Movable water area target identification verification system

Abstract

The application provides a movable water area target identification and verification system, which comprises a load platform, a video acquisition module, a target identification module and a target positioning module; the load platform is used for supporting the equipment of water area target identification and verification; based on the load platform, the video acquisition module is used to acquire water area target image information, the target identification module is used to acquire video data and detect targets, and target information is obtained; the target positioning module is used to acquire the target information, and the position information of the target is obtained. The unmanned ship-aircraft combined water area suspicious target identification and verification system adopted by the application has the mobility, can be carried on the unmanned ship and unmanned aircraft platform, realizes the stereoscopic observation of the patrol water area, the unmanned ship can supply energy to the unmanned aircraft through the wireless charging parking apron, the operation efficiency of the unmanned ship-aircraft combined target identification and verification is improved, and the risk of manually carrying out suspicious target identification and verification in complex and dangerous water areas is reduced.

Description

Technical Field

[0001] This invention pertains to surface target identification and verification, specifically, to a portable water target identification system and verification method. More specifically, it relates to a portable water target identification system and verification method, and more specifically, to the design of a system and method for jointly identifying and verifying suspicious surface targets using an unmanned surface vessel (USV) and an unmanned aerial vehicle (UAV) through a target identification system and navigation module. The term "portable" refers to its ability to be mounted on USVs and UAV platforms to achieve three-dimensional observation of patrolled waters. Background Technology

[0002] Most traditional water target identification and verification tasks require manual intervention, resulting in relatively low efficiency. However, with the rapid development of intelligent equipment, the application of cross-domain unmanned systems in water target identification and verification has attracted widespread attention.

[0003] Compared to traditional methods of water target identification and verification, unmanned systems can effectively reduce operating costs and quickly and accurately locate and verify water targets. Among these, unmanned surface vessels (USVs), as a crucial tool for water target identification and verification, can conduct long-term, wide-area target identification and verification in complex and dangerous sea conditions. However, USVs have limited field of vision, hindering the rapid and accurate acquisition of target identification and verification information. Unmanned aerial vehicles (UAVs), with their advantages of three-dimensional maneuverability and wide field of vision, can compensate for the limitations of USVs' field of vision. Furthermore, USVs can simultaneously address the issues of short endurance and weak payload capacity of UAVs.

[0004] However, existing water target identification systems are single-platform systems, which suffer from low efficiency in target identification and verification, leading to high verification costs and weak autonomous power for unmanned patrols. This problem urgently needs to be solved. Summary of the Invention

[0005] In view of the deficiencies in the prior art, the purpose of this invention is to provide a portable water target identification and verification system.

[0006] A portable water target identification and verification system provided by the present invention includes: a payload platform, a video acquisition module, a target recognition module, and a target positioning module;

[0007] The payload platform is used to support equipment for the identification and verification of water targets.

[0008] Based on the payload platform, the video acquisition module acquires water target image information, the target recognition module acquires video data and detects targets to obtain target information.

[0009] The target information is obtained through the target positioning module, and the target's location information is obtained.

[0010] Preferably, the payload platform includes: an unmanned aerial vehicle (UAV) flight platform, an unmanned surface vessel (USV) and a ground monitoring platform;

[0011] The unmanned aerial vehicle (UAV) flight platform is used to detect, identify, and locate suspicious targets on the water surface; the suspicious targets on the water surface are boats.

[0012] The unmanned surface vessel (USV) is a catamaran unmanned surface vessel (USV). The USV is used to receive the location information of the suspected target on the water surface and plan its path.

[0013] The ground monitoring platform is used to display the status information of the UAV and issue control commands.

[0014] Preferably, it can realize the wide-area search stage, the surface target identification and positioning stage, and the joint submarine-aircraft approach identification and verification stage;

[0015] The wide-area search phase includes:

[0016] Commands are issued through the ground control platform to instruct the UAV and the unmanned surface vessel to reach the patrol position and begin patrolling; the video acquisition module is instructed to acquire water target image information through the UAV; and the UAV is instructed to score and rank the targets based on the target image information using a comprehensive weight ranking method to obtain the priority order for verification.

[0017] The water surface target identification and localization stage includes:

[0018] The target recognition module determines whether the UAV has detected a suspicious target on the water surface; if the result is no, the UAV returns to the unmanned vessel for charging after the patrol mission ends; if the result is yes, the suspicious target on the water surface is identified and located according to the priority order of the verification, and the target information is obtained.

[0019] The joint submarine-aircraft approach identification and verification phase includes:

[0020] The target information is obtained through the target positioning module, and the target's location information is obtained. The UAV is instructed to send the target's location information to the unmanned surface vessel, which then approaches and verifies the suspicious target on the water surface based on the target's location information. After verification, the UAV returns to its origin.

[0021] Preferably, in the wide-area search stage, the comprehensive weight ranking method is to represent the evaluation value of the attribute using triangular fuzzy numbers, and then prioritize the attribute based on the evaluation value.

[0022] The expression for the triangular fuzzy number is:

[0023]

[0024] in, Let a be a triangular fuzzy number. i For the minimum value, b i For the most likely value, c i It is the maximum value;

[0025] For maximizing the objective, the linear membership function of the triangular fuzzy number is expressed as:

[0026]

[0027] For the minimization objective, the linear membership function of the triangular fuzzy number is expressed as:

[0028]

[0029] For dynamic characteristics, the expression for the linear membership function is:

[0030]

[0031] in, For dynamic characteristics, use a linear membership function;

[0032] In the comprehensive weight ranking method, the weight of each attribute, i.e., w, is determined. I w T w D With w C This reflects the relative importance of each attribute in the verification task, and its mathematical expression is:

[0033] w I +w T +w D +w C =1(5)

[0034] Among them, w I Weights for importance; w T Weights for threat level; w D Weights for dynamic characteristics; w C Weighting based on the difficulty of verification;

[0035] Based on the w I w T w D With w C For each target i, calculate the comprehensive score, the mathematical expression of which is:

[0036]

[0037] Among them, S i It is a comprehensive score. It is the degree of membership of target i in terms of importance. Let i be the membership degree of target i in terms of threat level. Let i be the membership degree of the target i in terms of dynamic characteristics. Let represent the membership degree of target i in terms of verification difficulty; the symbol · represents the product;

[0038] All targets are sorted in descending order based on the comprehensive score; the higher the comprehensive score, the higher the priority of verification.

[0039] Preferably, in the water surface target identification and localization stage, the unmanned surface vessel adjusts its own position information based on the position information of the unmanned aerial vehicle (UAV); the position error between the unmanned surface vessel and the UAV is mathematically expressed as:

[0040]

[0041] Where, ΔX iav-usv The positional error along the X-axis between the unmanned surface vessel and the unmanned aerial vehicle; ΔY iav-usv The positional error along the Y-axis between the unmanned surface vessel (USV) and the unmanned aerial vehicle (UAV); ΔZ uav-usv X represents the positional error along the Z-axis between the unmanned surface vessel and the unmanned aerial vehicle; a Y a With Z a These are the drone's position information along the X-axis, Y-axis, and Z-axis, respectively; X s Y s With Z s These are the unmanned surface vessel's position information along the X-axis, Y-axis, and Z-axis, respectively.

[0042] Determine whether the unmanned surface vessel (USV) meets the position error requirement. If the result is yes, then the position of the USV is not adjusted; if the result is no, then the position of the USV is adjusted.

[0043] The position error requirement is as follows:

[0044] ΔX uav-usv =0

[0045] ΔY uav-usv =0

[0046] ΔZ uav-usv =Z a

[0047] Among them, Z a This refers to the drone's position information along the Z-axis.

[0048] Preferably, the unmanned surface vessel (USV) escorting the UAV maintains a relative posture by using a process control objective cost function;

[0049] The process control objective cost function is mathematically expressed as follows:

[0050]

[0051] Where, min J is the process control objective cost function; Q represents the weight of the situation maintenance error; the superscript T is the transpose identifier; and X is the position of the unmanned surface vessel. R is the control variable of the unmanned surface vessel; R is the weight of the control variable difference; ΔU a X represents the target value of the unmanned surface vessel's control variables. uav A reference trajectory is given to the drone.

[0052] Preferably, during the joint approach identification and verification phase of the unmanned surface vessel and aircraft, the unmanned surface vessel, according to A * The global path planning algorithm obtains and verifies the target based on the nearest path;

[0053] In the wide-area search phase, water target image information is obtained using the YOLOv8 model;

[0054] Preferably, the UAV hovers in a fixed position and sends the target's location information to the unmanned surface vessel.

[0055] Preferably, the drone follows a "bow"-shaped patrol path.

[0056] Preferably, the UAV collects 25 frames of image data per second, flies at an altitude of 50m, and patrols at a speed of 5m / s.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] 1. The unmanned surface vessel-drone joint operation system for identifying and verifying suspicious targets in waters, as used in this invention, is portable and can be mounted on unmanned surface vessels and drone platforms to achieve three-dimensional observation of patrolled waters. Furthermore, the unmanned surface vessel can recharge the drone via a wireless charging helipad, which improves the operational efficiency of unmanned surface vessel-drone joint target identification and verification and reduces the risk of manually identifying and verifying suspicious targets in complex and dangerous waters.

[0059] 2. The unmanned surface vessel-drone joint identification and verification of suspicious targets in waters provided by this invention consists of a combination of phased identification and verification strategies. Compared with traditional identification and verification methods, the identification and verification method of this invention is designed for typical waters to be patrolled. First, suspicious targets are extracted through wide-area search, and a comprehensive weight ranking method is proposed to prioritize the close-up confirmation and verification of suspicious targets. Then, the suspicious targets are identified and located from the high-altitude perspective of the drone, and the location information of the suspicious targets is uploaded to the unmanned surface vessel. The unmanned surface vessel and the drone work together to approach the vicinity of the suspicious targets to carry out identification and verification.

[0060] 3. This invention provides a boat-aircraft cooperative search model that meets the needs of unmanned autonomous target identification and verification. Compared with traditional target identification and verification methods, the unmanned boat-aircraft joint target identification and verification has high efficiency, low cost, and strong energy autonomy for unmanned autonomous patrol. Attached Figure Description

[0061] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0062] Figure 1 A schematic diagram of the system composition of the load platform provided by the present invention;

[0063] Figure 2 A schematic diagram illustrating the working principle of this invention;

[0064] Figure 3 The flowchart for the identification and verification of suspicious surface targets using a combined unmanned surface vessel and aircraft method provided by this invention;

[0065] Figure 4 The first flowchart of the main working mode of the unmanned surface vessel provided by the present invention;

[0066] Figure 5 The second flowchart illustrates the main operating modes of the UAV provided by this invention. Detailed Implementation

[0067] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0068] The present invention provides a water target identification system and verification method. Compared with the current state of existing technology, the present invention focuses on the research of "land-air-sea cross-domain joint, unmanned autonomous identification and verification".

[0069] This embodiment provides a suspicious target identification system and verification method for water areas. The identification system is portable and can be carried on platforms such as unmanned surface vessels and drones.

[0070] A portable water target identification system according to the present invention includes: a video acquisition module, a target recognition module, and a target positioning module;

[0071] The video acquisition module includes: a binocular camera, a video decoding module, and a video stream output module; the video acquisition module can acquire real-time image information of water targets through the binocular camera.

[0072] The target recognition module is used to acquire video data in real time and to detect and identify suspicious targets in the water area using an improved YOLOv8 model.

[0073] The target positioning module is used to acquire the target information identified by the target recognition module in real time. By extracting the pixel coordinates of the target in the window and performing coordinate transformation, the target positioning module can further receive the positioning information of the payload platform in real time and finally calculate the position information of the target in the geodetic coordinates.

[0074] Specifically, this embodiment uses a payload platform carrying the water area identification system proposed in this invention to illustrate its working principle and method. The payload platform includes: a quadcopter UAV flight platform, a catamaran unmanned surface vessel and a ground monitoring platform. The method is divided into three stages: wide-area search for suspicious targets on the water surface, identification and positioning of suspicious targets on the water surface, and joint approach identification and verification by the unmanned surface vessel and the UAV.

[0075] The quadcopter drone flight platform includes: a control module, a navigation and positioning module, a communication module, a wireless charging module, and a power system. The drone flight platform can be equipped with a water target identification system for detecting, identifying, and locating suspicious targets on the water surface. The drone's control module is used for drone flight attitude control. The drone's navigation and positioning module is used for drone route planning and precise location of suspicious targets on the water surface. The drone's communication module is used to receive command and control data from the ground monitoring platform and transmit suspicious target location data to the catamaran unmanned surface vessel, and to transmit suspicious target data back to the ground monitoring platform. The wireless charging module is used for energy replenishment when the drone docks at a wireless charging landing pad. The drone's power system is used to enable the drone to quickly maneuver and search for suspicious targets on the water surface.

[0076] The ground monitoring platform includes: a communication module, monitoring software, and a remote control terminal; the communication module of the ground monitoring platform is connected to a wireless data transmission module and is used to receive UAV status information, video information, and identified suspicious target location information transmitted back by the UAV communication module; the monitoring software is used to display UAV status information, video information, and suspicious target location information, and is used to receive command and control information from the ground remote control terminal; the remote control terminal of the ground monitoring platform is used to issue UAV control commands and to control the UAV's flight speed and direction;

[0077] Figure 1 This is a schematic diagram of the system composition of the load platform described in this invention, as shown below. Figure 1 As shown, the quadcopter UAV flight platform includes: a target identification system, a differential positioning unit, a wireless data transmission unit, and a flight control unit;

[0078] The target identification system is used to perform wide-area target search in the target water area, exclude inherent targets on the water surface, and identify and locate suspicious targets on the water surface by combining the improved YOLOv8 model. The relative position of the suspicious target is calculated and converted by combining the differential positioning data of the UAV. The converted location information of the suspicious target on the water surface is transmitted to the unmanned surface vessel via wireless data transmission. The suspicious target identification and positioning process is controlled by the flight control unit to control the attitude and altitude of the UAV.

[0079] The catamaran unmanned surface vessel (USV) includes: a target identification system, a mission planning unit, a propulsion and drive unit, and a wireless data transmission unit. The USV is mainly used to receive the coordinate position information of suspicious targets on the water surface from the UAV, and to perform global path planning using the improved A* algorithm. In addition, the USV's target identification system can acquire suspicious targets on the water surface in real time and perform path replanning to the vicinity of the suspicious targets.

[0080] The ground monitoring platform mainly uses the communication module to interact with the airborne flight control unit. The monitoring software is used to display the status information of the UAV in real time and issue control commands. The remote control terminal is used to manually operate the UAV and has the function of switching between autonomous and manual modes.

[0081] This embodiment provides a method for identifying and verifying suspicious targets on the water surface using a combined unmanned surface vessel (USV) and USV approach. Its primary functions include wide-area target search by the USV, identification and localization of suspicious targets on the water surface, and autonomous route planning by the USV to approach suspicious targets. The specific system working principle is as follows: Figure 2 As shown;

[0082] Taking a reservoir to be patrolled as an example, let's assume the total area of ​​the water body is 3.7 km². 2 The water surface contains fixed targets such as buoys and islands. The unmanned surface vessel-drone joint identification and verification platform is permanently docked at the command center's pier. After receiving patrol mission instructions, the unmanned surface vessel carries the drone to the mission's starting point to await orders. The drone then takes off to patrol altitude to observe suspicious targets on the water surface; these suspicious targets are vessels with questionable flight paths. The drone is equipped with a 150° wide-angle camera, flies at an altitude of 50m, patrols at a speed of 5m / s, and collects 25 frames of image data per second, covering a distance of 1km. 2 The waterway inspection task takes 10 minutes.

[0083] Therefore, while ensuring the search efficiency of drones, two drones are used in rotation. When the drone's battery is low, it can autonomously return to the unmanned surface vessel for wireless charging, efficiently completing the identification and verification of targets in the water. The target identification and verification of the unmanned surface vessel-drone joint identification and verification platform consists of three stages: wide-area search stage, water surface target identification and positioning stage, and boat-drone joint approach identification and verification stage.

[0084] Specifically, the wide-area search phase is performed as follows:

[0085] Step 101: The unmanned surface vessel-machine joint identification and verification platform is stationed at the dock in the accident-prone waters. After receiving the water patrol mission instructions from the command department, it departs from the dock and sails quickly to the patrol starting point.

[0086] Step 102: After the unmanned surface vessel-drone joint identification and verification platform arrives at the patrol starting point, the drone takes off and flies 50m into the air. It then uses its onboard 150° wide-angle camera to conduct a wide-area search of the patrol waters. The onboard high-performance visual edge processing computer quickly detects whether there are any suspected or suspicious targets in the waters within the field of view.

[0087] Step 103: If a suspected target is initially detected, the UAV performs preliminary positioning by processing the image coordinates of the suspected target and combining it with the onboard high-precision single-antenna RTK positioning data. The preliminary positioning information of the suspected target is compared with the marked location of a long-term target on the water surface. If the two positions are within a set error range r, the target is identified as a long-term target on the water surface; otherwise, the UAV approaches further for detection and positioning. If no suspected target is initially detected (i.e., a suspected target on the water surface), the UAV autonomously executes a "bow"-shaped patrol path, using the UAV's onboard camera's field of view as the spacing of the "bow"-shaped path to ensure search efficiency.

[0088] Step 104: The UAV sorts the identified suspected targets, mainly using a comprehensive weighted sorting method. Each target attribute includes importance, threat level, dynamic characteristics, and verification difficulty. The evaluation value of each attribute is represented using a triangular fuzzy number. For attribute x of target i, its triangular fuzzy number can be expressed as:

[0089]

[0090] in, Let a be a triangular fuzzy number. i For the minimum value, b i For the most likely value, c i This is the maximum value.

[0091] Furthermore, to transform fuzzy evaluation into specific numerical values, it is necessary to define a linear membership function.

[0092] For maximizing objectives, such as importance I and threat level T, the mathematical expression for the linear membership function is:

[0093]

[0094] For minimizing the objective, such as the verification difficulty, i.e., C, the mathematical expression of the linear membership function is:

[0095]

[0096] For dynamic characteristics, i.e., D, an appropriate membership function can be selected according to specific needs, such as:

[0097]

[0098] in, For dynamic characteristics, use a linear membership function;

[0099] Furthermore, determine the weight w of each attribute. I ,w T ,w D ,w C The weights mentioned above reflect the relative importance of each attribute in the verification task. The weights can be determined by expert scoring and the analytic hierarchy process (AHP) to meet the conditions.

[0100] In other words, in the comprehensive weight ranking method, the weight of each attribute, i.e., w, is determined. I w T w D With w C This reflects the relative importance of each attribute in the verification task, and its mathematical expression is:

[0101] w I +w T +w D +w C =1(5)

[0102] Among them, w I Weights for importance; w T Weights for threat level; w D Weights for dynamic characteristics; w C Weighting based on the difficulty of verification;

[0103] Furthermore, a comprehensive score is calculated for each target i. i :

[0104]

[0105] in, It is the degree of membership of target i in terms of importance. Let i be the membership degree of target i in terms of threat level. Let i be the membership degree of the target i in terms of dynamic characteristics. Let represent the membership degree of target i in terms of verification difficulty; the symbol · represents the product;

[0106] Furthermore, based on the calculated comprehensive score S i All targets are sorted in descending order, with higher scores indicating higher priority for verification;

[0107] Specifically, the steps for the water surface target identification and localization stage are as follows:

[0108] Step 201: If the drone does not detect any suspected targets on the water surface during the patrol, it will continue to follow the "bow" shaped patrol path until the mission is completed, and then return to the unmanned boat for wireless charging.

[0109] Step 202: If the UAV detects multiple suspected targets for identification and verification during the patrol, it will stop the autonomous patrol mode, identify the observed suspected targets, and perform preliminary localization of the targets based on the target localization algorithm.

[0110] Step 203: Prioritize suspicious targets. The UAV will approach and identify and locate the suspicious targets according to their priority. If the target is a false identification and verification target, the UAV will continue to perform the "bow" shaped autonomous patrol mode.

[0111] Step 204: The unmanned surface vessel implements a companion mechanism for the UAV based on the UAV's minimum return requirements, mainly considering the constraints of remaining endurance and communication quality.

[0112] Furthermore, during the process of the UAV approaching the target for precise positioning, the unmanned surface vessel (USV) needs to ensure the UAV's low battery return condition; therefore, the USV needs to accompany the UAV. Based on the above constraints, this is transformed into a trajectory tracking problem. The UAV transmits its own position information, i.e., the reference trajectory given by the UAV, denoted as X. uav =[X a ,Y a Z a ] T After receiving the position information from the drone, the unmanned surface vessel (USV) adjusts its own position to maintain relative status. The positional error between the USV and the drone can be expressed as:

[0113]

[0114] Where, ΔX uav-usv The positional error along the X-axis between the unmanned surface vessel and the unmanned aerial vehicle; ΔY uav-usv The positional error along the Y-axis between the unmanned surface vessel (USV) and the unmanned aerial vehicle (UAV); ΔZ uav-usv Let X be the positional error along the Z-axis between the unmanned surface vessel and the unmanned aerial vehicle; where X a Y a With Z a These are the drone's position information along the X-axis, Y-axis, and Z-axis, respectively; X s Y s With Z sThese are the unmanned surface vessel's position information on the X-axis, Y-axis, and Z-axis, respectively.

[0115] To ensure that the unmanned surface vessel can accurately maintain its attitude relative to the unmanned aerial vehicle (UAV), the horizontal position error should satisfy ΔX. uav-usv =0, ΔY uav-usv =0. The unmanned surface vessel is set to a height of 0 when moving on the water surface; therefore, ΔZ uav-usv =Z a ;

[0116] The model predictive control algorithm implements unmanned surface vessel (USV) escorting unmanned aerial vehicle (UAV) through rolling optimization, ensuring that the predicted output of the USV at time P approximates the expected state of the UAV. The process control objective cost function J for maintaining the relative state of the USV escorting the UAV is mathematically expressed as:

[0117]

[0118] Where, min J is the process control objective cost function; Q represents the weight of the situation maintenance error; the superscript T is the transpose identifier; and X is the position of the unmanned surface vessel. For the control variables of the unmanned surface vessel; ΔU a The target value for the control variables of the unmanned surface vessel;

[0119] In the formula, X uav The reference trajectory is given to the UAV; Q represents the weight of the situational awareness error. The larger the value, the smaller the difference between the predicted trajectory and the actual reference trajectory, that is, the more accurate the tracking; R represents the weight of the control quantity difference. The larger the value, the smoother the change in control increment.

[0120] subject to E mim ≤E a

[0121] C min ≤C uav-usv

[0122] Z min ≤Z a ≤Z max

[0123] ΔU min ≤ΔU a ≤ΔU max

[0124] Among them, E a This indicates the drone's endurance, requiring that the drone's endurance be no less than the power required for return. "Subject to" refers to the control target. E min Minimum battery power required for return; C uav-usvThis represents the packet loss rate in communication between the UAV and the unmanned surface vessel (USV). The packet loss rate is not less than the set minimum packet loss rate C. min Z min ≤Z a ≤Z max The safe zone for drone flight has been defined; Z a ΔU represents the flight altitude of the drone. min ≤ΔU a ≤ΔU max This indicates that the control variables of the unmanned surface vessel should remain within a stable range; ΔU min For the minimum control variable of the unmanned surface vessel, ΔU max ΔU is the maximum value of the unmanned surface vessel's control variable. a Target values ​​for unmanned surface vessel control variables;

[0125] Step 205: If the UAV locates the real target, it will send the location information to the unmanned surface vessel.

[0126] Specifically, the steps for the joint submarine-aircraft approach identification and verification phase are as follows:

[0127] Step 301: The unmanned surface vessel receives the target location information for identification and verification, and utilizes the improved A... * A global path planning algorithm autonomously approaches, identifies, and verifies targets.

[0128] Step 302: The UAV locates the target on the water surface for identification and verification, quickly approaches the target for identification and verification, and reduces its flight altitude while approaching to ensure the accuracy of identification. Once the UAV reaches the required identification accuracy and positioning precision, it hovers in place and continuously sends the target positioning information to the unmanned surface vessel.

[0129] Step 303: The unmanned surface vessel (USV) quickly approaches to identify and verify the target. If the USV accurately approaches the identification and verification range R, it slows down and stops. Finally, the drone lands on the USV landing pad to complete the target identification and verification task. The USV-drone joint identification and verification platform returns to the permanent dock.

[0130] In other words, the aforementioned method for joint unmanned surface vessel-aircraft (USV-A) target verification in water areas consists of three stages: wide-area search for suspicious targets on the water surface, identification and location of suspicious targets on the water surface, and joint USV-A / A joint approach identification and verification.

[0131] The wide-area search phase for suspicious targets on the water surface includes:

[0132] Step 101: The water area to be patrolled is gridded to determine the geodetic coordinates of long-standing water surface obstacles;

[0133] Step 102: The drone flies away from the wireless charging landing pad of the unmanned surface vessel and is equipped with a water target identification system to detect suspicious targets on the water surface in real time;

[0134] Step 103: The drone takes off from a fixed point, clears inherent obstacles on the water surface, and searches for suspected or suspicious targets;

[0135] Step 104: The unmanned surface vessel remains stationary at the patrol starting point;

[0136] The stage of identifying and locating suspicious targets on the water surface includes:

[0137] Step 201: The drone performs an autonomous patrol mode to search for suspicious targets on the water surface;

[0138] Step 202: The UAV is equipped with a water surface target identification system to detect suspicious targets on the water surface in real time and calculate their relative positions. The UAV is controlled to move based on the relative deviation between the suspicious targets on the water surface and the center of the view window. At that time, the UAV forwards the position information of the suspicious targets on the water surface to the unmanned surface vessel. The water surface target identification system is used to collect video data and perform real-time identification through an improved YOLOv8 model. The improved YOLOv8 model has completed the pre-training of the suspicious target dataset.

[0139] Step 203: The unmanned surface vessel maintains escort status based on constraints such as heading and distance with the unmanned aerial vehicle;

[0140] Step 204: This invention proposes a comprehensive weight ranking method to verify multiple suspicious targets. Target attributes are designed to determine the priority of close-range identification and verification of suspicious targets. The target attributes include four aspects: importance, threat level, dynamic characteristics, and verification difficulty. Triangular fuzzy numbers are used to represent the evaluation value of each attribute.

[0141] The unmanned surface vessel-aircraft joint approach identification and verification phase includes:

[0142] Step 301: The UAV detects the target, quickly approaches and locates it, and uploads the target's location to the unmanned surface vessel;

[0143] Step 302: The unmanned surface vessel receives the location information of the target on the water surface in real time and replans the global path in combination with the improved A* algorithm, and quickly and autonomously approaches the vicinity of the suspicious target for verification;

[0144] Step 302: During the approach of the unmanned surface vessel (USV) and unmanned aerial vehicle (UAV) platforms to the suspicious target, the USV acquires the UAV's location, heading, and battery information in real time, establishes a USV-UAV cooperative search model, and ensures that the UAV returns to base when its battery is low.

[0145] Step 303: The unmanned surface vessel and the drone simultaneously send the status information of the suspicious target to the ground station for display, and the shore-based operators make identification and verification decisions.

[0146] Step 304: After the suspicious target is successfully identified and verified, the unmanned surface vessel carries the suspicious target back to the ground monitoring terminal. The drone autonomously returns to the ground monitoring terminal. If the drone's battery is insufficient to return to the ground monitoring terminal, it will autonomously land on the wireless charging landing pad on the unmanned surface vessel and return to the ground monitoring terminal together.

[0147] Unmanned surface vessels (USVs) possess advantages such as long endurance and strong payload capacity, which can compensate for the shortcomings of unmanned aerial vehicles (UAVs) such as short endurance and weak payload capacity. Therefore, when UAVs are performing target identification and verification tasks in water patrols, if their endurance is insufficient, they can maneuver to land on USVs, ensuring the safety of the USV-UAV joint identification and verification platform operation. The identification and verification task execution process is as follows: Figure 3 As shown;

[0148] Furthermore, in the execution of unmanned surface vessel-drone collaborative search missions, the main working modes of the unmanned surface vessel are divided into a complete process, including autonomously arriving at the cruise starting point, escorting the drone, and autonomously arriving near the target for identification and verification through global path planning. The specific workflow diagram is shown below. Figure 4 As shown, the MPC is a model prediction controller used for unmanned surface vessels to accompany unmanned aerial vehicles (UAVs).

[0149] Furthermore, in the execution of unmanned surface vessel-aircraft (USV) collaborative search missions, the main working modes of the USV include wide-area target search, autonomous path planning and patrol, target identification and verification, target location, and autonomous return. The workflow of the USV at different stages is as follows: Figure 5 As shown, the RTK is a high-precision differential positioning module.

[0150] During the identification and verification of targets in water areas, drones, equipped with high-definition cameras and long-distance video transmission equipment, can transmit information from the accident site over long distances. At the same time, unmanned surface vessels (USVs) can provide data relay and energy resupply services for drones to ensure that information can be effectively transmitted back, enabling command departments to understand the situation of suspicious targets in water areas in a timely manner, thereby effectively improving the efficiency and success rate of target identification and verification.

[0151] Based on this, the design of a water target identification system and verification method for a cross-domain unmanned system composed of unmanned surface vessels and drones can effectively improve the efficiency of identification and verification and reduce costs.

[0152] Those skilled in the art will understand that, besides implementing the system and its various devices, modules, and units provided by this invention in the form of purely computer-readable program code, the same functions can be achieved entirely through logical programming of the method steps, making the system and its various devices, modules, and units of this invention function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, the system and its various devices, modules, and units provided by this invention can be considered as a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; alternatively, the devices, modules, and units for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0153] In the description of this application, it should be understood that the terms "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0154] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A migratable aquatic target discrimination verification system, comprising: The system comprises: a load platform, a video acquisition module, a target identification module, and a target positioning module; the load platform is used for supporting the equipment for water target identification and verification; based on the load platform, the video acquisition module is used to acquire water target image information, the target identification module is used to acquire video data and detect targets, and target information is obtained; the target positioning module is used to acquire the target information and obtain the position information of the target; the load platform comprises a UAV flight platform, an unmanned boat, and a ground monitoring platform; the UAV flight platform is used to detect, identify, and position suspicious water targets; the suspicious water target is a boat; the unmanned boat, i.e., a catamaran unmanned boat, is used to receive the position information of the suspicious water target and plan a path; the ground monitoring platform is used to display the state information of the UAV and issue control instructions; the system can realize the stages of wide-area search, water target identification and positioning, and boat-UAV joint close-in identification and verification; the wide-area search stage comprises: the ground monitoring platform issues instructions to make the UAV and the unmanned boat arrive at a patrol position and start patrol, the video acquisition module acquires water target image information through the UAV, and the UAV scores and ranks targets according to the target image information through a comprehensive weight ranking method to obtain a priority order for verification; in the wide-area search stage, the comprehensive weight ranking method uses a triangular fuzzy number to represent the evaluation value of an attribute and then ranks the priority according to the evaluation value; the expression of the triangular fuzzy number is: wherein, is a triangular fuzzy number, a i is a minimum value, b i is a most likely value, c i is a maximum value; for a maximization target, the linear membership function of the triangular fuzzy number has the expression: for a minimization target, the linear membership function of the triangular fuzzy number has the expression: for dynamic characteristics, the linear membership function has the expression: wherein, is a linear membership function of the dynamic characteristic; In the comprehensive weight ordering method, the weight of each attribute, i.e. w I , w T , w D and w C , is determined to reflect the relative importance of each attribute in the verification task, and the mathematical expression is as follows: w I +w T +w D +w C =1 (5) wherein w I is a weight for importance; w T is a weight for threat level; w D is a weight for dynamic nature; w C is a weight for difficulty of verification; Based on the w I , w T , w D and w C , for each target i, a comprehensive score is calculated, the mathematical expression of which is: wherein S i is the comprehensive score, is the membership of the target i in importance, is the membership of the target i in threat degree, is the membership of the target i in dynamic characteristic, is the membership of the target i in verification difficulty; the symbol • is the product; all targets are arranged in descending order according to the comprehensive score; the higher the score of the comprehensive score, the higher the priority for verification; in the water target identification and positioning stage, the unmanned boat adjusts its position information according to the position information of the UAV; the position error between the unmanned boat and the UAV has the mathematical expression: Wherein, ΔX uav-usv is the position error between the unmanned ship and the unmanned aerial vehicle in the X-axis direction; ΔY uav-usv is the position error between the unmanned ship and the unmanned aerial vehicle in the Y-axis direction; ΔZ uav-usv is the position error between the unmanned ship and the unmanned aerial vehicle in the Z-axis direction; X a , Y a and Z a are the position information of the unmanned aerial vehicle in the X-axis, the Y-axis and the Z-axis respectively; X s , Y s and Z s are the position information of the unmanned ship in the X-axis, the Y-axis and the Z-axis respectively; it is determined whether the unmanned boat meets the requirement of the position error; if the result is yes, the position of the unmanned boat is not adjusted; if the result is no, the position of the unmanned boat is adjusted; the requirement of the position error is: ΔX uav-usv = 0 ΔY uav-usv = 0 ΔZ uav-usv = Z a wherein Z a is the position information of the UAV in the Z-axis.

2. The transferable water target identification and verification system according to claim 1, wherein the water target identification and positioning stage comprises: the target identification module is used to determine whether the UAV discovers a suspicious water target; if the result is no, the UAV returns to the unmanned boat for charging after the patrol task is completed; if the result is yes, the suspicious water target is identified and positioned according to the priority order for verification to obtain target information; the boat-UAV joint close-in identification and verification stage comprises: The target positioning module obtains the target information, and obtains position information of the target; the unmanned aerial vehicle sends the position information of the target to the unmanned ship, and the unmanned ship approaches and verifies the suspicious target on the water surface according to the position information of the target, and returns after verification is completed.

3. The migratable aquatic target discrimination verification system of claim 1, wherein, The process control target cost function is used to make the unmanned ship accompany the unmanned aerial vehicle to keep a relative situation; The process control target cost function is mathematically expressed as: where min J is the process control objective cost function; Q represents the weight of the situation keeping error; superscript T is the transpose identifier; X is the position of the USV; is the control variable of the USV; R is the weight of the control variable difference; ΔU a is the control variable target value of the USV; X uav is the given reference trajectory of the UAV.

4. The migratable aquatic target discrimination verification system of claim 1, wherein, In the boat-aircraft combined approach identification and verification phase, the unmanned boat obtains and verifies the target according to the approach path A * The global path planning algorithm obtains and verifies the target according to the approach path. In the wide-area search stage, the YOLOv8 model is used to obtain water target image information.

5. The migratable aquatic target discrimination verification system of claim 2, wherein, The unmanned aerial vehicle keeps hovering at a fixed point and sends the position information of the target to the unmanned ship.

6. The migratable aquatic target discrimination verification system of claim 2, wherein, The unmanned aerial vehicle performs a "bow" shape patrol path.

7. The migratable aquatic target discrimination verification system of claim 2, wherein, The unmanned aerial vehicle collects 25 frames of image data per second, flies at a height of 50 m, and patrols at a speed of 5 m / s.

Images