An intrusion detection method and device for a perimeter security system

Abstract

The present invention discloses an intrusion detection method and device applied to a perimeter security system, relating to the technical field of intrusion detection. The present invention utilizes adaptive background modeling combined with time series analysis to dynamically update the background model, maintains background stability in dynamic environments such as illumination changes and swaying leaves, and distinguishes different types of background changes through a Gaussian mixture model, which can adapt to the coexistence of long-term static backgrounds and short-term dynamic changes; in the target detection stage, the front and back frame difference method and the background subtraction method are combined to extract moving targets using the complementary characteristics of the two; in the target classification and behavior analysis stage, the spatial morphological characteristics of the target are extracted, and the target movement trend is predicted in combination with time series analysis, and the Kalman filter is used for trajectory prediction, so that the tracking stability can be maintained even when the target is temporarily occluded or moves slowly.

Description

Technical Field

[0001] The present invention relates to the technical field of intrusion detection technology, and in particular to an intrusion detection method and device applied to a perimeter security system. Background Art

[0002] To ensure safety, most outdoor parking areas are equipped with intrusion detection devices. Traditional intrusion detection technologies mainly rely on video surveillance, motion detection and target detection algorithms, or use frame difference and background subtraction technology to analyze changes between video frames to determine whether an intruder has entered the monitored area.

[0003] However, the outdoor parking environment is complex, with a large number of dynamic interference factors in the background, such as wind-blown leaves, changes in light and shadow, and dust. These factors may cause false alarms, making it difficult for the detection system to accurately distinguish between real intruders and environmental noise. In addition, static backgrounds such as trees and vehicles in the parking lot may be similar in shape to intruder targets, further increasing the risk of misjudgment. In low-light or long-distance monitoring scenarios, the contrast between the target and the background is reduced. Traditional target detection algorithms such as YOLO only focus on spatial information and have difficulty in accurately extracting boundaries, resulting in a decrease in detection accuracy.

[0004] In order to reduce the background false detection rate, some traditional methods introduce background modeling, motion detection optimization and multimodal fusion strategies. The background modeling method continuously learns scene changes and constructs a stable background model in areas where the target has not been detected for a long time to reduce false alarms, but it is still prone to failure in environments such as wind and grass movement, water wave reflection, etc.; and motion detection optimization relies on timing information for analysis, such as using optical flow or front and back frame matching to distinguish between moving objects and static background interference, but when the intrusion target moves slowly or is obscured, the detection effect is significantly reduced; it can be seen that in complex background environments, there is still a high false detection rate, and there is an urgent need for an intruder detection method and device suitable for field parking perimeter security systems to improve detection accuracy and reduce the impact of environmental interference. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] The present invention provides an intrusion detection method and device for use in perimeter security systems to solve the problems of traditional intrusion detection methods having a high false detection rate in complex backgrounds, being affected by dynamic interference, low contrast, and target occlusion, having insufficient detection stability, and being difficult to effectively identify real intruders.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides an intrusion detection device for a perimeter security system, comprising:

[0009] An environmental perception module is used to collect real-time image data of the monitored area through a visible light camera and a thermal imaging sensor, and to perform noise filtering and preprocessing on the image data;

[0010] The target detection and optimization module uses the previous and next frame difference method to detect the dynamically changing areas in the scene based on the updated background model, and combines the background subtraction method to eliminate long-term stable background information and extract the moving target area;

[0011] The target classification and behavior analysis module extracts the spatial form and motion trajectory characteristics of the intruder based on the optimized moving target area, predicts the target movement trend based on time series analysis, and generates classification and behavior analysis results;

[0012] During the classification and behavior analysis process, a density cluster analysis method is used to detect anomalies in the motion trajectory, identify the type of intruder, and determine whether there is abnormal behavior based on the motion characteristics and spatiotemporal location of the intruder;

[0013] The alarm triggering and response module adjusts the target detection strategy based on the classification and behavior analysis results, and triggers an alarm when the preset alarm conditions are met.

[0014] As a preferred solution of the intrusion detection device applied to the perimeter security system described in the present invention, wherein: in the environmental perception module, an adaptive background modeling method is used to construct a background model, dynamic learning is performed on areas where no intruders are detected for a long time, and the background model is updated based on time series analysis. The updated background model serves as the input of the target detection and optimization module.

[0015] As a preferred solution of the intrusion detection device applied to the perimeter security system described in the present invention, in which: during the extraction process of the moving target area, adaptive contrast enhancement technology is used to improve the recognizability of the target area, and the target boundary is optimized based on edge information. The optimized moving target area is used as the input of the target classification and behavior analysis module.

[0016] In a second aspect, the present invention provides an intruder detection method for a perimeter security system, comprising:

[0017] Step S1, collecting real-time image data of the monitored area through a visible light camera and a thermal imaging sensor, and performing noise filtering and preprocessing on the image data;

[0018] Adaptive background modeling is used to build a background model, dynamically learn areas where no intruders have been detected for a long time, and update the background model based on time series analysis.

[0019] Step S2: Based on the background model updated in step S1, the frame difference method is used to detect the dynamically changing area in the scene, and the background subtraction method is combined to eliminate the long-term stable background information and extract the moving target area;

[0020] In the process of extracting the moving target area, an adaptive contrast enhancement technique is used to improve the recognizability of the target area, and the target boundary is optimized based on edge information;

[0021] Step S3, based on the optimized moving target area in step S2, extracting the spatial form and movement trajectory characteristics of the intruder in the moving target area, and predicting the target movement trend based on time series analysis to generate classification and behavior analysis results;

[0022] Step S4: Adjust the target detection strategy based on the classification and behavior analysis results, and trigger an alarm when the preset alarm conditions are met.

[0023] As a preferred embodiment of the intrusion detection method for a perimeter security system described in the present invention, the steps of constructing a background model using an adaptive background modeling method, dynamically learning areas where no intruders have been detected for a long time, and updating the background model based on time series analysis are as follows:

[0024] Initialize the background model, and set the input image sequence to be: I t (x,y),

[0025] Among them, I t (x,y) represents the grayscale or color value of the pixel point (x,y) at time t, t represents the time series index, and x,y represents the pixel coordinates in the image.

[0026] The background model B t (x,y) is initialized to the mean of the previous N frames:

[0027]

[0028] Among them, B0(x,y) represents the initial background model, N is the number of initialization frames,

[0029] Adaptive Gaussian mixture model GMM is used to update the background, and the background distribution is defined as K Gaussian components. The probability distribution calculation formula is:

[0030]

[0031] Among them, P(I t (x,y)) represents the pixel value I t The probability distribution of (x,y), K represents the number of Gaussian distributions, w i (x,y,t) is the weight of the i-th Gaussian component, μ i (x,y,t) is the mean, is the normal distribution with variance, μ i (x,y,t) is the mean of the i-th Gaussian component, is the variance of the i-th Gaussian component,

[0032] The Gaussian component parameter update method is:

[0033] If the current pixel value I t If (x,y) belongs to a Gaussian component, then update its mean and variance. The update formula is:

[0034] μ i (x,y,t+1)=(1-α)μ i (x,y,t)+αI t (x,y),

[0035]

[0036] Among them, α is the learning rate,

[0037] If I t If (x,y) does not belong to any existing Gaussian component, then replace it with the Gaussian component with the smallest weight:

[0038] w i (x,y,t+1)=(1-η)w i (x,y,t)+η,

[0039] Where η is the initialization weight of the new component;

[0040] The background model is updated using the time series analysis method, and the exponentially weighted moving average (EWMA) is used to smooth the historical data. The update formula is:

[0041] B t (x,y)=λI t (x,y)+(1-λ)B t-1 (x,y),

[0042] Among them, B t (x,y) is the background model value at time t, λ is the time series smoothing factor, and its value range is (0,1);

[0043] For areas where no intruders are detected for a long time, an adaptive learning rate is used to adjust the background update. The adjustment formula is:

[0044] λ′=λ·exp(-γ·T stable ),

[0045] Among them, λ′ is the dynamically adjusted learning rate, γ is the adjustment parameter, T stable Indicates the stable time during which no intruders are detected in the area.

[0046] As a preferred embodiment of the intrusion detection method for a perimeter security system described in the present invention, the steps of detecting the dynamically changing area in the scene by using the front and back frame difference method and removing the long-term stable background information by combining the background subtraction method to extract the moving target area are as follows:

[0047] The pixel change between the current frame and the previous frame is calculated using the difference between the previous and next frames. The calculation formula is:

[0048] D t (x,y)=|I t (x,y)-I t-1 (x,y)|,

[0049] Among them, D t (x,y) represents the inter-frame change value of the pixel point (x,y) at time t.

[0050] Use the binarization method to extract the motion area:

[0051] If D t (x,y)>θ d , then M t (x,y)=1, otherwise M t (x,y)=0,

[0052] Among them, M t (x, y) is a binary motion mask, 1 represents the motion area, 0 represents the background, θ d is the frame difference binarization threshold;

[0053] Combined with the background subtraction method to remove the stable background, based on the background model B generated in step S1 t (x,y), calculate the foreground area, the calculation formula is:

[0054] F t (x,y)=|I t (x,y)-B t (x,y)|,

[0055] Among them, F t (x,y) represents the foreground pixel intensity after background subtraction,

[0056] Use the binarization method to extract the foreground area:

[0057] If F t (x,y)>θ f , then G t (x,y)=1, otherwise Gt (x,y)=0,

[0058] Among them, G t (x,y) is the foreground binary mask, θ f is the binarization threshold for background subtraction;

[0059] Combining the difference between the previous and next frames and the background subtraction results, we use logical operations to combine the difference between the previous and next frames and the background subtraction method to remove noise points:

[0060] R t (x,y)=M t (x,y)∩G t (x,y),

[0061] Among them, R t (x, y) is the final extracted moving target area, ∩ represents the logical AND operation;

[0062] Optimize the moving target area. The optimization steps include:

[0063] The extracted moving target area R t (x,y) performs contrast enhancement in the following way:

[0064]

[0065] Among them, I′ t (x, y) is the enhanced pixel value, I min ,I max The minimum and maximum pixel values of the motion area,

[0066] Use Sobel operator to calculate the edge:

[0067]

[0068] Among them, E t (x,y) is the edge strength, G x ,G y Represent the gradients in the horizontal and vertical directions respectively,

[0069] The final optimized moving target area is O t (x,y):

[0070] O t (x,y)=R t (x,y)∪E t (x,y),

[0071] Among them, O t (x, y) is the target area that is finally extracted, and ∪ represents a logical OR operation.

[0072] As a preferred embodiment of the intruder detection method for a perimeter security system described in the present invention, in the process of classification and behavior analysis, a density cluster analysis method is used to detect abnormalities in the motion trajectory, identify the intruder category, and determine whether abnormal behavior exists based on the motion characteristics and spatiotemporal location of the intruder. The abnormal behavior includes:

[0073] a) The target enters the preset sensitive area,

[0074] b) The target stays in the monitoring area for a long time exceeding the set threshold.

[0075] As a preferred embodiment of the intruder detection method for a perimeter security system described in the present invention, the steps of extracting the spatial form and motion trajectory characteristics of the intruder in the moving target area, predicting the target motion trend based on time series analysis, and generating classification and behavior analysis results are as follows:

[0076] Calculate the geometric characteristics of the target area, including area A t , center of gravity C t , aspect ratio r t , the calculation formulas are:

[0077]

[0078]

[0079] Among them, A t represents the area of the target area, C t is the coordinate of the center of gravity of the target area, w t ,h t is the width and height of the target area, r t is the aspect ratio of the target area,

[0080] Use Kalman filtering to predict the target trajectory and define the state vector X t :

[0081]

[0082] The update formula is:

[0083] X t+1 =FX t +W t ,

[0084] Among them, X t is the target state, including the position (x t ,y t ) and speed (v x ,v y ), F is the state transfer matrix, W tis the process noise,

[0085] Use density clustering to analyze motion trajectories, calculate trajectory point density and classify targets:

[0086]

[0087] Among them, Class(X t ) represents the target state X at time t t Category identification, P i (X t ) is the trajectory probability of category i.

[0088] As a preferred embodiment of the intruder detection method for a perimeter security system according to the present invention, in step S4, the target detection strategy is adjusted in the following manner:

[0089] If an intruder is detected but the confidence level is lower than the set threshold, a multi-frame fusion strategy is used to enhance the target features;

[0090] If the classification and behavior analysis results meet the alarm conditions, an alarm is triggered and the detection results are reconfirmed based on the visible light and thermal imaging dual-modal data.

[0091] As a preferred embodiment of the intrusion detection method for a perimeter security system described in the present invention, the steps of adjusting the target detection strategy based on the classification and behavior analysis results and triggering an alarm when a preset alarm condition is met are as follows:

[0092] If an intruder is detected but the confidence level is lower than the set threshold θ c , then a multi-frame fusion strategy is used to enhance the target features, and the adjustment formula is:

[0093]

[0094] Among them, I′ t (x,y) is the fused image, N is the number of fused frames,

[0095] If the target meets the alarm conditions, the alarm is triggered and the target is reconfirmed based on the dual-modal data.

[0096]

[0097] Where S represents the cumulative trajectory classification confidence from t = 0 to t = T, T represents the maximum time range of trajectory analysis, and P t (X t ) represents the target state X at time t t The confidence level of a classification belonging to a certain category, if S>θ s , triggering an alarm.

[0098] The beneficial effects of the present invention are as follows: the present invention utilizes adaptive background modeling combined with time series analysis to dynamically update the background model, maintains background stability in dynamic environments such as lighting changes and swaying leaves, and distinguishes different types of background changes through a Gaussian mixture model, and can adapt to the coexistence of long-term static background and short-term dynamic changes.

[0099] In the target detection stage, the present invention combines the front-to-back frame difference method with the background subtraction method, utilizing their complementary characteristics to extract moving targets. At the same time, adaptive contrast enhancement is used to optimize the recognizability of the target area, and the Sobel operator is used to enhance the target edge details, so that intruders can still be accurately identified in low-contrast environments. In the target classification and behavior analysis stage, the spatial morphological characteristics of the target are extracted, and the target motion trend is predicted by combining time series analysis. Kalman filtering is used for trajectory prediction, so that tracking stability can be maintained even when the target is temporarily occluded or moves slowly.

[0100] The present invention adopts density clustering method to analyze target trajectory, distinguish different types of intruders, and detect abnormal behavior, such as targets entering sensitive areas or staying for a long time, thereby reducing the missed detection rate of abnormal targets and improving the robustness of detection.

[0101] The present invention combines a multi-frame fusion strategy to enhance low-confidence target features and performs target reconfirmation based on visible light and thermal imaging dual-modal data, ensuring detection reliability when alarm conditions are triggered and improving real-time response capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0102] 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 only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0103] Figure 1 Schematic diagram of the framework of the intrusion detection device applied to the perimeter security system of the present invention.

[0104] Figure 2 Schematic diagram of the flow of the intruder detection method applied to the perimeter security system of the present invention. DETAILED DESCRIPTION

[0105] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0106] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0107] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0108] Example 1, reference Figure 1 and Figure 2 This embodiment provides an intrusion detection device for use in a perimeter security system, comprising:

[0109] The environmental perception module is used to collect real-time image data of the monitored area through visible light cameras and thermal imaging sensors, and to perform noise filtering and preprocessing on the image data;

[0110] In the environmental perception module, an adaptive background modeling method is used to construct a background model. Areas where no intruders have been detected for a long time are dynamically learned and updated based on time series analysis. The updated background model serves as input to the target detection and optimization module.

[0111] The target detection and optimization module uses the previous and next frame difference method to detect the dynamically changing areas in the scene based on the updated background model, and combines the background subtraction method to eliminate long-term stable background information and extract the moving target area;

[0112] In the process of extracting the moving target area, adaptive contrast enhancement technology is used to improve the recognizability of the target area, and the target boundary is optimized based on edge information. The optimized moving target area serves as the input of the target classification and behavior analysis module;

[0113] The target classification and behavior analysis module extracts the spatial form and motion trajectory characteristics of the intruder based on the optimized moving target area, predicts the target movement trend based on time series analysis, and generates classification and behavior analysis results;

[0114] During the classification and behavior analysis process, density cluster analysis methods are used to detect anomalies in the motion trajectory, identify the type of intruder, and determine whether there is abnormal behavior based on the motion characteristics and spatiotemporal location of the intruder;

[0115] The alarm triggering and response module adjusts the target detection strategy based on the classification and behavior analysis results, and triggers the alarm when the preset alarm conditions are met.

[0116] This embodiment further provides a detection method of the above-mentioned intrusion detection device applied to a perimeter security system, including:

[0117] Step S1: collect real-time image data of the monitored area through a visible light camera and a thermal imaging sensor, and perform noise filtering and preprocessing on the image data;

[0118] Adaptive background modeling is used to build a background model, dynamically learn areas where no intruders have been detected for a long time, and update the background model based on time series analysis.

[0119] The steps of constructing a background model using the adaptive background modeling method, dynamically learning the area where no intruders are detected for a long time, and updating the background model based on time series analysis are as follows:

[0120] Initialize the background model, and set the input image sequence to be: I t (x,y),

[0121] Among them, I t (x,y) represents the grayscale or color value of the pixel point (x,y) at time t, t represents the time series index, and x,y represents the pixel coordinates in the image.

[0122] The background model B t (x,y) is initialized to the mean of the previous N frames:

[0123]

[0124] Among them, B0(x,y) represents the initial background model, N is the number of initialization frames,

[0125] Adaptive Gaussian mixture model GMM is used to update the background, and the background distribution is defined as K Gaussian components. The probability distribution calculation formula is:

[0126]

[0127] Among them, P(I t (x,y)) represents the pixel value I t The probability distribution of (x,y), K represents the number of Gaussian distributions, w i (x,y,t) is the weight of the i-th Gaussian component, μ i (x,y,t) is the mean, is the normal distribution with variance, μ i (x,y,t) is the mean of the i-th Gaussian component, is the variance of the i-th Gaussian component,

[0128] The Gaussian component parameter update method is:

[0129] If the current pixel value I t If (x,y) belongs to a Gaussian component, then update its mean and variance. The update formula is:

[0130] μ i (x,y,t+1)=(1-α)μ i (x,y,t)+αI t (x,y),

[0131]

[0132] Among them, α is the learning rate,

[0133] If I t If (x,y) does not belong to any existing Gaussian component, then replace it with the Gaussian component with the smallest weight:

[0134] w i (x,y,t+1)=(1-η)w i (x,y,t)+η,

[0135] Where η is the initialization weight of the new component;

[0136] The background model is updated using the time series analysis method, and the exponentially weighted moving average (EWMA) is used to smooth the historical data. The update formula is:

[0137] B t (x,y)=λI t (x,y)+(1-λ)B t-1 (x,y),

[0138] Among them, B t (x,y) is the background model value at time t, λ is the time series smoothing factor, and its value range is (0,1);

[0139] For areas where no intruders are detected for a long time, an adaptive learning rate is used to adjust the background update. The adjustment formula is:

[0140] λ′=λ·exp(-γ·T stable ),

[0141] Among them, λ′ is the dynamically adjusted learning rate, γ is the adjustment parameter, T stable Indicates the stable time in which no intruders are detected in the area;

[0142] Specifically, the initial background is constructed using initial mean calculation, and then dynamically modeled using the Gaussian mixture model (GMM) to make the background model adaptive. The GMM allows multiple Gaussian distributions to represent different types of background changes, such as illumination changes or periodic moving objects (such as swaying leaves). The background is then smoothly updated using the time series analysis (EWMA) method to make it more stable. For areas without intruders for a long time, the learning rate is adjusted using exponential decay to prevent the background model from being over-updated due to short-term noise. This effectively copes with illumination changes and dynamic environmental changes, improving the accuracy and robustness of intruder detection.

[0143] Step S2: Based on the background model updated in step S1, the frame difference method is used to detect the dynamically changing area in the scene, and the background subtraction method is combined to eliminate the long-term stable background information and extract the moving target area;

[0144] In the process of extracting the moving target area, adaptive contrast enhancement technology is used to improve the recognizability of the target area, and the target boundary is optimized based on edge information;

[0145] The method of differentiating the previous and next frames is used to detect the dynamic changing areas in the scene, and the background subtraction method is combined to eliminate the long-term stable background information. The steps of extracting the moving target area are as follows:

[0146] The pixel change between the current frame and the previous frame is calculated using the difference between the previous and next frames. The calculation formula is:

[0147] D t (x,y)=|I t (x,y)-I t-1 (x,y)|,

[0148] Among them, D t (x,y) represents the inter-frame change value of the pixel point (x,y) at time t.

[0149] Use the binarization method to extract the motion area:

[0150] If D t (x,y)>θ d , then M t (x,y)=1, otherwise M t (x,y)=0,

[0151] Among them, M t (x, y) is a binary motion mask, 1 represents the motion area, 0 represents the background, θ d is the frame difference binarization threshold;

[0152] Combined with the background subtraction method to remove the stable background, based on the background model B generated in step S1 t(x,y), calculate the foreground area, the calculation formula is:

[0153] F t (x,y)=|I t (x,y)-B t (x,y)|,

[0154] Among them, F t (x,y) represents the foreground pixel intensity after background subtraction,

[0155] Use the binarization method to extract the foreground area:

[0156] If F t (x,y)>θ f , then G t (x,y)=1, otherwise G t (x,y)=0,

[0157] Among them, G t (x,y) is the foreground binary mask, θ f is the binarization threshold for background subtraction;

[0158] Combining the difference between the previous and next frames and the background subtraction results, we use logical operations to combine the difference between the previous and next frames and the background subtraction method to remove noise points:

[0159] R t (x,y)=M t (x,y)∩G t (x,y),

[0160] Among them, R t (x, y) is the final extracted moving target area, ∩ represents the logical AND operation;

[0161] Optimize the moving target area. The optimization steps include:

[0162] The extracted moving target area R t (x,y) performs contrast enhancement in the following way:

[0163]

[0164] Among them, I′ t (x, y) is the enhanced pixel value, I min ,I max The minimum and maximum pixel values of the motion area are calculated using the Sobel operator:

[0165]

[0166] Among them, E t (x,y) is the edge strength, G x,G y Represent the gradients in the horizontal and vertical directions respectively. The final optimized moving target area is O t (x,y):

[0167] O t (x,y)=R t (x,y)∪E t (x,y),

[0168] Among them, O t (x, y) is the target area finally extracted, ∪ represents the logical OR operation;

[0169] Specifically, the frame difference method is used to detect the dynamic changing area in the scene, and the background subtraction method is combined to eliminate the long-term stable background information, and finally the moving target area is extracted;

[0170] Calculate the difference between the previous and next frames to generate the motion area mask, then use the background modeling method to calculate the background subtraction foreground and perform binarization processing, and combine the two to obtain the final motion target area;

[0171] To improve the quality of the target area, an adaptive contrast enhancement method is used to improve the recognizability, and the Sobel operator is used to optimize the edge information to generate the final moving target area and effectively suppress noise;

[0172] Step S3, based on the optimized moving target area in step S2, extracting the spatial form and movement trajectory characteristics of the intruder in the moving target area, and predicting the target movement trend based on time series analysis to generate classification and behavior analysis results;

[0173] During the classification and behavior analysis process, density cluster analysis is used to detect anomalies in the motion trajectory, identify the intruder category, and determine whether there is abnormal behavior based on the intruder's motion characteristics and spatiotemporal location. Abnormal behavior includes:

[0174] a) The target enters the preset sensitive area,

[0175] b) The target stays in the monitoring area for a long time exceeding the set threshold,

[0176] The steps to extract the spatial form and motion trajectory characteristics of the intruder in the moving target area, and predict the target movement trend based on time series analysis, and generate classification and behavior analysis results are as follows:

[0177] Calculate the geometric characteristics of the target area, including area A t , center of gravity C t , aspect ratio r t , the calculation formulas are:

[0178]

[0179] Among them, A t represents the area of the target area, C t is the coordinate of the center of gravity of the target area, w t ,h t is the width and height of the target area, x t is the aspect ratio of the target area,

[0180] Use Kalman filtering to predict the target trajectory and define the state vector X t :

[0181]

[0182] The update formula is:

[0183] X t+1 =FX t +W t ,

[0184] Among them, X t is the target state, including the position (x t ,y t ) and speed (v x ,v y ), F is the state transfer matrix, W t is the process noise,

[0185] Use density clustering to analyze motion trajectories, calculate trajectory point density and classify targets:

[0186]

[0187] Among them, Class(X t ) represents the target state X at time t t Category identification, P i (X t ) is the trajectory probability of category i;

[0188] Specifically, here we extract spatial morphological features based on the optimized moving target region, including area, center of gravity and aspect ratio, and use the Kalman filter method to calculate the target motion trajectory;

[0189] In addition, the density clustering method is used to analyze the target trajectory and classify the intruders, effectively identifying different types of intruders. Time series analysis is also combined to predict the future movement trend of the target, improving the accuracy of classification and behavior analysis.

[0190] Step S4: Adjust the target detection strategy based on the classification and behavior analysis results, and trigger an alarm when the preset alarm conditions are met;

[0191] In step S4, the target detection strategy is adjusted in the following ways:

[0192] If an intruder is detected but the confidence level is lower than the set threshold, a multi-frame fusion strategy is used to enhance the target features;

[0193] If the classification and behavior analysis results meet the alarm conditions, an alarm is triggered and the detection results are reconfirmed based on visible light and thermal imaging dual-modal data;

[0194] According to the classification and behavior analysis results, the target detection strategy is adjusted, and the steps to trigger the alarm when the preset alarm conditions are met are as follows:

[0195] If an intruder is detected but the confidence level is lower than the set threshold θ c , then a multi-frame fusion strategy is used to enhance the target features, and the adjustment formula is:

[0196]

[0197] Among them, I′ t (x,y) is the fused image, N is the number of fused frames,

[0198] If the target meets the alarm conditions, the alarm is triggered and the target is reconfirmed based on the dual-modal data.

[0199]

[0200] Where S represents the cumulative trajectory classification confidence from t = 0 to t = T, T represents the maximum time range of trajectory analysis, and P t (X t ) represents the target state X at time t t The confidence level of a classification belonging to a certain category, if >θ s , triggering an alarm;

[0201] Specifically, the detection strategy is dynamically adjusted based on the target classification results, and multi-frame fusion is used to enhance low-confidence targets. If the target meets the preset conditions, it is reconfirmed based on visible light and thermal imaging data to improve the accuracy of alarm triggering.

[0202] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intrusion detection device for a perimeter security system, characterized by: include, An environmental perception module is used to collect real-time image data of the monitored area through a visible light camera and a thermal imaging sensor, and to perform noise filtering and preprocessing on the image data; The target detection and optimization module uses the previous and next frame difference method to detect the dynamically changing areas in the scene based on the updated background model, and combines the background subtraction method to eliminate long-term stable background information and extract the moving target area; The target classification and behavior analysis module extracts the spatial form and motion trajectory characteristics of the intruder based on the optimized moving target area, predicts the target movement trend based on time series analysis, and generates classification and behavior analysis results; During the classification and behavior analysis process, a density cluster analysis method is used to detect anomalies in the motion trajectory, identify the type of intruder, and determine whether there is abnormal behavior based on the motion characteristics and spatiotemporal location of the intruder; An alarm triggering and response module adjusts the target detection strategy based on the classification and behavior analysis results and triggers an alarm when the preset alarm conditions are met; In the target detection and optimization module, an adaptive background modeling method is used to construct a background model, dynamically learn areas where no intruders have been detected for a long time, and update the background model based on time series analysis. The steps are as follows: Initialize the background model, and set the input image sequence to be: I t (x,y), Among them, I t (x,y) represents the grayscale or color value of the pixel point (x,y) at time t, t represents the time series index, and x,y represents the pixel coordinates in the image. The background model B t (x,y) is initialized to the mean of the previous N frames: Among them, B0(x,y) represents the initial background model, N is the number of initialization frames, Adaptive Gaussian mixture model GMM is used to update the background, and the background distribution is defined as K Gaussian components. The probability distribution calculation formula is: Among them, P(I t (x,y)) represents the pixel value I t The probability distribution of (x,y), K represents the number of Gaussian distributions, w i (x,y,t) is the weight of the i-th Gaussian component, μ i (x,y,t) is the mean, is the normal distribution with variance, μ i (x,y,t) is the mean of the i-th Gaussian component, is the variance of the i-th Gaussian component, The Gaussian component parameter update method is: If the current pixel value I t If (x,y) belongs to a Gaussian component, then update its mean and variance. The update formula is: m i (x,y,t+1)=(1-a)μ i (x,y,t)+αI t (x,y), Among them, α is the learning rate, If I t If (x,y) does not belong to any existing Gaussian component, then replace it with the Gaussian component with the smallest weight: w i (x,y,t+1)=(1-η)w i (x,y,t)+η, Where η is the initialization weight of the new component; The background model is updated using the time series analysis method, and the exponentially weighted moving average (EWMA) is used to smooth the historical data. The update formula is: B t (x,y)=λI t (x,y)+(1-λ)B t-1 (x,y), Among them, B t (x,y) is the background model value at time t, λ is the time series smoothing factor, and its value range is (0,1); For areas where no intruders are detected for a long time, an adaptive learning rate is used to adjust the background update. The adjustment formula is: λ′=λ·exp(-γ·T stable ), Among them, λ ' is the dynamically adjusted learning rate, γ is the adjustment parameter, T stable Indicates the stable time during which no intruders are detected in the area.

2. The intrusion detection device for a perimeter security system according to claim 1, characterized in that: In the environmental perception module, an adaptive background modeling method is used to construct a background model, dynamically learn areas where no intruders are detected for a long time, and update the background model based on time series analysis. The updated background model serves as the input of the target detection and optimization module.

3. The intrusion detection device for a perimeter security system according to claim 2, wherein: In the process of extracting the moving target area, adaptive contrast enhancement technology is used to improve the recognizability of the target area, and the target boundary is optimized based on edge information. The optimized moving target area is used as the input of the target classification and behavior analysis module.

4. A method for detecting an intruder applied to a perimeter security system, based on the intruder detection device applied to a perimeter security system according to any one of claims 1 to 3, characterized in that: include: Step S1, collecting real-time image data of the monitored area through a visible light camera and a thermal imaging sensor, and performing noise filtering and preprocessing on the image data; Adaptive background modeling is used to build a background model, dynamically learn areas where no intruders have been detected for a long time, and update the background model based on time series analysis. Step S2: Based on the background model updated in step S1, the frame difference method is used to detect the dynamically changing area in the scene, and the background subtraction method is combined to eliminate the long-term stable background information and extract the moving target area; In the process of extracting the moving target area, an adaptive contrast enhancement technique is used to improve the recognizability of the target area, and the target boundary is optimized based on edge information; Step S3, based on the optimized moving target area in step S2, extracting the spatial form and movement trajectory characteristics of the intruder in the moving target area, and predicting the target movement trend based on time series analysis to generate classification and behavior analysis results; Step S4: Adjust the target detection strategy based on the classification and behavior analysis results, and trigger an alarm when the preset alarm conditions are met.

5. The intrusion detection method for a perimeter security system according to claim 4, wherein: The steps of using the frame difference method to detect the dynamic change area in the scene and combining the background subtraction method to eliminate the long-term stable background information and extract the moving target area are as follows: The pixel change between the current frame and the previous frame is calculated using the difference between the previous and next frames. The calculation formula is: D t (x,y)=|I t (x,y)-I t-1 (x,y)|, Among them, D t (x,y) represents the inter-frame change value of the pixel point (x,y) at time t. Use the binarization method to extract the motion area: If D t (x,y)>θ d , then M t (x,y)=1, otherwise M t (x,y)=0, Among them, M t (x, y) is a binary motion mask, 1 represents the motion area, 0 represents the background, θ d is the frame difference binarization threshold; Combined with the background subtraction method to remove the stable background, based on the background model B generated in step S1 t (x,y), calculate the foreground area, the calculation formula is: F t (x,y)=|I t (x,y)-B t (x,y)|, Among them, F t (x,y) represents the foreground pixel intensity after background subtraction, Use the binarization method to extract the foreground area: If F t (x,y)>θ f , then G t (x,y)=1, otherwise G t (x,y)=0, Among them, G t (x,y) is the foreground binary mask, θ f is the binarization threshold for background subtraction; Combining the difference between the previous and next frames and the background subtraction results, we use logical operations to combine the difference between the previous and next frames and the background subtraction method to remove noise points: R t (x,y)=M t (x,y)∩G t (x,y), Among them, R t (x, y) is the final extracted moving target area, ∩ represents the logical AND operation; Optimize the moving target area. The optimization steps include: The extracted moving target area R t (x,y) performs contrast enhancement in the following way: Among them, I' t (x, y) is the enhanced pixel value, I min ,I max The minimum and maximum pixel values of the motion area, Use Sobel operator to calculate the edge: Among them, E t (x,y) is the edge strength, G x ,G y Represent the gradients in the horizontal and vertical directions respectively, The final optimized moving target area is O t (x,y): EITHER t (x,y)=R t (x,y)∪E t (x,y), Among them, O t (x, y) is the target area that is finally extracted, and ∪ represents a logical OR operation.

6. The intrusion detection method for a perimeter security system according to claim 5, characterized in that: During the classification and behavior analysis process, a density cluster analysis method is used to detect anomalies in the motion trajectory, identify the type of intruder, and determine whether there is abnormal behavior based on the motion characteristics and spatiotemporal location of the intruder. The abnormal behavior includes: a) The target enters the preset sensitive area, b) The target stays in the monitoring area for a long time exceeding the set threshold.

7. The intrusion detection method for a perimeter security system according to claim 6, wherein: The steps of extracting the spatial form and motion trajectory characteristics of the intruder in the moving target area, predicting the target movement trend based on time series analysis, and generating classification and behavior analysis results are as follows: Calculate the geometric characteristics of the target area, including area A t , center of gravity C t , aspect ratio r t , the calculation formulas are: Among them, A t represents the area of the target area, C t is the coordinate of the center of gravity of the target area, w t ,h t is the width and height of the target area, r t is the aspect ratio of the target area, Use Kalman filtering to predict the target trajectory and define the state vector X t : The update formula is: X t+1 =FX t +W t , Among them, X t is the target state, including the position (x t ,y t ) and speed (v x ,v y ), F is the state transfer matrix, W t is the process noise, Use density clustering to analyze motion trajectories, calculate trajectory point density and classify targets: Among them, Class(X t ) represents the target state X at time t t Category identification, P i (X t ) is the trajectory probability of category i.

8. The intrusion detection method for a perimeter security system according to claim 7, wherein: In step S4, the target detection strategy is adjusted in the following ways: If an intruder is detected but the confidence level is lower than the set threshold, a multi-frame fusion strategy is used to enhance the target features; If the classification and behavior analysis results meet the alarm conditions, an alarm is triggered and the detection results are reconfirmed based on the visible light and thermal imaging dual-modal data.

9. The intrusion detection method for a perimeter security system according to claim 8, wherein: The steps of adjusting the target detection strategy based on the classification and behavior analysis results and triggering the alarm when the preset alarm conditions are met are: If an intruder is detected but the confidence level is lower than the set threshold θ c , then a multi-frame fusion strategy is used to enhance the target features, and the adjustment formula is: Among them, I' t (x,y) is the fused image, N is the number of fused frames, If the target meets the alarm conditions, the alarm is triggered and the target is reconfirmed based on the dual-modal data. Where S represents the cumulative trajectory classification confidence from t = 0 to t = T, T represents the maximum time range of trajectory analysis, and P t (X t ) represents the target state X at time t t The confidence level of a classification belonging to a certain category, if S>θ s , triggering an alarm.

Images