Method for cooperative reconnaissance of key area based on electric reconnaissance and photoelectric heterogeneous information

Abstract

The application relates to a method for the cooperative reconnaissance of a key area based on electric reconnaissance and photoelectric heterogeneous information, which comprises the following steps: an electric reconnaissance unmanned aerial vehicle is loaded with electric reconnaissance equipment, and remote reconnaissance is carried out on a full task area at a high altitude, so that an electronic target list is formed and is broadcasted to a photoelectric unmanned aerial vehicle; the photoelectric unmanned aerial vehicle is loaded with day-and-night photoelectric reconnaissance equipment, and close reconnaissance is carried out on a key area at a low altitude; the photoelectric unmanned aerial vehicle forms a local target result from the video of the reconnaissance, the local target result is re-identified with the target in the target list sent by the electric reconnaissance group leader, and the uniqueness of the target is confirmed; after the target is determined, terminal guidance is carried out to strike; and the method can efficiently and autonomously complete the reconnaissance and striking of electromagnetic targets in a denial environment and damage evaluation in the striking process.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicles (UAVs), specifically to a collaborative operation among swarms of UAVs. More specifically, it refers to a mission-oriented collaborative reconnaissance method based on heterogeneous electronic and optoelectronic information from key areas, particularly suitable for reconnaissance scenarios involving swarms of UAVs targeting key controlled areas in denial environments. Background Technology

[0002] The development of UAV technology has shifted from single-unit operations to multi-unit collaborative operations. The application scenarios for swarm collaborative reconnaissance are also becoming increasingly complex and diverse, evolving from traditional image-based target reconnaissance missions to scenarios involving the reconnaissance, confirmation, engagement, and damage assessment of electromagnetic targets within enemy satellite communication control zones. To reconnoiter ground radar, it is necessary to equip UAVs with long-range electronic reconnaissance equipment, and then use UAVs equipped with optoelectronic devices for close-range confirmation and engagement.

[0003] Typically, during missions, a small squadron of drones equipped with different mission devices can be assigned to conduct area reconnaissance. Ground personnel then use the real-time intelligence to provide data support for command and decision-making. However, with the increasing complexity of battlefield environments, key areas are generally monitored by enemy ground radars conducting air reconnaissance, interfering with the communication and navigation equipment of drones. This makes it impossible for ground personnel to conduct battlefield situational awareness and drone command and control. Existing technologies mostly address the area search problem from the perspective of mission planning. They have not yet proposed a specific method for collaborative reconnaissance of key controlled areas, considering the autonomous cooperation between electronic reconnaissance wide-area drones and electro-optical drones, the functional characteristics of different drone configurations, and the entire information generation process.

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

[0005] This invention provides a collaborative reconnaissance method for key areas based on heterogeneous information from electronic and photoelectric sources. It can efficiently and autonomously complete the reconnaissance and strike of electromagnetic targets in denial environments, as well as damage assessment during the strike process, thereby overcoming the defects of existing technologies to a certain extent.

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

[0007] According to a first aspect of the present invention, a method for collaborative reconnaissance of key areas based on heterogeneous electronic and photoelectric information is provided, the method comprising:

[0008] The electronic reconnaissance UAV is equipped with electronic reconnaissance equipment to conduct long-range reconnaissance of the entire mission area from high altitude; the electronic reconnaissance equipment identifies the type and parameters of the target source and forms a single-unit target sorting result;

[0009] The electronic reconnaissance UAV sends the target selection results of the individual UAV to the electronic reconnaissance information team leader UAV. The team leader UAV merges the targets sent by the individual UAV to form the target results of the whole area. It then sorts the target results of the whole area by threat to form a list of electronic targets and broadcasts it to the electro-optical UAV.

[0010] The electro-optical UAV is equipped with day and night electro-optical reconnaissance equipment to conduct close-range reconnaissance of key areas at low altitudes. Based on the target location information in the electronic reconnaissance target list, the day and night electro-optical reconnaissance equipment is allocated to several electro-optical UAVs in the vicinity, and the electro-optical UAVs conduct close-range search flights.

[0011] During the sweeping process of the electro-optical UAV, the reconnaissance video is used to form the target results of the machine; the target results of the machine are then compared with the target list sent by the electronic reconnaissance team leader to re-identify the targets and confirm their uniqueness.

[0012] After identifying a target, the electro-optical UAV continuously points its electro-optical equipment at the target area. Based on the target's pixel position, it provides continuous geographic guidance, transitions to tracking mode, and directly enters the strike guidance mode. In image guidance mode, the electro-optical UAV conducts guided strikes against the target. During the approach to the target, the electro-optical payload automatically detects the target's vital parts based on the target type, adjusts the tracking and attack position, and updates the line-of-sight angular rate in real time. The electro-optical UAV then conducts terminal guidance strikes based on the line-of-sight angular rate.

[0013] During the terminal guidance process of the electro-optical UAV, the long-range electronic reconnaissance UAV continuously monitors the target of the interference source. If the target's electromagnetic characteristics disappear after the attack and the target is not in the target list, the corresponding target in the target list will be marked as disappeared.

[0014] In some exemplary embodiments, the electronic reconnaissance UAV employs a side-looking scanning method.

[0015] In some exemplary embodiments, before the electronic reconnaissance UAV sends the single-unit target sorting results to the electronic reconnaissance information team leader UAV, the method further includes:

[0016] The electronic reconnaissance UAV determines the required data bandwidth for data transmission between computers based on the amount of data and time of the target results generated by the UAV. The bandwidth is then sent to the UAV's communication network equipment, and the bandwidth configuration is completed after the communication network setup is finished.

[0017] In some exemplary embodiments, while the electro-optical unmanned aerial vehicle (UAV) is conducting a close-range search, the method further includes:

[0018] Electro-optical UAVs use images captured by photoelectric sensors to perform scene matching calculations. The matching results, i.e. the UAV's position, are sent to the flight control and navigation computer via the network. In the absence of satellite navigation, the UAV uses the scene matching results to correct its attitude and navigate.

[0019] In some exemplary embodiments, the method further includes:

[0020] During the approach to the target, the electro-optical UAV reads the UAV link communication parameters to determine the communication status: when the communication is normal, the electro-optical UAV transmits high-definition, high-bandwidth reconnaissance images to the airborne link terminal, and ground personnel can observe real-time high-definition video; if the link communication is abnormal, but the link status is stable within a short communication period, the electro-optical UAV will increase the resolution of the region of interest and blur other areas, transmitting narrow-bandwidth image data to the airborne link terminal, reducing the transmission bandwidth requirement, and still ensuring that ground personnel can observe real-time reconnaissance video.

[0021] In some exemplary embodiments, the plurality of electro-optical unmanned aerial vehicles (UAVs) assigned to the adjacent area include:

[0022] Determine the number of sorties, n, for the electro-optical UAV;

[0023] Calculate the distance between the electro-optical UAV and the target;

[0024] The first n UAVs are selected based on their distance from the target, from closest to furthest.

[0025] In some exemplary embodiments, determining the number of sorties of the electro-optical UAV includes:

[0026] Based on the size of the reconnaissance area, the size of the reconnaissance target, and the flight altitude of the UAV, the optoelectronic equipment on the optoelectronic UAV calculates the single-aircraft area sweep width in real time, and calculates the number of optoelectronic units to be assigned for cooperative scanning according to the scanning range of the electronic reconnaissance target position.

[0027] In some exemplary embodiments, the uniqueness verification of the target includes:

[0028] The electro-optical UAV reads the locally pre-loaded target model and target type lookup table, and obtains the target type corresponding to the target model based on the target model in the electronic reconnaissance target list;

[0029] The electro-optical UAV detection and recognition module loads the target model library and performs target detection and recognition during the electro-optical UAV's straight-line approach to the target, obtaining the target detection and recognition confidence rate V. item0 Target longitude and latitude W item0 =(L item 0, B item0 The distance D between the photoelectric payload's line of sight and the target is obtained through laser ranging.item0 At the same moment, the longitude and latitude W of the drone uav =(L uav B uav );

[0030] Calculate the distance between the photoelectric detection target and the drone based on the drone's current location.

[0031] D (uav，item0) =D[(L uav B uav ),(L item0 B item0 The slant distance projected onto the ground is D. 投影(uav，item0) ;

[0032] Calculate the distance between the electronic reconnaissance target and the drone based on the drone's current location.

[0033] D (uav，item) =D[(L uav B uav ),(L item B item The slant distance projected onto the ground is D. 投影(uav，item) ;

[0034] If the projected distance is less than the longitude of the electronic reconnaissance target, i.e., |D 投影(uav，item0) -D 投影(uav，item) | <D item And the target confidence rate V item If the percentage is greater than 90%, then the target item detected by photoelectric detection and the target item 0 detected by electronic detection are considered to be the same target.

[0035] According to a second aspect of the present invention, a storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the collaborative reconnaissance method for key areas based on heterogeneous electronic and photoelectric information as described in the first aspect.

[0036] According to a third aspect of the present invention, a computer program product is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, the collaborative reconnaissance method for key areas based on heterogeneous and heterogeneous information of electronic and photoelectric sources described in the first aspect is implemented.

[0037] According to a fourth aspect of the present invention, an electronic device is provided, comprising:

[0038] Processor; and

[0039] Memory for storing the executable instructions of the processor;

[0040] The processor is configured to implement the collaborative reconnaissance method for key areas based on heterogeneous electronic and photoelectric information as described in the first aspect when executing the executable instructions.

[0041] The collaborative reconnaissance method for key areas based on heterogeneous electronic and photoelectric information provided in the embodiments of the present invention has the following advantages:

[0042] 1. Electronic reconnaissance offers long-range detection capabilities, while electro-optical systems provide precise detection and positioning. Utilizing a combined long-range and short-range reconnaissance approach reduces the time required to lock onto targets in an area. Combined with electronic scanning, this lowers the probability of missed targets and increases the effectiveness of strikes against time-sensitive targets within the mission area.

[0043] 2. The output of single-unit electronic reconnaissance results is a target list, which is transmitted to the team leader's machine via inter-machine communication. The system proactively requests inter-machine bandwidth based on transmission bandwidth requirements, dynamically adjusting bandwidth resources to adapt to situations with limited inter-machine bandwidth. An airborne multi-source target fusion method is employed to eliminate duplicate electronic targets, reducing the false alarm rate.

[0044] 3. Electro-optical UAVs approach the target area according to the assigned area. The electro-optical equipment uses an automatic sweeping mode to traverse and search during the approach, achieving automatic payload drive without manual control by ground personnel, thus reducing the operational burden. In close-range reconnaissance scenarios targeting key objectives, multiple UAVs simultaneously can quickly locate the target.

[0045] 4. Even in the face of potential denial-of-access situations during approach, the image-matching navigation method can still maintain aircraft attitude control. By employing region-of-interest (ROI) video transmission, images are uploaded to the ground, adapting to situations with intermittent link interruptions and timing. This ensures ground command personnel can maintain reconnaissance and surveillance of the site.

[0046] 5. After the airborne intelligent identification module automatically identifies the target, it drives the optoelectronic equipment to work automatically. This fully automatic guidance-assisted control method does not require ground personnel intervention and can realize the search-to-track mode. Simultaneously, guidance can identify vital parts of the target as the distance increases, improving the effectiveness of the strike.

[0047] 6. During the strike, the long-range surveillance capabilities of electronic reconnaissance UAVs and radar UAVs were utilized. By combining electromagnetic type sorting and image recognition, the presence and damage effects of the strike targets were assessed. The objective results were transmitted to the ground command and control system, providing objective evidence for supplementary strikes.

[0048] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0049] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0050] Figure 1 This is a flowchart of the method of the present invention;

[0051] Figure 2 This is a schematic diagram of the database structure of the present invention;

[0052] Figure 3 This is a schematic diagram of the structure of the multi-machine collaborative target data of the present invention;

[0053] Figure 4 This is a schematic diagram of the search capabilities of the electronic reconnaissance UAV of the present invention;

[0054] Figure 5 This is a schematic diagram of a single-unit search operation of the photoelectric UAV of the present invention;

[0055] Figure 6 This is a schematic diagram of collaborative reconnaissance data transmission according to the present invention;

[0056] Figure 7 This is a flowchart illustrating the scene matching implementation of the present invention. Detailed Implementation

[0057] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the invention will be more comprehensive and complete, and will fully convey the concept of the exemplary 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.

[0058] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0059] To address the shortcomings and deficiencies of existing technologies, this example implementation provides a collaborative reconnaissance method for key areas based on heterogeneous information from electronic reconnaissance and electro-optical sources. It utilizes an autonomous collaborative working mode between electronic reconnaissance UAVs and electro-optical UAVs to reconnoiter and strike electromagnetic targets in key areas. A traversal planning method using several electronic reconnaissance UAVs and a threat source classification and identification algorithm are employed to sort targets within the key area according to threat level, forming a threat target list for long-range coarse reconnaissance. In communication and navigation interference environments, the UAVs use scene matching positioning for autonomous navigation. Based on the characteristics of electro-optical equipment, an automatic and rapid target traversal sweeping working mode is proposed to enable electro-optical UAVs to confirm targets in the area. In weak network conditions, frequency hopping communication is used for data downlink to adapt to communication and navigation interference from interfering sources.

[0060] refer to Figure 1 As shown, the specific steps may include:

[0061] Step 1: Equipped with electronic reconnaissance equipment, the electronic reconnaissance UAV conducts long-range reconnaissance of the entire mission area from high altitude, generating single-aircraft target sorting results;

[0062] Step 2: Combine the target sorting results of each electronic reconnaissance UAV to form the target results for the entire area; and broadcast the target list to the electro-optical UAV.

[0063] Step 3: The electro-optical UAV is equipped with day and night electro-optical reconnaissance equipment and conducts close-range reconnaissance of key areas at low altitude; based on the target location information in the electronic reconnaissance target list, several electro-optical UAVs are assigned to the nearby area, and the electro-optical UAVs conduct close-range search flights;

[0064] Step 4: During the approach to the target, the photoelectric model UAV reads the UAV link communication parameters, determines the communication status, and transmits images based on the communication status;

[0065] Step 5: The electro-optical UAV generates target results from the reconnaissance video and re-identifies the targets against the target list sent by the electronic reconnaissance team leader to confirm the uniqueness of the targets;

[0066] Step 6: After the electro-optical UAV identifies the target, it conducts a terminal-guided strike;

[0067] Step 7: During the terminal guidance process of the UAV, the long-range electronic reconnaissance UAV continuously monitors the target of the interference source. If the target is not in the target list, the corresponding target in the target list is marked as disappeared.

[0068] The steps in this exemplary embodiment will now be described in more detail with reference to the accompanying drawings and embodiments.

[0069] In step S1, multiple electronic reconnaissance drones are launched from the ground. These drones are equipped with electronic reconnaissance equipment and conduct long-range reconnaissance of the entire mission area from high altitude. They can detect electromagnetic signal targets within the receiving area, such as ground-based interference and radiation sources. The drones fly in a multi-drone coordinated formation according to the mission plan. The electronic reconnaissance equipment receives signals from interference and radiation sources through its signal acquisition module, performing signal detection, parameter extraction, and template matching to identify the target source's type and parameters, thus generating a single-drone target sorting result.

[0070] Specifically, the electronic reconnaissance UAV uses side-looking scanning. Given the known length and width (W, L) of the mission area (in meters), the time required to traverse the area (Time in seconds), and the number of UAV sorties (N),... uav The flight speed of the drone, V uav Meters per second, capable of calculating the flight path formation of multiple electronic reconnaissance UAVs when conducting reconnaissance of electromagnetic target areas.

[0071] The calculation method differs depending on the number of electronic reconnaissance drones. Here, we set N as... uav =3, electronic reconnaissance drones use an equilateral triangular formation, flying along the wider side W, such as Figure 2 As shown. The side length Del of the triangle. uav The calculation method is as follows:

[0072]

[0073] Here you set the required electronic reconnaissance drone ID. uav The order is 1, 2, 3. The electronic reconnaissance UAVs are arranged in the queue, with the UAVs being UAV1, UAV2, and UAV3 in that order.

[0074] In step 2, all electronic reconnaissance UAVs, based on the data volume and timing of the multi-UAV collaborative target data, send the required data bandwidth for inter-computer transmission to their respective communication network devices. After the communication network configuration is complete, the inter-UAV network devices send the multi-UAV collaborative target data to the electronic reconnaissance information fusion team leader. The targets sent by each UAV are then merged again to form a target result for the entire area. The electronic reconnaissance information team leader sorts the reconnaissance target results according to threat rules, forming a list of electronic targets. The electronic reconnaissance information team leader then broadcasts the target list to electro-optical UAVs. The entire process is as follows: Figure 3 As shown.

[0075] Specifically, on the ground, the input radiation source descriptive words are first preprocessed to extract the feature set of the radiation sources. Then, based on the extracted feature set and a known radiation source information database, some data in the feature set is labeled using manual or automatic machine annotation methods, serving as a training dataset. Next, based on the labeled dataset, a radiation source model recognition module is constructed through a recognition approach. Finally, the radiation source model recognition module is used to process the unlabeled data in the radiation source feature set for model recognition. This results in a single-machine target list, structured as follows: Figure 4 As shown. Single-machine target data size N 单机 Transmission time T 传输 Calculate the required inter-machine communication bandwidth.

[0076] Specifically, each drone sends its bandwidth requirement to the group leader drone, which then calculates the total bandwidth SumM. 机间 =M uav1 +M uav2 +M uav3 Dynamically allocate the transmission bandwidth of electronic reconnaissance drones.

[0077] Specifically, the electronic reconnaissance drone team leader receives the list of individual targets transmitted by the team members' drones and completes target fusion according to the following methods and steps.

[0078] The electronic reconnaissance drone team leader receives a list of individual targets transmitted by team members' drones and completes target fusion according to the following steps:

[0079] 1) First, signal feature matching is performed based on parameters such as arrival time, frequency, and pulse width of each individual radiation source. By judging whether the difference of the same feature parameter meets the error threshold requirement, it is determined whether multiple individual electromagnetic threat radiation sources can be correlated. If a certain feature parameter does not meet the error threshold requirement, it is determined that the individual electromagnetic threat radiation sources cannot be correlated.

[0080] 2) If multiple single-unit electromagnetic threat radiation sources can be correlated, the correlation degree of each characteristic parameter is calculated according to the following formula: (1-error / system error) / (1+error / system error);

[0081] The final set of correlation coefficient values ​​is obtained by averaging the sum of the correlation coefficients of all feature parameters over the dimensions.

[0082] 3) Select the item with the highest correlation degree from the set and compare it with the correlation threshold. If the highest correlation degree value is greater than the correlation threshold value, then determine that multiple single-unit radiation sources belong to the same radiation source and perform batch processing to generate a comprehensive radiation source and report it.

[0083] 4) While processing the batch, the timestamp of the comprehensive electromagnetic threat radiation source is compared with the latest time threshold in real time. If the time difference is greater than the threshold value, it is determined that the radiation source has disappeared, and the conclusion that the electromagnetic threat radiation source has disappeared is generated and reported.

[0084] The target list format for multi-machine fusion is as follows: Figure 5 As shown.

[0085] Specifically, the target list is sorted according to threat rules. The level determination mainly involves calculating the weight of each factor, such as frequency repetition threat, azimuth threat, pulse width threat, carrier frequency threat, status threat, and type threat, to form a radiation source threat level parameter.

[0086] The membership function of the repetition frequency is: (unit: kHz)

[0087]

[0088] The azimuth membership function is:

[0089]

[0090] The membership function of pulse width can be expressed as: (unit: µs)

[0091]

[0092] The membership function of a carrier frequency can be expressed as: (unit: GHz)

[0093]

[0094] Modern radar radiation sources can be broadly categorized into three operating modes: guidance mode, tracking mode, and search mode. Their membership functions can be expressed as follows:

[0095]

[0096] The importance attribute value is set as follows:

[0097]

[0098] The importance of the six factors is assessed as follows: the importance ratio between operating status and purpose is 1; the ratio between carrier frequency and operating status is 1 / 8; the importance ratio between pulse width and carrier frequency is 3 / 2; the ratio between azimuth and pulse width is 2; and the ratio between repetition rate and azimuth is 2. Therefore, the pairwise comparison discrimination matrix is ​​as follows:

[0099]

[0100] The weight vector of each factor can be obtained using the eigenvalue method:

[0101] W=(0.2193,0.1097,0.0496,0.0366,0.2924,0.2924) T

[0102] For a group of multiple radiation source targets, after obtaining their attribute values ​​through reconnaissance, the threat level of each radiation source can be calculated using a formula:

[0103]

[0104] The threat levels of all radiation sources can be represented as set A:

[0105] A={a i |i=1,2,…,n}

[0106] In the formula, n is the number of radiation sources.

[0107] Since interference sources affect the normal operation of the machine, once a signal is identified as an interference source, it will be set to the highest threat level and an alarm will be triggered immediately.

[0108] Threat level is represented by the target number, with the highest threat level having the smallest target number.

[0109] In step 3, the electro-optical UAV is equipped with day and night electro-optical reconnaissance equipment to conduct close-range reconnaissance of key areas at low altitude. Based on the target location information in the electronic reconnaissance target list, several electro-optical UAVs are assigned to nearby areas. The electro-optical UAVs conduct close-range search flights. Simultaneously, the UAVs use the images captured by the electro-optical system to perform scene matching calculations, and send the matching results, i.e., the UAV's position, to the onboard flight control and navigation computer via the network. In the absence of satellite navigation, the UAV uses the scene matching results to correct its attitude for navigation. The scene matching process is as follows: Figure 7 As shown.

[0110] Specifically, the electro-optical UAV is equipped with day and night electro-optical reconnaissance equipment to conduct close-range reconnaissance of key areas at low altitudes. Based on the target location information in the electronic reconnaissance target list... (ID、目标型号、目标经度、目标纬度) The target location's longitude and latitude W item =(L item B item The current location of the UAV and the photoelectric model is traversed.

[0111] Calculate the distance D between the electro-optical UAV and the target. uav Select the closest drones to carry out the mission. The specific number of drones to be calculated is explained in step 5.

[0112] Specifically, before the mission, during ground preparation, electronic maps are pre-loaded according to the mission area; after the UAV takes off, changes in inertial navigation data and satellite positioning markers are monitored in real time.

[0113] INS (俯仰、航向) ≥3*INS (俯仰经度、航向经度) If so, it is considered that the inertial navigation data has changed significantly.

[0114] If the satellite positioning mark DW GPS(TnoGPS) =0, then the satellite is considered to be unpositioned.

[0115] If either of the above two conditions is met, the drone will immediately initiate scene matching and simultaneously record the satellite loss time. noGPS time.

[0116] Based on the current location of the drone, expand the appropriate area to find the corresponding map and achieve the first scene matching.

[0117] If the system shuts down satellite navigation and flies silently before entering the denial zone to prevent enemy detection, the UAV's inertial navigation data will have a large error when the first scene matching is started. At this time, scene matching is started, and the key points are traversed and matched for the first time based on several key points in the bound key point library.

[0118] After the initial successful match, a small area map is cropped based on the corrected inertial navigation data and the width of the reconnaissance image, and scene matching is performed with the current reconnaissance image to obtain the matching point pairs between the image and the electronic map.

[0119] Based on the matching relationship between feature points in the electronic map and the reconnaissance image, and combined with the pixel coordinates of the target detection results, the target location is obtained.

[0120] Based on the pairing relationship between feature points in the electronic map and the reconnaissance image, and combined with the UAV pose data and the payload's intrinsic / pose data, the rendezvous module is invoked to calculate the aircraft's position.

[0121] Combining scene matching speed capability and inertial navigation integration time requirements, the scene matching module is periodically invoked to achieve periodic scene matching and positioning function, outputting the positioning results of the carrier and target, as well as the corresponding time. The following information is output to the integrated navigation module, details of which are as follows: WeiZhi (经度、纬度、高度) Time (匹配) .

[0122] The drone's navigation module is in T noGPS Time and moment (匹配) Between these points, the angular velocities of the gyroscope and the accelerations of the accelerometer in the northeast, north, and south directions of the inertial navigation system will be recorded, and the results will be analyzed using WeiZhi. (经度、纬度、高度) This is used to correct the attitude of the drone.

[0123] In step 4, as the electro-optical UAV approaches the target, it reads the UAV link communication parameters to determine the communication status. When communication is normal, the electro-optical UAV transmits high-definition, high-bandwidth reconnaissance images to the onboard link terminal, allowing ground personnel to observe real-time high-definition video. If the link communication is abnormal, but the link status stabilizes within a short communication period, the UAV will increase the resolution of the region of interest and blur other areas, transmitting narrow-bandwidth image data to the onboard link terminal. This reduces the transmission bandwidth requirement while still ensuring ground personnel can observe real-time reconnaissance video.

[0124] Specifically, the drone reads its own link communication parameter signal AGC (Automatic Gain Control) Date. (agc、uav) and bit error rate Date (误码率、uav) The link communication status is determined by rules. Date over a certain distance... (agc、距离) The AGC value is fixed.

[0125] If Date (agc、uav) <Date (agc、距离) or Date (误码率、uav) If the value is greater than 0 and the duration of the above state is greater than 10 seconds, then the communication state is considered poor.

[0126] Specifically, when communication is poor, the video from the real-time reconnaissance by the electro-optical UAV undergoes Region of Interest (ROI) processing. It receives window size control commands and obtains the center position and size of the ROI based on these commands. For the windowed image, it obtains the ROI image quality assessment value in real-time through histogram information entropy statistics. The encoder architecture is optimized, refining from one frame to a macroblock, setting quantization parameters for each block to control the compression bitrate. Based on the real-time image quality of the local ROI region, a threshold is set to control and adjust the ROI region bitrate, ensuring high bitrate and high-definition image quality in the ROI region, while other regions have low bitrate and negligible image quality.

[0127] In step 5, based on the size of the reconnaissance area, the size of the reconnaissance target, and the UAV's flight altitude, the optoelectronic equipment on the optoelectronic UAV calculates the single-unit area sweep width in real time. According to the scanning range of the electronic reconnaissance target location, the number of optoelectronic units allocated for collaborative scanning is calculated. During the sweeping process, the UAV inputs the reconnaissance video into its intelligent detection and recognition module to generate its target results. These results are then compared with targets in the target list sent by the electronic reconnaissance team leader for re-identification. Based on the target's confidence rate, electronic reconnaissance target positioning error, and other information, the uniqueness of the target is confirmed.

[0128] Specifically, the optoelectronic team leader calculates the required number of drones for close-range reconnaissance based on optoelectronic parameters and then assigns the tasks.

[0129] Distans, the target at the center of the field of view (UAV&Item)meters, drone altitude H UAV Calculate the pitch angle α UAV The pitch angle is calculated as follows:

[0130]

[0131] X represents the horizontal resolution of the photoelectric image, Y represents the vertical resolution of the photoelectric image, a represents the target size, and m represents the number of target imaging pixels. For example... Figure 6 As shown, the calculation method for the sweep width parameter is as follows:

[0132] The method for calculating the horizontal field of view A (in degrees) is as follows:

[0133]

[0134] The method for calculating the pitch field of view B (in degrees) is as follows:

[0135]

[0136] The width of a single horizontal reconnaissance frame is L A (Unit: meters)

[0137]

[0138] Longitudinal reconnaissance single-width L B (Unit: meters)

[0139] L B =[tan(α) UAV +B / 2)-tan(α UAV -B / 2)]×H UAV

[0140] If n swath widths are scanned within the reconnaissance time period, then the total swath width S of a single unit during the sweeping motion is... AB =L A ×cos 倾斜角 ×n.

[0141] The error in electronic reconnaissance target localization is D. item If the distance is meters, then the number of close-range reconnaissance electro-optical drones that need to be allocated is... The drones are assigned tasks based on their numbers. Multiple drones fly simultaneously in a straight line, scanning and adjusting their distance to the laser vehicle as they gradually approach the reconnaissance target.

[0142] Specifically, the machine inputs the reconnaissance video into its intelligent detection and recognition module to generate target results. Simultaneously, the target results are compared with targets in the target list sent by the electronic reconnaissance team leader to confirm the uniqueness of the targets.

[0143] The electro-optical UAV reads a pre-loaded target model and target type lookup table locally. Based on the target model in the electronic reconnaissance target list, it obtains the target type corresponding to the target model. The UAV detection and recognition module loads this target model library and performs target detection and recognition during the electro-optical UAV's straight-line approach to the target, obtaining the target detection and recognition confidence rate V. item0 Target longitude and latitude W item0 =(L item 0, B item0 The distance D between the photoelectric payload's line of sight and the target is obtained through laser ranging. item0 At the same moment, the longitude and latitude W of the drone uav =(L uav B uav ).

[0144] Calculate the distance between the photoelectric detection target and the drone based on the drone's current location.

[0145] D (uav，item0) =D[(L uav B uav ),(L item0 B item0 The slant distance projected onto the ground is D. 投影(uav，item0) .

[0146] Calculate the distance between the electronic reconnaissance target and the drone based on the drone's current location.

[0147] D (uav，item) =D[(L uav B uav ),(L item B item The slant distance projected onto the ground is D. 投影(uav，item) .

[0148] If the projected distance is less than the longitude of the electronic reconnaissance target, i.e., |D 投影(uav，item0) -D 投影(uav，item) | <D item And the target confidence rate V item If the percentage is greater than 90%, then the target item detected by photoelectric detection and the target item 0 detected by electronic detection are considered to be the same target.

[0149] Step 6: After the electro-optical UAV identifies the target, its electro-optical equipment remains pointed at the target area. Based on the target's pixel position, it continuously provides geographic guidance, transitions to tracking mode, and directly enters the strike guidance mode. In image-guided mode, the UAV conducts a guided strike on the target. During the approach, the electro-optical payload automatically detects the target's vital parts based on the target type, adjusts the tracking and attack position, and updates the line-of-sight angular rate in real time. The UAV then performs a terminal-guided strike based on the line-of-sight angular rate.

[0150] Specifically, after target confirmation, the optoelectronic device automatically executes geographic guidance commands based on the target's location. As the drone and target become smaller, the optoelectronic device switches to target tracking mode. The optoelectronic device begins image guidance, outputting the line-of-sight angular rate, and the drone's control module initiates guidance mode based on the line-of-sight angular rate. During the approach, as the target's pixel size increases, it becomes possible to identify the target's vital parts.

[0151] During image guidance, the UAV judges the image quality based on the information entropy of the image. If the image quality is not up to standard, the visible light and infrared images captured by photoelectric imaging are fused together, and the fused image is used for image guidance.

[0152] Step 7: During the terminal guidance process of the UAV, the long-range electronic reconnaissance UAV continuously monitors the target of the interference source. If the target's electromagnetic characteristics disappear after the attack and the target is not in the target list, the corresponding target in the target list will be marked as disappeared.

[0153] Specifically, during the terminal guidance process of the electro-optical UAV, the long-range electronic reconnaissance UAV continuously monitors the interference source target. If the electromagnetic characteristics of target Item0 in the target list cannot be matched, the corresponding target in the target list will be marked as disappeared.

[0154] It should be noted that, as another aspect, this 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 storage medium carries one or more programs, which, when executed by an electronic device, cause the electronic device to perform the methods described in the following embodiments.

[0155] In one embodiment, this application provides a computer program product including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0156] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0157] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of 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 not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the claims.

[0158] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is defined only by the appended claims.

Claims

1. A collaborative reconnaissance method for key areas based on heterogeneous and heterogeneous information from electronic and photoelectric sources, characterized in that, The method includes: The electronic reconnaissance UAV is equipped with electronic reconnaissance equipment to conduct long-range reconnaissance of the entire mission area from high altitude; the electronic reconnaissance equipment identifies the type and parameters of the target source and forms a single-unit target sorting result; The electronic reconnaissance UAV sends the target selection results of the individual UAV to the electronic reconnaissance information team leader UAV. The team leader UAV merges the targets sent by the individual UAV to form the target results of the whole area. It then sorts the target results of the whole area by threat to form a list of electronic targets and broadcasts it to the electro-optical UAV. The electro-optical UAV is equipped with day and night electro-optical reconnaissance equipment to conduct close-range reconnaissance of key areas at low altitudes. Based on the target location information in the electronic reconnaissance target list, the day and night electro-optical reconnaissance equipment is allocated to several electro-optical UAVs in the vicinity, and the electro-optical UAVs conduct close-range search flights. During the sweeping operation of the electro-optical UAV, the reconnaissance video is used to form the target results of the local unit; the local target results are then compared with the targets in the target list sent by the electronic reconnaissance team leader to re-identify the targets and confirm their uniqueness; the uniqueness confirmation of the targets includes: The electro-optical UAV reads the locally pre-loaded target model and target type lookup table, and obtains the target type corresponding to the target model based on the target model in the electronic reconnaissance target list; The electro-optical UAV detection and recognition module loads the target model library and performs target detection and recognition during the electro-optical UAV's straight-line approach to the target, obtaining the confidence rate of target detection and recognition. Target longitude and latitude The distance between the photoelectric payload's line of sight and the target being detected is obtained through laser ranging. The longitude and latitude of the drone at the same moment ; Calculate the distance between the photoelectric detection target and the drone based on the drone's current location. The distance of the slant range projected onto the ground is ; Calculate the distance between the electronic reconnaissance target and the drone based on the drone's current location. The distance of the slant range projected onto the ground is ; If the projected distance is less than the longitude of the electronic reconnaissance target location, that is... And the target confidence rate Then the target of photoelectric detection is considered to be Targets detected by electronic reconnaissance For the same goal; After identifying a target, the electro-optical UAV continuously points its electro-optical equipment at the target area. Based on the target's pixel position, it provides continuous geographic guidance, transitions to tracking mode, and directly enters the strike guidance mode. In image guidance mode, the electro-optical UAV conducts guided strikes against the target. During the approach to the target, the electro-optical payload automatically detects the target's vital parts based on the target type, adjusts the tracking and attack position, and updates the line-of-sight angular rate in real time. The electro-optical UAV then conducts terminal guidance strikes based on the line-of-sight angular rate. During the terminal guidance process of the electro-optical UAV, the long-range electronic reconnaissance UAV continuously monitors the target of the interference source. If the target's electromagnetic characteristics disappear after the attack and the target is not in the target list, the corresponding target in the target list will be marked as disappeared. After the electromagnetic targets in this key area have been attacked, 2. The method according to claim 1, characterized in that, The electronic reconnaissance UAV uses a side-view scanning method.

3. The method according to claim 1 or 2, characterized in that, Before the electronic reconnaissance UAV sends the target sorting results from a single UAV to the electronic reconnaissance information team leader UAV, the method further includes: The electronic reconnaissance UAV determines the required data bandwidth for data transmission between computers based on the amount of data and time of the target results generated by the UAV. The bandwidth is then sent to the UAV's communication network equipment, and the bandwidth configuration is completed after the communication network setup is finished.

4. The method according to claim 1, characterized in that, While the electro-optical UAV is conducting close-range search, the method also includes: Electro-optical UAVs use images captured by photoelectric sensors to perform scene matching calculations. The matching results, i.e. the UAV's position, are sent to the flight control and navigation computer via the network. In the absence of satellite navigation, the UAV uses the scene matching results to correct its attitude and navigate.

5. The method according to claim 1, characterized in that, The method further includes: During the approach to the target, the electro-optical UAV reads the UAV link communication parameters to determine the communication status: when the communication is normal, the electro-optical UAV transmits high-definition, high-bandwidth reconnaissance images to the airborne link terminal, and ground personnel can observe real-time high-definition video; if the link communication is abnormal, but the link status is stable within a short communication period, the electro-optical UAV will increase the resolution of the region of interest and blur other areas, transmitting narrow-bandwidth image data to the airborne link terminal, reducing the transmission bandwidth requirement, and still ensuring that ground personnel can observe real-time reconnaissance video.

6. The method according to claim 1, characterized in that, The several electro-optical unmanned aerial vehicles (UAVs) assigned to the adjacent area include: Determine the number of sorties for electro-optical UAVs. n ; Calculate the distance between the electro-optical UAV and the target; Selecting targets based on their distance from near to far using the electro-optical UAV n A drone.

7. The method according to claim 6, characterized in that, The determination of the number of sorties of the electro-optical UAV includes: Based on the size of the reconnaissance area, the size of the reconnaissance target, and the flight altitude of the UAV, the optoelectronic equipment on the optoelectronic UAV calculates the single-aircraft area sweep width in real time, and calculates the number of optoelectronic units to be assigned for cooperative scanning according to the scanning range of the electronic reconnaissance target position.

8. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the collaborative reconnaissance method for key areas based on heterogeneous and heterogeneous information from electronic and photoelectric sources, as described in any one of claims 1 to 7.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the collaborative reconnaissance method for key areas based on heterogeneous and heterogeneous information from electronic and photoelectric sources, as described in any one of claims 1 to 7.

Images