Task-oriented radar and photoelectric heterogeneous heterogenous information cooperative reconnaissance method

Abstract

The invention particularly relates to a task-oriented radar and photoelectric heterogeneous heterogenous information cooperative reconnaissance method, which adopts a multi-radar traversal planning mode and a target automatic identification algorithm to form a battlefield map and complete remote rough reconnaissance. A shared reconnaissance information structure adapting to weak network bandwidth and role definition of an information group leader are provided, reconnaissance information is shared in unmanned aerial vehicles of the same configuration, and meanwhile, a target is distributed to a close-range guide type photoelectric unmanned aerial vehicle. A target fusion method of different-source information of an SAR image and a visible light image is used to carry out target re-identification in a close-range view field. And automatic tracking of the same target of the photoelectric unmanned aerial vehicle is realized. And the other photoelectric unmanned aerial vehicle in the area performs real-time monitoring in guidance to complete damage evaluation in the striking process. The cooperative reconnaissance method integrating reconnaissance and evaluation is

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) reconnaissance technology, and in particular to a task-oriented radar and optoelectronic heterogeneous heterogeneous information collaborative reconnaissance method, which is particularly suitable for the reconnaissance scenario of clustered UAVs. Background Art

[0002] The development of drone technology has begun to shift from single-machine to multi-machine collaborative operations. Cluster collaborative reconnaissance methods are widely used in fields such as wide-area reconnaissance and environmental monitoring. During a mission, a group of drones can be assigned to conduct regional reconnaissance, and ground personnel can provide data support for command and decision-making based on the intelligence transmitted back in real time. However, with the increase in the number of drones and the limitation of communication bandwidth, ground personnel can no longer go deep into the specific mission planning and intelligence processing of each drone.

[0003] In the existing technology, most of them solve the regional search problem from the aspect of mission planning. They have not proposed a specific method for the autonomous collaboration of radar-type wide-area reconnaissance UAVs and optoelectronic close-range guidance UAVs, the functional characteristics of UAVs of different configurations, and the whole process of information generation.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The present invention provides a task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method, which can realize autonomous collaborative reconnaissance between radar-type unmanned aerial vehicles and optoelectronic-type unmanned aerial vehicles, thereby overcoming the defects existing in the prior art to a certain extent.

[0006] Other features and advantages of the present invention will become apparent from the following detailed description, or may be learned in part by practice of the present invention.

[0007] According to a first aspect of the present invention, a task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method is provided, the method comprising:

[0008] Based on the radar-type UAV group reconnaissance, a target result list of the entire mission area is obtained, and the target result list is sorted according to the target value; the targets in the target result list that meet the target value requirements are sent to the optoelectronic UAV group;

[0009] The optoelectronic UAV group allocates reconnaissance tasks according to target information. The optoelectronic UAV assigned with the reconnaissance task sends reconnaissance images in real time, and obtains and identifies targets based on the reconnaissance images; targets identified by the optoelectronic UAV and targets identified by the radar UAV are matched;

[0010] The optoelectronic UAV that successfully matches the target will start the guidance auxiliary control mode, calculate the target tracking pixel deviation in real time based on the reconnaissance image and send it synchronously to the optoelectronic payload. The optoelectronic payload captures the target according to the target tracking pixel deviation and continues to track the target; at the same time, it outputs the line of sight angular rate to the control module to ensure the terminal guidance of the UAV.

[0011] In some exemplary embodiments, the radar-based UAV group reconnaissance to obtain a target result list for the entire mission area includes:

[0012] Multiple radar-type drones conduct long-range reconnaissance of the entire mission area at high altitudes and output SAR images;

[0013] Perform target recognition based on SAR images and output target results;

[0014] The target results of all radar-type UAVs are integrated to perform target re-identification and obtain a target result list for the entire mission area; the target result list includes the target serial number, target longitude, target latitude, and target slice.

[0015] In some exemplary embodiments, the radar-type UAV is equipped with radar reconnaissance equipment; the route is planned according to the mission, and the UAV flies in parallel in the same direction to ensure the overlap rate of regional scanning; the radar reconnaissance equipment adopts SAR strip mode and the antenna is in a forward and side-view mode to complete imaging processing.

[0016] In some exemplary embodiments, the method for calculating the number of multiple radar-type drones is specifically as follows:

[0017] Calculate the radar width W based on the incident angle, flight altitude and radar beam width of the radar reconnaissance equipment sar ;

[0018] Required radar type drone uav The calculation formula is:

[0019]

[0020] Among them, L misson is the length of the mission area, and Del is the overlapping width of the reconnaissance width.

[0021] In some exemplary embodiments, the electro-optical UAV group performs reconnaissance mission allocation according to target information, including:

[0022] The entire mission area is divided into multiple small grids, and the optoelectronic UAVs are divided into groups to conduct close-range persistent reconnaissance according to the small grid areas;

[0023] The leader of the optoelectronic UAV team determines the small grid number where the target is located based on the location of the target and the information of the optoelectronic UAV currently conducting persistent reconnaissance;

[0024] The target information and close-range search mission are sent to an optoelectronic UAV that patrols the small grid area where the target is located.

[0025] In some exemplary embodiments, the optoelectronic UAV is equipped with day and night optoelectronic reconnaissance equipment and performs hovering flight at a certain radius; the working parameters of each circle of the optoelectronic circular scan are calculated in real time according to the area size, target size, and optoelectronic parameters to achieve automatic driving of the circular scan.

[0026] In some exemplary embodiments, the method for calculating the target tracking pixel deviation includes:

[0027] The coordinates of the target center point are calculated according to the size of the input image, the position of the target on the feature map of the input image, and the offset of the target center point relative to the upper left corner of the feature map grid unit;

[0028] The target tracking pixel deviation is calculated based on the coordinates of the target center point and the width and height of the target bounding box.

[0029] In some exemplary embodiments, the method further comprises:

[0030] During the terminal guidance process of the optoelectronic UAV, another optoelectronic UAV in the grid starts damage assessment. According to the key parts model trained in advance, it determines whether the target physical components are damaged based on key parts detection, and forms the damage effect into results to support ground personnel in arranging subsequent UAV operation tasks.

[0031] According to a second aspect of the present invention, there is provided a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the task-oriented radar and optoelectronic heterogeneous and heterogeneous source information collaborative reconnaissance method described in the first aspect is implemented.

[0032] According to a third aspect of the present invention, there is provided a computer program product having a computer program stored thereon, which, when executed by a processor, implements the task-oriented radar and optoelectronic heterogeneous and heterogeneous source information collaborative reconnaissance method described in the first aspect.

[0033] The task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method provided by the embodiment of the present invention has the following advantages:

[0034] 1. Radar detection has the characteristics of long-range reconnaissance, and optoelectronics has the function of precise reconnaissance and positioning. The long-range and short-range collaborative reconnaissance methods are used to reduce the time of regional target locking. Combined with the radar scanning method, the overlapping area is increased during route planning to reduce the probability of target leakage. The optoelectronic parameters are combined to allocate the operation area of ​​optoelectronic UAVs, which facilitates the rapid dispatch of UAVs and shortens the time of close-range target locking.

[0035] 2. The single-machine radar reconnaissance results are output as a target list. After the targets are sorted according to their value, they are sent to the leader machine through the inter-machine communication equipment. This method is suitable for weak bandwidth between machines. The airborne multi-source target fusion algorithm is adopted, combined with the reconnaissance mission route, to eliminate duplicate targets and reduce the false alarm rate of target detection. The distributed processing method of each drone is adopted to save ground-to-air bandwidth resources.

[0036] 3. Photoelectric UAVs fly according to their respective hovering radius. Photoelectric equipment uses the automatic scanning mode to traverse and search small grid areas, shortening the area coverage time and realizing automatic load drive. It does not require manual control by ground personnel, thus reducing the operating burden of personnel. In the small grid traversal reconnaissance scenario, the target can be quickly searched.

[0037] 4. After the onboard intelligent recognition module automatically identifies the target, it drives the optoelectronic equipment to work automatically. This fully automatic guidance and auxiliary control method does not require intervention from ground personnel and can realize the search-to-tracking mode. It can be applied to multiple UAV operation scenarios.

[0038] 5. Combining the features of radar SAR images and visible light images, we add a target association tracking method based on scene registration to the traditional re-identification algorithm. This is suitable for the case where there are fewer targets in the scene, and solves the problem of rapid identification of targets shot by different drones at different scales and angles.

[0039] 6. Taking advantage of the clear video quality of optoelectronic UAVs at close range, and using the critical parts detection method, the damage results after the target strike are directly given, and the objective results are transmitted to the ground command and control system. The human-in-the-loop parameter damage assessment provides a comprehensive and objective basis for supplementary strikes.

[0040] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present invention, and together with the specification are used to explain the principles of the present invention. Obviously, the accompanying drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0042] Figure 1 It is a schematic diagram of the structure of the database of the present invention;

[0043] Figure 2 This is a schematic diagram of the radar and optoelectronic heterogeneous reconnaissance deployment of the present invention;

[0044] Figure 3A schematic diagram of a search route for a radar-type UAV of the present invention;

[0045] Figure 4 A schematic diagram of a search route for an optoelectronic UAV of the present invention;

[0046] Figure 5 This is a schematic diagram of cooperative reconnaissance data transmission according to the present invention;

[0047] Figure 6 A flowchart of the method for implementing heterogeneous homologous target fusion of the present invention;

[0048] Figure 7 It is a flowchart of the object association method of the present invention;

[0049] Figure 8 This is a flow chart of the automatic auxiliary control tracking of the present invention. DETAILED DESCRIPTION

[0050] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present invention will be more comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0051] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0052] This example implementation provides a task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method to achieve autonomous collaborative reconnaissance between radar-type UAVs and optoelectronic UAVs. A multi-radar traversal planning method is adopted, and a target automatic recognition algorithm is used to form a picture of the battlefield and complete long-distance coarse reconnaissance. A shared reconnaissance information structure that adapts to weak network bandwidth and the role definition of the information group leader are proposed to share the reconnaissance information among homogeneous UAVs, and at the same time assign targets to short-range guided optoelectronic UAVs. A target fusion method using heterogeneous information of SAR images and visible light images is used to re-identify targets in a close-range field of view. Automatic tracking of the same target of an optoelectronic UAV is achieved. Another optoelectronic UAV in the area performs real-time monitoring during guidance to complete damage assessment of the strike process. A collaborative reconnaissance process that integrates observation, attack and evaluation is achieved.

[0053] The method of forming a table reduces the false alarm rate of the target. The semantic reconnaissance information adapts to the limitations of the communication network. The regional search method combined with the working parameters of the mission equipment improves the regional search efficiency of the optoelectronic UAV. The method of the invention shortens the confirmation and tracking time of the target from long-range coarse reconnaissance to close-range reconnaissance. It reduces the operating burden of ground personnel and provides comprehensive data support for subsequent guidance decisions.

[0054] refer to Figure 1 As shown, the task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method can specifically include the following steps:

[0055] Step 1: Launch multiple radar drones from the ground. Radar drones are equipped with radar reconnaissance equipment to conduct long-range reconnaissance of the entire mission area in high-altitude areas. Radar drones plan routes according to the mission, ensure the overlap rate of regional scanning, and fly in parallel in the same direction. The radar equipment uses SAR strip mode and the antenna is in a positive and side-view mode to complete imaging processing and output SAR images of the area. Through the Gigabit network port, the SAR image is input into the airborne intelligent detection and recognition algorithm module to detect and identify the target and output the target result. All radar drones send the target to the radar information fusion team leader through the inter-machine networking equipment, re-identify the target in the overlapping area, eliminate the same target, and form a target result list for the entire area. The radar information fusion team leader sorts the reconnaissance target results according to the target value.

[0056] Step 2: The optoelectronic UAV is equipped with day and night optoelectronic reconnaissance equipment to conduct low-altitude, close-range and small-area reconnaissance. The UAV hovers at a certain radius. The working parameters of each circle of the optoelectronic ring scan are calculated in real time according to the area size, target size, and optoelectronic parameters to achieve automatic driving of the ring scan. While performing persistent reconnaissance, wait for the task dispatch of the optoelectronic UAV team leader.

[0057] Step 3: The radar drone sends the information of the top-ranked targets to the leader of the optoelectronic drone in the collaborative target data format through the inter-machine networking device. The leader of the drone determines the small grid number where the target is located based on the location of the target and the information of the optoelectronic drone currently conducting persistent reconnaissance. The inter-machine networking communication device sends the target information and the task of close-range search to the optoelectronic drone that is patrolling the grid of the small area.

[0058] Step 4: The optoelectronic drones in the small grid area send the area video to their respective onboard intelligent processing modules in real time. According to the location and slice information of the target sent by the radar drone, the scene-based target association tracking algorithm is used to re-identify the target and complete the uniqueness confirmation of the target.

[0059] Step 5: The optoelectronic UAV that has identified the target starts the guidance auxiliary control mode, sends the geographic guidance command and the target position to the optoelectronic reconnaissance equipment, and the onboard intelligent processing module outputs the target tracking pixel deviation in real time and sends it to the optoelectronic reconnaissance equipment synchronously. The optoelectronic reconnaissance equipment captures the target based on the target tracking pixel deviation and continues to track the target. At the same time, it outputs the line of sight angular rate to the onboard guidance control module to ensure the terminal guidance of the optoelectronic UAV.

[0060] Step 6: During the terminal guidance process of the optoelectronic UAV, another optoelectronic UAV in the grid starts damage assessment. According to the key parts model trained in advance, it determines whether the target physical components are damaged based on key parts detection, and forms the damage effect into results to support ground personnel in arranging subsequent optoelectronic UAV operation tasks.

[0061] Below, each step of the task-oriented radar and optoelectronic heterogeneous and heterogeneous source information collaborative reconnaissance method in this example implementation will be described in more detail with reference to the accompanying drawings and embodiments.

[0062] In the above step 1, specifically including steps 11-13;

[0063] Step 11:

[0064] The radar uses a side-view scanning method in a strip mode to calculate the number of drones required to complete reconnaissance of the mission area based on radar parameters and flight parameters.

[0065] The radar width is calculated based on the incident angle, flight altitude and radar beam width of the radar reconnaissance equipment. The calculation formula for the radar width is:

[0066]

[0067] Where φ is the incident angle of the radar device, H is the flight altitude, θ is the radar beam width, and W sar is the radar width.

[0068] In order to ensure that no area is missed during reconnaissance, the overlap width of the reconnaissance width is set to Del kilometers, and the width of the mission area is W. misson kilometers, length is L misson kilometers, the number of drones required n iav The calculation method is:

[0069]

[0070] Therefore, the radar is set to strip mode, and the parameters include resolution, width W sar 、Action distance L misson 、Number n uav , complete the radar reconnaissance mission planning. Here set the required drone IDuav They are 1, 2, 3, and 4. Radar drones are sorted in queues, and drones are UAVs. 1 、UAV 2 、UAV 3 、UAV 4 .

[0071] Step 12:

[0072] The single-machine radar inputs the strip reconnaissance image to the intelligent processing module, which receives the attitude information of the UAV and calls the detection algorithm. The recognition algorithm used is an end-to-end convolutional neural network target detection algorithm that integrates the joint attention mechanism.

[0073] Each radar drone will complete the target positioning after detection and identification, and the detection results will be in the form of target list data List Item(UAV) To other UAVs, the target positioning accuracy is assumed to be 50m. The UAV with the smallest ID number is set as the group leader. 1 For the radar type UAV team leader, UAV 2 、UAV 3 、UAV 4 The drone sends the target list to the leader UAV through the inter-machine communication networking device. 1 , List Item(UAV1) 、List Item(UAV2) 、List Item(UAV3) 、List Item(UAV4) The four target lists are first categorized according to target location.

[0074] Radar UAV 1 The first target latitude and longitude is (Log, Lat) Item1(UAV1) , radar type UAV 2 The second target latitude and longitude is (Log, Lat) Item2(UAV2) If the difference between the two positions is within a certain range, the target is classified into one category, and so on, completing the initial classification of the target.

[0075] The classified targets are re-identified using self-paced learning, contrastive learning and hybrid memory models to complete the secondary classification of the targets.

[0076] Finally, a target list data of radar-type UAV reconnaissance is generated by fusion, and the target list with a confidence rate of more than 70% is sorted according to the confidence rate of detection and recognition. Item(UAV_sar) Sent to the leader of the photoelectric drone, the main data of the target list includes the target number, target longitude, target latitude, and target slice, which are specifically represented by Item uav_sar(Num、Long、Lat、Jpg) .

[0077] In the above step 2, specifically including steps 21-22;

[0078] Step 21:

[0079] The entire mission area is divided into multiple small grids. Photoelectric UAVs are divided into groups according to the area for close-range persistent reconnaissance, using a circling flight route. Combined with the reconnaissance characteristics of photoelectric equipment, the grid is divided into squares. The grids are named according to the order of the grid rows and columns in the north-left-west direction.

[0080] GridNET (行序号，列序号) The numbers are NET (1，1) , NET (1，2) wait.

[0081] The grid ID number consists of the flight number and the column number. (行序号，列序号) The grid position includes four vertices, with the top corner point as point 1, and is sorted clockwise. The grid position information is represented as follows

[0082] NET ID(Long1、Lat1)(Long2、Lat2)(Long3、Lat3)(Long4、Lat4)

[0083] The numbering of optoelectronic UAVs is based on the grid in which they are located. (IDnet，IDuav) ,Subsequent task assignment is based on the identity ID of the UAV, and the communication and transmission of data between machines are carried out.

[0084] Step 22:

[0085] X is the lateral resolution of the photoelectric image, a is the target size, L 0 is the maximum distance to the target, H is the flight altitude, L 1 is the distance between the target and the center point of the ring scan, and m is the number of target imaging pixels. The calculation method of the ring scan width parameter is as follows:

[0086] The calculation method of width A (in degrees) is:

[0087]

[0088] The pitch angle α is calculated as follows:

[0089]

[0090] B is the vertical vision, and the calculation method is:

[0091] Circular scanning width W tv , calculated as

[0092] W tv =[tanα-tan(α-B)]×H

[0093] According to the above method, the scanning width of each circle of the optoelectronic device is calculated. When the optoelectronic UAV hovers, each time it completes a circle, the distance and pitch angle of the area covered by the optoelectronic device will change. tv Recalculate and adjust. This is how persistent reconnaissance of a small area grid is accomplished.

[0094] In the above step 3, step 3 is specifically:

[0095] Through step 1, the target information that needs to be attacked and reconnaissanceed at close range is known. The leader of the photoelectric drone sends the target location Item sent by the radar drone. (num、Long、Lat) and the small grid location of the area NET ID(Long1、Lat1)(Long2、Lat2)(Long3、Lat3)(Long4、Lat4) Enter the coordinate calculation and get the small grid number IDnet where the target is located (x，y) , assume that there are two UAVs operating in this area, and determine that the optoelectronic UAV operating in this grid is UAV (IDnet，1) and UAVs (IDnet，2) .

[0096] Will attack reconnaissance instructions and target list information Item uav_sar(Num、Long、Lat、Jpg) The inter-machine task allocation instruction is sent to the two optoelectronic drones of the two flights through the inter-machine communication equipment of the optoelectronic drone team leader. The task allocation instruction structure is as follows:

[0097]

[0098] Among them, SendID is UAV (IDnet，1) and UAVs (IDnet，2) , misson is a reconnaissance and strike mission, Item uav_sar This is the target information of the radar UAV reconnaissance in step 12.

[0099] In the above step 4, step 4 is specifically:

[0100] The two optoelectronic drones performed patrol reconnaissance according to the disc flight route. During the flight, the reconnaissance images were detected and identified in real time, and the targets were sliced. The reconnaissance images and electronic maps were matched electronically with high precision to obtain the high-precision position of the target. The target results formed by the two optoelectronic drones were and

[0101] The current target information of the reconnaissance strike is Item uav_sar(Num、Long、Lat、Jpg) , the target association tracking and recognition module calls the algorithm to determine and Item uav_sar The consistency of the target matching success of the UAV, assuming that the UAV (IDnet，1) Enter the next image guidance stage.

[0102] The specific implementation steps of the association tracking algorithm are shown in the attached Figure 7 . A grayscale-based heterogeneous registration algorithm is used. Based on the reference image (fixed image), the statistical correlation of mutual information is used to search for the best position of the image to be registered (floating image). The similarity is determined by the image registration algorithm based on mutual information. The optimization search algorithm refers to an optimization process that performs iterative search according to the loss function, continuously adjusts the spatial transformation parameters to obtain the optimal solution, and makes the registered images as aligned as possible.

[0103] In the above step 5, step 5 is specifically:

[0104] The optoelectronic UAV that identifies the target starts the guidance auxiliary control mode, sends the geographic guidance command and the target position to the optoelectronic reconnaissance equipment, and the onboard intelligent processing module outputs the target tracking pixel deviation in real time and sends it to the optoelectronic reconnaissance equipment synchronously. The optoelectronic reconnaissance equipment captures the target based on the target tracking pixel deviation and continues to track the target. At the same time, it outputs the line of sight angular rate to the onboard guidance control module to ensure the terminal guidance of the optoelectronic UAV.

[0105] The optoelectronic UAV with successful target matching will form the instruction frame Ins with optoelectronic control instructions and target position parameters according to the following table structure. SendTV(Guide、Log、Lat) , sent to the optoelectronic reconnaissance equipment through the serial port.

[0106] Serial number Fields Contents 1 Guide Geographical Guidance 2 Log longitude 3 Lat latitude

[0107] The optoelectronic reconnaissance equipment performs geographic guidance based on the positioning information, so that the target continues to appear in the reconnaissance image, and performs continuous target detection, identification and tracking on the reconnaissance image, repeating step 4. If the detected target and the target sent by the radar are determined to be the same target, the target is continuously detected and tracked. The pixel deviation between the target and the center of the image is obtained.

[0108] The pixel deviation is calculated as follows:

[0109] The input image size is W×H and the feature map size is F w ×F H , the position of the target on the feature map (i, j),

[0110] dx and dy are the offsets of the target center point relative to the upper left corner of the feature map grid cell. The center point coordinates (cx, cy) are calculated as

[0111]

[0112] Width and height of the target bounding box:

[0113] w=e dw ×W 0

[0114] h=e dh ×H 0

[0115] where dw and dh are logarithmic scaling factors for model predictions, and W 0 and H 0 It is a fixed base width and height.

[0116] The offset required for the optoelectronic device to track the target:

[0117] Δh=cx-H / 2

[0118] Δw=cy-W / 2

[0119] (Δh, Δw) is sent to the optoelectronic device, which adjusts the optoelectronic servo angle according to the offset, automatically calculates the line of sight angular rate after tracking, and transmits it to the control module in real time to realize the UAV guidance process.

[0120] In the above step 6, step 6 is specifically:

[0121] In step 4, no target optoelectronic UAV was detected. (IDnet，2) , keep the original route, adjust the optoelectronic pitch angle, direct the field of view to the radar target, recalculate the optoelectronic equipment working parameters through the calculation method of step 22, and the optoelectronic equipment works according to the new parameters. (IDnet，1) During the terminal guidance process, the reconnaissance video including the target is taken in real time. When a fire is detected near the target, the optoelectronic UAV performs damage assessment. (IDnet，2) Then assess the damage to critical parts.

[0122] First, the target detection module is started to detect the target with a complete object outline, and then the key parts of the target are detected. If the key part cannot be detected, the part does not exist. If the key part is detected, a conclusion is drawn from the image perspective that the key part exists.

[0123] The graphic damage results and slices after the target is hit are sent to the ground command and control system to support the personnel's subsequent combat mission deployment.

[0124] It should be noted that, as another aspect, the present application also provides a storage medium, which may be included in an electronic device; or may exist independently without being assembled into the electronic device. The above storage medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the following embodiments.

[0125] In one embodiment, the present application provides a computer program product, including a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0126] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0127] Other embodiments of the invention will readily occur to those skilled in the art after considering the specification and practicing the invention herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the claims.

[0128] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method, characterized in that: The method comprises: Based on the radar-type UAV group reconnaissance, a target result list of the entire mission area is obtained, and the target result list is sorted according to the target value; the targets in the target result list that meet the target value requirements are sent to the optoelectronic UAV group; The optoelectronic UAV group allocates reconnaissance tasks according to target information. The optoelectronic UAV assigned with the reconnaissance task sends reconnaissance images in real time, and obtains and identifies targets based on the reconnaissance images; targets identified by the optoelectronic UAV and targets identified by the radar UAV are matched; The optoelectronic UAV that successfully matches the target will start the guidance auxiliary control mode, calculate the target tracking pixel deviation in real time based on the reconnaissance image and send it synchronously to the optoelectronic payload. The optoelectronic payload captures the target according to the target tracking pixel deviation and continues to track the target; at the same time, it outputs the line of sight angular rate to the control module to ensure the terminal guidance of the UAV.

2. The task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method according to claim 1 is characterized in that: The target result list of the whole mission area obtained by radar-based UAV group reconnaissance includes: Multiple radar-type drones conduct long-range reconnaissance of the entire mission area at high altitudes and output SAR images; Perform target recognition based on SAR images and output target results; The target results of all radar-type UAVs are integrated to perform target re-identification and obtain a target result list for the entire mission area; the target result list includes the target serial number, target longitude, target latitude, and target slice.

3. The task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method according to claim 2 is characterized in that: The radar-type UAV is equipped with radar reconnaissance equipment; it plans the route according to the mission and flies in parallel in the same direction to ensure the overlapping rate of regional scanning; the radar reconnaissance equipment adopts SAR strip mode and the antenna is in a forward and side-view mode to complete imaging processing.

4. The task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method according to claim 2 is characterized in that: The calculation method for the number of multiple radar-type drones is as follows: Calculate the radar width W based on the incident angle, flight altitude and radar beam width of the radar reconnaissance equipment sar ; Required radar type drone uav The calculation formula is: Among them, L misson is the length of the mission area, and Del is the overlapping width of the reconnaissance width.

5. The task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method according to claim 1 is characterized in that: The electro-optical UAV group performs reconnaissance mission allocation according to target information, including: The entire mission area is divided into multiple small grids, and the optoelectronic UAVs are divided into groups to conduct close-range persistent reconnaissance according to the small grid areas; The leader of the optoelectronic UAV team determines the small grid number where the target is located based on the location of the target and the information of the optoelectronic UAV currently conducting persistent reconnaissance; The target information and close-range search mission are sent to an optoelectronic UAV that patrols the small grid area where the target is located.

6. The task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method according to any one of claims 1 or 5, characterized in that: The optoelectronic UAV is equipped with day and night optoelectronic reconnaissance equipment and performs hovering flight at a certain radius; the working parameters of each circle of the optoelectronic ring scan are calculated in real time according to the area size, target size, and optoelectronic parameters, thereby realizing automatic driving of the ring scan.

7. The task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method according to claim 1 is characterized in that: The method for calculating the target tracking pixel deviation includes: The coordinates of the target center point are calculated according to the size of the input image, the position of the target on the feature map of the input image, and the offset of the target center point relative to the upper left corner of the feature map grid unit; The target tracking pixel deviation is calculated based on the coordinates of the target center point and the width and height of the target bounding box.

8. The task-oriented radar and optoelectronic heterogeneous and heterogeneous information collaborative reconnaissance method according to claim 1 is characterized in that: The method further comprises: During the terminal guidance process of the optoelectronic UAV, another optoelectronic UAV in the grid starts damage assessment. According to the key parts model trained in advance, it determines whether the target physical components are damaged based on key parts detection, and forms the damage effect into results to support ground personnel in arranging subsequent UAV operation tasks.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the task-oriented radar and optoelectronic heterogeneous and heterogeneous source information collaborative reconnaissance method as described in any one of claims 1 to 8 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the task-oriented radar and optoelectronic heterogeneous and heterogeneous source information collaborative reconnaissance method described in any one of claims 1 to 8 is implemented.

Images