-dimensional spectral attention map.

[0130] For example, the feature map 140 is represented as , the spectral features of the feature map 140 are extracted through the spectral attention mechanism (CA) to obtain a one-dimensional spectral attention map, which is recorded as The one-dimensional spectral attention map is used to regulate the importance of different channels in the feature map, further improving the robustness and expressiveness of the features. Figure 16 1 is a schematic diagram of the spectral attention mechanism, where 160 represents the input of the spectral attention mechanism, for example, In this spectral attention mechanism, mean pooling and maximum pooling operations are first used to aggregate the spatial information of the feature map, thereby generating two different spatial context descriptors, for example, The spatial context descriptor obtained by mean pooling is expressed as ,right The spatial context descriptor obtained by performing maximum pooling is expressed as . Further, and Pass into the shared network and get the feature vector and The shared network uses a multilayer perceptron (MLP) with one hidden layer to reduce the overhead of network parameters and effectively improve the representation and extraction capabilities of features. Then, the element-by-element summation method is used to and Merge and get the merge result, which is expressed as . Further, the Sigmoid function is used to process the combined result and obtain . It can be expressed as the following formula (2):

[0131] (2)

[0132] S1502: Multiply the feature map and the spectral attention map and then add the result to the feature map to obtain an intermediate result.

[0133] In order to obtain rich spectral features, the embodiment of the present disclosure adopts a combination of spectral attention mechanism and residual learning. Figure 14 As shown, the feature map and spectral attention map After element-wise multiplication, Add together to get the intermediate result, which is expressed as , It can be expressed as the following formula (3):

[0134] (3)

[0135] in, It can be Figure 14 Intermediate result 141 is shown.

[0136] In addition, in the embodiment of the present disclosure, the spatial-spectral dual attention module may include multiple (e.g., 5) spectral attention mechanisms connected in series, such as Figure 17 As shown in , the deep spectral features can be extracted through the multiple cascaded spectral attention mechanisms. In this case, Figure 17 The intermediate result 171 shown is the intermediate result obtained by multiplying the output of the last spectral attention mechanism by its input and then adding it to the input.

[0137] S1503. Perform spatial feature extraction on the intermediate result through the spatial attention mechanism to obtain a two-dimensional spatial attention map.

[0138] like Figure 14 As shown, the spatial attention mechanism extracts spatial features from the intermediate result 141 to obtain a two-dimensional spatial attention map. Figure 17 As shown, the spatial attention mechanism extracts spatial features from the intermediate result 171 and obtains a two-dimensional spatial attention map. Figure 18 The figure shows a schematic diagram of the spatial attention mechanism, where 180 represents the input of the spatial attention mechanism, for example, the input can be Figure 14 The intermediate result 141 or Figure 17 The intermediate result 171 is shown. Here, the input is recorded as In the spatial attention mechanism (SA), mean pooling and maximum pooling are first used to After processing, two different context descriptors are obtained, namely and Compared with the mean pooling and maximum pooling in the spectral attention mechanism (CA) described above, the mean pooling and maximum pooling in the spatial attention mechanism (SA) are performed along the channel axis and are mainly used to extract spatial information. and It can be regarded as context information used to guide attention generation. After obtaining these context descriptors, these context descriptors are spliced together along the channel dimension and processed by the convolution layer. Then, the output of the convolution layer is processed by the Sigmoid function to obtain a two-dimensional spatial attention map. The two-dimensional spatial attention map is represented as . It is expressed as the following formula (4):

[0139] (4)

[0140] in, Represents a convolution operation with a kernel size of 7×7.

[0141] S1504: Multiply the intermediate result and the spatial attention map and add the result to the intermediate result to obtain output information of the spatial-spectral dual attention module.

[0142] For example Figure 14 or Figure 17 As shown, the intermediate results and spatial attention map After element-wise multiplication, Add together to get the output information of the space-spectrum dual attention module, which is expressed as , It can be expressed as the following formula (5):

[0143] (5)

[0144] The embodiment of the present disclosure adjusts the weights of different areas in the spatial attention map so that the spatial attention mechanism can extract spatial features more accurately, thereby improving the performance of the target detection model. In addition, the spatial-spectral dual attention module in the embodiment of the present disclosure is composed of a spectral attention mechanism and a spatial attention mechanism in series. The spectral attention mechanism outputs a one-dimensional spectral attention map, and the spatial attention mechanism outputs a two-dimensional spatial attention map. The spectral attention mechanism is used to redistribute each weight, and the contribution of each channel feature is adjusted accordingly, so that the network pays more attention to useful features. The spatial attention mechanism is then used to identify local areas in the image that are critical to the current task, so that the target detection model can focus on the most important visual information when processing complex scenes, ignoring irrelevant background or interference, thereby greatly improving the accuracy of image processing tasks.

[0145] Optionally, the available search equipment includes drones and unmanned boats; the method also includes: based on deep reinforcement learning, constructing a joint search model for water distress targets for the drones and the unmanned boats, in which the water environment and the distribution of obstacles are used as the environment, and the drones and the unmanned boats are used as intelligent agents to construct a Markov decision process to achieve autonomous control of the search process of the drones and the unmanned boats.

[0146] For example, available search equipment includes drones and unmanned boats. Based on deep reinforcement learning, a joint search model for targets in distress on water using drones and unmanned boats has been constructed. This model uses the water environment and the distribution of obstacles as the environment, and uses drones and unmanned boats as intelligent agents to construct a Markov decision process, enabling autonomous control of the drone and unmanned boat search process. The state space includes the wind, wave, and current environment in which the drones and unmanned boats are located, as well as obstacles around them (fixed obstacles and moving drones and unmanned boats, etc.), while the action space includes the drones and unmanned boats' own heading control and speed adjustment. In the reward function design, a multi-layer reward mechanism is designed, including: 1) target discovery reward, that is, when the drones and unmanned boats discover the target, they are given a high positive reward to encourage rapid target positioning; 2) target proximity reward, that is, when the drones and unmanned boats approach the target, they are given a certain positive reward to guide them to move towards the target; 3) search efficiency reward, that is, rewards are given based on the search efficiency of the drones and unmanned boats. For example, when the drones and unmanned boats cover a new search area, they are given a positive reward; when the unmanned boats repeat the search of the covered area, they are given a negative reward; 4) safety reward, that is, when the drones and unmanned boats avoid collisions or obstacles, they are given a positive reward to ensure the safety of the drones and unmanned boats; 5) overall optimal reward, that is, when the total reward value of the drones and unmanned boats' search process for multiple targets becomes larger, they are given a positive reward, otherwise, they are given a negative reward.

[0147] During the training phase, all drones and unmanned boats share global information, improving learning efficiency through centralized training. During the execution phase, each drone and unmanned boat makes decisions based on its own local observations, achieving distributed execution. An experience replay mechanism is used to store and replay historical experience, helping the unmanned boats learn more complex strategies.

[0148] Figure 19 The schematic diagram of the structure of the device for searching for a target in distress on water provided by the embodiment of the present disclosure. The device for searching for a target in distress on water provided by the embodiment of the present disclosure can execute the processing flow provided by the embodiment of the method for searching for a target in distress on water, such as Figure 19 As shown, the device for searching for a target in distress on water 190 includes:

[0149] A first acquisition module 191 is used to obtain a starting position and a starting time for drift prediction of a target in distress on water, wherein the drift prediction includes prediction of drift speed, drift position, drift trajectory, and search range;

[0150] The second acquisition module 192 is used to obtain the environmental prediction information corresponding to the starting time within a preset spatial range around the starting position;

[0151] a generating module 193 configured to generate a plurality of initial positions for the drift prediction based on the starting position, generate a plurality of initial times for the drift prediction based on the starting time, and generate a plurality of initial environmental information for the drift prediction based on environmental prediction information corresponding to the starting time;

[0152] A first constructing module 194 is configured to construct multiple sets of initial conditions based on the multiple initial positions, the multiple initial times, and the multiple initial environmental information, each set of initial conditions including any initial position, any initial time, and any initial environmental information;

[0153] Prediction module 195 is configured to predict, based on each set of initial conditions, the drift speed and drift position of the target at distress at multiple target time points after any of the initial times, wherein the drift speed of the target at distress at each target time point is obtained based on environmental prediction information corresponding to a preset spatial range around the target's drift position at the target time point, and the drift speed of the target before the target time point, and the drift positions of the target at distress at the multiple target time points constitute a drift trajectory; and predict a search range for the target at distress based on the endpoint of each of the multiple drift trajectories corresponding to the multiple sets of initial conditions;

[0154] The collaborative search module 196 is configured to collaboratively search for the distressed target on water within the search range using available search equipment.

[0155] Optionally, when the second acquisition module 192 acquires the environmental prediction information corresponding to the starting time within a preset spatial range around the starting position, it is specifically configured to:

[0156] The position information corresponding to each of the multiple first-resolution grids contained in the preset spatial range around the starting position, the environmental prediction information corresponding to each of the multiple first-resolution grids at the starting time, and the position information corresponding to each of the multiple second-resolution grids contained in the preset spatial range are input into the downscaling deep learning model, and the environmental prediction information corresponding to each of the multiple second-resolution grids at the starting time output by the downscaling deep learning model is used as the environmental prediction information corresponding to the preset spatial range around the starting position at the starting time, wherein the second resolution is greater than the first resolution.

[0157] Optionally, the environmental prediction information corresponding to a preset spatial range around the drift position of the target in distress on water at the target time point is obtained according to the following method:

[0158] The position information corresponding to multiple first-resolution grids contained in a preset spatial range around the drift position of the target on water at the target time point, the environmental prediction information corresponding to the multiple first-resolution grids at the target time point, and the position information corresponding to multiple second-resolution grids contained in the preset spatial range are input into the downscaling deep learning model, and the environmental prediction information corresponding to the multiple second-resolution grids at the target time point output by the downscaling deep learning model is used as the environmental prediction information corresponding to the preset spatial range around the drift position of the target on water at the target time point, wherein the second resolution is greater than the first resolution.

[0159] Optionally, the environmental prediction information includes wind field forecast results, wave field forecast results, and flow field forecast results;

[0160] The downscaling deep learning model is trained according to the following steps:

[0161] Calculating environmental prediction information for a plurality of first-resolution grids in the target waters at preset time intervals within a preset future time period according to a wind-wave-current coupled prediction model, wherein the wind-wave-current coupled prediction model is a coupled model of an atmospheric numerical model, a wave numerical model, and a hydrodynamic numerical model;

[0162] Calculating, according to the wind-wave-current coupled prediction model, environmental prediction information of a plurality of second-resolution grids in the target waters at preset time intervals within the future preset time period;

[0163] Inputting the position information corresponding to the plurality of first-resolution grids, the environmental prediction information of the plurality of first-resolution grids at preset time intervals within the future preset time period, and the position information corresponding to the plurality of second-resolution grids into a downscaling deep learning model to be trained, the downscaling deep learning model outputting the environmental prediction information of the plurality of second-resolution grids at preset time intervals within the future preset time period;

[0164] The downscaling deep learning model is trained based on the environmental prediction information of the multiple second-resolution grids output by the downscaling deep learning model at preset time intervals within the future preset time period, and the environmental prediction information of the multiple second-resolution grids calculated by the wind-wave-current coupling forecast model at preset time intervals within the future preset time period.

[0165] Optionally, when the prediction module 195 predicts the drift speed and drift position of the target in distress on water at multiple water time points after any initial time according to each set of initial conditions, it is specifically configured to:

[0166] Inputting any of the initial environmental information into a drift speed intelligent prediction model corresponding to the target in distress on the water, and the drift speed intelligent prediction model outputting the drift speed of the target in distress on the water at any of the initial times;

[0167] For each target time point after any of the initial times, calculating the drift position of the target in distress on the water at the target time point based on the drift speed and drift position of the target in distress on the water at the previous target time point;

[0168] The environmental prediction information corresponding to a preset spatial range around the drift position of the target in distress on the water at the target time point and the drift speed of the target in distress on the water before the target time point are input into the drift speed intelligent prediction model, and the drift speed intelligent prediction model outputs the drift speed of the target in distress on the water at the target time point.

[0169] Optionally, the intelligent prediction model for the drift speed of the target in distress on water is trained according to the following steps:

[0170] Obtaining, by means of a BeiDou positioning system, drift positions of an experimental target representing the target in distress on water at a plurality of preset time points during its free drift in the target waters;

[0171] Calculating the drift speeds of the experimental target corresponding to the plurality of preset time points according to the drift positions corresponding to the plurality of preset time points;

[0172] For each of the plurality of preset time points, inputting environmental prediction information corresponding to a preset spatial range around a drift position corresponding to the preset time point of the experimental target and a drift speed of the experimental target before the preset time point into the drift speed intelligent prediction model, the drift speed intelligent prediction model outputting the drift speed of the experimental target corresponding to the preset time point;

[0173] The drift speed intelligent prediction model is trained according to the calculated drift speed corresponding to the experimental target at the preset time point and the drift speed corresponding to the experimental target at the preset time point output by the drift speed intelligent prediction model.

[0174] Optionally, the device for searching for targets in distress on water 190 further includes a guiding module 197 for guiding the remote sensing satellite to observe within the search range after the prediction module 195 predicts the search range of the targets in distress on water.

[0175] Optionally, the prediction module 195 is also used for: when the remote sensing satellite observes the distressed target on the water, based on the remote sensing observation position and remote sensing observation time point of the distressed target on the water, using the drift speed intelligent prediction model corresponding to the distressed target on the water to perform a re-drift prediction on the distressed target on the water, to obtain a new search range for the distressed target on the water, the remote sensing observation position is the starting position for the re-drift prediction, and the remote sensing observation time point is the starting time for the re-drift prediction.

[0176] Optionally, the water distress target search device 190 also includes a selection module 198, which is used to select a preset number of end points around the water distress target within the search range when the remote sensing satellite observes the water distress target within the search range; the prediction module 195 is also used to: predict the drift speed, drift position, drift trajectory and search range of the other distress targets based on the initial conditions corresponding to the preset number of end points and the drift speed intelligent prediction model corresponding to other distress targets that are in distress at the same time as the water distress target, and the size of the other distress targets is smaller than the size of the water distress target.

[0177] Optionally, the device for searching for a target in distress on water 190 further includes:

[0178] An input module 199 is configured to input the remote sensing image captured by the remote sensing satellite into a target detection model. The target detection model includes a backbone network, a spatial-spectral dual attention module, and a detection head. The backbone network is configured to extract features from the remote sensing image to obtain a feature map.

[0179] a processing module 1910 configured to process the feature map using the spatial-spectral dual attention module, wherein the detection head is configured to predict the type of the distressed aquatic target in the remote sensing image and the location information of the distressed aquatic target in the remote sensing image based on the output information of the spatial-spectral dual attention module;

[0180] The determination module 1911 is configured to determine the remote sensing observation position of the target in distress on the water according to the position information of the target in distress on the water in the remote sensing image.

[0181] Optionally, the spatial-spectral dual attention module includes a spectral attention mechanism and a spatial attention mechanism. When the spatial-spectral dual attention module processes the feature map, it is specifically used to:

[0182] Extracting spectral features from the feature map using the spectral attention mechanism to obtain a one-dimensional spectral attention map;

[0183] Multiplying the feature map and the spectral attention map and then adding the result to the feature map to obtain an intermediate result;

[0184] Performing spatial feature extraction on the intermediate result through the spatial attention mechanism to obtain a two-dimensional spatial attention map;

[0185] The intermediate result and the spatial attention map are multiplied and then added to the intermediate result to obtain the output information of the spatial-spectral dual attention module.

[0186] Optionally, the available search equipment includes drones and unmanned boats; the water distress target search device 190 also includes: a second construction module 1912, which is used to construct a joint search model for water distress targets for the drone and the unmanned boat based on deep reinforcement learning. In the joint search model, the water environment field and the distribution of obstacles are used as the environment, and the drone and the unmanned boat are used as intelligent agents to construct a Markov decision process to achieve autonomous control of the search process of the drone and the unmanned boat.

[0187] Figure 19 The device for searching for targets in distress on water in the illustrated embodiment can be used to implement the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effects are similar and will not be described in detail here.

[0188] The above describes the internal functions and structure of the device for searching for objects in distress on water. The device can be implemented as an electronic device. Figure 20 This is a schematic diagram of the structure of an electronic device embodiment provided by the present disclosure. Figure 20 As shown, the electronic device includes a memory 201 and a processor 202 .

[0189] The memory 201 is used to store programs. In addition to the aforementioned programs, the memory 201 may also be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, contact data, phone book data, messages, images, videos, etc.

[0190] The memory 201 can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0191] The processor 202 is coupled to the memory 201 and executes the program stored in the memory 201 to implement the technical solution of the above method embodiment.

[0192] Further, if Figure 20 As shown, the electronic device may further include: a communication component 203, a power component 204, an audio component 205, a display 206 and other components. Figure 20 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 20 Components shown.

[0193] The communication component 203 is configured to facilitate wired or wireless communication between the electronic device and other devices. The electronic device can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 203 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 203 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0194] The power supply component 204 provides power to various components of the electronic device. The power supply component 204 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device.

[0195] The audio component 205 is configured to output and / or input audio signals. For example, the audio component 205 includes a microphone (MIC), which is configured to receive external audio signals when the electronic device is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 201 or transmitted via the communication component 203. In some embodiments, the audio component 205 also includes a speaker for outputting audio signals.

[0196] The display 206 includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0197] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement the method described in the above embodiment.

[0198] The exemplary embodiments of the present disclosure further provide a computer program product, including a computer program, wherein when the computer program is executed by a processor of a computer, the computer is configured to enable the computer to implement the method described in the above embodiment.

[0199] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0200] The foregoing description is intended only to provide specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments described herein, but rather to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for searching for a target in distress on water, characterized in that: The method comprises: Obtaining a starting position and a starting time for drift prediction of a target in distress on water, wherein the drift prediction includes prediction of drift speed, drift position, drift trajectory, and search range; Obtaining environmental prediction information corresponding to the starting time within a preset spatial range around the starting position; generating a plurality of initial positions for the drift prediction based on the starting position, generating a plurality of initial times for the drift prediction based on the starting time, generating a plurality of initial environmental information for the drift prediction based on environmental prediction information corresponding to the starting time, and constructing a plurality of sets of initial conditions based on the plurality of initial positions, the plurality of initial times, and the plurality of initial environmental information, each set of initial conditions including any initial position, any initial time, and any initial environmental information; predicting, based on each set of initial conditions, a drift speed and a drift position of the target in distress at a plurality of target time points after any of the initial times, wherein the drift speed of the target in distress at each target time point is obtained based on environmental prediction information corresponding to a preset spatial range around the drift position of the target in distress at the target time point, and the drift speed of the target in distress before the target time point, and the drift positions of the target in distress at the plurality of target time points forming a drift trajectory; predicting a search range for the target in distress on the water based on an end point of each drift trajectory in the plurality of drift trajectories corresponding to the plurality of sets of initial conditions; A collaborative search is performed for the target in distress on the water within the search range using available search equipment.

2. The method according to claim 1, characterized in that The environmental prediction information corresponding to the preset spatial range around the drift position of the target in distress at the target time point is obtained according to the following method: The position information corresponding to multiple first-resolution grids contained in a preset spatial range around the drift position of the target on water at the target time point, the environmental prediction information corresponding to the multiple first-resolution grids at the target time point, and the position information corresponding to multiple second-resolution grids contained in the preset spatial range are input into the downscaling deep learning model, and the environmental prediction information corresponding to the multiple second-resolution grids at the target time point output by the downscaling deep learning model is used as the environmental prediction information corresponding to the preset spatial range around the drift position of the target on water at the target time point, wherein the second resolution is greater than the first resolution.

3. The method according to claim 2, characterized in that The environmental prediction information includes wind field forecast results, wave field forecast results, and flow field forecast results; The downscaling deep learning model is trained according to the following steps: Calculating environmental prediction information for a plurality of first-resolution grids in the target waters at preset time intervals within a preset future time period according to a wind-wave-current coupled prediction model, wherein the wind-wave-current coupled prediction model is a coupled model of an atmospheric numerical model, a wave numerical model, and a hydrodynamic numerical model; Calculating, according to the wind-wave-current coupled prediction model, environmental prediction information of a plurality of second-resolution grids in the target waters at preset time intervals within the future preset time period; Inputting the position information corresponding to the plurality of first-resolution grids, the environmental prediction information of the plurality of first-resolution grids at preset time intervals within the future preset time period, and the position information corresponding to the plurality of second-resolution grids into a downscaling deep learning model to be trained, the downscaling deep learning model outputting the environmental prediction information of the plurality of second-resolution grids at preset time intervals within the future preset time period; The downscaling deep learning model is trained based on the environmental prediction information of the multiple second-resolution grids output by the downscaling deep learning model at preset time intervals within the future preset time period, and the environmental prediction information of the multiple second-resolution grids calculated by the wind-wave-current coupling forecast model at preset time intervals within the future preset time period.

4. The method according to claim 1, wherein Predicting, based on each set of initial conditions, the drift speed and drift position of the target in distress on water at a plurality of target time points after any of the initial times, comprises: Inputting any of the initial environmental information into a drift speed intelligent prediction model corresponding to the target in distress on the water, and the drift speed intelligent prediction model outputting the drift speed of the target in distress on the water at any of the initial times; For each target time point after any of the initial times, calculating the drift position of the target in distress on the water at the target time point based on the drift speed and drift position of the target in distress on the water at the previous target time point; The environmental prediction information corresponding to a preset spatial range around the drift position of the target in distress on the water at the target time point and the drift speed of the target in distress on the water before the target time point are input into the drift speed intelligent prediction model, and the drift speed intelligent prediction model outputs the drift speed of the target in distress on the water at the target time point.

5. The method according to claim 4, characterized in that The intelligent prediction model for the drift speed of the target in distress on water is trained according to the following steps: Obtaining, by means of a BeiDou positioning system, drift positions of an experimental target representing the target in distress on water at a plurality of preset time points during its free drift in the target waters; Calculating the drift speeds of the experimental target corresponding to the plurality of preset time points according to the drift positions corresponding to the plurality of preset time points; For each of the plurality of preset time points, inputting environmental prediction information corresponding to a preset spatial range around a drift position corresponding to the preset time point of the experimental target and a drift speed of the experimental target before the preset time point into the drift speed intelligent prediction model, the drift speed intelligent prediction model outputting the drift speed of the experimental target corresponding to the preset time point; The drift speed intelligent prediction model is trained according to the calculated drift speed corresponding to the experimental target at the preset time point and the drift speed corresponding to the experimental target at the preset time point output by the drift speed intelligent prediction model.

6. The method according to claim 1, characterized in that After predicting the search range of the target in distress on water, the method further includes: The remote sensing satellite is guided to conduct observations within the search range.

7. The method according to claim 1, characterized in that The method further comprises: When the remote sensing satellite observes the distressed target on the water, the drift prediction of the distressed target on the water is performed again according to the remote sensing observation position and remote sensing observation time point of the distressed target on the water using the drift speed intelligent prediction model corresponding to the distressed target on the water to obtain a new search range of the distressed target on the water. The remote sensing observation position is the starting position for the re-drift prediction, and the remote sensing observation time point is the starting time for the re-drift prediction.

8. The method according to claim 1, characterized in that The method further comprises: When the remote sensing satellite observes the distress target on the water within the search range, a preset number of end points around the distress target on the water are selected within the search range; Based on the initial conditions corresponding to the preset number of end points and the drift speed intelligent prediction model corresponding to other distressed targets that are in distress at the same time as the distressed target on the water, the drift speed, drift position, drift trajectory and search range of the other distressed targets are predicted, and the size of the other distressed targets is smaller than the size of the distressed target on the water.

9. The method according to any one of claims 6 to 8, characterized in that The method further comprises: Inputting the remote sensing image captured by the remote sensing satellite into a target detection model, wherein the target detection model includes a backbone network, a spatial-spectral dual attention module and a detection head, wherein the backbone network is used to extract features from the remote sensing image to obtain a feature map; The feature map is processed by the spatial-spectral dual attention module, and the detection head is used to predict the type of the distressed target on the water in the remote sensing image and the location information of the distressed target on the water in the remote sensing image according to the output information of the spatial-spectral dual attention module; The remote sensing observation position of the target in distress on the water is determined according to the position information of the target in distress on the water in the remote sensing image.

10. The method according to claim 9, characterized in that The spatial-spectral dual attention module includes a spectral attention mechanism and a spatial attention mechanism. The spatial-spectral dual attention module processes the feature map, including: Extracting spectral features from the feature map using the spectral attention mechanism to obtain a one-dimensional spectral attention map; Multiplying the feature map and the spectral attention map and then adding the result to the feature map to obtain an intermediate result; Performing spatial feature extraction on the intermediate result through the spatial attention mechanism to obtain a two-dimensional spatial attention map; The intermediate result and the spatial attention map are multiplied and then added to the intermediate result to obtain the output information of the spatial-spectral dual attention module.

11. The method according to claim 1, wherein The available search equipment includes unmanned aerial vehicles (UAVs) and unmanned boats (UAVs); and the method further includes: Based on deep reinforcement learning, a joint search model for water distress targets of the UAV and the unmanned boat is constructed. In the joint search model, the water environment and the distribution of obstacles are used as the environment, and the UAV and the unmanned boat are used as intelligent agents to construct a Markov decision process to achieve autonomous control of the search process of the UAV and the unmanned boat.

12. A device for searching for a target in distress on water, characterized in that: The device comprises: A first acquisition module is used to obtain a starting position and a starting time for drift prediction of a target in distress on water, wherein the drift prediction includes prediction of drift speed, drift position, drift trajectory, and search range; A second acquisition module is used to obtain environmental prediction information corresponding to the starting time within a preset spatial range around the starting position; a generating module, configured to generate a plurality of initial positions for the drift prediction according to the starting position, generate a plurality of initial times for the drift prediction according to the starting time, and generate a plurality of initial environmental information for the drift prediction according to the environmental prediction information corresponding to the starting time; A first constructing module is configured to construct multiple groups of initial conditions based on the multiple initial positions, the multiple initial times, and the multiple initial environmental information, each group of initial conditions including any initial position, any initial time, and any initial environmental information; a prediction module for predicting, based on each set of initial conditions, the drift speed and drift position of the target in distress at a plurality of target time points after any of the initial times, wherein the drift speed of the target in distress at each target time point is obtained based on environmental prediction information corresponding to a preset spatial range around the drift position of the target in distress at the target time point, and the drift speed of the target in distress before the target time point, and the drift positions of the target in distress at the plurality of target time points constitute a drift trajectory; and predicting a search range for the target in distress based on the endpoint of each of the plurality of drift trajectories corresponding to the plurality of sets of initial conditions; The collaborative search module is used to perform a collaborative search for the distressed target on the water within the search range by using available search equipment.

13. An electronic device, characterized in that: include: Memory; processor; as well as computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method according to any one of claims 1 to 11.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images