An anti-unmanned system based on multimodal detection information fusion and distributed countermeasures

Abstract

This invention relates to the field of anti-unmanned equipment defense technology, and discloses an anti-unmanned system based on multimodal detection information fusion and distributed countermeasures. It includes a multimodal fusion detection module, an intelligent identification module, a collaborative control module, and a hierarchical intelligent countermeasures module. The detection module detects various types of unmanned equipment through multiple detection units and processes the signals from each detection unit using a data fusion algorithm to output accurate target information. The identification module extracts multi-dimensional features of the target, generates identification results by comparing them with a feature library of a full-category unmanned equipment identification model, and outputs a threat level assessment result based on the target's motion parameters. The control module generates countermeasure commands based on the target information and threat level. The countermeasures module selects matching methods from the countermeasures units to execute countermeasure operations according to the commands. This invention achieves accurate detection and hierarchical countermeasures against all types of unmanned equipment, improving system robustness, identification accuracy, and anti-false alarm capabilities.

Description

Technical Field

[0001] This invention relates to the field of anti-unmanned equipment defense technology, and discloses an anti-unmanned system based on multimodal detection information fusion and distributed countermeasures. Background Technology

[0002] With the rapid development and widespread adoption of unmanned equipment technologies such as drones, unmanned vehicles, unmanned ships, and robotic dogs, their applications in military reconnaissance, precision strikes, and illegal intrusion are becoming increasingly frequent, posing a serious threat to the security of critical facilities, field positions, and near-shore areas. Therefore, building a defense system capable of effectively detecting and countering various types of unmanned equipment has become a critical issue that urgently needs to be addressed in the current security field.

[0003] Current ground-based anti-drone systems mainly focus on anti-drone technology, which suffers from limited detection coverage and limited countermeasures.

[0004] Therefore, there is an urgent need for a ground-based anti-unmanned system with a reasonable structural design that can achieve collaborative detection of multiple types of unmanned equipment, hierarchical and classified countermeasures, and flexible deployment, so as to improve the defense capabilities against various types of unmanned equipment in complex environments. Summary of the Invention

[0005] In view of this, this application provides an anti-unmanned system based on multimodal detection information fusion and distributed countermeasures, so as to realize the collaborative detection, hierarchical classification and countermeasures and flexible deployment of various types of unmanned equipment in the air, on the ground and on the water, and improve the defense capability against various types of unmanned equipment in complex environments.

[0006] This application provides an anti-unmanned system based on multimodal detection information fusion and distributed countermeasures, including: The multimodal fusion detection module is configured to detect different types of unmanned equipment in the air, on the ground and on the water through various types of detection units, and to use a full-category data fusion algorithm to filter, calibrate and integrate the detection signals of each detection unit, and output accurate target information. The accurate target information includes at least the position, speed, category and trajectory of the unmanned equipment. The intelligent identification module, connected to the multimodal fusion detection module, is configured to extract multi-dimensional features of unmanned equipment from precise target information and generate multi-dimensional feature vectors based on these features. These multi-dimensional feature vectors are then input into a comprehensive unmanned equipment identification model constructed using a deep learning neural network algorithm. The model is compared with a pre-set comprehensive unmanned equipment feature library to generate identification results, including the category, type, and legitimacy of the unmanned equipment. Finally, based on the identification results, the speed, trajectory, and location of the unmanned equipment, and the intrusion intent determined from the speed, trajectory, and location, the module outputs a corresponding threat level assessment result. The collaborative control module is connected to the multimodal fusion detection module and the intelligent identification module respectively. It is configured to receive accurate target information and threat level assessment results, and generate and output corresponding countermeasure control commands based on the accurate target information and threat level assessment results. The hierarchical intelligent countermeasure module is connected to the collaborative control module and includes multiple pre-configured countermeasure units corresponding to different threat levels. It is configured to receive countermeasure control commands, parse the threat level and unmanned equipment category information contained in the countermeasure control commands, and select the matching countermeasure unit and corresponding countermeasure means from multiple countermeasure units to perform countermeasure operations on the unmanned equipment based on the threat level and unmanned equipment category information.

[0007] Optional, the multimodal fusion detection module includes: The high-sensitivity low-altitude radar unit is configured to use a multi-band low-altitude detection radar to detect unmanned aerial and ground equipment and output the target azimuth information of the unmanned equipment; wherein, the target azimuth information includes at least azimuth angle, elevation angle and range information. The photoelectric infrared detection unit is connected to the high-sensitivity low-altitude radar unit and is configured to integrate a visible light camera and an infrared detector to perform real-time imaging and tracking of unmanned equipment on the ground, water surface and low altitude, and output photoelectric detection signals; wherein, the photoelectric detection signals contain at least the image data of the unmanned equipment and the corresponding tracking data; the photoelectric infrared detection unit is also configured to automatically adjust the focal length and detection angle according to the target azimuth information transmitted by the high-sensitivity low-altitude radar unit. The fiber-optic guided unmanned equipment detection unit is configured to use laser scattering detection technology. It emits a low-power laser beam and captures the fiber optic scattering signals generated by the fiber-optic guided unmanned equipment during operation. Based on the fiber optic scattering signals and combined with a preset fiber optic scattering feature library, it locates and tracks the fiber-optic guided unmanned equipment and outputs fiber optic detection signals. The fiber optic detection signals contain at least the position data of the unmanned equipment and the corresponding tracking data. The autonomous unmanned equipment detection unit is configured to use a combination of artificial intelligence image recognition, acoustic detection, and vibration detection. It captures the operating noise, shape features, movement trajectory, and ground vibration signals of the autonomous unmanned equipment, and identifies and locates the autonomous unmanned equipment based on a preset feature library of all types of autonomous unmanned equipment, and outputs autonomous detection signals. The autonomous detection signals include at least the identification results of the unmanned equipment and the corresponding location data. The surface / nearshore dedicated detection unit is connected to the photoelectric infrared detection unit and is configured to use a combination of ultrasonic and microwave detection. It emits ultrasonic beams and microwave signals and captures the echo signals reflected by the unmanned surface equipment to detect and track the unmanned surface equipment and output the location information of the unmanned surface equipment. The photoelectric infrared detection unit is also configured to image the unmanned equipment on the water surface in response to the received location information of the unmanned equipment.

[0008] Optional, the intelligent recognition module includes: The feature extraction unit is signal-connected to the multimodal fusion detection module and is configured to receive precise target information and extract multi-dimensional features of the unmanned equipment from the precise target information; wherein, the multi-dimensional features include at least shape features, frequency band features, scattering features, acoustic features, vibration features and trajectory features; The artificial intelligence recognition unit is signal-connected to the feature extraction unit and configured to receive multi-dimensional features and generate multi-dimensional feature vectors based on the multi-dimensional features. The multi-dimensional feature vectors are input into a full-category unmanned equipment recognition model constructed by a deep learning neural network algorithm. The full-category unmanned equipment recognition model is compared with a preset full-category unmanned equipment feature library to generate recognition results. The recognition results include at least the category, type, and legality of the unmanned equipment. The threat level assessment unit is connected to the artificial intelligence recognition unit and the multimodal fusion detection module. It is configured to receive the recognition results and precise target information, and output the corresponding threat level assessment results based on the speed, trajectory, and position of the unmanned equipment contained in the recognition results and precise target information, as well as the intrusion intent determined based on the speed, trajectory, and position.

[0009] Optionally, the threat level assessment unit can be configured as follows: Based on the identification results, and combined with the speed, trajectory, and location of the unmanned equipment, the unmanned equipment was classified into low-threat, medium-threat, and high-threat levels; among them, Low threat level corresponds to civilian unmanned equipment whose legitimacy identification result is legitimate and has no intention of intrusion. The medium threat level corresponds to civilian unmanned equipment whose legitimacy identification result is illegal intrusion but no attack behavior; High threat level corresponds to at least one of the following: military unmanned equipment, fiber optic guided unmanned equipment, autonomous attack unmanned equipment, and unmanned equipment clusters.

[0010] Optionally, unmanned equipment includes at least one of drones, unmanned vehicles, unmanned boats, unmanned vessels, and robotic dogs.

[0011] Optional, the layered intelligent countermeasure module includes: The low-threat countermeasure unit is configured to use corresponding deterrence-type countermeasures to counter different categories of legal civilian unmanned equipment that have been determined to be low-threat by the threat level assessment unit. Specifically, it uses a combination of sonic deterrence and light warning for legal civilian drones, a combination of sonic deterrence and vibration warning for legal civilian unmanned vehicles and legal civilian robot dogs, and a combination of sonic deterrence and water surface warning lights for legal civilian unmanned boats and legal civilian unmanned vessels. The medium threat countermeasure unit is configured to use corresponding soft-kill jamming methods to counter different types of illegally intruding civilian unmanned equipment that are identified as medium threats by the threat level assessment unit. Specifically, it uses high-power directional electromagnetic interference technology to cut off the communication and navigation links of illegally intruding civilian drones, uses directional electromagnetic interference technology to paralyze the control systems of illegally intruding civilian unmanned vehicles and illegally intruding civilian robot dogs, and uses a combination of directional microwave interference and surface signal interference to cut off the control links of illegally intruding civilian unmanned boats and illegally intruding civilian unmanned vessels. The high-threat countermeasure unit is configured to employ corresponding hard-kill destruction methods to counter different types of military unmanned equipment identified as high-threat by the threat level assessment unit. Specifically, high-power laser generators are used for targeted destruction of individual military drones, unmanned vehicles, unmanned boats, unmanned surface vessels, robotic dogs, and fiber-optic guided unmanned equipment; high-power microwave generators are used for area destruction of various military unmanned equipment clusters; net capture devices are used for physical capture of close-range military drones, unmanned vehicles, and robotic dogs; surface interception devices are used for interception of military unmanned boats and unmanned surface vessels; and a combination of laser and microwave methods is used to destroy autonomous attack unmanned equipment.

[0012] Optional high-threat countermeasures units include: The laser countermeasure subunit is configured to use a high-power laser generator to target and destroy individual military drones, military unmanned vehicles, military unmanned boats, military unmanned surface vessels, military robot dogs, and fiber-optic guided unmanned equipment. The high-power microwave countermeasure subunit is configured to use a high-power microwave generator to carry out area damage against military unmanned equipment clusters; The net-capture countermeasure subunit is configured to use a net-capture device to physically capture military drones, military unmanned vehicles, and military robot dogs at close range. The surface interception subunit is configured to use a surface interception device to intercept military unmanned ships and military unmanned boats through a combination of physical interception and electromagnetic interference. Among them, the laser countermeasure subunit and the high-power microwave countermeasure subunit are also configured to work together, using a combination of laser and microwave to destroy autonomous attack unmanned equipment.

[0013] Optionally, the anti-unmanned system based on multimodal detection information fusion and distributed countermeasures also includes a power supply module. The power supply module adopts a power supply mode that combines mains power supply, lithium battery power supply and solar charging. It is electrically connected to the multimodal fusion detection module, intelligent identification module, collaborative control module and hierarchical intelligent countermeasures module, and is configured to provide working power to each module.

[0014] Optionally, a mobile deployment module, a multimodal fusion detection module, an intelligent identification module, a collaborative control module, a hierarchical intelligent countermeasure module, and a power supply module are all integrated on the mobile deployment module; The mobile deployment module comes in two forms: a portable bracket and a vehicle-mounted platform. Each module is connected to the mobile deployment module via a quick-plug connection.

[0015] Optionally, the collaborative control module is also configured as follows: Through a full-category collaborative control algorithm, the detection resources of the multi-modal fusion detection module and the countermeasure resources of the hierarchical intelligent countermeasure module are automatically allocated for different categories of unmanned equipment. The system monitors the working status of each module in real time and automatically alarms and switches to the corresponding backup module when a module failure is detected. The human-computer interaction interface displays the type, location, and threat level of unmanned equipment, as well as the working status and countermeasure effects of each module in real time, and supports manual intervention and control by operators. It also automatically stores detection data, identification data, countermeasure data, and system operation data, and supports data export and review analysis.

[0016] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention include at least the following: This invention achieves accurate detection of all types of unmanned aerial vehicles (UAVs), ground unmanned vehicles and robotic dogs, and surface unmanned boats and unmanned vessels by constructing a multimodal fusion detection module containing five detection units. By designing low, medium, and high threat levels and corresponding layered countermeasure units, it configures differentiated deterrence, jamming, and hard-kill methods for different types of unmanned equipment, solving the problems of existing countermeasures being too simplistic and unable to cope with fiber-optic guided and autonomous attack equipment. Through a mobile deployment method combining a portable bracket and a vehicle-mounted platform, and a quick-plug connection structure, it enables flexible adjustment of module configuration according to the protection scenario. Through deep learning neural networks and multi-dimensional feature comparison, it achieves accurate identification of the type, category, and legitimacy of unmanned equipment, effectively avoiding false countermeasures. Through a collaborative control module, it achieves fully automated linkage throughout the process, significantly improving the system's operational efficiency and intelligence level. Other beneficial effects will be described in detail in the specific implementation methods. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0018] Figure 1 A block diagram of an anti-unmanned system provided by the present invention; Figure 2 This is a system block diagram of the multimodal fusion detection module provided by the present invention; Figure 3 This is a system block diagram of the intelligent recognition module provided by the present invention; Figure 4 This is a block diagram of the hierarchical intelligent countermeasure module system provided by the present invention; Figure 5 A flowchart of the anti-unmanned system provided by the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] In this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0021] As can be seen from the above background technology, how to achieve comprehensive and accurate detection of various types of unmanned equipment in the air, on the ground and on the water, and take appropriate countermeasures according to different threat levels, while meeting the needs of flexible deployment in multiple scenarios, is a major technical challenge currently facing ground-based anti-unmanned systems.

[0022] In existing technologies, ground-based anti-unmanned systems mainly focus on the field of anti-drone technology, which suffers from limited detection coverage and difficulty in effectively identifying targets such as unmanned vehicles, robotic dogs, and unmanned surface vessels. Countermeasures are relatively simple and lack a layered countermeasure system for different types and threat levels, making it difficult to effectively deal with fiber-optic guided and autonomous attack unmanned equipment and swarm attacks. The system structure is rigid and lacks modular design, making it difficult to flexibly adjust the allocation of detection and countermeasure resources according to different protection scenarios such as field, near-shore, and fixed facilities.

[0023] Therefore, this application provides an anti-unmanned system based on multimodal detection information fusion and distributed countermeasures, such as... Figure 1 As shown, the system includes a multimodal fusion detection module, an intelligent identification module, a collaborative control module, and a hierarchical intelligent countermeasure module.

[0024] The multimodal fusion detection module detects different types of unmanned equipment in the air, on the ground, and on the water through various types of detection units. It also uses a full-category data fusion algorithm to filter, calibrate, and integrate the detection signals from each detection unit, and outputs accurate target information. This accurate target information includes at least the position, speed, category, and trajectory of the unmanned equipment.

[0025] The intelligent identification module is signal-connected to the multimodal fusion detection module to extract multi-dimensional features of unmanned equipment from precise target information and generate multi-dimensional feature vectors based on these features. The multi-dimensional feature vectors are then input into a full-category unmanned equipment identification model constructed by a deep learning neural network algorithm. This model is compared with a preset full-category unmanned equipment feature library to generate identification results that include the category, type, and legitimacy of the unmanned equipment. Simultaneously, based on the identification results, the speed, trajectory, and location of the unmanned equipment, and the intrusion intent determined based on these parameters, the corresponding threat level assessment results are output.

[0026] The collaborative control module is connected to the multimodal fusion detection module and the intelligent identification module respectively, receives accurate target information and threat level assessment results, and generates and outputs corresponding countermeasure control commands accordingly.

[0027] The hierarchical intelligent countermeasure module is connected to the collaborative control module. It has multiple pre-configured countermeasure units corresponding to different threat levels. After receiving the countermeasure control command, the module analyzes the threat level and unmanned equipment category information contained therein, and selects the matching countermeasure unit and corresponding countermeasure method from multiple countermeasure units to perform countermeasure operations on the unmanned equipment based on this information.

[0028] Furthermore, this solution achieves wide-area coverage detection of all types of unmanned equipment in the air, on land, and on water through a multimodal fusion detection module, solving the problem of limited detection range in existing technologies; the intelligent identification module combines deep learning and multi-dimensional feature comparison to ensure the accuracy of target identification; and the linkage between the collaborative control module and the hierarchical countermeasure module enables intelligent defense that dynamically adjusts countermeasure strategies according to the threat level.

[0029] It should be noted that the full-category data fusion algorithm adopts a well-known data-level fusion method in the field of multi-sensor information fusion, and the specific implementation method will not be described in detail here.

[0030] In some embodiments, such as Figure 2 As shown, the multimodal fusion detection module specifically includes a high-sensitivity low-altitude radar unit, an electro-optical infrared detection unit, a fiber-optic guided unmanned equipment detection unit, an autonomous unmanned equipment detection unit, and a dedicated surface / nearshore detection unit.

[0031] The high-sensitivity low-altitude radar unit employs a multi-band low-altitude detection radar to detect unmanned aerial vehicles (UAVs) in the air and on the ground, and outputs target location information, including at least azimuth, elevation, and range information. The electro-optical infrared detection unit is signal-connected to the high-sensitivity low-altitude radar unit, integrating a visible light camera and an infrared detector. It performs real-time imaging and tracking of ground, water, and low-altitude UAVs, outputting an electro-optical detection signal containing image and tracking data. This unit also automatically adjusts the focal length and detection angle based on the target location information transmitted by the high-sensitivity low-altitude radar unit.

[0032] The fiber-optic guided unmanned equipment detection unit adopts laser scattering detection technology. It emits a low-power laser beam and captures the fiber scattering signals generated during the operation of fiber-optic guided unmanned equipment. Combined with a preset fiber scattering feature library, it locates and tracks the fiber-optic guided unmanned equipment and outputs fiber optic detection signals containing position data and tracking data.

[0033] The autonomous unmanned equipment detection unit adopts a combination of artificial intelligence image recognition, acoustic detection, and vibration detection. It captures the operating noise, shape features, movement trajectory, and ground vibration signals of autonomous unmanned equipment, and identifies and locates the autonomous unmanned equipment based on a preset feature library of all types of autonomous unmanned equipment, outputting an autonomous detection signal containing the identification results and location data.

[0034] The surface / nearshore dedicated detection unit is connected to the photoelectric infrared detection unit and adopts a combination of ultrasonic and microwave detection. It detects and tracks the unmanned surface equipment by emitting ultrasonic beams and microwave signals and capturing the echo signals reflected by the unmanned surface equipment, and outputs the location information of the unmanned surface equipment. The photoelectric infrared detection unit also images the unmanned surface equipment based on the received location information.

[0035] Furthermore, the five detection units mentioned above each perform their own functions and work together: the radar unit is responsible for long-range initial exploration, the photoelectric unit achieves fine imaging confirmation, the fiber optic detection unit fills the gap in the detection of wire-guided targets, the autonomous detection unit solves the problem of detecting targets without radio radiation, the surface-specific unit enhances the ability to perceive targets on water, and the collaborative operation of multiple units enables the system to have accurate detection capabilities in all scenarios.

[0036] In some embodiments, such as Figure 3 As shown, the intelligent identification module includes a feature extraction unit, an artificial intelligence identification unit, and a threat level assessment unit.

[0037] The feature extraction unit is connected to the multimodal fusion detection module to receive accurate target information and extract multi-dimensional features of the unmanned equipment from it. These features include at least shape features, frequency band features, scattering features, acoustic features, vibration features, and trajectory features.

[0038] The artificial intelligence recognition unit is signal-connected to the feature extraction unit, receives multi-dimensional features and generates multi-dimensional feature vectors based on them, and inputs the vectors into a full-category unmanned equipment recognition model constructed by a deep learning neural network algorithm. The model is then compared with a preset full-category unmanned equipment feature library to generate recognition results that include the category, type and legality of the unmanned equipment.

[0039] The threat level assessment unit is connected to the artificial intelligence identification unit and the multimodal fusion detection module, respectively. It receives the identification results and precise target information, and outputs the corresponding threat level assessment results based on the speed, trajectory, position of the unmanned equipment and the intrusion intent determined based on these parameters contained in the identification results and precise target information.

[0040] It should be noted that deep learning neural network algorithms are well-known technologies in the field of target recognition. The model training methods and feature library construction methods can all be implemented using conventional industry methods, and will not be elaborated here.

[0041] Furthermore, the identification module significantly improves the accuracy of identifying various types of unmanned equipment through multi-dimensional feature extraction and deep learning model comparison, and can clearly distinguish between legitimate civilian targets and illegal intrusion targets; the threat level assessment unit integrates the target's identity and behavioral intent, providing a scientific basis for subsequent countermeasure decisions.

[0042] In some embodiments, the threat level assessment unit classifies unmanned equipment into low-threat, medium-threat, and high-threat levels based on the identification results and in conjunction with the speed, trajectory, and location of the unmanned equipment. Specifically, the low-threat level corresponds to civilian unmanned equipment whose legitimacy identification result is legitimate and has no intent to intrude; the medium-threat level corresponds to civilian unmanned equipment whose legitimacy identification result is illegal intrusion but has no offensive behavior; and the high-threat level corresponds to at least one of the following: military unmanned equipment, fiber-optic guided unmanned equipment, autonomous attack unmanned equipment, and unmanned equipment clusters.

[0043] Furthermore, this three-tiered classification method organically combines the target's legal attributes, behavioral characteristics, and military attributes, making threat assessment more objective and accurate, and providing clear execution standards for subsequent countermeasures of varying strengths.

[0044] In some embodiments, unmanned equipment includes at least one of drones, unmanned vehicles, unmanned boats, unmanned vessels, and robotic dogs.

[0045] Furthermore, this broad product range enables the system to adapt to the needs of various protection scenarios, such as field positions, critical facilities, and near-shore waters, truly achieving integrated defense.

[0046] In some embodiments, such as Figure 4 As shown, the hierarchical intelligent countermeasure module includes a low-threat countermeasure unit, a medium-threat countermeasure unit, and a high-threat countermeasure unit.

[0047] The low-threat countermeasure unit employs corresponding deterrence measures to counter different categories of legal civilian unmanned equipment deemed to pose a low threat: for legal civilian drones, a combination of acoustic deterrence and light warning is used; for legal civilian unmanned vehicles and legal civilian robot dogs, a combination of acoustic deterrence and vibration warning is used; and for legal civilian unmanned boats and legal civilian unmanned vessels, a combination of acoustic deterrence and water surface warning lights is used.

[0048] The medium threat countermeasure unit employs corresponding soft-kill jamming methods to counter different types of illegally intruding civilian unmanned equipment identified as medium threats: high-power directional electromagnetic interference is used to cut off the communication and navigation links of illegally intruding civilian drones; directional electromagnetic interference is used to paralyze the control systems of illegally intruding civilian unmanned vehicles and unmanned robots; and a combination of directional microwave interference and surface signal interference is used to cut off the control links of illegally intruding civilian unmanned boats and unmanned surface vessels.

[0049] The high-threat countermeasure unit employs corresponding hard-kill destruction methods to counter different types of military unmanned equipment identified as high-threat: high-power laser generators are used for targeted destruction of individual military drones, unmanned vehicles, unmanned boats, unmanned surface vessels, robotic dogs, and fiber-optic guided unmanned equipment; high-power microwave generators are used for area destruction of various military unmanned equipment clusters; net-capture devices are used for physical capture of close-range military drones, unmanned vehicles, and robotic dogs; surface interception devices are used for interception of military unmanned boats and unmanned surface vessels; and a combination of laser and microwave methods is used to destroy autonomous attack unmanned equipment.

[0050] Furthermore, this layered countermeasure design fully considers the threat level and handling requirements of different targets: low-threat units protect legitimate operational rights with non-destructive expulsion methods, medium-threat units cut off the control links of illegally intruding targets through soft-kill interference, and high-threat units comprehensively utilize a variety of hard-kill methods to effectively deal with high-value targets and cluster attacks. In particular, the laser and microwave combined strike method solves the problem of the difficulty in completely destroying autonomous attack targets.

[0051] In some embodiments, the high-threat countermeasure unit includes a laser countermeasure subunit, a high-power microwave countermeasure subunit, a net-catching countermeasure subunit, and a surface interception subunit.

[0052] The laser countermeasure subunit uses a high-power laser generator to target and destroy individual military drones, unmanned vehicles, unmanned boats, unmanned surface vessels, robotic dogs, and fiber-optic guided unmanned equipment. The high-power microwave countermeasure subunit uses a high-power microwave generator to inflict area damage on clusters of military unmanned equipment.

[0053] The net-capture countermeasure subunit uses a net-capture device to physically capture military drones, military unmanned vehicles, and military robot dogs at close range.

[0054] The surface interception subunit employs surface interception devices, combining physical interception with electromagnetic interference to intercept military unmanned ships and unmanned surface vessels. The laser countermeasure subunit and the high-power microwave countermeasure subunit also work together, using a combined laser and microwave approach to destroy autonomous attack unmanned equipment.

[0055] Furthermore, these four sub-units have clearly defined roles and can work together: the laser sub-unit is responsible for precisely targeting high-value targets, the microwave sub-unit is responsible for wide-area destruction of cluster targets, the net capture sub-unit achieves close-range physical capture to avoid secondary damage, the surface interception sub-unit fills the gap in water defense, and the composite strike mode ensures the complete destruction of the most difficult autonomous attack targets.

[0056] In some embodiments, the system further includes a power supply module, which adopts a power supply mode combining mains power supply, lithium battery power supply and solar charging, and is electrically connected to the multimodal fusion detection module, intelligent identification module, collaborative control module and hierarchical intelligent countermeasure module, respectively, to provide working power for each module.

[0057] Furthermore, this hybrid power supply design allows the system to be deployed long-term in fixed locations with mains power access, as well as to operate continuously in field environments without grid coverage using lithium batteries. The solar charging function further extends the field endurance.

[0058] In some embodiments, the system further includes a mobile deployment module, on which a multimodal fusion detection module, an intelligent identification module, a collaborative control module, a hierarchical intelligent countermeasure module, and a power supply module are all integrated. The mobile deployment module is available in two forms: a portable bracket and a vehicle-mounted platform. Each module is connected to the mobile deployment module via a quick-plug connection.

[0059] Furthermore, this modular integration and rapid assembly / disassembly design enables the system to flexibly configure detection and countermeasure resources according to different protection scenarios such as field positions, important facilities, and near-shore waters, achieving the goal of "deployment on demand and flexible expansion".

[0060] In some embodiments, the collaborative control module is further configured to: automatically allocate detection resources of the multimodal fusion detection module and countermeasure resources of the hierarchical intelligent countermeasure module for different types of unmanned equipment through a full-category collaborative control algorithm; monitor the working status of each module in real time, and automatically alarm and switch to the corresponding backup module when a module failure is detected; display the category, location and threat level of the unmanned equipment, the working status of each module and the countermeasure effect in real time through a human-machine interface, and support manual intervention control by operators; and automatically store detection data, identification data, countermeasure data and system operation data, and support data export and review analysis.

[0061] It should be noted that the full-category collaborative control algorithm is implemented based on well-known technologies in the field of resource scheduling, and the specific algorithm process will not be described in detail here.

[0062] Furthermore, these auxiliary functions enable the system to have intelligent management capabilities: resource scheduling optimizes work efficiency, status monitoring ensures operational reliability, human-computer interaction provides flexible control methods, and data storage and review analysis lay a solid foundation for continuous system optimization.

[0063] Working principle like Figure 5 As shown, the workflow of this system includes five steps: deployment and startup, multimodal detection, intelligent identification and threat assessment, layered countermeasures, and review and optimization, forming a complete automated closed-loop process.

[0064] During the deployment and startup phase, operators use the mobile deployment module to set up the system in the target protection area. Depending on the characteristics of the protection scenario (such as a field environment, near-shore area, or fixed facility), the configuration of the multimodal fusion detection module and the layered intelligent countermeasure module are flexibly adjusted. For example, in near-shore scenarios, dedicated surface / near-shore detection units and surface interception subunits are added; in field scenarios, anti-drone and anti-unmanned vehicle modules are strengthened. After completing the module configuration, the power supply module is activated, the system enters standby mode, and the multimodal fusion detection module begins omnidirectional scanning.

[0065] In the multimodal detection step, the five detection units of the multimodal fusion detection module work collaboratively. The high-sensitivity low-altitude radar unit scans airborne and ground-based unmanned equipment, outputting the target's azimuth, elevation, and distance information; the electro-optical infrared detection unit automatically adjusts the focal length and detection angle based on the target's azimuth information transmitted by the radar, performing real-time imaging and tracking of ground, water, and low-altitude unmanned equipment; the fiber-optic guided unmanned equipment detection unit emits a low-power laser beam to capture fiber optic scattering signals generated during the operation of fiber-optic guided unmanned equipment, and performs positioning and tracking based on a pre-set fiber optic scattering feature library; the autonomous unmanned equipment detection unit captures the operating noise, shape characteristics, movement trajectory, and ground vibration signals of autonomous unmanned equipment, and performs identification and positioning based on a pre-set feature library of autonomous full-category unmanned equipment; the water surface / nearshore dedicated detection unit uses a combination of ultrasonic and microwave detection to detect and track water surface unmanned equipment, and sends the detected position information to the electro-optical infrared detection unit to guide it in imaging water surface targets. The detection signals output by each detection unit are filtered, calibrated and integrated by a full-category data fusion algorithm. After eliminating false signals, the output contains accurate target information including the location, speed, category and trajectory of the unmanned equipment.

[0066] In the intelligent identification and threat assessment step, the intelligent identification module receives precise target information. The feature extraction unit extracts multi-dimensional features of the unmanned equipment from the precise target information, including shape features, frequency band features, scattering features, acoustic features, vibration features, and trajectory features. The artificial intelligence identification unit generates a multi-dimensional feature vector based on the multi-dimensional features and inputs this vector into a full-category unmanned equipment identification model constructed by a deep learning neural network algorithm. The model is compared with a preset full-category unmanned equipment feature library to generate an identification result that includes the category, type, and legitimacy of the unmanned equipment. The threat level assessment unit, based on the identification result and combined with the unmanned equipment speed, trajectory, and location contained in the precise target information, as well as the intrusion intent determined based on these parameters, classifies the unmanned equipment into low-threat, medium-threat, or high-threat levels and outputs the corresponding threat level assessment result.

[0067] In the layered countermeasure step, the collaborative control module receives precise target information and threat level assessment results. Based on this information, it generates and outputs corresponding countermeasure control commands, which include threat level and unmanned equipment category information. After receiving the countermeasure control commands, the layered intelligent countermeasure module analyzes the threat level and unmanned equipment category information, selects a matching countermeasure unit and corresponding countermeasure method from multiple pre-configured countermeasure units, and executes the countermeasure operation. For low-threat targets, the low-threat countermeasure unit is activated. For legitimate civilian drones, a combination of acoustic repulsion and light warning is used; for legitimate civilian unmanned vehicles and robots, a combination of acoustic repulsion and vibration warning is used; and for legitimate civilian unmanned boats and unmanned surface vessels, a combination of acoustic repulsion and surface warning lights is used. For medium-threat targets, the medium-threat countermeasures unit is activated. For illegally intruding civilian drones, high-power directional electromagnetic interference is used to sever their communication and navigation links. For illegally intruding civilian unmanned vehicles and unmanned aerial vehicles (UAVs), directional electromagnetic interference is used to paralyze their control systems. For illegally intruding civilian unmanned ships and UAVs, a combination of directional microwave interference and surface signal jamming is used to sever their control links. For high-threat targets, the high-threat countermeasures unit is activated. For individual military drones, military UAVs, military UAVs, military UAVs, military UAVs, military UAVs, military UAVs, and fiber-optic guided unmanned equipment, laser countermeasures subunits are used for targeted destruction. For clusters of various military unmanned equipment, high-power microwave countermeasures subunits are used for area damage. For close-range military drones, military UAVs, and military UAVs, net-capture countermeasures subunits are used for physical capture. For military UAVs and military UAVs, surface interception subunits are used for physical interception and electromagnetic interference. For autonomous attack UAVs, laser countermeasures subunits and high-power microwave countermeasures subunits work in tandem, using a combined laser and microwave approach for destruction. During the countermeasure execution process, the multimodal fusion detection module continuously tracks the target and feeds back the countermeasure effect to the collaborative control module in real time.

[0068] During the review and optimization phase, the system automatically stores detection, identification, countermeasure, and system operation data from the entire defense process. Operators can retrieve historical data through the human-machine interface for review and analysis, studying the attack characteristics and countermeasure effects of different types of unmanned equipment, and optimizing identification model parameters and countermeasure strategies accordingly. If the target is not completely countered, the system automatically returns to the multimodal detection phase to continue tracking and countermeasures until the target is successfully driven away or destroyed, forming a complete closed-loop workflow.

[0069] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0070] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A counter-unmanned system based on multimodal detection information fusion and distributed countermeasures, characterized in that, include: The multimodal fusion detection module is configured to detect different types of unmanned equipment in the air, on the ground and on the water through multiple types of detection units, and to use a full-category data fusion algorithm to filter, calibrate and integrate the detection signals of each detection unit to output accurate target information. The accurate target information includes at least the position, speed, category and trajectory of the unmanned equipment. The intelligent identification module, signal-connected to the multimodal fusion detection module, is configured to extract multi-dimensional features of the unmanned equipment from the precise target information and generate a multi-dimensional feature vector based on these features. The multi-dimensional feature vector is then input into a full-category unmanned equipment identification model constructed using a deep learning neural network algorithm. This model is compared with a preset full-category unmanned equipment feature library to generate an identification result, which includes the category, type, and legality of the unmanned equipment. Finally, based on the identification result, the speed, trajectory, and position of the unmanned equipment, and the intrusion intent determined based on the speed, trajectory, and position, a corresponding threat level assessment result is output. The collaborative control module is connected to the multimodal fusion detection module and the intelligent identification module respectively, and is configured to receive the precise target information and the threat level assessment result, and generate and output the corresponding countermeasure control command based on the precise target information and the threat level assessment result; The hierarchical intelligent countermeasure module is signal-connected to the collaborative control module and includes multiple pre-configured countermeasure units corresponding to different threat levels. It is configured to receive the countermeasure control command, parse the threat level and unmanned equipment category information contained in the countermeasure control command, and select a matching countermeasure unit and corresponding countermeasure means from the multiple countermeasure units to perform countermeasure operations on the unmanned equipment according to the threat level and unmanned equipment category information. The multimodal fusion detection module includes: The high-sensitivity low-altitude radar unit is configured to use a multi-band low-altitude detection radar to detect unmanned aerial and ground equipment and output the target azimuth information of the unmanned equipment; wherein the target azimuth information includes at least azimuth angle, elevation angle and range information. The photoelectric infrared detection unit is connected to the high-sensitivity low-altitude radar unit and is configured to integrate a visible light camera and an infrared detector to perform real-time imaging and tracking of unmanned equipment on the ground, water surface, and low altitude, and output photoelectric detection signals; wherein, the photoelectric detection signals include at least the image data of the unmanned equipment and the corresponding tracking data; the photoelectric infrared detection unit is also configured to automatically adjust the focal length and detection angle according to the target azimuth information transmitted by the high-sensitivity low-altitude radar unit. The fiber-optic guided unmanned equipment detection unit is configured to use laser scattering detection technology. It emits a low-power laser beam and captures the fiber optic scattering signals generated by the fiber-optic guided unmanned equipment during operation. Based on the fiber optic scattering signals and combined with a preset fiber optic scattering feature library, it locates and tracks the fiber-optic guided unmanned equipment and outputs fiber optic detection signals. The fiber optic detection signals contain at least the position data of the unmanned equipment and the corresponding tracking data. The autonomous unmanned equipment detection unit is configured to combine artificial intelligence image recognition with acoustic and vibration detection. By capturing the operating noise, shape features, movement trajectory, and ground vibration signals of the autonomous unmanned equipment, and based on a preset feature library of all types of autonomous unmanned equipment, it identifies and locates the autonomous unmanned equipment and outputs an autonomous detection signal. The autonomous detection signal includes at least the identification result of the unmanned equipment and the corresponding location data. A dedicated surface / nearshore detection unit is connected to the photoelectric infrared detection unit and configured to use a combination of ultrasonic and microwave detection. It emits ultrasonic beams and microwave signals and captures the echo signals reflected by the unmanned surface equipment to detect and track the unmanned surface equipment and output the location information of the unmanned surface equipment. The photoelectric infrared detection unit is also configured to image the unmanned equipment on the water surface in response to the received location information of the unmanned equipment. The hierarchical intelligent countermeasure module includes: The low-threat countermeasure unit is configured to perform countermeasure operations by employing corresponding drive-away countermeasures on different categories of legal civilian unmanned equipment that are determined to be low-threat by the intelligent identification module. Specifically, it employs a combination of acoustic drive-away and light warning for legal civilian drones, a combination of acoustic drive-away and vibration warning for legal civilian unmanned vehicles and legal civilian robot dogs, and a combination of acoustic drive-away and water surface warning lights for legal civilian unmanned boats and legal civilian unmanned vessels. The medium threat countermeasure unit is configured to perform countermeasures against different types of illegally intruding civilian unmanned equipment identified as medium threats by the intelligent identification module, using corresponding soft-kill jamming methods. Specifically, it uses high-power directional electromagnetic interference technology to cut off the communication and navigation links of illegally intruding civilian drones, uses directional electromagnetic interference technology to paralyze the control systems of illegally intruding civilian unmanned vehicles and illegally intruding civilian robot dogs, and uses a combination of directional microwave interference and surface signal interference to cut off the control links of illegally intruding civilian unmanned boats and illegally intruding civilian unmanned vessels. The high-threat countermeasure unit is configured to perform countermeasures against different types of military unmanned equipment identified as high threats by the intelligent identification module, using corresponding hard-kill destruction methods. Specifically, it uses a high-power laser generator for targeted destruction of individual military drones, military unmanned vehicles, military unmanned boats, military unmanned surface vessels, military robot dogs, and fiber-optic guided unmanned equipment; it uses a high-power microwave generator for area destruction of various military unmanned equipment clusters; it uses a net capture device for physical capture of close-range military drones, military unmanned vehicles, and military robot dogs; it uses a surface interception device for interception of military unmanned boats and military unmanned surface vessels; and it uses a combination of laser and microwave methods to destroy autonomous attack unmanned equipment.

2. The anti-unmanned system based on multimodal detection information fusion and distributed countermeasures according to claim 1, characterized in that, The intelligent recognition module includes: The feature extraction unit is signal-connected to the multimodal fusion detection module and configured to receive the precise target information and extract multi-dimensional features of the unmanned equipment from the precise target information; wherein, the multi-dimensional features include at least shape features, frequency band features, scattering features, acoustic features, vibration features and trajectory features; An artificial intelligence recognition unit, signal-connected to the feature extraction unit, is configured to receive the multi-dimensional features and generate a multi-dimensional feature vector based on the multi-dimensional features; input the multi-dimensional feature vector into a full-category unmanned equipment recognition model constructed by a deep learning neural network algorithm; compare the full-category unmanned equipment recognition model with a preset full-category unmanned equipment feature library to generate a recognition result; wherein, the recognition result includes at least the category, type, and legality of the unmanned equipment; The threat level assessment unit is signal-connected to the artificial intelligence recognition unit and the multimodal fusion detection module, respectively. It is configured to receive the recognition result and the precise target information, and output the corresponding threat level assessment result based on the speed, trajectory, and position of the unmanned equipment contained in the recognition result and the precise target information, as well as the intrusion intent determined based on the speed, trajectory, and position.

3. The anti-unmanned system based on multimodal detection information fusion and distributed countermeasures according to claim 2, characterized in that, The threat level assessment unit is specifically configured as follows: Based on the identification results, and combined with the speed, trajectory, and location of the unmanned equipment, the unmanned equipment is classified into low-threat, medium-threat, and high-threat levels; among which, The low threat level corresponds to a legality identification result of a legitimate civilian unmanned equipment with no intent to intrude. The threat level mentioned above corresponds to civilian unmanned equipment whose legitimacy identification result is illegal intrusion but no attack behavior; The high threat level corresponds to at least one of the following: military unmanned equipment, fiber-optic guided unmanned equipment, autonomous attack unmanned equipment, and unmanned equipment clusters.

4. The anti-unmanned system based on multimodal detection information fusion and distributed countermeasures according to claim 3, characterized in that, The unmanned equipment includes at least one of the following: drones, unmanned vehicles, unmanned boats, unmanned vessels, and robotic dogs.

5. The anti-unmanned system based on multimodal detection information fusion and distributed countermeasures according to claim 4, characterized in that, The high-threat countermeasures unit includes: The laser countermeasure subunit is configured to use a high-power laser generator to target and destroy individual military drones, military unmanned vehicles, military unmanned boats, military unmanned surface vessels, military robot dogs, and fiber-optic guided unmanned equipment. The high-power microwave countermeasure subunit is configured to use a high-power microwave generator to carry out area damage against military unmanned equipment clusters; The net-capture countermeasure subunit is configured to use a net-capture device to physically capture military drones, military unmanned vehicles, and military robot dogs at close range. The surface interception subunit is configured to use a surface interception device to intercept military unmanned ships and military unmanned boats through a combination of physical interception and electromagnetic interference. The laser countermeasure subunit and the high-power microwave countermeasure subunit are configured to work together, using a combination of laser and microwave to destroy autonomous attack unmanned equipment.

6. The anti-unmanned system based on multimodal detection information fusion and distributed countermeasures according to claim 1, characterized in that, Also includes: The power supply module adopts a power supply mode that combines mains power supply, lithium battery power supply and solar charging. It is electrically connected to the multimodal fusion detection module, the intelligent identification module, the collaborative control module and the hierarchical intelligent countermeasure module, respectively, and is configured to provide working power to each module.

7. The anti-unmanned system based on multimodal detection information fusion and distributed countermeasures according to claim 6, characterized in that, It also includes a mobile deployment module, on which the multimodal fusion detection module, the intelligent identification module, the collaborative control module, the hierarchical intelligent countermeasure module, and the power supply module are all integrated; The mobile deployment module includes two forms: a portable bracket and a vehicle-mounted platform. Each module is connected to the mobile deployment module via a quick-plug connection.

8. The anti-unmanned system based on multimodal detection information fusion and distributed countermeasures according to claim 1, characterized in that, The collaborative control module is also configured to: Through a full-category collaborative control algorithm, the detection resources of the multimodal fusion detection module and the countermeasure resources of the hierarchical intelligent countermeasure module are automatically allocated for different categories of unmanned equipment. The system monitors the working status of each module in real time and automatically alarms and switches to the corresponding backup module when a module failure is detected. The human-computer interaction interface displays in real time the type, location, threat level, working status of each module, and countermeasure effects of the unmanned equipment, and supports manual intervention and control by operators. It also automatically stores detection data, identification data, countermeasure data, and system operation data, and supports data export and review analysis.

Images