A low-altitude communication, navigation, surveillance, and anti-fusion perception and control method and system

Abstract

The present invention discloses a low-altitude communication, navigation, surveillance, and anti-fusion perception and control method and system, which belongs to the field of target detection and tracking technology. The method includes obtaining active position report information of an aircraft, obtaining an active detection data set for spatiotemporal correlation matching, and generating a set of targets to be identified; calling a high-definition optical detection device to track the target, and fusing pre-acquired real-time meteorological environment data to enhance the tracking process, generating enhanced target feature data for target attribute identification, and when the target attribute identification result is an illegal target, combining the real-time meteorological environment data with a preset shootdown area to generate an adaptive counter-action decision instruction, driving the counter-action device to perform a counter-action operation. The present invention adopts the method of fusing active report information with active detection data to identify the target, and combines real-time meteorological data to perform feature enhancement and adaptive counter-action decision-making, which can identify and deal with low-altitude illegal targets in all weather conditions and with high precision.

Description

Technical Field

[0001] The present invention relates to the field of target detection and tracking technology, and in particular to a low-altitude communication, navigation, surveillance, and anti-fusion perception and control method and system. Background Art

[0002] Low-altitude security is a crucial component of national and public safety. With the increasing prevalence of drones and other low-flying, slow-moving, and small aircraft, the need for low-altitude protection in key areas such as airports, nuclear power plants, and large-scale event venues is becoming increasingly urgent. Low-altitude surveillance and defense systems typically utilize a variety of sensors, including radar, radio detection, and photoelectric detection, to monitor airspace to detect, identify, track, and address potential threats. The use of radio waves or other waves for ranging, speed measurement, and positioning is a core technology for airspace surveillance.

[0003] In existing technologies, the detection and disposal processes for low-altitude targets are typically fragmented and independent. Radar or radio detection equipment is typically used for initial early warning. Once a suspicious target is detected, operators manually or semi-automatically guide high-definition optical equipment for confirmation. Once the target is confirmed as a threat, independent jamming or strike equipment is activated for countermeasures. This model, characterized by multiple discrete systems and poor information exchange, relies on coordination between different devices and the operator's experience and judgment.

[0004] However, the isolated data from various detection sensors lacks an effective fusion processing mechanism, making it difficult to quickly distinguish cooperative targets broadcasting legitimate identities from non-cooperative targets without active signals. This results in a high false alarm rate and low processing efficiency. Furthermore, high-precision recognition equipment, such as optical systems, is highly susceptible to interference from complex weather conditions such as wind, rain, and fog, resulting in degraded image quality and distorted target features, seriously impacting recognition accuracy and the system's all-weather capability. Summary of the Invention

[0005] To solve the above problems, the present invention provides a low-altitude communication, navigation, surveillance and anti-fusion perception and control method and system, which uses the fusion of active reporting information and active detection data to identify targets, and combines real-time meteorological data for feature enhancement and adaptive countermeasure decision-making. It can identify and deal with low-altitude illegal targets with high precision around the clock.

[0006] The above objectives can be achieved through the following solutions:

[0007] A low-altitude communication, guidance, surveillance, and anti-fusion perception and control method and system, comprising obtaining active position report information of an aircraft and an active detection data set generated by scanning a preset airspace with multi-source active detection equipment, performing spatiotemporal correlation matching on the active position report information and the active detection data set to generate a set of targets to be identified; based on the target distribution in the set of targets to be identified, calling a high-definition optical detection device to track the target, and integrating pre-acquired real-time meteorological environment data to enhance the tracking process and generate enhanced target feature data; performing target attribute identification based on the enhanced target feature data to generate a target attribute identification result, and when the target attribute identification result is an illegal target, combining the real-time meteorological environment data with a preset shootable area to generate an adaptive counter-decision instruction; and driving the counter-operation device to perform a counter-operation according to the adaptive counter-decision instruction.

[0008] Optionally, generating the set of targets to be identified includes: obtaining active position report information of the aircraft, and obtaining an active detection data set generated by scanning a preset airspace with multi-source active detection equipment; extracting the motion characteristic parameters of the target from the active detection data set, and extracting the track parameters of the legitimate aircraft from the active position report information; calculating the correlation score between the motion characteristic parameters and the track parameters, and generating a matching result based on comparing the correlation score with a preset matching threshold; based on the matching result, aggregating the active detection targets that have not been successfully matched to generate a set of targets to be identified.

[0009] Optionally, after generating the set of targets to be identified, the method further includes: calculating and generating a system threat level based on the speed, distance and cluster density of each target to be identified in the set of targets to be identified; when the system threat level exceeds a preset level threshold, generating a device parameter adjustment instruction to increase the scanning frequency and sampling rate of the multi-source active detection device.

[0010] Optionally, the generating of enhanced target feature data includes: acquiring real-time meteorological environment data, and generating a meteorological correction parameter set based on the real-time meteorological environment data; calling a high-definition optical detection device to extract feature data of the target to be identified in the target set to be identified, and using the meteorological correction parameter set to adjust the feature data of the target to be identified to obtain enhanced feature data; predicting the motion trajectory of the target to be identified in the target set to be identified to obtain a predicted target trajectory, and using the meteorological correction parameter set to compensate the predicted motion trajectory to generate compensated predicted trajectory data; generating enhanced target feature data based on the enhanced feature data and the compensated predicted trajectory data.

[0011] Optionally, before calling the high-definition optical detection device, the method also includes: when the real-time meteorological environment data meets the preset deterioration condition, increasing the image sampling frame rate of the high-definition optical detection device and collecting multispectral images to generate a multispectral image sequence; inputting the multispectral image sequence into a deep learning recognition network to generate a compensated recognition result; and using the compensated recognition result instead of the enhanced target feature data for subsequent target attribute recognition.

[0012] Optionally, the generating of the adaptive counter-decision instruction includes: performing target attribute identification based on the enhanced target feature data to generate a target attribute identification result; when the target attribute identification result is an illegal target, determining whether the illegal target is located in a preset shootdown area; if it is located in the shootdown area, calculating the device power adjustment parameter based on the real-time meteorological environment data; if it is not located in the shootdown area, generating an expulsion path planning by combining the real-time meteorological environment data with the preset sensitive area location information; encapsulating the device power adjustment parameter or the expulsion path planning to generate the adaptive counter-decision instruction.

[0013] Optionally, while executing the counter-action operation, the method further includes: dynamically calculating the counter-action influence range based on the working parameters of the counter-action device; obtaining legal targets based on the target attribute identification results, and monitoring the positions of legal targets in the airspace in real time, and determining whether they enter the counter-action influence range; if so, generating and sending a counter-action termination instruction to stop the counter-action operation, and generating airspace situation warning information.

[0014] Optionally, the method also includes: after executing the counter operation, continuously monitoring the illegal target to generate real-time motion status data, and generating counter effect evaluation data based on the real-time motion status data; evaluating the counter effect based on the counter effect evaluation data to obtain a counter evaluation value; when the counter evaluation value is less than a preset evaluation threshold, obtaining the current real-time meteorological environment data to update the meteorological correction parameter set; based on the updated meteorological correction parameter set and the real-time motion status data, updating the counter strategy optimization instruction to perform another counter.

[0015] Optionally, the updating of the countermeasure strategy optimization instruction for re-countering includes: obtaining context information of historical countermeasure events, building a historical countermeasure case database, and building a countermeasure effectiveness prediction model based on the historical countermeasure case database; inputting the updated meteorological correction parameter set into the countermeasure effectiveness prediction model to generate equipment parameter optimization suggestions; and generating a countermeasure strategy optimization instruction for re-countering based on the equipment parameter optimization suggestions.

[0016] Based on the same inventive concept, the present invention also provides a low-altitude communication, guidance, surveillance, and anti-fusion perception and control system, which includes: a target acquisition module for acquiring active position report information of an aircraft, and acquiring an active detection data set generated by scanning a preset airspace with a multi-source active detection device, performing spatiotemporal correlation matching on the active position report information and the active detection data set to generate a set of targets to be identified; a feature enhancement module for calling high-definition optical detection equipment to track the target according to the target distribution in the set of targets to be identified, and integrating pre-acquired real-time meteorological environment data to enhance the tracking process to generate enhanced target feature data; a counter-decision module for performing target attribute identification based on the enhanced target feature data, generating a target attribute identification result, and when the target attribute identification result is an illegal target, combining the real-time meteorological environment data with the preset shootable area to generate an adaptive counter-decision instruction; a counter-execution module for driving the counter-decision device to perform a counter-operation according to the adaptive counter-decision instruction.

[0017] Compared with the prior art, the present invention has the following advantages:

[0018] 1. Through multi-source information fusion and environmental adaptive closed-loop control, the present invention achieves intelligent and precise positioning and tracking control of low-altitude targets throughout the entire process. The present invention spatially and temporally correlates aircraft active reporting information with multi-source active detection data, effectively filtering out known legitimate targets and accurately generating a set of unknown targets to be identified. This significantly reduces the processing burden and false alarm rate of subsequent identification and countermeasure systems, and improves the accuracy and efficiency of the entire system in detecting potential threats.

[0019] 2. This invention deeply integrates real-time meteorological environmental data into the target identification and tracking process. By enhancing and correcting optical detection data and compensating and predicting the target motion trajectory, it effectively overcomes the impact of adverse weather conditions such as wind, rain, and fog on detection performance, ensuring the stability of target feature extraction and the reliability of recognition results in various complex environments, and achieving all-weather high-precision detection and tracking capabilities.

[0020] 3. The present invention has established a dynamic, intelligent and secure adaptive countermeasure decision-making and execution mechanism. It can not only flexibly select the optimal countermeasure strategy such as attack or expulsion according to the different areas where illegal targets are located in combination with real-time meteorological data, but also monitor and avoid the impact on legitimate targets in real time during the countermeasure process; through closed-loop evaluation of countermeasure effects and historical case learning, the system can continuously self-optimize countermeasure strategies, significantly improving the success rate and safety of disposal, and realizing the leap from active response to active optimization.

[0021] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 The present invention is a flowchart of a low-altitude communication, navigation, monitoring, and anti-fusion sensing and control method.

[0024] Figure 2 Schematic diagram of target acquisition and screening according to an embodiment of the present invention.

[0025] Figure 3 2 is a schematic diagram comparing meteorological correction trajectories according to an embodiment of the present invention.

[0026] Figure 4 It is a structural diagram of a low-altitude communication, navigation, monitoring, and anti-fusion perception and control system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0028] Reference Figure 1 One embodiment of the present invention proposes a low-altitude communication, navigation, surveillance, and anti-fusion perception and control method, which uses the fusion of active reporting information and active detection data to identify targets, and combines real-time meteorological data to perform feature enhancement and adaptive countermeasure decision-making. It can identify and deal with low-altitude illegal targets with high precision around the clock.

[0029] The method of this embodiment specifically includes:

[0030] Obtaining active position report information from an aircraft and an active detection dataset generated by scanning a preset airspace using multi-source active detection equipment, performing spatiotemporal correlation matching on the active position report information and the active detection dataset to generate a set of targets to be identified;

[0031] According to the target distribution in the target set to be identified, high-definition optical detection equipment is called to track the target, and pre-acquired real-time meteorological environment data is integrated to enhance the tracking process to generate enhanced target feature data;

[0032] Performing target attribute recognition based on the enhanced target feature data to generate a target attribute recognition result, and when the target attribute recognition result is an illegal target, combining the real-time meteorological environment data with a preset shootdown area to generate an adaptive countermeasure decision instruction;

[0033] According to the adaptive countermeasure decision instruction, the countermeasure device is driven to perform a countermeasure operation.

[0034] Specifically, the method first constructs a target set containing only unknown or non-cooperative targets by temporally and spatially correlating the position information actively broadcast by aircraft within the airspace with data acquired by multi-source active detection equipment. This allows for preliminary target screening and focusing. Subsequently, the method uses high-definition optical equipment to track and identify targets within this set. During this process, it actively integrates real-time meteorological environmental data, dynamically compensating and enhancing the optical detection process to generate high-quality target signatures that are unaffected by environmental interference. Finally, after identifying illegal targets based on these enhanced signatures, the method further combines real-time meteorological data with pre-set geospatial rules to generate countermeasure decision instructions adapted to the current environment and situation, and drives the countermeasure equipment to execute them. This complete technical closed loop, from multi-source fusion discovery to environmentally enhanced identification and finally to situation-adaptive decision-making, significantly improves the intelligence, precision, and reliability of low-altitude safe tracking and positioning control. By integrating active and passive information, the method effectively filters out a large number of legitimate, cooperative targets, significantly reducing the system's processing load and false alarm rate, allowing monitoring resources to focus on real potential threats and improving the efficiency and accuracy of target detection. Incorporating real-time meteorological data into the optical recognition and countermeasure decision-making process overcomes the performance degradation of traditional optical systems in inclement weather, ensuring the system's stable, all-weather operation in a variety of environments and achieving more reliable target identification results. Ultimately, the adaptive countermeasure decision-making mechanism eliminates fixed and rigid countermeasure actions, enabling dynamic adjustments based on target location and environmental factors. This ensures countermeasure success while minimizing the risk of collateral damage, achieving efficient, precise, and safe low-altitude defense.

[0035] Optionally, generating a set of targets to be identified includes:

[0036] Obtain active position report information from aircraft and obtain active detection data sets generated by scanning preset airspaces with multi-source active detection equipment;

[0037] Extracting target motion characteristic parameters from the active detection data set, and extracting legitimate aircraft track parameters from the active position report information;

[0038] Calculating a correlation score between the motion feature parameter and the track parameter, and generating a matching result based on comparing the correlation score with a preset matching threshold;

[0039] Based on the matching results, the unmatched active detection targets are aggregated to generate a set of targets to be identified.

[0040] Specifically, by screening all detected targets in the airspace, a precise target set containing only unknown or non-cooperative targets is generated, providing critical input for subsequent high-precision identification and countermeasures. Information is first obtained from two independent data sources. The first is active position reports sent by aircraft. This information is typically provided by cooperative targets such as civil airliners and general aviation aircraft via Automatic Dependent Surveillance-Broadcast (ADS-B) and contains precise identification, three-dimensional position, velocity vector, and other track parameters. The second is an active detection dataset acquired by scanning multiple active detection devices deployed in a predefined airspace, such as 5G-A, phased array radar, and radio spectrum monitoring equipment. This dataset contains raw detection information, such as motion characteristic parameters such as position and velocity, for all targets detectable by the devices in the airspace, but lacks explicit identity information. Next, to distinguish cooperative from non-cooperative targets, the system performs spatiotemporal correlation matching on these two data sets. Specifically, the system extracts the motion characteristic parameters of each target from the active detection dataset and the track parameters of all legitimate aircraft from the active position reports. Then, the correlation score between any active detection target and a legitimate aircraft track is calculated. This score is used to quantify the possibility that the two belong to the same target at the same time. The calculation of the correlation score can use the weighted distance of the state vector, such as the Mahalanobis distance, to comprehensively consider the differences in multi-dimensional parameters such as position and speed and their measurement uncertainty. , you can have:

[0041] ,

[0042] In this formula, Represents the association score. The smaller the value, the higher the possibility of the two targets being associated. is the target state vector extracted from the active detection data set, which contains the three-dimensional coordinates and velocity components of the target. is the state vector of the legal aircraft extracted from the active position report information, and its structure is the same as The two state vectors must be aligned to the same timestamp for calculation. Represents the measurement covariance matrix of the system, which reflects the measurement errors and uncertainties of the multi-source active detection equipment and the active reporting information. Its value is obtained based on the estimation results of the equipment calibration parameters and the filtering algorithm. The inverse matrix of It is used to normalize and decorrelate parameter differences in different dimensions, ensuring the robustness of the calculation. After the association score is calculated, it will be compared with a preset matching threshold. If the association score is less than or equal to the matching threshold, it is determined that the active detection target is successfully matched with the actively reported legal aircraft, that is, the target is confirmed as a known, legal cooperative target. On the contrary, if the association score is greater than the matching threshold, it is determined that the match failed. All active detection targets that failed to match, that is, those targets that cannot be associated with any known legal aircraft track, are aggregated to form the final set of targets to be identified. Figure 2 As shown, if the active detection target is not associated with the active detection trajectory, it is determined to be a target to be identified.

[0043] Optionally, after generating the set of targets to be identified, the method further includes:

[0044] Calculate and generate a system threat level based on the speed, distance, and cluster density of each target to be identified in the set of targets to be identified;

[0045] When the system threat level exceeds a preset level threshold, a device parameter adjustment instruction is generated to increase the scanning frequency and sampling rate of the multi-source active detection device.

[0046] Specifically, a quantitative system threat level is first calculated based on the generated set of targets to be identified. This level is calculated by integrating the speed and distance of each target in the set, as well as the cluster density between targets. Cluster density refers to the density of targets within a preset spatial range and is a key indicator for assessing the threat of saturation attacks or cluster coordinated attacks. The system threat level can be calculated using a weighted summation model, for example:

[0047] ,

[0048] in, It represents the final calculated system threat level and is a dimensionless comprehensive evaluation value. Indicates traversing and summing all targets in the target set to be identified. For the i-th target in the set, is the target's velocity, is the distance of the target relative to the center of the detection device. Both parameters are directly obtained from the set of targets to be identified. It is the number of targets in the same cluster as the target, obtained by performing clustering analysis algorithms such as DBSCAN on the target set. , and These are preset weight coefficients representing the importance of speed, distance, and cluster density in threat assessment, with their sum being 1. They are configured based on the needs of specific defense scenarios. 、 and These are the reference values ​​used for normalization, including reference speed, maximum detection range, and reference number of clusters. After calculating the system threat level, the system immediately compares it with a preset threshold. If the system threat level exceeds this threshold, it indicates that unknown targets in the current airspace exhibit dangerous characteristics such as high speed, close proximity, or high-density clustering, escalating the overall threat situation. At this point, a device parameter adjustment command is automatically generated and sent to the front-end multi-source active detection equipment. The core content of this command is to increase the scanning frequency and sampling rate of these devices. The scanning frequency refers to the rate at which detection equipment, such as radar, completes a full airspace scan. Increasing this frequency means faster target position updates and shortens the data refresh cycle. The sampling rate, primarily for equipment such as radio detection, refers to the rate at which they digitally acquire electromagnetic signals in space. Increasing this rate enables the capture of weaker, wider-bandwidth signals and richer target details.

[0049] Optionally, generating enhanced target feature data includes:

[0050] Acquiring real-time meteorological environmental data, and generating a meteorological correction parameter set based on the real-time meteorological environmental data;

[0051] calling a high-definition optical detection device to extract feature data of a target to be identified in the set of targets to be identified, and adjusting the feature data of the target to be identified using the meteorological correction parameter set to obtain enhanced feature data;

[0052] Predicting the motion trajectory of the target to be identified in the set of targets to be identified to obtain a predicted target trajectory, and compensating the predicted motion trajectory using the meteorological correction parameter set to generate compensated predicted trajectory data;

[0053] Enhanced target feature data is generated based on the enhanced feature data and the compensated predicted trajectory data.

[0054] Specifically, the system first acquires real-time meteorological data within the deployment area through a meteorological sensor network. This data includes, but is not limited to, key parameters such as atmospheric temperature, humidity, air pressure, wind speed, wind direction, and atmospheric visibility. Based on these raw meteorological readings, a meteorological correction parameter set is calculated and generated. This parameter set is not the raw data itself, but rather parameters that have been converted through a model and can be directly used for calculations. For example, it includes the atmospheric refractive index structure constant, which represents the intensity of atmospheric turbulence; the atmospheric transmittance, which is used to correct image contrast and clarity; and an accurate three-dimensional wind field vector. Subsequently, high-definition optical detection equipment, such as a high-magnification zoom camera or an infrared thermal imager, is used to continuously track the identified target and extract its feature data. This feature data represents the target's raw visual information, such as outline, size, color, and texture. However, in severe weather, these raw features can be distorted by atmospheric disturbances. The generated meteorological correction parameter set is then used to adjust these raw feature data. Specifically, the atmospheric transmittance parameters can be used to restore the true brightness and contrast of the target attenuated by haze; at the same time, the atmospheric turbulence intensity parameters are used as input to image restoration algorithms, such as adaptive optical compensation or blind deconvolution algorithms, to reduce image jitter and blur, thereby obtaining a clearer and more reliable enhanced feature data. At the same time, this method also predicts and compensates for the motion trajectory of the target. Based on the historical position and velocity information of the target to be identified, Kalman filtering or more complex motion models are used to predict its motion trajectory in the short future time to generate a predicted target trajectory. This prediction is accurate in a windless environment, but in practice it will be affected by wind force and produce deviations. Therefore, the three-dimensional wind field vector in the meteorological correction parameter set will be used to compensate for the predicted motion trajectory. For example, a simplified compensation model can be expressed as:

[0055] ,

[0056] in, Represents the compensated predicted trajectory data after wind compensation, which is a three-dimensional space position vector. is the original predicted target trajectory generated by the motion model, which is also a three-dimensional space position vector. It is a three-dimensional wind field vector obtained from the meteorological correction parameter set, indicating the wind speed and direction in the airspace where the target is located. is the time step of the prediction. By superimposing the displacement increment caused by the wind force during the prediction period on the original prediction position, a more realistic compensated prediction trajectory data is generated, such as Figure 3 Finally, the enhanced feature data obtained from the above processing and the compensated predicted trajectory data are aggregated to form enhanced target feature data, providing high-quality input for subsequent target attribute recognition.

[0057] Optionally, before calling the high-definition optical detection device, the method further includes:

[0058] When the real-time meteorological environment data meets a preset deterioration condition, the image sampling frame rate of the high-definition optical detection device is increased and multispectral images are collected to generate a multispectral image sequence;

[0059] Inputting the multispectral image sequence into a deep learning recognition network to generate a compensated recognition result;

[0060] The compensated recognition result is used instead of the enhanced target feature data for subsequent target attribute recognition.

[0061] Specifically, this method provides an emergency response process to ensure target identification continuity under extremely adverse weather conditions. It serves as a critical pre-judgment and alternative to conventional enhancement using high-definition optical detection equipment. This process is initiated by monitoring real-time meteorological environmental data. When this data meets pre-determined deterioration conditions, such as atmospheric visibility falling below a certain threshold, heavy precipitation, or dense fog, which severely impairs conventional optical imaging, conventional feature enhancement is discontinued and this special processing mode is activated instead. In this mode, a command is first sent to the high-definition optical detection equipment to increase the image sampling frame rate and switch to multispectral imaging mode. Increasing the image sampling frame rate means capturing more image frames per unit time, which helps eliminate transient noise interference such as rain and snow streaks by analyzing inter-frame variations. The core operation is the acquisition of multispectral imagery, a technology that simultaneously captures images of a target across multiple different electromagnetic spectrum bands, including the visible, near-infrared, and short-wave infrared. Because different bands have varying atmospheric penetration capabilities—for example, infrared is better at penetrating smoke and haze than visible light—multispectral data can provide target information that would otherwise be lost in a single band. These continuously acquired multispectral images constitute a multispectral image sequence. This multispectral image sequence, containing both temporal and spectral domain information, is then fed into a pre-trained deep learning recognition network. This network, typically a convolutional neural network (CNN) or a variant of a recurrent neural network (RNN) that incorporates time-series processing capabilities, is specifically designed and trained to learn how to fuse information from blurred and distorted image sequences across multiple spectral bands under adverse weather conditions, reconstructing or directly inferring the target's clear features and attributes. By processing the entire sequence, the network effectively suppresses noise, filters out interference, and extracts the most stable and reliable target signatures from the complementary spectral information. The network's output, defined as a compensated recognition result, is not a simple image but a structured data package containing direct identification of key attributes such as target type, outline, and size. Its information content is comparable to the enhanced target feature data generated using conventional methods. Finally, the compensated recognition result generated directly by the deep learning network replaces the enhanced target feature data originally generated by conventional methods and is seamlessly fed into the subsequent target attribute recognition process, ensuring the integrity of the entire perception and decision-making chain.

[0062] Optionally, generating an adaptive countermeasure decision instruction includes:

[0063] Performing target attribute recognition based on the enhanced target feature data to generate a target attribute recognition result;

[0064] When the target attribute identification result is an illegal target, determining whether the illegal target is located in a preset shootdown area;

[0065] If the aircraft is located in the shoot-down zone, then the power adjustment parameters of the equipment are calculated according to the real-time meteorological environment data;

[0066] If the aircraft is not located in the shoot-down zone, a repelling path plan is generated by combining the real-time meteorological environment data with the preset sensitive area location information;

[0067] The device power adjustment parameter or the expulsion path planning is encapsulated to generate the adaptive countermeasure decision instruction.

[0068] Specifically, target attribute identification is performed based on the enhanced target feature data generated in the previous step. Once the target attribute identification result is determined to be an illegal target, the hierarchical decision-making process is immediately initiated. First, it is determined whether the current spatial position of the illegal target is within the preset shootdown area. This shootdown area is pre-determined based on regulations, safety assessments and geographic information. It is considered safe to perform hard kill countermeasures within these areas. If the judgment result is yes, that is, the illegal target is located in the shootdown area, a direct strike strategy will be adopted. To ensure the accuracy and effectiveness of the strike, the device power adjustment parameters of the countermeasure equipment will be dynamically calculated based on real-time meteorological environmental data, such as atmospheric density, humidity and wind speed. For example, for laser weapons, water vapor and suspended particles in the atmosphere will absorb and scatter energy. It is necessary to compensate for energy attenuation and increase the transmission power based on these meteorological parameters. The adjustment process can be described by the following model:

[0069] ,

[0070] in, This is the final device power adjustment parameter, representing the actual operating power that the countermeasure device needs to be set to. It is the reference power of the countermeasure equipment under standard atmospheric conditions, which is a known inherent parameter of the equipment. It is a dimensionless comprehensive adjustment function that integrates real-time meteorological environment data Distance to target This function, calculated using a physical model, reflects the energy loss under varying weather conditions and ranges, ensuring that the energy applied to the target achieves the desired damage or disruption effect. If the illegal target is not within a targetable zone, particularly near pre-defined sensitive locations such as schools and hospitals, a non-destructive repulsion strategy will be employed. A complex path optimization calculation is performed based on the illegal target's current motion status, the location of pre-defined sensitive areas, and wind field information from real-time weather data to generate a repulsion path plan. This plan aims to use soft-kill techniques such as electronic jamming to force the illegal target to follow a pre-calculated, safe trajectory that will quickly escape sensitive areas and avoid entering other restricted areas. Ultimately, both the calculated device power adjustment parameters and the generated repulsion path plan are packaged into a standardized adaptive countermeasure decision instruction and sent to downstream countermeasure devices for execution.

[0071] Optionally, while performing the countermeasure operation, the method further includes:

[0072] Dynamically calculating the countermeasure impact range based on the operating parameters of the countermeasure device;

[0073] Acquire a legitimate target based on the target attribute recognition result, monitor the position of the legitimate target in the airspace in real time, and determine whether it enters the countermeasure influence range;

[0074] If so, a countermeasure termination instruction is generated and sent to stop the countermeasure operation, and airspace situation warning information is generated.

[0075] Specifically, while executing countermeasures against illegal targets, this method simultaneously initiates a dynamic safety monitoring and termination mechanism to ensure the safety of legitimate targets within the airspace. First, based on the current operating parameters of the countermeasure device, the real-time countermeasure impact range of the current countermeasure operation is dynamically calculated. Operating parameters include the countermeasure device's transmit power, antenna gain, operating frequency, and beam direction, which together determine the spatial distribution of the countermeasure energy. The countermeasure impact range is a three-dimensional spatial region whose boundaries are defined by points where the countermeasure energy or interference signal strength decays below a preset safety threshold—the minimum safety standard established to protect the normal operation of the legitimate target's onboard equipment. Simultaneously, based on previously acquired target attribute recognition results, information on all legitimate targets is extracted, and the precise three-dimensional positions of these legitimate targets in the airspace are continuously monitored in real time using the communication, navigation, and monitoring system. Next, a continuous spatial position comparison is performed, comparing the real-time position coordinates of each legitimate target with the dynamically calculated countermeasure impact range to determine whether the legitimate target has entered or is about to enter the danger zone. If so, indicating a risk of a legitimate target entering the countermeasure range, a high-priority countermeasure termination command is immediately generated and sent to the active countermeasure device, instructing it to immediately cease all countermeasure actions, thereby preventing any unintended interference or damage to the legitimate target. Simultaneously with the termination command, a detailed airspace situation warning is generated and communicated to the operator at the monitoring center. This information includes details of the conflict, identification of the legitimate and illegal targets involved, and the automated termination measures implemented, providing a basis for subsequent manual decision-making.

[0076] Optionally, the method further includes:

[0077] After executing the countermeasure operation, continuously monitoring the illegal target to generate real-time motion state data, and generating countermeasure effect evaluation data based on the real-time motion state data;

[0078] Evaluate the countermeasure effect based on the countermeasure effect evaluation data to obtain a countermeasure evaluation value;

[0079] When the countermeasure evaluation value is less than a preset evaluation threshold, obtaining current real-time meteorological environment data to update the meteorological correction parameter set;

[0080] Based on the updated meteorological correction parameter set and the real-time motion status data, the countermeasure strategy optimization instruction is updated to perform another countermeasure.

[0081] Specifically, this method constructs a closed-loop evaluation and adaptive optimization process after executing the counter-action to ensure the final effect of the counter-action. After the counter-action device starts to perform the counter-action on the illegal target according to the instruction, it will not stop monitoring it, but will continue to use multi-source active detection equipment or high-definition optical detection equipment to lock the illegal target and generate its continuous real-time motion state data, which includes the target's three-dimensional position, velocity vector, attitude angle and other dynamic information. Based on this real-time motion state data, counter-action effect evaluation data will be further generated. This data is not a list of original motion parameters, but a series of quantitative indicators calculated by comparing the state changes before and after the counter-action, such as the attenuation rate of the target speed, the angle of deviation of the heading from the predetermined trajectory, or the degree of instability of the body attitude. Subsequently, based on this counter-action effect evaluation data, a single, dimensionless counter-action evaluation value is calculated through a comprehensive evaluation model to accurately measure the effectiveness of the current counter-action strategy. The calculation of the counter-action evaluation value can be expressed as:

[0082] ,

[0083] in, Represents the final countermeasure evaluation value. and are preset weight coefficients, which respectively represent the importance of speed decay and trajectory deviation in the overall evaluation, and their sum is 1. Represents the current real-time speed of the illegal target, is its initial speed before the counterattack begins. Both speed values ​​are obtained from the real-time motion state data. Characterizes the relative attenuation of velocity. is the actual offset distance of the target's current position relative to its original predicted trajectory, and It is the minimum safe offset distance expected to be achieved according to the countermeasure strategy. This value reflects the effectiveness of the repelling effect. When the countermeasure evaluation value falls below the threshold, it indicates that the current countermeasures have failed to achieve the desired effect. This may be due to environmental changes or countermeasures implemented by the target. At this point, the system immediately re-obtains current real-time weather data from the meteorological sensor network and uses this latest data to update the previously used weather correction parameter set. Finally, this updated weather correction parameter set is combined with the target's latest real-time motion data to recalculate the countermeasure decision, generating an optimized countermeasure strategy instruction. This instruction then drives the countermeasure device to execute a new, more targeted countermeasure operation.

[0084] Optionally, updating the countermeasure strategy optimization instruction to perform countermeasure again includes:

[0085] Obtain contextual information about historical countermeasure events and build a historical countermeasure case database;

[0086] Constructing a countermeasure effectiveness prediction model based on the historical countermeasure case database;

[0087] Inputting the updated meteorological correction parameter set into the countermeasure effectiveness prediction model to generate equipment parameter optimization suggestions;

[0088] Based on the device parameter optimization suggestions, a countermeasure strategy optimization instruction is generated to perform further countermeasures.

[0089] Specifically, the first step is to systematically capture and record the complete contextual information for each historical countermeasure event. This information forms a multi-dimensional case record, encompassing the attributes and motion status of the countermeasure target, real-time weather and environmental data at the time of execution, the countermeasure strategy employed and specific equipment operating parameters, and ultimately, the countermeasure evaluation value calculated from countermeasure effectiveness evaluation data. By storing all these historical countermeasure case records in a structured manner, a continuously growing and improving historical countermeasure case database is constructed. Based on this historical countermeasure case database, a countermeasure effectiveness prediction model is constructed and trained. This model is essentially a machine learning model, such as a gradient boosted decision tree or a deep neural network. Its training objective is to learn and grasp the complex nonlinear relationship between different combinations of input conditions and the final countermeasure effectiveness. The model input is a feature vector describing the countermeasure mission scenario, including the target state, weather conditions, and planned countermeasure equipment parameters; the model output is a prediction of the countermeasure evaluation value that can be achieved by the countermeasure action. When a second countermeasure is needed, the updated weather correction parameter set obtained in the previous step, along with the illegal target's current real-time motion status data, are fed into the trained countermeasure effectiveness prediction model as fixed conditions. Subsequently, with the goal of maximizing the predicted countermeasure effectiveness, an optimization calculation is performed within the parameter range allowed by the countermeasure device. The model ultimately outputs a set of device parameter combinations predicted to be most likely to succeed. This combination is known as the device parameter optimization recommendation. Finally, this device parameter optimization recommendation, including specific values, is packaged into a standard countermeasure strategy optimization instruction and issued to the countermeasure device to execute an intelligently optimized second countermeasure.

[0090] Based on the same inventive concept, Figure 4 As shown, the present invention also provides a low-altitude communication, guidance, monitoring, and anti-fusion sensing and control system, the system comprising:

[0091] a target acquisition module configured to acquire active position report information from an aircraft and an active detection dataset generated by scanning a preset airspace with multi-source active detection equipment, perform spatiotemporal correlation matching on the active position report information and the active detection dataset, and generate a set of targets to be identified;

[0092] A feature enhancement module is used to call high-definition optical detection equipment to track the target according to the target distribution in the target set to be identified, and to enhance the tracking process by fusing pre-acquired real-time meteorological environment data to generate enhanced target feature data;

[0093] a countermeasure decision module, configured to identify target attributes based on the enhanced target feature data, generate a target attribute identification result, and, when the target attribute identification result indicates an illegal target, generate an adaptive countermeasure decision instruction by combining the real-time meteorological environment data with a preset shootdown zone;

[0094] The countermeasure execution module is used to drive the countermeasure device to perform the countermeasure operation according to the adaptive countermeasure decision instruction.

[0095] To verify the feasibility of this invention, it was applied to a low-altitude security scenario at an airport. The airport sought to implement round-the-clock, intelligent low-altitude security monitoring and protection for its core airspace (e.g., runways, approach areas, and aprons) to address the growing threat posed by illegal low-altitude targets such as "illegal" drones.

[0096] Currently, low-altitude protection at airports relies heavily on manual observation, simple radio frequency detection, and jamming equipment in fixed areas. These traditional methods, when faced with complex weather conditions, clustered targets, or highly maneuverable targets, suffer from problems such as delayed detection, difficulty identifying, low handling efficiency, and the potential for collateral damage. Especially at night or in foggy or hazy weather, the effectiveness of traditional methods drops dramatically, failing to meet the extreme safety and operational efficiency requirements of large hub airports. The airport hopes to adopt the method of this invention to achieve integrated, fused perception and adaptive closed-loop control of low-altitude targets using "communication, guidance, surveillance, air, and countermeasures."

[0097] In this embodiment, the airport deployed the low-altitude communication, navigation, surveillance, and anti-fusion perception and control system described in this invention. Through its target acquisition module, the system accesses data from the civil aviation ADS-B (Automatic Dependent Surveillance-Broadcast) system in real time, acquiring active position reports from all participating civil aircraft. Simultaneously, multi-source active detection equipment, such as radar and radio spectrum detectors, deployed around the airport perimeter scans the pre-defined airspace to generate an active detection dataset. The system automatically performs spatiotemporal correlation matching on these two types of data, aggregating active detection targets that cannot be matched to any legitimate flight information (e.g., an undeclared quadcopter drone) to create a target set for identification.

[0098] The system then uses the feature enhancement module to track drones based on their distribution within the target set. For example, if the system detects a real-time wind speed of 15 m / s from the airport weather station, it automatically integrates this weather data to perform feedforward compensation on the optical tracking servo system, counteracting image jitter caused by strong winds. Simultaneously, the system uses wind field data to correct the drone's predicted trajectory, generating more accurate compensated predicted trajectory data. These processes together create enhanced target feature data, laying the foundation for subsequent accurate identification.

[0099] The countermeasure decision module identifies the drone's attributes based on enhanced target signature data and determines it to be a commercial consumer drone, making it an illegal intrusion target. The system then determines its location. If the drone is heading toward the open grass area at the end of the runway (the designated "shootdown zone"), the system, based on current humidity and temperature, calculates the minimum transmit power required by the high-power microwave countermeasure device to ensure effective damage and generates adaptive countermeasure decision instructions containing the device's power adjustment parameters. If the drone is heading toward the terminal area (the designated "sensitive area"), the system switches to a dispersal strategy, utilizing wind field information to plan a dispersal path that will maximize its flight away from the terminal and out of the airport, and generates corresponding navigation decoy instructions.

[0100] Finally, the countermeasure execution module, based on the received adaptive countermeasure decision, activates the corresponding countermeasure device (high-power microwave or navigation decoy device) to execute the countermeasure operation. During the countermeasure execution process, the system monitors the position of all legitimate civil aircraft in the airspace in real time. If an aircraft is detected approaching the countermeasure device's range, the system immediately issues a countermeasure termination command and sends airspace situation warning information to the tower and air traffic control center to ensure absolute safety.

[0101] To verify the beneficial effects of the present invention, the international airport conducted a six-month comparative test. The area where the present invention's system was deployed served as the experimental zone, while another area, protected only by traditional manual labor and simple equipment, served as the control zone. During the test, various weather and intrusion scenarios were simulated.

[0102] In terms of target recognition, the system in the experimental area took an average of 8 seconds to identify illegal targets, with an accuracy rate of 98%. This was particularly true at night and in moderate haze conditions. Thanks to multispectral fusion and deep learning compensation algorithms, the system was able to maintain a recognition rate of over 90%. In the control area, manual target identification took an average of 2 minutes in good weather and was virtually ineffective in inclement weather.

[0103] In terms of countermeasure effectiveness, the experimental area system took an average of 12 seconds from detection to completion of adaptive countermeasure decisions for a single target, with a disposal success rate of 95%. For example, in one test, after determining that the target was in a "shootdown zone," the system calculated and adjusted the laser weapon power based on real-time meteorological data, successfully shooting down the target in one go. In another test where the target was close to a "sensitive area," the system successfully planned an escape route, forcing the target to safely leave the no-fly zone within 90 seconds. The control area used manually operated jamming equipment, with an average disposal time of over 5 minutes and a success rate of less than 60%. The inability to accurately assess the effectiveness of the disposal resulted in repeated intrusions by the target on multiple occasions.

[0104] In terms of closed-loop optimization, this invention demonstrates unique learning capabilities. During a countermeasure effectiveness evaluation, the system discovered that the initial navigation decoy was ineffective (the countermeasure evaluation value fell below the threshold). Immediately, combining the latest wind data with a database of historical countermeasure cases, it optimized the frequency and waveform of the decoy signal using a countermeasure effectiveness prediction model. The resulting optimized countermeasure strategy successfully repelled the target during a second countermeasure. The entire optimization and re-countermeasure process was completed within 30 seconds.

[0105] Data shows that the application of this invention has significantly improved the airport's low-altitude security capabilities. The detection rate, identification accuracy, and successful handling rate of illegal targets in the experimental area far exceeded those in the control area, and decision-making and response times were shortened by over 90%. The system's adaptive and closed-loop optimization capabilities ensure efficient and safe performance in complex and changing environments.

[0106] Table 1 Comparison of low-altitude target recognition performance data

[0107]

[0108] Table 2 Comparison of countermeasure effectiveness data

[0109]

[0110] Table 3 Closed-loop optimization and secondary countermeasure data

[0111]

[0112] It can be seen from the data in Tables 1-3 above that after applying the method of the present invention, the experimental area has achieved significant improvements in various key performance indicators. The target recognition time has been shortened from more than 2 minutes in the control area to less than 10 seconds, and it still maintains a high accuracy rate in severe weather. The countermeasure disposal efficiency is extremely high, the average disposal time is only a fraction of that in the control area, and the success rate is stable at around 95%. Its dynamic safety monitoring and termination mechanism effectively ensures airspace safety. More importantly, the data in Table 3 fully demonstrates the unique closed-loop evaluation and intelligent optimization capabilities of the present invention, which enables it to have the "learning and evolution" characteristics that traditional methods do not have at all, and can continuously adapt to new threats and new environments. These data results fully demonstrate the advancement, efficiency and intelligent advantages of the present invention in the field of low-altitude safety protection.

[0113] It should be noted that the formulas appearing above can translate physical quantities of different properties into unitless standard values ​​or superimposable parameters of the same dimension through the principle of dimensional consistency and mathematical standardization means (such as normalization, dimensionless parameter conversion or unit system unification), thereby eliminating the interference of different dimensions on the operation logic, so that the formulas have mathematical operation rationality and objective law adaptability while retaining the distribution characteristics of the original data. It is a conventional technical means and will not be elaborated here. The electrical connection between the above-mentioned units does not necessarily mean a direct connection of the circuit. The indirect connection method can be applied to the embodiments of the present invention as long as the purpose of the present invention is achieved. The above is only an exemplary embodiment of the present invention and the scope of the present invention cannot be limited thereto.

[0114] That is, any equivalent changes and modifications made according to the teachings of the present invention are still within the scope of the present invention. Those skilled in the art will readily conceive of other embodiments of the present invention after considering the disclosure of the specification and practical truths. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary technical means in the art not described herein.

Claims

1. A low-altitude communication, navigation, monitoring, and anti-fusion sensing and control method, characterized in that: The method comprises: Obtaining active position report information from an aircraft and an active detection dataset generated by scanning a preset airspace using multi-source active detection equipment, performing spatiotemporal correlation matching on the active position report information and the active detection dataset to generate a set of targets to be identified; According to the target distribution in the target set to be identified, a high-definition optical detection device is called to track the target, and the pre-acquired real-time meteorological environment data is integrated to enhance the tracking process to generate enhanced target feature data; the method includes: acquiring real-time meteorological environment data, and generating a meteorological correction parameter set according to the real-time meteorological environment data; calling a high-definition optical detection device to extract feature data of the target to be identified in the target set to be identified, and adjusting the feature data of the target to be identified by using the meteorological correction parameter set to obtain enhanced feature data; predicting the motion trajectory of the target to be identified in the target set to be identified to obtain a predicted target trajectory, and compensating the predicted motion trajectory by using the meteorological correction parameter set to generate compensated predicted trajectory data; generating enhanced target feature data based on the enhanced feature data and the compensated predicted trajectory data; Target attribute recognition is performed based on the enhanced target feature data to generate a target attribute recognition result, and when the target attribute recognition result is an illegal target, the real-time meteorological environment data and the preset shootdown area are combined to generate an adaptive counter-decision instruction; which includes: target attribute recognition is performed based on the enhanced target feature data to generate a target attribute recognition result; when the target attribute recognition result is an illegal target, determining whether the illegal target is located in the preset shootdown area; if it is located in the shootdown area, calculating the device power adjustment parameter according to the real-time meteorological environment data; if it is not located in the shootdown area, generating an expulsion path plan by combining the real-time meteorological environment data and the preset sensitive area location information; encapsulating the device power adjustment parameter or the expulsion path plan to generate the adaptive counter-decision instruction; According to the adaptive countermeasure decision instruction, the countermeasure device is driven to perform a countermeasure operation.

2. A low-altitude communication, navigation, monitoring, and anti-fusion sensing and control method according to claim 1, characterized in that: Generating a target set to be identified includes: Obtain active position report information from aircraft and obtain active detection data sets generated by scanning preset airspaces with multi-source active detection equipment; Extracting target motion characteristic parameters from the active detection data set, and extracting legitimate aircraft track parameters from the active position report information; Calculating a correlation score between the motion feature parameter and the track parameter, and generating a matching result based on comparing the correlation score with a preset matching threshold; Based on the matching results, the unmatched active detection targets are aggregated to generate a set of targets to be identified.

3. A low-altitude communication, navigation, monitoring, and anti-fusion sensing and control method according to claim 1, characterized in that: After generating the set of targets to be identified, the method further includes: Calculate and generate a system threat level based on the speed, distance, and cluster density of each target to be identified in the set of targets to be identified; When the system threat level exceeds a preset level threshold, a device parameter adjustment instruction is generated to increase the scanning frequency and sampling rate of the multi-source active detection device.

4. The low-altitude communication, navigation, monitoring, and anti-fusion sensing and control method according to claim 1 is characterized in that: Before calling the high-definition optical detection device, the method further includes: When the real-time meteorological environment data meets a preset deterioration condition, the image sampling frame rate of the high-definition optical detection device is increased and multispectral images are collected to generate a multispectral image sequence; Inputting the multispectral image sequence into a deep learning recognition network to generate a compensated recognition result; The compensated recognition result is used instead of the enhanced target feature data for subsequent target attribute recognition.

5. The low-altitude communication, navigation, monitoring, and anti-fusion sensing and control method according to claim 1 is characterized in that: While performing the countermeasure operation, the method further includes: Dynamically calculating the countermeasure impact range based on the operating parameters of the countermeasure device; Acquire a legitimate target based on the target attribute recognition result, monitor the position of the legitimate target in the airspace in real time, and determine whether it enters the countermeasure influence range; If so, a countermeasure termination instruction is generated and sent to stop the countermeasure operation, and airspace situation warning information is generated.

6. The low-altitude communication, navigation, monitoring, and anti-fusion sensing and control method according to claim 1 is characterized in that: The method further comprises: After executing the countermeasure operation, continuously monitoring the illegal target to generate real-time motion state data, and generating countermeasure effect evaluation data based on the real-time motion state data; Evaluate the countermeasure effect based on the countermeasure effect evaluation data to obtain a countermeasure evaluation value; When the countermeasure evaluation value is less than a preset evaluation threshold, obtaining current real-time meteorological environment data to update the meteorological correction parameter set; Based on the updated meteorological correction parameter set and the real-time motion status data, the countermeasure strategy optimization instruction is updated to perform another countermeasure.

7. A low-altitude communication, navigation, monitoring, and anti-fusion sensing and control method according to claim 6, characterized in that: The updating of the countermeasure strategy optimization instruction to perform countermeasure again includes: Obtain contextual information about historical countermeasure events and build a historical countermeasure case database Constructing a countermeasure effectiveness prediction model based on the historical countermeasure case database; Inputting the updated meteorological correction parameter set into the countermeasure effectiveness prediction model to generate equipment parameter optimization suggestions; Based on the device parameter optimization suggestions, a countermeasure strategy optimization instruction is generated to perform further countermeasures.

8. A low-altitude communication, navigation, monitoring, and anti-fusion sensing and control system, applied to the low-altitude communication, navigation, monitoring, and anti-fusion sensing and control method according to any one of claims 1 to 7, characterized in that: The system comprises: a target acquisition module configured to acquire active position report information from an aircraft and an active detection dataset generated by scanning a preset airspace with multi-source active detection equipment, perform spatiotemporal correlation matching on the active position report information and the active detection dataset, and generate a set of targets to be identified; A feature enhancement module is configured to call a high-definition optical detection device to track a target based on the target distribution in the target set to be identified, and to fuse pre-acquired real-time meteorological environment data to enhance the tracking process and generate enhanced target feature data; the module comprises: acquiring real-time meteorological environment data, and generating a meteorological correction parameter set based on the real-time meteorological environment data; calling a high-definition optical detection device to extract feature data of the target to be identified in the target set to be identified, and adjusting the feature data of the target to be identified using the meteorological correction parameter set to obtain enhanced feature data; predicting the motion trajectory of the target to be identified in the target set to be identified to obtain a predicted target trajectory, and compensating the predicted motion trajectory using the meteorological correction parameter set to generate compensated predicted trajectory data; and generating enhanced target feature data based on the enhanced feature data and the compensated predicted trajectory data. A countermeasure decision module is used to perform target attribute identification based on the enhanced target feature data, generate a target attribute identification result, and when the target attribute identification result is an illegal target, combine the real-time meteorological environment data and the preset shootdown area to generate an adaptive countermeasure decision instruction; including: performing target attribute identification based on the enhanced target feature data to generate a target attribute identification result; when the target attribute identification result is an illegal target, determining whether the illegal target is located in the preset shootdown area; if it is located in the shootdown area, calculating the device power adjustment parameter according to the real-time meteorological environment data; if it is not located in the shootdown area, combining the real-time meteorological environment data with the preset sensitive area location information to generate an expulsion path plan; encapsulating the device power adjustment parameter or the expulsion path plan to generate the adaptive countermeasure decision instruction; The countermeasure execution module is used to drive the countermeasure device to perform the countermeasure operation according to the adaptive countermeasure decision instruction.

Images