A smart airport perimeter security monitoring method, system, device and storage medium

Abstract

This application relates to the field of security early warning technology, and discloses a smart airport perimeter security monitoring method, system, equipment and storage medium. The method includes: collecting monitoring information through a multi-type sensor array and performing time synchronization processing to obtain multi-source synchronous monitoring data; performing spatial registration and noise reduction processing on the data, configuring weights according to sensor reliability, and generating situation fusion data; extracting spatiotemporal features to construct intrusion feature representations and obtain threat assessment results; determining the early warning level and matching response measures to form a disposal plan; obtaining the optimal prevention and control plan through situation deduction; optimizing monitoring parameters based on execution data to generate an updated monitoring strategy. This application achieves accurate identification and rapid response to perimeter security threats through intelligent analysis and fusion processing of multi-source data.

Description

Technical Field

[0001] The present application relates to the field of security warning, and in particular to a smart airport perimeter security monitoring method, system, equipment and storage medium. Background Art

[0002] With the continuous expansion of airports and increasing security requirements, perimeter security monitoring faces severe challenges. Existing airport perimeter security monitoring methods primarily rely on single technologies such as video surveillance and infrared detection, employing fixed threshold alarm mechanisms. In practice, existing technologies address security threats through manual inspections, fixed sentries, and simple coordinated response. These technologies lack intelligent analysis and adaptive response mechanisms. Furthermore, existing monitoring systems are often deployed independently, with insufficient information sharing between subsystems, making it difficult to achieve deep data integration and coordinated response.

[0003] However, these traditional monitoring methods have significant shortcomings. First, single technical approaches are easily affected by environmental factors such as weather changes and lighting conditions, resulting in unstable monitoring results. Second, fixed alarm thresholds cannot adapt to the security needs of different scenarios and time periods, and false alarms and missed alarms are common. Third, manual response methods are slow and difficult to respond to sudden threats. Furthermore, information silos between subsystems prevent the full utilization of multi-source data for intelligent analysis and decision-making, affecting overall prevention and control effectiveness. Summary of the Invention

[0004] The present application provides a smart airport perimeter security monitoring method, system, device and storage medium for accurately identifying and rapidly responding to perimeter security threats through intelligent analysis and fusion processing of multi-source data.

[0005] In the first aspect, the present application provides a smart airport perimeter security monitoring method, which includes: collecting monitoring information of the perimeter area through a multi-type sensor array, performing time synchronization processing on the collected monitoring information through a time synchronization server to obtain multi-source synchronous monitoring data; using a spatial registration system to perform spatial registration and noise reduction processing on the multi-source synchronous monitoring data, and dynamically configuring weights according to the reliability of each sensor to generate perimeter situation fusion data; extracting and analyzing spatiotemporal features based on the perimeter situation fusion data, and constructing perimeter intrusion feature representation through multi-level security features. , and then analyze it according to the security threat level assessment rules to obtain the perimeter threat assessment results; based on the perimeter threat assessment results, determine the security warning level through the dynamic threshold system, and match the response measures from the plan library based on historical disposal experience to form a perimeter security disposal plan; according to the perimeter security disposal plan, establish a security resource scheduling strategy, and verify the plan through the situation deduction platform to obtain the optimal perimeter prevention and control plan; based on the execution data of the optimal perimeter prevention and control plan, evaluate and screen the perimeter security monitoring parameters, and adjust the monitoring thresholds and warning rules according to the screening results to generate an updated perimeter security monitoring strategy.

[0006] On the second aspect, the present application provides a smart airport perimeter security monitoring system, which includes: a processing module for collecting monitoring information of the perimeter area through a multi-type sensor array, and performing time synchronization processing on the collected monitoring information through a time synchronization server to obtain multi-source synchronous monitoring data; a noise reduction module for using a spatial registration system to perform spatial registration and noise reduction processing on the multi-source synchronous monitoring data, and dynamically configure weights according to the reliability of each sensor to generate perimeter situation fusion data; an extraction module for extracting and analyzing spatiotemporal features based on the perimeter situation fusion data, and constructing perimeter intrusion feature representation through multi-level security features , and then analyze it according to the security threat level assessment rules to obtain the perimeter threat assessment results; the matching module is used to determine the security warning level through the dynamic threshold system based on the perimeter threat assessment results, and match the response measures from the plan library based on historical disposal experience to form a perimeter security disposal plan; the verification module is used to establish a security resource scheduling strategy based on the perimeter security disposal plan, and verify the plan through the situation deduction platform to obtain the optimal perimeter prevention and control plan; the screening module is used to evaluate and screen the perimeter security monitoring parameters based on the execution data of the optimal perimeter prevention and control plan, and adjust the monitoring threshold and warning rules according to the screening results to generate an updated perimeter security monitoring strategy.

[0007] The third aspect of the present application provides a computer device, wherein the memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor and the memory communicate through a bus, and when the machine-readable instructions are executed by the processor, the steps of the above-mentioned smart airport perimeter security monitoring method are performed.

[0008] The fourth aspect of the present application provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on a computer, it enables the computer to execute the above-mentioned smart airport perimeter security monitoring method.

[0009] In the technical solution provided by the present application, monitoring information of the perimeter area is collected by a multi-type sensor array, and time synchronization processing is performed using a time synchronization server, which solves the problem of temporal consistency of data from different sensors and ensures the synchronization and integrity of multi-source monitoring data; a spatial registration system is used to perform spatial registration and noise reduction processing on the multi-source synchronous monitoring data, and dynamic weight configuration is performed according to the reliability of the sensors, effectively improving the accuracy and reliability of data fusion; spatiotemporal feature extraction and analysis are performed on the perimeter situation fusion data, and a perimeter intrusion feature representation is constructed through multi-level security features, thereby achieving accurate identification of intrusion threats; a dynamic threshold system is used to determine the security warning level, and response measures are matched from the plan library based on historical disposal experience, thereby improving the accuracy of the warning and the targeted disposal; by establishing a security resource scheduling strategy and using a situation deduction platform to verify the plan, the optimal configuration of prevention and control resources is achieved; the perimeter security monitoring parameters are evaluated and screened, and the monitoring thresholds and warning rules are dynamically adjusted according to the screening results, establishing a set of adaptive monitoring strategy update mechanisms. The overall solution forms a complete closed-loop monitoring system. From data collection, analysis and processing, threat identification to emergency response, each link is closely connected and data flows smoothly, which greatly improves the intelligent level of airport perimeter security monitoring. The solution fully utilizes the complementary advantages of multi-source data and effectively solves the problems existing in traditional monitoring methods through intelligent analysis methods and adaptive response mechanisms. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 This is a schematic diagram of an embodiment of the smart airport perimeter security monitoring method in an embodiment of the present application;

[0012] Figure 2This is a schematic diagram of the spatial area division of the airport boundary in an embodiment of the present application;

[0013] Figure 3 This is a schematic diagram of an embodiment of the smart airport perimeter security monitoring system in the embodiment of the present application;

[0014] Figure 4 Schematic diagram of the structure of the computer device in the embodiment of the present application. DETAILED DESCRIPTION

[0015] The embodiments of the present application provide a smart airport perimeter security monitoring method, system, device and storage medium. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products or devices.

[0016] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In one embodiment of the present application, a method for monitoring security of a smart airport perimeter includes:

[0017] Step S101: collecting monitoring information of a perimeter area via a multi-type sensor array, and performing time synchronization processing on the collected monitoring information via a time synchronization server to obtain multi-source synchronous monitoring data;

[0018] Step S102: Using a spatial registration system to perform spatial registration and noise reduction on the multi-source synchronous monitoring data, and dynamically weighting each sensor according to its reliability to generate perimeter situation fusion data;

[0019] Step S103: Extract and analyze spatiotemporal features based on the perimeter situation fusion data, construct perimeter intrusion feature representations using multi-level security features, and then analyze based on security threat level assessment rules to obtain perimeter threat assessment results;

[0020] Step S104: Based on the perimeter threat assessment results, a security warning level is determined through a dynamic threshold system, and response measures are matched from a plan library based on historical handling experience to form a perimeter security handling plan;

[0021] Step S105: Establish a security resource scheduling strategy based on the perimeter security disposal plan, and verify the plan through the situation simulation platform to obtain the optimal perimeter prevention and control plan;

[0022] Step S106: Based on the execution data of the optimal perimeter prevention and control plan, the perimeter security monitoring parameters are evaluated and screened, and the monitoring thresholds and warning rules are adjusted according to the screening results to generate an updated perimeter security monitoring strategy.

[0023] It is understandable that the execution subject of this application can be a smart airport perimeter security monitoring system, or a terminal or a server, which is not limited here. The embodiment of this application is described by taking the server as the execution subject as an example.

[0024] Specifically, a multi-type sensor array collects monitoring information from the perimeter. This multi-type sensor array includes a video surveillance subsystem, infrared thermal imaging equipment, vibration fiber, and millimeter-wave radar, which are responsible for collecting visible light image data, thermal imaging data, ground vibration data, and airspace detection data, respectively. The raw monitoring information collected by the sensors is grouped and labeled according to the monitoring time, and each group of monitoring information is assigned a unique timestamp. The timestamp encoding uses the UTC time format and is accurate to the millisecond level to ensure data time sequence. The timestamp-bearing monitoring information is divided into time windows with a length of 100 milliseconds. The monitoring information from different sensors within the same time window is correlated and matched to generate time-correlated monitoring information. The time-correlated monitoring information undergoes signal quality assessment, using metrics such as signal-to-noise ratio, data integrity, and signal stability. This signal quality assessment eliminates monitoring information with a signal-to-noise ratio below a preset threshold. The selected valid monitoring information then undergoes time synchronization calibration. Time synchronization calibration aligns the monitoring information collected by different sensors to a unified time base. Missing data points are supplemented using linear interpolation during the calibration process to generate multi-source synchronized monitoring data.

[0025] Multi-source synchronous monitoring data undergoes spatial registration and noise reduction. Spatial registration transforms the coordinate system, unifying the sensor data into the WGS84 coordinate system. Spatial overlap regions are then identified and feature data extracted from these overlapping regions. Noise intensity analysis is performed on the feature data in these overlapping regions, and a signal interference model is established to remove interference. For the noise-reduced feature data, the signal fluctuation coefficient of each sensor is calculated to assess the signal stability and obtain a sensor reliability index. Data fusion weights are calculated based on the sensor reliability index, and a multi-source data weighted fusion matrix is ​​constructed to generate perimeter situation fusion data. This perimeter situation fusion data is used for spatiotemporal feature extraction and analysis. The fused data is segmented into 5-minute time series segments. Data variation characteristics within each time segment are extracted to generate time series feature data. The monitored area is also divided into several spatial regions, and the data distribution characteristics within each region are calculated to generate spatial feature data. Correlation analysis is performed between the time series feature data and the spatial feature data to construct a feature correlation matrix and build a multi-level security signature. Abnormal behavior analysis is performed based on the multi-level security signature, extracting intrusion behavior feature sequences and generating perimeter intrusion signature representations. The matching degree between the boundary intrusion feature representation and the security threat level assessment rules is calculated, the threat level is marked, and the boundary threat assessment result is output.

[0026] Perimeter threat assessment results are processed by a dynamic threshold system to determine the security warning level. Threat assessment results are analyzed over time windows to extract fluctuations in threat levels and generate threat trend data. Threat trend data is compared with historical data to calculate threat deviations and determine threat threshold parameters. Warning intervals are divided based on the threat threshold parameters, resulting in four warning levels: Level 1 (red), Level 2 (orange), Level 3 (yellow), and Level 4 (blue). Similarity calculations are performed between the security warning level data and historical response experience to extract response elements and generate response matching data. Scenario adaptability analysis is performed on the response matching data, and appropriate response measures are selected from the plan library to generate a perimeter security response plan. Control task elements are extracted from the perimeter security response plan, and statistical analysis of required human and equipment resources is performed to generate scheduling demand data. Scheduling demand data is categorized and organized by resource type and compared with the current resource status to generate resource matching data. The resource matching data is analyzed for temporal and spatial distribution, resource scheduling priorities are prioritized, and a security resource scheduling strategy is established. The security resource scheduling strategy is input into the situation simulation platform for scenario simulation analysis, generating simulation verification data. Quantitatively evaluate the prevention and control effectiveness of the simulation verification data, extract key indicator parameters, and generate scenario evaluation data. From the scenario evaluation data, select the strategy combination with the best prevention and control effect to form the optimal perimeter prevention and control plan.

[0027] The execution data of the optimal perimeter control plan is used for system optimization and updates. Perimeter security monitoring parameters are extracted from the execution data and classified and organized by parameter type to obtain a monitoring parameter set. Statistical analysis is performed on the monitoring parameter set to calculate the fluctuation range and distribution characteristics of the parameters and generate parameter evaluation data. Based on the parameter evaluation data, abnormal fluctuation parameters are eliminated, key monitoring indicators are extracted, and parameter screening results are obtained. The correspondence between each monitoring threshold in the parameter screening results and the actual threat is analyzed to construct a monitoring threshold mapping table. The monitoring threshold mapping table is compared with the existing warning rules, and the rule items that need to be updated are marked to generate a rule update list. The original rules are replaced according to the updated items in the rule update list to generate an updated perimeter security monitoring strategy.

[0028] For example, within a section of an airport perimeter, the video surveillance subsystem captured an unusually moving target, thermal imaging equipment detected heat fluctuations, vibration fiber optics detected ground vibration signals, and millimeter-wave radar detected an aerial object. These raw data were time-synchronized to align all data to the same time reference. The spatial registration system uniformly converted the coordinate information from the various sensor data and calculated a sensor signal stability index, with a weight of 0.3 for video data, 0.25 for thermal imaging data, 0.25 for vibration data, and 0.2 for radar data. Spatiotemporal feature extraction was performed on the fused data, revealing that the unusual target's motion trajectory, thermal signature, and vibration signature all indicated a perimeter intrusion. The system matched the multi-dimensional features to the threat level assessment rules and determined a Level 2 threat. Based on the threat level, the system selected a corresponding response plan from a database and dispatched the nearest security personnel and equipment. The entire process of data transmission, processing, and analysis forms a closed loop, ensuring timely and accurate perimeter security monitoring.

[0029] In an embodiment of the present application, monitoring information of the perimeter area is collected by a multi-type sensor array, and time synchronization processing is performed using a time synchronization server, which solves the problem of temporal consistency of data from different sensors and ensures the synchronization and integrity of multi-source monitoring data; a spatial registration system is used to perform spatial registration and noise reduction processing on the multi-source synchronous monitoring data, and dynamic weight configuration is performed according to the reliability of the sensors, effectively improving the accuracy and reliability of data fusion; spatiotemporal feature extraction and analysis are performed on the perimeter situation fusion data, and a perimeter intrusion feature representation is constructed through multi-level security features, thereby achieving accurate identification of intrusion threats; a dynamic threshold system is used to determine the security warning level, and response measures are matched from the plan library based on historical disposal experience, thereby improving the accuracy of the warning and the targeted disposal; by establishing a security resource scheduling strategy and using a situation deduction platform to verify the plan, the optimal configuration of prevention and control resources is achieved; the perimeter security monitoring parameters are evaluated and screened, and the monitoring thresholds and warning rules are dynamically adjusted according to the screening results, establishing a set of adaptive monitoring strategy update mechanisms. The overall solution forms a complete closed-loop monitoring system. From data collection, analysis and processing, threat identification to emergency response, each link is closely connected and data flows smoothly, which greatly improves the intelligent level of airport perimeter security monitoring. The solution fully utilizes the complementary advantages of multi-source data and effectively solves the problems existing in traditional monitoring methods through intelligent analysis methods and adaptive response mechanisms.

[0030] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0031] (1) A multi-type sensor array scans the perimeter area at multiple angles. The video monitoring subsystem collects visible light image data, the infrared thermal imaging device collects thermal imaging data, the vibration optical fiber collects ground vibration data, and the millimeter-wave radar collects airspace detection data to obtain the original monitoring information.

[0032] (2) The original monitoring information is grouped and marked according to the monitoring time, and a unified timestamp code is assigned to each group of original monitoring information to obtain monitoring information with a timestamp;

[0033] (3) Divide the monitoring information with timestamps into time windows, correlate and match the monitoring information in the same time window, and obtain time-correlated monitoring information;

[0034] (4) Perform signal quality assessment on the time-correlated monitoring information, eliminate the monitoring information with a signal-to-noise ratio lower than a preset threshold, and obtain effective monitoring information;

[0035] (5) Time synchronization calibration is performed on the effective monitoring information, and the monitoring information collected by different sensors is aligned to a unified time base to obtain time-calibrated monitoring information;

[0036] (6) Time calibration monitoring information is used to check data integrity, interpolate the time points of missing data, and generate multi-source synchronous monitoring data.

[0037] Specifically, the multi-type sensor array consists of a video surveillance subsystem, infrared thermal imaging equipment, vibration fiber, and millimeter-wave radar, each responsible for collecting different types of data. The video surveillance subsystem uses a high-definition camera array, installed every 50 meters along the perimeter, with adjacent cameras' fields of view overlapping by 30%, to collect visible light image data. The infrared thermal imaging equipment uses dual-spectral imaging technology, operating in the 8-14μm band to detect temperature changes in targets. The vibration fiber, buried 0.5 meters underground, collects ground vibration signals. The millimeter-wave radar operates in the 77GHz frequency band and uses phased array technology to achieve 360-degree scanning and detect aerial targets. A unified timestamp encoding mechanism is used to time-stamp raw monitoring information. Each data record contains three basic fields: data source identifier, acquisition time, and data content. The data source identifier is represented by a four-digit code. The first digit represents the sensor type (1 - video, 2 - infrared, 3 - vibration, 4 - radar), and the last three digits represent the device number. The acquisition time is recorded in Unix timestamp format, accurate to the millisecond level. The data content field stores the specific data values ​​collected by the sensor. Time stamp processing sorts and groups data from different sensors according to the acquisition time to ensure the temporal sequence of the data.

[0038] Time windows are divided using a sliding window method, with a window length of 100 milliseconds and a sliding step of 20 milliseconds. Within each time window, data from the same source are aggregated based on the data source identifier to extract data features. For video data, features such as target location, size, and direction of movement are extracted; for infrared data, features such as temperature distribution and thermal anomalies are extracted; for vibration data, features such as amplitude and frequency are extracted; and for radar data, features such as target distance, velocity, and azimuth are extracted. Features from different source data within the same time window are correlated and matched to establish a feature correlation matrix. Signal quality is assessed using a multi-metric comprehensive evaluation method. The signal-to-noise ratio (SNR) is calculated, and the ratio of signal strength to background noise must exceed a preset threshold: 30dB for video images, 25dB for infrared images, 20dB for vibration signals, and 15dB for radar signals. Next, data integrity is assessed, checking for frame loss and field integrity. Finally, signal stability is assessed, calculating the amplitude of signal fluctuations over a short period of time. Data with a comprehensive score below the threshold is discarded, and the remaining data constitutes valid monitoring information.

[0039] Time synchronization calibration addresses the issue of inconsistent sampling rates among different sensors. The video sampling rate is 25 frames per second, the infrared sampling rate is 15 frames per second, the vibration sampling rate is 1000 Hz, and the radar sampling rate is 200 Hz. Linear interpolation is used to resample all data to a unified time point. Interpolation calculations use a weighted average of two adjacent sampling points, with the weight inversely proportional to the time interval. The calibrated data has a unified time base and a maximum sampling rate of 1000 Hz. Data integrity is checked using a two-way verification mechanism. The continuity of the time series is checked, and time points with missing data are marked. The data content is then checked for integrity, including data format, numerical range, and logical relationships. For missing data points, different interpolation methods are used depending on the data type. State data uses nearest neighbor interpolation to maintain state discreteness, while continuous data uses cubic spline interpolation to maintain curve smoothness. After interpolation, multi-source synchronous monitoring data is generated.

[0040] For example, during an intrusion at the airport perimeter, the video surveillance subsystem captured a moving target at time T with an image signal-to-noise ratio of 35dB. The target's position coordinates (x, y) and velocity v were extracted. An infrared device at the same location detected a temperature anomaly with a signal-to-noise ratio of 27dB, indicating a temperature 8°C above the background. A vibrating fiber optic sensor detected a vibration signal at time T+15ms with a signal-to-noise ratio of 22dB and an amplitude five times that of the background. The radar detected the target at time T+30ms with a signal-to-noise ratio of 18dB, measuring radial velocity and azimuth. These asynchronously collected data were time-synchronized and aligned to a sampling rate of 1000Hz. If vibration data at a sampling point was missing, it was calculated using cubic spline interpolation. The amplitude at the interpolated point was consistent with the changing trend of adjacent points. After integrity checks and interpolation, a set of multi-source synchronized target feature data was generated. This data record clearly demonstrates the temporal and spatial correlation of the intrusion target's characteristics.

[0041] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0042] (1) Perform spatial coordinate conversion on multi-source synchronous monitoring data, unify the data collected by different sensors into the same spatial coordinate system, and obtain unified coordinate system monitoring data;

[0043] (2) Identify the spatial overlapping areas of the unified coordinate system monitoring data, extract the data features of the overlapping areas, and obtain the feature data of the overlapping areas;

[0044] (3) Analyze the noise intensity of the feature data in the overlapping area, establish a signal interference model, eliminate the interference signal, and obtain the feature data after noise reduction;

[0045] (4) Evaluate the signal stability of each sensor in the noise-reduced feature data, calculate the signal fluctuation coefficient, and obtain the sensor reliability index;

[0046] (5) Calculate the weight of the noise-reduced feature data based on the sensor reliability index, establish a multi-source data weighted fusion matrix, and obtain weighted fusion data;

[0047] (6) Organize and sort the weighted fusion data according to the temporal and spatial correlation, perform data consistency verification, and generate boundary situation fusion data.

[0048] Specifically, spatial coordinate transformation is performed on multi-source synchronous monitoring data, unifying all sensor data into the WGS84 coordinate system. The pixel coordinates (u, v) of the video surveillance subsystem are converted to world coordinates (x, y, z) through the internal and external parameter matrices; the image coordinates of the infrared thermal imaging device are converted to actual physical coordinates after distortion correction; the linear distance of the vibrating optical fiber is converted to three-dimensional spatial coordinates; and the polar coordinates (r, θ, φ) of the millimeter-wave radar are converted to rectangular coordinates. After all sensor data are converted to the same coordinate system, subsequent spatial analysis and data fusion are facilitated. In the process of identifying overlapping areas, the spatial overlap degree is calculated using the following formula:

[0049] ;

[0050] in: Indicates the recognition degree of overlapping area; represents the reference sensor data point set; represents a set of data points from sensors; Represents the total data point set in the target area; M, N, K represent the number of three data point sets respectively; α and β are weight coefficients.

[0051] When extracting data features from overlapping areas, the space is divided into grid cells, and the distribution of data points within each grid cell is analyzed. Noise intensity analysis is performed on the feature data from overlapping areas, classifying ambient noise into background noise and sudden interference. Background noise, which exhibits a Gaussian distribution, is suppressed using Gaussian filtering; sudden interference is removed using a combination of median filtering and wavelet transform. A signal interference model is established to compare the signal features of different sensors in the same area, identifying and eliminating anomalous interference signals. Signal stability is evaluated on the noise-reduced feature data, calculating the signal fluctuation coefficient for each sensor. Evaluation metrics include signal amplitude stability, phase stability, and delay stability. For video and infrared images, image quality and target detection stability are primarily evaluated; for vibration signals, amplitude and frequency stability are evaluated; and for radar signals, the stability of range, velocity, and azimuth measurements is evaluated. Sensor reliability metrics are calculated based on the evaluation results and used as weights for data fusion.

[0052] Data fusion weights are calculated based on sensor reliability indicators to establish a weighted fusion matrix for multi-source data. Weight calculation takes into account the sensor's historical performance, current state, and environmental adaptability. Data from each sensor is weighted according to its weight to construct a multidimensional feature space. Within this feature space, data from different sources is organized based on temporal and spatial correlations to form a unified data structure. Data consistency checks are performed to verify that the fused data meets physical constraints and logical relationships, eliminating unreasonable data combinations.

[0053] Perimeter situation fusion data is the output of weighted fusion of multi-source data, containing comprehensive information such as the target's location, motion state, and characteristic attributes. For example, during perimeter monitoring, a suspicious target is detected at a certain location: video surveillance captures the moving target's image features, infrared equipment detects temperature anomalies, vibration fiber optics detects ground vibrations, and millimeter-wave radar measures the target's velocity. After spatial coordinate conversion, these data are determined to be in the same spatial region. Overlapping region identification reveals that the data from all four sensors points to the same target. After noise analysis removes environmental interference, the quality of each sensor data is evaluated: the video image is clear and stable, the infrared image exhibits slight fluctuations due to temperature, the vibration signal exhibits some noise due to ground conditions, and the radar signal is relatively stable. Fusion weights are determined based on this evaluation, with video and radar data given higher weights and infrared and vibration data appropriately lower weights. The fused data fully describes the target's location, motion trajectory, temperature characteristics, and vibration characteristics.

[0054] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0055] (1) Segment the boundary situation fusion data into time series, extract the time series change characteristics of the data in each time period, and obtain the time series feature data;

[0056] (2) Divide the time series feature data into spatial regions, calculate the data distribution characteristics in each region, and obtain spatial feature data;

[0057] (3) Correlation analysis is performed on the temporal feature data and the spatial feature data to establish a feature correlation matrix and generate multi-level security features;

[0058] (4) Analyze abnormal behavior based on multi-level security features, extract intrusion behavior feature sequences, and construct boundary intrusion feature representations;

[0059] (5) Calculate the matching degree between the boundary intrusion feature representation and the security threat level assessment rules, mark the threat level, and obtain the threat level annotation data;

[0060] (6) Aggregate and analyze the threat level annotation data according to the spatiotemporal dimensions and output the boundary threat assessment results.

[0061] Specifically, the boundary situation fusion data is segmented into time series using the sliding time window method, with the window length set to 5 minutes and the sliding step length to 1 minute. In each time period, the statistical characteristics, change trends and mutation points of the data are extracted. Statistical characteristics include mean, standard deviation, kurtosis and skewness; the change trend is obtained through linear regression and curve fitting; the mutation point is identified through the cumulative sum test method. These characteristics constitute the time series feature data. When the time series feature data is spatially divided into regions, an adaptive grid division method is used. Based on the terrain characteristics and protection requirements of the monitoring area, the boundary area is divided into several grid units of varying sizes. The grid density is higher near the airport runway and around important facilities; in open areas, the grid density is relatively low. The distribution characteristics of the data in each grid unit are calculated, including data density, aggregation, directionality and correlation. The data density distribution is calculated by the kernel density estimation method, the degree of aggregation of the data is calculated by spatial autocorrelation analysis, and the main distribution direction of the data is determined by principal component analysis to obtain spatial feature data. As Figure 2 The figure shows a schematic diagram of the spatial area division of the airport fence in an embodiment of the present application, which illustrates the intelligent monitoring grid division scheme for the spatial area of ​​the airport fence. According to different protection levels, the areas are divided into three categories: Core protection area (red area): including the area around the runway, using a high-density grid division of 5m×5m, equipped with high-density video surveillance points and infrared detectors to achieve all-round coverage without blind spots. Key protection area (green area): including important facility areas such as the cargo area, using a medium-density grid division of 10m×10m, with video surveillance and infrared detection equipment evenly distributed. General protection area (blue area): including open areas, using a low-density grid division of 20m×20m, and monitoring equipment arranged according to the terrain characteristics. The correlation analysis of time series feature data and spatial feature data adopts the tensor decomposition method. The two types of feature data are organized into a third-order tensor, with the three dimensions representing time, space, and feature attributes respectively. The correlation pattern between features is extracted through Tucker decomposition, and a feature correlation matrix is ​​established. The feature correlation matrix reflects the interaction relationship between different features and generates multi-level security features. Multi-layered security features form a hierarchical feature system, comprising bottom-level basic features, mid-level combined features, and high-level semantic features. Abnormal behavior analysis is performed based on these multi-layered security features, using deep learning methods to identify abnormal patterns. Convolutional neural networks extract spatial features, recurrent neural networks capture temporal features, and attention mechanisms fuse multiple layers of features. Abnormal behavior is determined based on distance metrics and probability distributions in the feature space. Intrusion behavior feature sequences are extracted from detected abnormal behaviors, including intrusion path, intrusion speed, and intrusion method, to construct a perimeter intrusion feature representation.

[0062] The formula for calculating the matching degree between the boundary intrusion feature representation and the security threat level assessment rules is as follows:

[0063] ;

[0064] in: Indicates the threat level assessment value; represents the intrusion feature vector; represents the threat rule weight; Indicates the detection time interval; Indicates scene complexity; represents the prior risk coefficient; P and Q represent the number of features and the number of rules respectively; γ represents the threat level category.

[0065] Threat level annotated data is aggregated and analyzed along temporal and spatial dimensions. In the temporal dimension, the changing trend and duration of threat levels are calculated; in the spatial dimension, the spatial clustering and diffusion of threat distribution are analyzed. High-risk areas and high-incidence periods are identified through spatiotemporal clustering methods, generating perimeter threat assessment results.

[0066] For example, in airport perimeter monitoring, monitoring data from a specific perimeter section revealed time-series feature data documenting abnormal activity over a continuous 30-minute period: sporadic vibration signals in the first 10 minutes, sustained heat changes in the middle 10 minutes, and significant displacement patterns in the final 10 minutes. Spatial feature data revealed that these abnormal activities were concentrated within a 50-by-50-meter area, gradually progressing from the outside inward. Spatial-temporal feature correlation analysis revealed a clear temporal progression of vibration signals, heat changes, and displacement patterns, with a strong spatial concentration. Abnormal behavior analysis identified this series of features as a typical deliberate intrusion pattern. Based on the duration, activity range, and behavioral characteristics of the feature sequence, a match was calculated against threat level assessment rules. The results indicated that the intrusion was clearly premeditated and dangerous, meeting the characteristics of a Level 2 threat. The threat assessment clearly describes the development process, severity, and impact of the intrusion.

[0067] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0068] (1) Perform time window analysis on the perimeter threat assessment results, extract threat fluctuation characteristics, and obtain threat trend data;

[0069] (2) Compare and analyze threat trend data with historical data, calculate threat deviation value, and obtain threat threshold parameters;

[0070] (3) Classify the threat threshold parameters according to the threat level, divide the warning interval, and obtain the security warning level data;

[0071] (4) Calculate the similarity between the safety warning level data and historical disposal experience, extract disposal elements, and obtain disposal matching data;

[0072] (5) Conduct scenario adaptability analysis on the disposal matching data, select response measures from the plan library, and obtain disposal response data;

[0073] (6) Prioritize and combine the response data to form a perimeter security response plan.

[0074] Specifically, a time window analysis is performed on the perimeter threat assessment results using a sliding time window method with a window size of 30 minutes and a sliding step of 5 minutes. Within each time window, the rate of change, fluctuation amplitude, and duration of the threat level are calculated. The rate of change reflects the rate of increase or decrease in the threat level; the fluctuation amplitude indicates the range of change in the threat level; and the duration records the duration of the threat. By combining these characteristic parameters, the threat development trend is extracted and generated into threat trend data. A time series pattern matching method is used to compare and analyze threat trend data with historical data. Threat records from similar scenarios are extracted from the historical database, including relevant factors such as threat type, occurrence time, and meteorological conditions. A dynamic time warping algorithm is used to calculate the similarity between the current threat trend and historical cases, identifying the most similar historical events. The deviation between the current threat trend and the historical average is calculated to obtain the threat deviation value. A larger deviation value indicates a higher degree of abnormality in the current threat. The threat threshold parameter is determined based on the distribution characteristics of the deviation value.

[0075] Threat threshold parameters are graded using a multi-level threshold method, dividing the threat level into four warning zones: blue (observation), yellow (concern), orange (alert), and red (emergency). The range of each zone is determined based on historical statistical data to ensure that the classification results are consistent with the actual threat level. When determining security warning level data, not only the current threat threshold parameters are considered, but also the spatial distribution and temporal evolution of the threat to avoid frequent fluctuations in the warning level. A case-based reasoning approach is used to calculate the similarity between security warning level data and historical response experience. Historical response cases matching the current warning level are retrieved from the emergency plan library, and the response elements of each case are extracted, including response level, personnel scheduling, equipment deployment, and response process. A feature vector is constructed to calculate the similarity between each case and the current situation, and the case with the highest similarity is selected as a reference. Key response elements are extracted from historical cases to form response matching data.

[0076] The scenario adaptability analysis of the disposal matching data focuses on five aspects: geographical environmental conditions, current resource status, weather factors, time constraints, and coordination difficulty. For each disposal element, its applicability in the current scenario is evaluated. For example, some disposal plans are difficult to implement at night or in severe weather conditions and need to be adjusted. The adaptability score of each disposal element is calculated using a linear weighted method, and response measures with higher adaptability are screened from the plan library to generate disposal response data. The priority sorting of disposal response data considers three dimensions: disposal efficiency, resource consumption, and implementation risk. Disposal efficiency reflects the timeliness of response measures; resource consumption includes the input of manpower and material resources; and implementation risk assessment includes potential uncertainties. The weight of each response measure is determined using the hierarchical analysis method, and the measures are ranked according to the comprehensive score. The response measures with higher priority are combined to form a disposal process, and a perimeter security disposal plan is generated.

[0077] For example, during airport perimeter monitoring, a persistent intrusion threat emerged within a certain perimeter section. Time window analysis revealed an increasing threat level over the past 20 minutes, evolving from an initial anomaly to a clear intrusion. Comparison with historical data revealed similar intrusions in the same area, with the current threat characteristics highly similar to those in these cases. The threat deviation exceeded a preset threshold, triggering an orange alert. The system retrieved similar historical response cases from a database of emergency plans and extracted response elements such as rapid response team dispatch, enhanced infrared imaging surveillance, and optimized ground patrol routes. Given the current nighttime hours, the deployment of night vision equipment was prioritized. The response plan was organized according to the principle of "containment first, verification second, and response third," clearly defining the execution sequence and coordination mechanism for each measure. The entire response process resulted in a comprehensive response plan encompassing emergency response force dispatch, technical support, and response process control.

[0078] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0079] (1) Extract the prevention and control task elements from the perimeter security disposal plan, conduct statistical analysis on the demand for human and equipment resources, and obtain the scheduling demand data;

[0080] (2) Classify and organize the scheduling demand data according to resource types, compare the existing resource status, and form resource matching data;

[0081] (3) Analyze the spatiotemporal distribution of resource matching data, divide resource scheduling priorities, and establish security resource scheduling strategies;

[0082] (4) Input the security resource scheduling strategy into the situation simulation platform, conduct scenario simulation and analysis, and obtain simulation verification data;

[0083] (5) Quantitatively evaluate the prevention and control effects in the simulation verification data, extract key indicator parameters, and generate program evaluation data;

[0084] (6) Combine the strategies with the best prevention and control effects in the program evaluation data to form the optimal perimeter prevention and control plan.

[0085] Specifically, control task elements are extracted from the perimeter security plan, including personnel deployment points, equipment placement, and patrol route arrangements. Specific resource requirement parameters are extracted for each task element, such as personnel numbers, professional categories, equipment models, and quantity specifications. A task decomposition approach is employed to break down complex control tasks into basic task units, and the human and equipment resources required for each unit are calculated. Human resources are counted based on professional skills, duty hours, and job requirements; equipment resources are categorized by functional type, performance parameters, and deployment conditions to generate dispatch demand data. This dispatch demand data is categorized and organized using a hierarchical resource management approach. Resource types are divided into three categories: mobile forces, fixed outposts, and technical equipment. Mobile forces include rapid response teams and patrol teams; fixed outposts include observation posts and guard posts; and technical equipment includes mobile surveillance equipment, communications equipment, and night vision equipment. A resource status table is created for each resource type, recording information such as resource location, status, and task load. The dispatch demand is compared with the existing resource status to calculate resource gaps and surpluses, focusing on resource supply and demand conflicts during peak mission periods to generate resource matching data.

[0086] Resource matching data is analyzed for spatiotemporal distribution, calculating resource demand density across regions and time periods. A heat map is used to visualize resource distribution characteristics, identifying hotspots and critical time periods for resource demand. Based on the degree of resource matching and task urgency, resource scheduling is divided into three priority levels: emergency scheduling, priority scheduling, and routine scheduling. Emergency scheduling addresses sudden threats and requires rapid resource deployment; priority scheduling addresses anticipated threats and allows ample scheduling time; and routine scheduling is used for routine prevention and control, implemented according to established plans. Based on the priority classification results, a detailed resource allocation plan is developed, clarifying the scheduling sequence, routing, and coordination mechanisms for various resources, and establishing a security resource scheduling strategy. The situational simulation platform utilizes a combination of 3D scenario modeling and simulation. A 3D scenario model of the airport perimeter is constructed, incorporating elements such as topography, buildings, and surveillance equipment. The security resource scheduling strategy is then imported into the simulation platform, and various threat scenarios are set to simulate the resource scheduling process. The simulation includes personnel movement trajectories, equipment coverage, and communication effectiveness. Through multiple simulations, data on response time, coverage effectiveness, and coordination efficiency under various scenarios is collected to form simulation validation data.

[0087] A multi-dimensional indicator system is used to quantitatively evaluate simulation and validation data. Evaluation indicators include response timeliness, regional coverage, resource utilization, and coordination. Response timeliness measures the time from threat discovery to the deployment of response forces; regional coverage measures the spatial distribution of prevention and control resources; resource utilization evaluates the efficiency of resource utilization; and coordination measures the degree of coordination between different resources. The weights of each indicator are determined using the Analytic Hierarchy Process (AHP), and the overall score of the prevention and control plan is calculated. Key indicator parameters are extracted to generate plan evaluation data. A step-by-step optimization strategy is used to develop the optimal perimeter prevention and control plan. Dimensionality reduction is performed on the plan evaluation data to extract key influencing factors. Based on the performance of each plan on key indicators, candidate plans with the highest overall scores are selected. Details of the candidate plans are optimized, resource allocation parameters are adjusted, scheduling sequences are optimized, and coordination mechanisms are improved. The optimized plans are re-simulated and validated, and the strategy combination with the best prevention and control effect is selected and integrated to form the optimal perimeter prevention and control plan.

[0088] For example, when an intrusion alarm occurred within a section of the airport perimeter, task elements extracted from the perimeter security plan included the deployment of a rapid response team, enhanced infrared surveillance equipment, and optimized ground patrol routes. Resource demand statistics indicated the need for the deployment of four patrol teams, two mobile team members, and two sets of infrared surveillance equipment. A comparison of resource status revealed that only two patrol teams were in place in the immediate vicinity, necessitating the deployment of additional forces from adjacent areas. Spatiotemporal distribution analysis indicated that the location of the alarm was located in a key surveillance area and occurred during nighttime, necessitating an emergency resource allocation priority. Situational simulations demonstrated that deploying patrol forces in a two-way encirclement strategy, combined with high-point surveillance and ground containment, could achieve effective containment in the shortest possible time. Evaluation data demonstrated that this plan achieved optimal response timeliness and regional containment effectiveness, while also achieving high resource utilization. The finalized prevention and control plan detailed the specific division of labor, deployment schedules, operational routes, and communication methods for each force.

[0089] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0090] (1) Extract perimeter security monitoring parameters from the execution data of the optimal perimeter prevention and control plan, classify and organize them according to parameter type, and obtain a monitoring parameter set;

[0091] (2) Conduct statistical analysis on the monitoring parameter set, calculate the fluctuation range and distribution characteristics of each parameter, and form parameter evaluation data;

[0092] (3) Based on the parameter evaluation data, eliminate abnormal fluctuation parameters, extract key monitoring indicators, and obtain parameter screening results;

[0093] (4) Based on the parameter screening results, analyze the corresponding relationship between each monitoring threshold and the actual threat, and build a monitoring threshold mapping table;

[0094] (5) Compare the monitoring threshold mapping table with the existing warning rules, mark the rule items that need to be updated, and generate a rule update list;

[0095] (6) Replace the original rules with the updated items in the rule update list to generate an updated perimeter security monitoring strategy.

[0096] Specifically, perimeter security monitoring parameters are extracted from the execution data of the optimal perimeter control plan. These parameters fall into three categories: equipment monitoring parameters, environmental threshold parameters, and behavioral characteristic parameters. Equipment monitoring parameters include the sensitivity settings, detection range, and alarm thresholds of various sensors; environmental threshold parameters include criteria for environmental factors such as light intensity, temperature fluctuations, and wind speed; and behavioral characteristic parameters include behavioral judgment indicators such as target movement speed, dwell time, and range. A hierarchical parameter structure is established based on parameter type, and related parameters are categorized and organized to form a monitoring parameter set. A multi-dimensional data analysis method is used to statistically analyze the monitoring parameter set. The actual value range of each parameter during execution is calculated, including the maximum, minimum, mean, and standard deviation. The temporal distribution characteristics of the parameters are then analyzed to statistically analyze the parameter variation patterns over different time periods and identify periodic patterns. The spatial distribution characteristics of the parameters are then analyzed to statistically analyze parameter differences across different regions and establish a spatial correlation model. Through these statistical analyses, the fluctuation patterns and distribution characteristics of each parameter are understood, generating parameter evaluation data.

[0097] Using parameter evaluation data as a benchmark, perform parameter anomaly analysis and screening. Use the 3σ principle to identify points of abnormal parameter fluctuation and calculate parameter stability indicators. Focus on analyzing frequently abnormal parameters to determine whether the cause is equipment failure or environmental interference. Principal component analysis is also used to identify monitoring indicators that are critical for threat assessment. Parameters with strong discriminative capabilities are retained as key monitoring indicators, while redundant or unstable parameters are eliminated to obtain parameter screening results. Based on the parameter screening results, establish a mapping between monitoring thresholds and actual threats. By analyzing historical alarm data, statistically analyze the correspondence between different parameter values ​​and threat levels. A decision tree approach is used to construct a multi-level judgment model for parameter thresholds. Combined judgment conditions are set, taking into account the interactions between parameters. These judgment rules are organized into a monitoring threshold mapping table to clearly define the alarm threshold and judgment logic for each parameter.

[0098] Compare the newly constructed monitoring threshold mapping table with the existing warning rules item by item. Check the judgment conditions, threshold settings, and trigger logic of each rule. Mark items where thresholds have changed, judgment logic needs to be adjusted, and rules need to be supplemented or deleted. Categorize and organize the rule items that need to be updated to form a rule update list. For each update item, record the content, reason, and scope of impact of the update in detail. Update the original rules according to the rule update list. Use an incremental update method to replace the rules that need to be modified item by item. During the update process, pay attention to maintaining the consistency of the rules to avoid conflicts between rules. Perform logical verification on the updated rules to ensure the integrity and rationality of the rules. Form an updated perimeter security monitoring strategy, including parameter configuration, judgment rules, and disposal procedures.

[0099] For example, in perimeter monitoring practices, false alarms frequently occurred at night. Execution data was analyzed to extract key parameters, such as the infrared sensor's temperature threshold, the video surveillance system's contrast parameter, and the vibration sensor's sensitivity. Statistical analysis showed that these parameters varied significantly under different time periods and weather conditions. Data screening revealed that the temperature threshold was too rigid and failed to account for seasonal variations, while the vibration sensor's sensitivity was clearly inadequate on rainy days. Based on this, a new threshold mapping was constructed, adjusting the temperature threshold to dynamically adjust with the season and incorporating weather factors into the vibration sensitivity decision. Comparing existing rules revealed several items requiring updates, such as replacing the fixed temperature difference threshold with a relative temperature difference and adding special handling rules for rainy days. The updated monitoring strategy has effectively reduced false alarms and improved monitoring accuracy in practice.

[0100] The above describes the smart airport perimeter security monitoring method in the embodiment of the present application. The following describes the smart airport perimeter security monitoring system in the embodiment of the present application. Figure 3 In one embodiment of the present application, a smart airport perimeter security monitoring system includes:

[0101] The processing module 201 is used to collect monitoring information of the enclosed area through a multi-type sensor array, and perform time synchronization processing on the collected monitoring information through a time synchronization server to obtain multi-source synchronous monitoring data;

[0102] The noise reduction module 202 is used to perform spatial registration and noise reduction processing on the multi-source synchronous monitoring data using the spatial registration system, and dynamically configure weights according to the reliability of each sensor to generate perimeter situation fusion data;

[0103] Extraction module 203 is used to extract and analyze spatiotemporal features based on perimeter situation fusion data, construct perimeter intrusion feature representations using multi-level security features, and then analyze them according to security threat level assessment rules to obtain perimeter threat assessment results;

[0104] Matching module 204 is used to determine the security warning level based on the perimeter threat assessment results through a dynamic threshold system, and match response measures from the plan library based on historical handling experience to form a perimeter security handling plan;

[0105] Verification module 205 is used to establish a security resource scheduling strategy based on the perimeter security disposal plan, and verify the plan through the situation simulation platform to obtain the optimal perimeter prevention and control plan;

[0106] The screening module 206 is used to evaluate and screen perimeter security monitoring parameters based on the execution data of the optimal perimeter prevention and control plan, and adjust the monitoring thresholds and warning rules according to the screening results to generate an updated perimeter security monitoring strategy.

[0107] Through the collaborative efforts of the aforementioned components, monitoring information from the perimeter area is collected through a multi-type sensor array and time synchronization is performed using a time synchronization server. This solves the problem of temporal consistency of data from different sensors and ensures the synchronization and integrity of multi-source monitoring data. A spatial registration system is used to perform spatial registration and noise reduction on the multi-source synchronous monitoring data, and dynamic weighting is configured based on sensor reliability, effectively improving the accuracy and reliability of data fusion. Spatiotemporal features are extracted and analyzed from the fused perimeter situation data, and a perimeter intrusion feature representation is constructed through multi-level security features, enabling accurate identification of intrusion threats. A dynamic threshold system is used to determine the security warning level, and response measures are matched from a plan library based on historical handling experience, improving the accuracy of warnings and the targeted nature of handling. By establishing a security resource scheduling strategy and verifying the plan using a situation simulation platform, the optimal allocation of prevention and control resources is achieved. Perimeter security monitoring parameters are evaluated and screened, and monitoring thresholds and warning rules are dynamically adjusted based on the screening results, establishing an adaptive monitoring strategy update mechanism. The overall solution forms a complete closed-loop monitoring system. From data collection, analysis and processing, threat identification to emergency response, each link is closely connected and data flows smoothly, which greatly improves the intelligent level of airport perimeter security monitoring. The solution fully utilizes the complementary advantages of multi-source data and effectively solves the problems existing in traditional monitoring methods through intelligent analysis methods and adaptive response mechanisms.

[0108] Based on the same technical concept, the embodiment of the present application also provides an electronic device. Figure 43 is a schematic diagram of the structure of an electronic device 300 provided in an embodiment of the present application, including a processor 301, a memory 302, and a bus 303. The memory 302 is used to store execution instructions and includes a memory 3021 and an external memory 3022. The memory 3021 is also referred to as internal memory and is used to temporarily store operation data in the processor 301 and data exchanged with an external memory 3022 such as a hard disk. The processor 301 exchanges data with the external memory 3022 through the memory 3021. When the electronic device 300 is running, the processor 301 and the memory 302 communicate via the bus 303.

[0109] The present application also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the computer executes the steps of the smart airport perimeter security monitoring method.

[0110] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0111] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

[0112] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A smart airport perimeter security monitoring method, characterized in that: The smart airport perimeter security monitoring method includes: The monitoring information of the enclosed area is collected through a multi-type sensor array, and the collected monitoring information is time-synchronized through a time synchronization server to obtain multi-source synchronous monitoring data; The spatial registration system is used to perform spatial registration and noise reduction on multi-source synchronous monitoring data, and dynamic weight configuration is performed according to the reliability of each sensor to generate perimeter situation fusion data; Based on the perimeter situation fusion data, the spatiotemporal features are extracted and analyzed, and the perimeter intrusion feature representation is constructed through multi-level security features. Then, the perimeter threat assessment result is obtained by analyzing it according to the security threat level assessment rules. Based on the perimeter threat assessment results, the security warning level is determined through a dynamic threshold system, and response measures are matched from the plan library based on historical handling experience to form a perimeter security handling plan; Establish a security resource scheduling strategy based on the perimeter security disposal plan, and verify the plan through the situation simulation platform to obtain the optimal perimeter prevention and control plan; Based on the execution data of the optimal perimeter control plan, the perimeter security monitoring parameters are evaluated and screened, and the monitoring thresholds and warning rules are adjusted according to the screening results to generate an updated perimeter security monitoring strategy; The spatial registration system is used to perform spatial registration and noise reduction on the multi-source synchronous monitoring data, and dynamically configure weights according to the reliability of each sensor to generate boundary situation fusion data, including: performing spatial coordinate conversion on the multi-source synchronous monitoring data, unifying the data collected by different sensors into the same spatial coordinate system, and obtaining unified coordinate system monitoring data; performing spatial overlapping area identification on the unified coordinate system monitoring data, extracting data features of the overlapping area, and obtaining overlapping area feature data; performing noise intensity analysis on the overlapping area feature data, establishing a signal interference model, eliminating interference signals, and obtaining noise-reduced feature data; evaluating the signal stability of each sensor in the noise-reduced feature data, calculating the signal fluctuation coefficient, and obtaining a sensor reliability index; performing weight calculation on the noise-reduced feature data according to the sensor reliability index, establishing a multi-source data weighted fusion matrix, and obtaining weighted fusion data; organizing and arranging the weighted fusion data according to spatiotemporal correlation, performing data consistency verification, and generating the boundary situation fusion data; The method comprises: extracting control task elements from the perimeter security disposal plan, statistically analyzing the demand for human and equipment resources, and obtaining scheduling demand data; classifying and arranging the scheduling demand data according to resource types, comparing the existing resource status, and forming resource matching data; performing spatiotemporal distribution analysis on the resource matching data, dividing resource scheduling priorities, and establishing the security resource scheduling strategy; inputting the security resource scheduling strategy into the situation deduction platform, performing scenario simulation and analysis, and obtaining deduction verification data; quantitatively evaluating the control effect in the deduction verification data, extracting key indicator parameters, and generating solution evaluation data; and integrating the strategies with the best control effect in the solution evaluation data to form the optimal perimeter control plan. The method extracts and analyzes the spatiotemporal features based on the perimeter situation fusion data, constructs the perimeter intrusion feature representation through multi-level security features, and then analyzes it according to the security threat level assessment rules to obtain the perimeter threat assessment result, including: segmenting the perimeter situation fusion data into time series, each time period is 5 minutes, extracting the time series change features for the data in each time period to obtain time series feature data; dividing the time series feature data into spatial regions, calculating the data distribution features in each region to obtain spatial feature data; correlating the time series feature data with the spatial feature data, establishing a feature correlation matrix, and generating the multi-level security features; performing abnormal behavior analysis based on the multi-level security features, extracting the intrusion behavior feature sequence, and constructing the perimeter intrusion feature representation; calculating the matching degree between the perimeter intrusion feature representation and the security threat level assessment rules, marking the threat level, and obtaining the threat level labeled data; aggregating and analyzing the threat level labeled data according to the spatiotemporal dimensions, and outputting the perimeter threat assessment result.

2. The smart airport perimeter security monitoring method according to claim 1 is characterized in that: The monitoring information of the enclosed area is collected by a multi-type sensor array, and the collected monitoring information is time synchronized by a time synchronization server to obtain multi-source synchronous monitoring data, including: The multi-type sensor array scans the fenced area at multiple angles, with the video monitoring subsystem collecting visible light image data, the infrared thermal imaging device collecting thermal imaging data, the vibrating optical fiber collecting ground vibration data, and the millimeter-wave radar collecting airspace detection data to obtain original monitoring information; The original monitoring information is grouped and marked according to the monitoring time, and a unified timestamp code is assigned to each group of original monitoring information to obtain monitoring information with a timestamp; Dividing the monitoring information with the timestamp into time windows, correlating and matching the monitoring information within the same time window to obtain time-correlated monitoring information; Performing signal quality evaluation on the time-correlated monitoring information, eliminating monitoring information with a signal-to-noise ratio below a preset threshold, and obtaining valid monitoring information; Performing time synchronization calibration on the effective monitoring information, aligning the monitoring information collected by different sensors to a unified time base, and obtaining time-calibrated monitoring information; The time calibration monitoring information is subjected to a data integrity check, and the time points of the missing data are interpolated and supplemented to generate the multi-source synchronous monitoring data.

3. The smart airport perimeter security monitoring method according to claim 1 is characterized in that: Based on the perimeter threat assessment results, the security warning level is determined through a dynamic threshold system, and response measures are matched from the plan library based on historical handling experience to form a perimeter security handling plan, including: Performing time window analysis on the perimeter threat assessment results, extracting threat fluctuation characteristics, and obtaining threat trend data; Comparing and analyzing the threat trend data with historical data, calculating the threat deviation value, and obtaining the threat threshold parameter; The threat threshold parameters are graded according to the threat degree, and the warning intervals are divided to obtain security warning level data; Calculate the similarity between the safety warning level data and historical handling experience, extract handling elements, and obtain handling matching data; Performing scenario adaptability analysis on the disposal matching data, screening response measures from the plan library, and obtaining disposal response data; The disposal response data are prioritized and combined to form the perimeter security disposal plan.

4. The smart airport perimeter security monitoring method according to claim 1 is characterized in that: The execution data of the optimal perimeter control plan is used to evaluate and screen perimeter security monitoring parameters, and the monitoring thresholds and warning rules are adjusted according to the screening results to generate an updated perimeter security monitoring strategy, including: Extracting perimeter security monitoring parameters from the execution data of the optimal perimeter prevention and control plan, classifying and arranging the parameters according to parameter type, and obtaining a monitoring parameter set; Performing statistical analysis on the monitoring parameter set, calculating the fluctuation range and distribution characteristics of each parameter, and forming parameter evaluation data; Based on the parameter evaluation data, abnormal fluctuation parameters are eliminated, key monitoring indicators are extracted, and parameter screening results are obtained; Based on the parameter screening results, the corresponding relationship between each monitoring threshold and the actual threat is analyzed, and a monitoring threshold mapping table is constructed; Compare the monitoring threshold mapping table with the existing warning rules, mark the rule items that need to be updated, and generate a rule update list; The updated items in the rule update list replace the original rules to generate the updated perimeter security monitoring policy.

5. A smart airport perimeter security monitoring system, used to implement the smart airport perimeter security monitoring method according to any one of claims 1 to 4, characterized in that: The smart airport perimeter security monitoring system includes: A processing module is used to collect monitoring information of the enclosed area through a multi-type sensor array, and perform time synchronization processing on the collected monitoring information through a time synchronization server to obtain multi-source synchronous monitoring data; The noise reduction module is used to perform spatial registration and noise reduction on multi-source synchronous monitoring data using the spatial registration system, and dynamically configure weights based on the reliability of each sensor to generate perimeter situation fusion data; The extraction module is used to extract and analyze spatiotemporal features based on perimeter situation fusion data, construct perimeter intrusion feature representations through multi-level security features, and then analyze them according to security threat level assessment rules to obtain perimeter threat assessment results; The matching module is used to determine the security warning level based on the perimeter threat assessment results through a dynamic threshold system, and match response measures from the plan library based on historical disposal experience to form a perimeter security disposal plan; The verification module is used to establish a security resource scheduling strategy based on the perimeter security disposal plan, and verify the plan through the situation simulation platform to obtain the optimal perimeter prevention and control plan; The screening module is used to evaluate and screen perimeter security monitoring parameters based on the execution data of the optimal perimeter prevention and control plan, and adjust the monitoring thresholds and warning rules according to the screening results to generate an updated perimeter security monitoring strategy.

6. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor and the memory communicate via the bus. When the machine-readable instructions are executed by the processor, the steps of the smart airport perimeter security monitoring method as described in any one of claims 1 to 4 are performed.

7. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the smart airport perimeter security monitoring method according to any one of claims 1 to 4 is implemented.

Images