Short-wave infrared-based multi-modal anti-drone detection method and device and medium

Abstract

The embodiment of the specification provides a multi-modal anti-unmanned aerial vehicle detection method and device based on short-wave infrared, equipment and medium, comprising: acquiring external environment information, performing real-time image quality evaluation on a visible light image and a short-wave infrared image of a detection airspace; according to the environment information and the image quality evaluation result, dynamically selecting an optimal imaging spectral combination and a working mode according to a preset decision rule; performing unmanned aerial vehicle target detection according to the selected working mode, collecting corresponding detection images, performing image processing and signal processing on the collected detection images, identifying the unmanned aerial vehicle target, and positioning and continuously tracking the identified unmanned aerial vehicle target; displaying and outputting the tracking result of the unmanned aerial vehicle target, and dynamically switching the working mode according to the real-time image quality evaluation result in the target tracking process, so as to ensure continuous and stable imaging of the unmanned aerial vehicle target, thereby solving the problem of balancing cost, service life, detection distance and all-weather adaptability of photoelectric detection.

Description

Technical Field

[0001] This invention relates to the field of photoelectric detection and imaging technology, and in particular to a multimodal anti-UAV detection method, device, equipment and medium based on shortwave infrared. Background Technology

[0002] With the rapid development and popularization of drone technology, low-altitude, slow-moving, and small drones have been widely used in civilian aerial photography, logistics delivery, and agricultural plant protection. However, their illegal flights and misuse in sensitive areas such as airport airspace, important facilities, and border patrols have also brought increasingly serious security threats. Therefore, how to achieve long-range, all-weather, and highly reliable detection and identification of low-altitude, slow-moving, and small drone targets has become an urgent technical problem to be solved in the field of counter-drone systems.

[0003] To address these needs, various photoelectric detection solutions have been developed. One is the visible light imaging solution, which offers advantages such as high resolution, rich detail, and low cost under clear daytime conditions, enabling precise identification of drones. The second is the long-wave infrared uncooled imaging solution, which achieves imaging at night and in low-light conditions by detecting the temperature difference between the target and the background, with relatively low system cost. The third is the mid-wave infrared cooled imaging solution, which uses a cooled detector and exhibits excellent performance in terms of detection range, sensitivity, and small target detection, enabling long-range drone detection.

[0004] However, all of the aforementioned existing solutions have significant technical drawbacks. Visible light solutions are highly dependent on natural lighting, and their contrast drops sharply at night, in fog, haze, backlight, and complex background conditions, making stable detection difficult. Long-wave infrared uncooled solutions are limited by detector noise and atmospheric transmission characteristics, resulting in limited spatial resolution and detection range, and insufficient long-range detection capability for small, thermally weak UAV targets. While mid-wave infrared cooled solutions offer excellent performance, their reliance on cryogenic refrigerators leads to high system costs, large size, high power consumption, limited lifespan, and complex maintenance, making them unsuitable for large-scale, long-term, distributed deployment engineering applications. Furthermore, existing solutions mostly use single sensors or simple parallel combinations, lacking adaptive mechanisms for changes in day / night cycles and environmental conditions, and cannot automatically switch to the optimal imaging mode in different scenarios.

[0005] Therefore, there is an urgent need for a multimodal anti-drone detection method based on shortwave infrared to solve the technical problem of achieving a balance between cost, lifespan, detection range and all-weather adaptability in photoelectric detection. Summary of the Invention

[0006] To overcome the problems existing in related technologies, this disclosure provides a multimodal anti-UAV detection method based on shortwave infrared, so as to solve the technical problem of achieving a balance between cost, lifespan, detection range and all-weather adaptability in photoelectric detection.

[0007] This specification provides one or more embodiments of a multimodal anti-UAV detection method based on shortwave infrared, including the following steps: Acquire external environmental information, including brightness information, time information and meteorological parameters, and perform real-time image quality evaluation on visible light images and shortwave infrared images of the probe airspace, including sharpness, contrast and signal-to-noise ratio evaluation. Based on environmental information and image quality evaluation results, the optimal imaging spectrum combination and working mode are dynamically selected according to preset decision rules. The working modes include daytime visible light mode, shortwave infrared passive imaging mode, and nighttime active shortwave infrared mode. Perform UAV target detection according to the selected working mode, collect corresponding detection images, perform image processing and signal processing on the collected detection images, identify UAV targets, and locate and continuously track the identified UAV targets. The tracking results of the UAV target are displayed and output. During the target tracking process, the working mode is dynamically switched according to the real-time image quality evaluation results to ensure continuous and stable imaging of the UAV target.

[0008] Preferably, the triggering condition for the daytime visible light mode is: When the ambient brightness is higher than the preset brightness threshold and the real-time image quality evaluation result of the visible light image meets the preset sharpness requirements, the daytime visible light mode is triggered. Upon triggering, visible light imaging is enabled for drone detection, while short-wave infrared active illumination is disabled.

[0009] Preferably, the triggering condition for the shortwave infrared passive imaging mode is: When the environment is detected to be foggy, backlit, or the background of the drone target is a complex background such as forest / mountain, and the contrast of the visible light image is lower than the preset contrast threshold, the short-wave infrared passive imaging mode is triggered. Upon triggering, shortwave infrared passive imaging is enabled for drone detection, while visible light imaging and shortwave infrared active illumination are disabled.

[0010] Preferably, the triggering condition for the nighttime active shortwave infrared mode is: When the ambient light is lower than the preset nighttime brightness threshold or the system is in a preset nighttime period, the nighttime active shortwave infrared mode is triggered. Upon triggering, the drone will use a combination of short-wave infrared imaging and active short-wave infrared illumination for detection, while the visible light imaging function will be disabled.

[0011] Preferably, the preset decision rule is a weighted algorithm, which configures weight coefficients for ambient brightness, image contrast, and meteorological parameters, and determines the optimal working mode based on the weighted calculation results.

[0012] This specification provides one or more embodiments of a multimodal anti-drone detection device based on shortwave infrared, comprising: The data collection module is used to acquire external environmental information, including brightness information, time information and meteorological parameters, and to perform real-time image quality evaluation on visible light images and shortwave infrared images of the detection airspace. The real-time image quality evaluation includes sharpness, contrast and signal-to-noise ratio evaluation. The mode selection module is used to dynamically select the optimal imaging spectrum combination and working mode according to the environmental information and image quality evaluation results and a preset decision rule. The working modes include daytime visible light mode, shortwave infrared passive imaging mode, and nighttime active shortwave infrared mode. The target localization module is used to perform UAV target detection according to the selected working mode, acquire corresponding detection images, perform image processing and signal processing on the acquired detection images, identify UAV targets, and locate and continuously track the identified UAV targets. The display and control module is used to display and output the tracking results of the UAV target. During the target tracking process, the working mode is dynamically switched according to the real-time image quality evaluation results to ensure continuous and stable imaging of the UAV target.

[0013] Preferably, the triggering condition for the daytime visible light mode is: When the ambient brightness is higher than the preset brightness threshold and the real-time image quality evaluation result of the visible light image meets the preset sharpness requirements, the daytime visible light mode is triggered. Upon triggering, visible light imaging is enabled for drone detection, while short-wave infrared active illumination is disabled.

[0014] Preferably, the triggering condition for the shortwave infrared passive imaging mode is: When the environment is detected to be foggy, backlit, or the background of the drone target is a complex background such as forest / mountain, and the contrast of the visible light image is lower than the preset contrast threshold, the short-wave infrared passive imaging mode is triggered. Upon triggering, shortwave infrared passive imaging is enabled for drone detection, while visible light imaging and shortwave infrared active illumination are disabled.

[0015] This specification provides one or more embodiments of a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the multimodal anti-drone detection method based on shortwave infrared as described above.

[0016] This specification provides one or more embodiments of a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the multimodal anti-UAV detection method based on shortwave infrared described above.

[0017] This disclosure provides a multimodal anti-drone detection method, apparatus, and medium based on shortwave infrared. Its advantages lie in its ability to comprehensively perceive ambient light, weather conditions, and current imaging quality by acquiring external brightness, time, and meteorological parameters, combined with real-time evaluation of the clarity, contrast, and signal-to-noise ratio of visible light and shortwave infrared images. This provides accurate and multi-dimensional input for intelligent decision-making regarding subsequent operating modes, avoiding misjudgments caused by relying on a single sensor. Based on environmental information and image quality evaluation results, the system dynamically selects the optimal imaging spectral combination and operating mode according to preset decision rules, achieving automatic switching between visible light and shortwave infrared passive imaging and active nighttime illumination modes. This enables the system to operate effectively in various scenarios, including day and night, fog and haze, backlighting, and complex backgrounds. It always operates in the optimal detection mode, significantly improving all-weather adaptability and target detection reliability; it performs target detection and acquires corresponding images according to the selected working mode, identifies UAV targets through image processing and signal processing, and then achieves positioning and continuous tracking. It can make full use of high-quality image information in the current optimal spectral mode, combined with AI recognition algorithms, to effectively improve the detection probability and tracking accuracy of long-distance and small targets; it displays and outputs the tracking results in real time, and dynamically switches the working mode according to the image quality evaluation results during the tracking process. It can adaptively cope with the decline in imaging quality caused by sudden environmental changes or changes in target attitude, ensure continuous and stable imaging of UAV targets, avoid target loss, and enhance the robustness of the system in complex dynamic environments. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a multimodal anti-UAV detection method based on shortwave infrared provided for one or more embodiments of this specification; Figure 2 A schematic diagram of the structure of a multimodal anti-UAV photoelectric detection system provided in one or more embodiments of this specification; Figure 3 A flowchart illustrating the multimodal operating mode switching process provided in one or more embodiments of this specification; Figure 4 A schematic diagram of a multi-modal anti-UAV detection device based on shortwave infrared provided for one or more embodiments of this specification; Figure 5 This is a schematic diagram of the structure of a computer provided for one or more embodiments of this specification. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this invention.

[0021] The present invention will now be described in detail with reference to specific embodiments and accompanying drawings.

[0022] Method Implementation Examples According to embodiments of the present invention, a multimodal anti-UAV detection method based on shortwave infrared + visible light + shortwave infrared supplementary illumination is provided, such as... Figure 1 The diagram shown is a flowchart of a multimodal anti-drone detection method based on shortwave infrared provided in this embodiment. It is applied to a multimodal anti-drone photoelectric detection system, realizing multimodal collaborative design and working mode switching. The system includes a visible light imaging unit, a shortwave infrared imaging unit, a shortwave infrared supplementary lighting unit, an image processing module, a signal processing module, a day / night and environmental condition adaptive working mechanism module, and an AI recognition and tracking module. Each imaging unit is installed on the same turntable or stable platform, and the detection, recognition, and tracking effects are displayed and controlled through a display and control platform. Figure 2 The diagram shown is a schematic representation of the multimodal anti-drone photoelectric detection system provided in this embodiment. The multimodal anti-drone detection method based on shortwave infrared according to this embodiment includes the following steps: S110. External environmental information is acquired through the intelligent sensing and control module. The environmental information includes brightness information, time information, and meteorological parameters. The image processing module is used to perform real-time image quality evaluation on the visible light image and shortwave infrared image of the probe airspace. The real-time image quality evaluation includes sharpness, contrast, and signal-to-noise ratio evaluation.

[0023] S120: The intelligent sensing and control module dynamically selects the optimal imaging spectral combination and working mode based on environmental information and image quality evaluation results, according to a preset decision rule or weighting algorithm. The preset decision rule is a weighting algorithm, which configures weighting coefficients for ambient brightness, image contrast, and meteorological parameters, and determines the optimal working mode based on the weighted calculation results. The working modes include daytime visible light mode, shortwave infrared passive imaging mode, and nighttime active shortwave infrared mode.

[0024] The triggering conditions for daytime visible light mode are: When the ambient brightness is higher than the preset brightness threshold and the real-time image quality evaluation result of the visible light image meets the preset sharpness requirements, the daytime visible light mode is triggered, and visible light imaging is enabled to perform drone detection, while the shortwave infrared active supplementary lighting function is turned off.

[0025] The triggering condition for shortwave infrared passive imaging mode is: When the environment is detected to be foggy, backlit, or the background of the drone target is a complex background such as forest / mountain, and the contrast of the visible light image is lower than the preset contrast threshold, the short-wave infrared passive imaging mode is triggered; after triggering, short-wave infrared passive imaging is enabled to perform drone detection, and visible light imaging and short-wave infrared active supplementary lighting functions are turned off.

[0026] The triggering conditions for the nighttime active shortwave infrared mode are: When the ambient brightness is lower than the preset nighttime brightness threshold or the system is in a preset nighttime period, the active shortwave infrared mode is triggered. After triggering, the drone detection is performed by combining shortwave infrared imaging with active shortwave infrared illumination, and the visible light imaging function is turned off.

[0027] The short-wave infrared band (0.9–1.7 μm) lies between visible and mid-wave infrared, possessing both good atmospheric transmittance and sensitivity to target reflection characteristics. Compared to passive thermal imaging in the mid-wave and long-wave infrared bands, this adaptive working mechanism fully leverages the advantages of visible light, short-wave infrared passive imaging, and short-wave infrared active supplementary lighting under different time periods and environmental conditions, achieving all-weather, highly reliable anti-drone detection.

[0028] S130. Perform UAV target detection according to the selected working mode, collect corresponding detection images, perform image processing and signal processing on the collected detection images, identify UAV targets, and locate and continuously track the identified UAV targets.

[0029] S140. Display and output the tracking results of the UAV target. During the target tracking process, the system dynamically switches the working mode according to the real-time image quality evaluation results to ensure continuous and stable imaging of the UAV target.

[0030] like Figure 3The diagram shown is a flowchart of the multimodal working mode switching provided in this embodiment.

[0031] Step 1: Start the system After the system is powered on, it initializes each imaging unit, sensor and processing module and enters the working preparation state.

[0032] Step 2: Environmental Detection and Image Analysis The system acquires ambient brightness information, time information, and meteorological parameters, and simultaneously performs real-time quality evaluation on visible light and shortwave infrared images of the probed airspace. Evaluation indicators include sharpness, contrast, and signal-to-noise ratio.

[0033] Step 3: Determine if it is a complex environment or severe weather. Based on environmental detection and image analysis results, the system determines whether the current environment is complex (such as forest, mountain background, backlight) or severe weather (such as fog and haze).

[0034] If so, then enter shortwave infrared mode (i.e., shortwave infrared passive imaging mode). If not, then enter visible light mode.

[0035] Step 4: Determine if it is nighttime After entering shortwave infrared mode, the system further determines whether it is nighttime: If it is nighttime, switch to shortwave infrared + supplementary light mode (i.e., nighttime active shortwave infrared mode). If it is not nighttime, then maintain shortwave infrared mode.

[0036] After entering visible light mode, the system also determines whether it is currently nighttime: If it is nighttime, switch to shortwave infrared + supplementary light mode; If it is not nighttime, then maintain visible light mode.

[0037] Step 5: AI Recognition and Tracking Function The system uses the AI ​​recognition and tracking module to detect, recognize, and track drone targets in images acquired under the selected working mode.

[0038] Step 6: Servo Control Based on the recognition and tracking results, control the turntable or stabilizing platform to adjust its attitude so that the target is always in the center of the imaging field of view.

[0039] Step 7: Start tracing The system initiates continuous tracking of the UAV target and dynamically switches working modes based on real-time image quality evaluation results during the tracking process to ensure continuous and stable imaging of the target.

[0040] The system senses the external environment and collects environmental information, including ambient brightness, time, and weather information, using a multispectral camera. Image quality evaluation parameters, such as sharpness, contrast, and signal-to-noise ratio, are selected to perform real-time image quality assessment. Brightness information is used to distinguish between day and night, while image sharpness, contrast, and signal-to-noise ratio are used to determine complex weather and environmental conditions, such as fog and backlighting. By integrating environmental information and evaluation function values, different environmental, temporal, and weather conditions are classified in real-time according to a pre-defined judgment scheme. Based on the acquired environmental information and image quality assessment results, the system dynamically evaluates the current environmental conditions and selects the optimal spectral combination and operating mode according to preset decision rules. The device's operating modes include daytime visible light mode, shortwave infrared passive imaging mode, and nighttime active shortwave infrared imaging mode. Daytime visible light mode is suitable for good lighting and environmental conditions; shortwave infrared passive imaging mode is suitable for good lighting, inclement weather, and complex environmental conditions; and nighttime active shortwave infrared imaging mode is suitable for low brightness, inclement weather, and complex environmental conditions. This closed-loop environmental perception and quality assessment system enables dynamic adaptation of the camera's operating mode to the external environment, ensuring image quality without manual intervention. The drone detection and tracking is performed according to the selected working mode. The camera captures images of the drone in flight as input, and a deep learning target detection algorithm is used to build a model to identify the drone in the images and drive a servo to achieve drone tracking. During the drone's flight, images are continuously processed to ensure recognition stability, achieving continuous target identification, localization, and tracking. The host computer software outputs the drone identification and tracking results, while the image quality evaluation system is converted into a dynamic working mode. Based on real-time visible light and short-wave infrared imaging results, the working mode of the multispectral camera is dynamically adjusted to ensure continuous and stable imaging, identification, and tracking. Environmental perception is combined with AI algorithms to achieve accurate target identification and stable tracking in complex environments, improving the camera's dynamic application capabilities.

[0041] The method provided in this embodiment acquires external brightness, time, and meteorological parameters, and combines this with real-time evaluation of the clarity, contrast, and signal-to-noise ratio of visible light and shortwave infrared images. This allows for a comprehensive perception of ambient light, weather conditions, and current imaging quality, providing accurate and multi-dimensional input for intelligent decision-making in subsequent operating modes, avoiding misjudgments caused by relying on a single sensor. Based on environmental information and image quality evaluation results, the optimal imaging spectrum combination and operating mode are dynamically selected according to preset decision rules. This enables automatic switching between passive imaging in visible light and shortwave infrared and active nighttime illumination modes, ensuring the system always operates in the best detection mode under various scenarios such as day and night, fog and haze, backlighting, and complex backgrounds, significantly improving performance. All-weather adaptability and target detection reliability; it performs target detection and acquires corresponding images according to the selected working mode, identifies UAV targets through image processing and signal processing, and then achieves positioning and continuous tracking. It can make full use of high-quality image information in the current optimal spectral mode, combined with AI recognition algorithms, to effectively improve the detection probability and tracking accuracy of long-distance and small targets; it displays and outputs tracking results in real time, and dynamically switches working modes according to image quality evaluation results during the tracking process. It can adaptively cope with the decline in imaging quality caused by sudden environmental changes or changes in target attitude, ensure continuous and stable imaging of UAV targets, avoid target loss, and enhance the robustness of the system in complex dynamic environments.

[0042] Device Examples According to embodiments of the present invention, a multi-modal anti-drone detection device based on shortwave infrared is provided, such as... Figure 4 The diagram shown is a structural diagram of the multi-modal anti-drone detection device based on shortwave infrared provided in this embodiment. According to this embodiment of the invention, the multi-modal anti-drone detection device based on shortwave infrared includes: The data collection module 41 is used to acquire external environmental information, including brightness information, time information and meteorological parameters, and to perform real-time image quality evaluation on visible light images and shortwave infrared images of the detection airspace. The real-time image quality evaluation includes sharpness, contrast and signal-to-noise ratio evaluation.

[0043] The mode selection module 42 is used to dynamically select the optimal imaging spectrum combination and working mode according to the environmental information and image quality evaluation results and the preset decision rules. The working modes include daytime visible light mode, shortwave infrared passive imaging mode, and nighttime active shortwave infrared mode.

[0044] The triggering conditions for daytime visible light mode are: When the ambient brightness is higher than the preset brightness threshold and the real-time image quality evaluation result of the visible light image meets the preset sharpness requirements, the daytime visible light mode is triggered; after triggering, visible light imaging is enabled to perform drone detection, and the short-wave infrared active supplementary lighting function is turned off.

[0045] The triggering condition for shortwave infrared passive imaging mode is: When the environment is detected to be foggy, backlit, or the background of the drone target is a complex background such as forest / mountain, and the contrast of the visible light image is lower than the preset contrast threshold, the short-wave infrared passive imaging mode is triggered; after triggering, short-wave infrared passive imaging is enabled to perform drone detection, and visible light imaging and short-wave infrared active supplementary lighting functions are turned off.

[0046] The target localization module 43 is used to perform UAV target detection according to the selected working mode, acquire corresponding detection images, perform image processing and signal processing on the acquired detection images, identify UAV targets, and locate and continuously track the identified UAV targets.

[0047] The display and control module 44 is used to display and output the tracking results of the UAV target. During the target tracking process, the working mode is dynamically switched according to the real-time image quality evaluation results to ensure continuous and stable imaging of the UAV target.

[0048] The device provided in this embodiment acquires external brightness, time, and meteorological parameters through the data collection module 41, and evaluates the clarity, contrast, and signal-to-noise ratio of visible light and short-wave infrared images in real time. This allows for a comprehensive perception of ambient light, weather conditions, and current imaging quality, providing accurate and multi-dimensional input for intelligent decision-making in subsequent operating modes, avoiding misjudgments caused by relying on a single sensor. The mode selection module 42 dynamically selects the optimal imaging spectrum combination and operating mode according to preset decision rules based on environmental information and image quality evaluation results. This enables automatic switching between visible light and short-wave infrared passive imaging and active nighttime illumination modes, ensuring the system always operates in the best detection mode under various scenarios such as day and night, fog and haze, backlighting, and complex backgrounds, significantly improving performance. The system enhances all-weather adaptability and target detection reliability. The target localization module 43 performs target detection and acquires corresponding images according to the selected working mode. It identifies UAV targets through image processing and signal processing, thereby achieving localization and continuous tracking. It can make full use of high-quality image information in the current optimal spectral mode and combine AI recognition algorithms to effectively improve the detection probability and tracking accuracy of long-distance and small targets. The display and control module 44 displays and outputs the tracking results in real time and dynamically switches the working mode according to the image quality evaluation results during the tracking process. It can adaptively cope with the decline in imaging quality caused by sudden environmental changes or changes in target attitude, ensure continuous and stable imaging of UAV targets, avoid target loss, and enhance the robustness of the system in complex dynamic environments.

[0049] The embodiments of the present invention are device embodiments corresponding to the above method embodiments. The specific operations of each module processing step can be understood with reference to the description of the method embodiments, and will not be repeated here.

[0050] like Figure 5As shown, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the multimodal anti-UAV detection method based on shortwave infrared as described above.

[0051] The present invention also provides a computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the above-described multimodal anti-UAV detection method based on shortwave infrared.

[0052] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0053] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for apparatus or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the description of the method embodiments. The apparatus and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0054] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and the contents not described in detail in the specification of the present invention are known to those skilled in the art.

Claims

1. A multi-modal anti-UAV detection method based on shortwave infrared, characterized in that, Includes the following steps: Acquire external environmental information, including brightness information, time information and meteorological parameters, and perform real-time image quality evaluation on visible light images and shortwave infrared images of the probe airspace, including sharpness, contrast and signal-to-noise ratio evaluation. Based on environmental information and image quality evaluation results, the optimal imaging spectrum combination and working mode are dynamically selected according to preset decision rules. The working modes include daytime visible light mode, shortwave infrared passive imaging mode, and nighttime active shortwave infrared mode. Perform UAV target detection according to the selected working mode, collect corresponding detection images, perform image processing and signal processing on the collected detection images, identify UAV targets, and locate and continuously track the identified UAV targets. The tracking results of the UAV target are displayed and output. During the target tracking process, the working mode is dynamically switched according to the real-time image quality evaluation results to ensure continuous and stable imaging of the UAV target.

2. The multi-modal anti-UAV detection method based on shortwave infrared as described in claim 1, characterized in that, The triggering condition for the daytime visible light mode is: When the ambient brightness is higher than the preset brightness threshold and the real-time image quality evaluation result of the visible light image meets the preset sharpness requirements, the daytime visible light mode is triggered. Upon triggering, visible light imaging is enabled for drone detection, while short-wave infrared active illumination is disabled.

3. The multi-modal anti-UAV detection method based on shortwave infrared as described in claim 1, characterized in that, The triggering condition for the shortwave infrared passive imaging mode is: When the environment is detected to be foggy, backlit, or the background of the drone target is a complex background such as forest / mountain, and the contrast of the visible light image is lower than the preset contrast threshold, the short-wave infrared passive imaging mode is triggered. Upon triggering, shortwave infrared passive imaging is enabled for drone detection, while visible light imaging and shortwave infrared active illumination are disabled.

4. The multi-modal anti-UAV detection method based on shortwave infrared as described in claim 1, characterized in that, The triggering condition for the nighttime active shortwave infrared mode is: When the ambient light is lower than the preset nighttime brightness threshold or the system is in a preset nighttime period, the nighttime active shortwave infrared mode is triggered. Upon triggering, the drone will use a combination of short-wave infrared imaging and active short-wave infrared illumination for detection, while the visible light imaging function will be disabled.

5. The multi-modal anti-UAV detection method based on shortwave infrared as described in claim 1, characterized in that, The preset decision rule is a weighted algorithm, which sets weight coefficients for ambient brightness, image contrast, and meteorological parameters, and determines the optimal working mode based on the weighted calculation results.

6. A multi-modal anti-UAV detection device based on shortwave infrared, characterized in that, include: The data collection module is used to acquire external environmental information, including brightness information, time information and meteorological parameters, and to perform real-time image quality evaluation on visible light images and shortwave infrared images of the detection airspace. The real-time image quality evaluation includes sharpness, contrast and signal-to-noise ratio evaluation. The mode selection module is used to dynamically select the optimal imaging spectrum combination and working mode according to the environmental information and image quality evaluation results and a preset decision rule. The working modes include daytime visible light mode, shortwave infrared passive imaging mode, and nighttime active shortwave infrared mode. The target localization module is used to perform UAV target detection according to the selected working mode, acquire corresponding detection images, perform image processing and signal processing on the acquired detection images, identify UAV targets, and locate and continuously track the identified UAV targets. The display and control module is used to display and output the tracking results of the UAV target. During the target tracking process, the working mode is dynamically switched according to the real-time image quality evaluation results to ensure continuous and stable imaging of the UAV target.

7. The multi-mode anti-UAV detection device based on shortwave infrared as described in claim 6, characterized in that, The triggering condition for the daytime visible light mode is: When the ambient brightness is higher than the preset brightness threshold and the real-time image quality evaluation result of the visible light image meets the preset sharpness requirements, the daytime visible light mode is triggered. Upon triggering, visible light imaging is enabled for drone detection, while short-wave infrared active illumination is disabled.

8. The multi-mode anti-UAV detection device based on shortwave infrared as described in claim 6, characterized in that, The triggering condition for the shortwave infrared passive imaging mode is: When the environment is detected to be foggy, backlit, or the background of the drone target is a complex background such as forest / mountain, and the contrast of the visible light image is lower than the preset contrast threshold, the short-wave infrared passive imaging mode is triggered. Upon triggering, shortwave infrared passive imaging is enabled for drone detection, while visible light imaging and shortwave infrared active illumination are disabled.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the multimodal anti-UAV detection method based on shortwave infrared as described in any one of claims 1 to 5.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the multimodal anti-UAV detection method based on shortwave infrared as described in any one of claims 1 to 5.

Images