Anti-intrusion alarm system based on laser ranging technology

Abstract

The invention discloses an anti-intrusion alarm system based on a laser ranging technology, and relates to the technical field of laser ranging, a data acquisition module of the system collects a motion track, a dynamic video and environment information of a target, constructs a target motion model by using a two-dimensional coordinate system, processes a video frame image, and obtains target motion data and a target frame picture; after feature extraction, obtaining target feature data, and preprocessing the environment data, the target trend data and the target feature data to obtain a target risk data set; and carrying out feature analysis, motion analysis and environmental influence analysis according to the target risk data set, calculating an intrusion judgment evaluation index fin to carry out preliminary intrusion behavior evaluation, executing target trend evolution analysis when an evaluation result is consistent with an intrusion feature, and carrying out deep intrusion behavior evaluation by calculating a comprehensive behavior evaluation index zxp. The system has the advantages of high precision, high intelligence and low false alarm rate, and can significantly improve the effect and response capability of anti-intrusion monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of laser ranging, and specifically to an anti-intrusion alarm system based on laser ranging technology. Background Art

[0002] With the continuous change of the social security situation and the advancement of the urbanization process, security prevention has become an issue for all walks of life, especially the core issue in the management of important public facilities and high-risk areas. Modern society faces increasingly complex security threats, posing higher requirements for traditional security prevention means. With the progress of technology, especially the development of laser ranging, video surveillance, and sensor technologies, modern security systems have gradually realized the transformation from traditional manual inspections to automated intelligent monitoring. The social demand for more efficient, accurate, and real-time security protection has promoted the innovation of anti-intrusion alarm technology. Especially in scenarios that require highly accurate monitoring and rapid response, laser ranging technology has shown great application potential in the field of security prevention.

[0003] Traditional anti-intrusion alarm systems usually rely on a single data source, such as motion sensors, infrared sensors, etc. Although these technologies are effective in certain environments, they also have obvious limitations. For example, the detection range of a single sensor is limited and is easily affected by environmental changes, weather factors, and target movements, resulting in a relatively serious phenomenon of false alarms and missed alarms. In addition, existing alarm systems are often not easy to conduct in-depth analysis of the behavior of targets, and can only judge whether a target is an intruder according to preset rules, lacking flexible dynamic judgment capabilities. Facing complex intrusion scenarios, traditional systems are difficult to effectively identify and evaluate the movement trajectories and behavior patterns of targets in real time, and thus are not easy to achieve accurate alarm responses. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides an anti-intrusion alarm system based on laser ranging technology, which solves the problems in the above background art.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: An anti-intrusion alarm system based on laser ranging technology includes a data acquisition module, a data processing module, a feature extraction module, an intrusion analysis module, and a movement trend analysis module;

[0006] The data acquisition module is used to monitor the dynamic movement trajectory, dynamic video, and environmental data of the target in real time based on laser ranging technology, a high-definition camera, and a sensor group;

[0007] The data processing module is used to construct a two-dimensional coordinate system and an image processing platform, process the dynamic movement trajectory of the target in the two-dimensional coordinate system, and process the dynamic video through the image processing platform to obtain target movement trend data and target frame pictures;

[0008] The feature extraction module is used to construct a target recognition model, input the target frame image into the target recognition model to obtain a target image set, extract features to obtain target feature data, and then preprocess the environmental data, target movement data, and target feature data to obtain a target risk data group;

[0009] The intrusion analysis module is used to perform feature analysis, movement analysis, and environmental impact analysis based on the target risk data group, and perform fitting based on the analysis results to obtain an intrusion judgment evaluation index fin for preliminary intrusion behavior evaluation;

[0010] The movement analysis module is used to perform target movement evolution analysis when the preliminary intrusion behavior evaluation conforms to the intrusion characteristics, and perform fitting based on the analysis results and the intrusion judgment evaluation index fin to obtain a comprehensive behavior evaluation index zxp for in-depth intrusion behavior evaluation.

[0011] Preferably, the data acquisition module includes a laser monitoring unit and a data acquisition unit;

[0012] The laser monitoring unit is used to use laser ranging technology in the security control area to monitor the dynamic movement trajectory of the target in real time;

[0013] The laser ranging technology installs a near-infrared laser rangefinder with a protection standard higher than IP65 in the security control area to emit laser beams to the surrounding environment in real time, and monitors the straight line 100 meters outward from the security control area in real time;

[0014] The data acquisition unit is used to monitor the dynamic video and environmental data of the target in the security control area in real time according to the installed high-definition camera and sensor group;

[0015] The high-definition camera is a high-definition camera with a resolution of not less than 1080p, a field of view angle between 90° and 120°, and a frame rate of not less than 30 frames per second, and the installation positions of the high-definition camera and the near-infrared laser rangefinder are aligned in the same coordinate system. The sensor group includes a wind speed sensor and a light sensor.

[0016] Preferably, the data processing module includes a two-dimensional model construction unit, a laser processing unit, and an image processing unit;

[0017] The two-dimensional model construction unit is used to construct a two-dimensional coordinate system for each near-infrared laser rangefinder according to the Cartesian coordinate system. The two-dimensional coordinate system uses the east-west direction as the x-axis, the north-south direction as the y-axis, and the near-infrared laser rangefinder as the origin;

[0018] The laser processing unit is used to process the dynamic movement trajectory of the target detected by the near-infrared laser rangefinder in real time to obtain target movement data, where the target movement data includes target speed v, movement angle θ, target acceleration a, and target direction deviation Δθ;

[0019] Based on the pulsed laser emitted by the near-infrared laser rangefinder and measuring the time interval jt from its emission to the reception of the reflected light, the distance jl between the target and the near-infrared laser rangefinder is calculated in combination with the speed of light c, specifically as follows: After obtaining the distance jl, in combination with the laser emission angle β, the target coordinates (x, y) are calculated, specifically as: (x, y) = (jl * cosβ, jl * sinβ). By continuously monitoring the target coordinates (x t , y t ) and (x t+1 , y t+1 ) at time t and t + 1 by the near-infrared laser rangefinder, the target speed v and movement angle θ are respectively calculated, specifically as: and In the formula, Δt represents the time interval from time t to time t + 1, and arctan represents the arctangent function. Then, the continuously obtained target speed v and movement angle θ are used to calculate the target acceleration a and target direction deviation Δθ, specifically as: Δθ = θ t+1 -θ t , where θ t+1 and θ t respectively represent the movement angles θ at time t + 1 and time t, and v t+1 and v t respectively represent the target speeds v at time t + 1 and time t;

[0020] The image processing unit is used to build an image processing platform, and send the dynamic video of the target captured in real time by the high-definition camera to the image processing platform through the video transmission protocol RTSP. After the image processing platform uses the video capture tool to open the dynamic video of the target, it uses the video processing library to read the content of the dynamic video of the target frame by frame, and reads the frame picture of each frame of the video, and then performs image denoising and image enhancement processing on the frame picture to obtain the target frame picture;

[0021] The image denoising is performed by convolving and smoothing the frame picture using the Gaussian function, and the image enhancement is performed by linearly transforming the pixel values of the frame picture to increase the brightness of the bright area of the frame picture and reduce the darkness of the dark area of the frame picture.

[0022] Preferably, the feature extraction module includes a model training unit, a feature extraction unit, and a data preprocessing unit;

[0023] The model training unit is used to construct a target recognition model based on the convolutional neural network (CNN) as the model framework, collect a large number of intrusion target images after annotating the targets, input them into the target recognition model, perform iterative training on the target recognition model, input the target frame images obtained in real time into the target recognition model, automatically identify the target positions and target boundaries in the target frame images, and then use an image segmentation algorithm to segment the targets from the background to obtain a target image set;

[0024] The feature extraction unit is used to extract features from the target image set to obtain target feature data;

[0025] Use camera calibration software to calibrate the physical size of pixels in the target image set, then use the area calculation algorithm to calculate the image size tc of the target based on the calibrated physical size of pixels, and combine the distance jl obtained by laser ranging technology and the camera focal length f to calculate the actual target size mj. Specifically:

[0026] Convert the target image set from the RGB color space to the HSV color space through an image processing library, count the colors of each pixel in the image in the HSV space, then extract the statistical features of the colors through a color histogram, and quantify the color mean through the statistical method to obtain the target color feature ys;

[0027] After obtaining the color features, convert the target image set into a grayscale image through the weighted average method, compare the grayscale value of each pixel in the image with the grayscale values of its adjacent pixels to form a co-occurrence matrix, and calculate the entropy of the target image set through the co-occurrence matrix to obtain the target texture feature wl.

[0028] Preferably, the data preprocessing unit is used to perform dimensionless processing, denoising, outlier processing, and rate-of-change analysis on the environmental data, target movement data, and target feature data to obtain a target risk data group;

[0029] The dimensionless processing is carried out by the Max-Min maximization method to eliminate the dimensional influence of the stacking impact data and the material stacking data. The denoising is carried out by decomposing the signals at different frequency scales through wavelet transform technology to eliminate the noise influence in the data. The outlier processing is carried out by using the interquartile range method to detect and process the outliers existing in the stacking impact data and the material stacking data;

[0030] The rate-of-change analysis is used to calculate the acceleration rate of change based on the target acceleration a obtained in real time Specifically: In the formula, a t+1 and a t respectively represent the target accelerations a at the t + 1 moment and the t moment, and Δt represents the time interval from the t moment to the t + 1 moment;

[0031] The target risk data group includes an intrusion recognition data group, a dynamic data group, and an environmental data group;

[0032] The intrusion recognition data group includes a laser ranging value jl, a target size mj, a target color feature ys, and a target texture feature wl;

[0033] The dynamic data group includes a speed v, an acceleration a, and an acceleration change rate and a target direction deviation Δθ;

[0034] The environmental data group includes a wind speed fs and a light intensity gz.

[0035] Preferably, the intrusion analysis module includes an intrusion analysis unit and an intrusion judgment unit;

[0036] The intrusion analysis unit is used to perform feature analysis, motion analysis, and environmental impact analysis respectively based on the acquired target risk data group;

[0037] The feature analysis is used to perform summary calculations based on the acquired intrusion recognition data group to obtain a multi-dimensional intrusion recognition index inv. The specific formula is as follows;

[0038]

[0039] In the formula, log represents the logarithmic function, and k represents the reflection coefficient of the target;

[0040] The motion analysis is used to perform summary calculations based on the acquired dynamic data group to obtain a dynamic motion evaluation index mot. The specific formula is as follows;

[0041]

[0042] In the formula, e represents the exponential function, and α represents the relationship coefficient;

[0043] The environmental impact analysis is used to perform summary calculations based on the acquired environmental data group to obtain an environmental interference correction index sbg. The specific formula is as follows;

[0044]

[0045] In the formula, exp represents the exponential decay function.

[0046] Preferably, the intrusion judgment unit includes a comprehensive analysis unit and an intrusion evaluation unit;

[0047] The comprehensive analysis unit is used to perform summary calculations based on the acquired multi-dimensional intrusion recognition index inv, dynamic motion evaluation index mot, and environmental interference correction index sbg to obtain an intrusion judgment evaluation index fin. The specific formula is as follows;

[0048]

[0049] The intrusion assessment unit is used to calculate the mean value of the historical intrusion judgment evaluation index fin based on all historical intrusion judgment evaluation indexes fin that meet the intrusion characteristics and normal behaviors, set a preset intrusion alarm threshold M based on the mean value, and perform a preliminary intrusion behavior assessment with the obtained intrusion judgment evaluation index fin. The specific assessment scheme is as follows;

[0050] When the intrusion judgment evaluation index fin > the intrusion alarm threshold M, it indicates that the target behavior conforms to the intrusion characteristics, and at this time, the target movement evolution analysis is executed;

[0051] When the intrusion judgment evaluation index fin ≤ the intrusion alarm threshold M, it indicates that the target behavior is normal, and continuous monitoring is maintained.

[0052] Preferably, the movement analysis module is used to execute the target movement evolution analysis when the preliminary intrusion behavior assessment conforms to the intrusion characteristics, and specifically includes a path acquisition unit, a movement evolution analysis unit, and a movement intrusion assessment unit;

[0053] The path acquisition unit is used to calculate the target offset based on the target coordinates (x t , y t ) and (x t+1 , y t+1 ) continuously monitored by the near-infrared laser rangefinder at time t and time t + 1, including the displacement offset Δh of the target on the x-axis and the displacement offset Δz on the y-axis. Specifically: Δh = x t+1 - x t , Δz = y t+1 - y t ;

[0054] The movement evolution analysis unit is used to perform a summary calculation based on the obtained target offset to obtain the movement evolution analysis index pat, which quantifies the offset of the target path and the change of the movement trajectory. The specific formula is as follows;

[0055]

[0056] In the formula, T represents the total detection time interval, Δh(t) and Δz(t) respectively represent the displacement offsets of the target relative to the x-axis and y-axis at time t, e represents the exponential function, α represents the time decay coefficient, t represents the time variable, and dt represents the time differential.

[0057] Preferably, the movement intrusion assessment unit includes a comprehensive movement analysis unit and a comprehensive behavior assessment unit;

[0058] The comprehensive trend analysis unit is used to perform summary calculations based on the obtained intrusion judgment evaluation index fin and the trend evolution analysis index pat to obtain the comprehensive behavior evaluation index zxp. The specific formula is as follows;

[0059]

[0060] In the formula, w1 represents the adjustment coefficient of the influence of the trend evolution analysis index pat on the comprehensive behavior evaluation, and w2 represents the control coefficient of the attenuation speed of the influence of the intrusion judgment evaluation index fin on the final score.

[0061] Preferably, the comprehensive behavior evaluation unit is used to preset the intrusion trajectory behavior threshold B according to the security standards in the field of intrusion detection, and perform in-depth intrusion behavior evaluation with the obtained comprehensive behavior evaluation index zxp. The specific evaluation scheme is as follows;

[0062] When the comprehensive behavior evaluation index zxp > the intrusion trajectory behavior threshold B, it indicates that there is an intrusion behavior of the target. At this time, an alarm message is generated and transmitted to the control center through the wireless network to notify relevant personnel to drive away the intrusion target;

[0063] When the comprehensive behavior evaluation index zxp ≤ the intrusion trajectory behavior threshold B, it indicates that the target has strayed in. At this time, a straying-in message is generated and transmitted to the control center through the wireless network.

[0064] The present invention provides an anti-intrusion alarm system based on laser ranging technology. It has the following beneficial effects:

[0065] (1) The data acquisition module of the system combines laser ranging technology, high-definition cameras and sensor groups, and can monitor the dynamic movement trajectory, dynamic video and environmental data of the target in real time, ensuring the synchronous collection of multi-source information. By using high-definition cameras with a resolution of not less than 1080p and high-standard near-infrared laser rangefinders, comprehensive dynamic tracking is achieved in the monitoring area. The data processing module constructs a two-dimensional coordinate system and an image processing platform to perform precise coordinate conversion and dynamic video analysis on the target movement trajectory, improving the processing efficiency of movement data, and optimizing the quality of the target frame image through image enhancement and denoising technologies, providing accurate visual data for subsequent target recognition and risk assessment.

[0066] (2) Based on the above data processing, the system feature extraction module relies on the convolutional neural network CNN for target image recognition and feature extraction. Through training the model with a large number of labeled images, it can not only accurately identify the position and boundary of the target, but also extract features such as the color, size, and texture of the target. By using an image segmentation algorithm to separate the target from the background, accurate recognition in complex environments is ensured. At the same time, the system can combine laser ranging technology to calculate the actual size of the target and quantify its color and texture features, providing more comprehensive data support for the intrusion analysis module. Through these precise target feature analyses, the accuracy of intrusion behavior recognition is improved. Especially in complex backgrounds, effective target discrimination and feature extraction can still be carried out, thus reducing the false alarm rate.

[0067] (3) The combined use of the system intrusion analysis module and the movement analysis module ensures the accurate assessment and rapid response to target intrusion behaviors. The intrusion analysis module conducts feature analysis, movement analysis, and environmental interference correction through the obtained target risk data set, effectively identifying the intrusion features of the target. This module relies on the multi-dimensional intrusion recognition index inv, the dynamic movement assessment index mot, and the environmental interference correction index sbg to comprehensively analyze the target from multiple dimensions, perform summary calculations, and obtain the intrusion judgment assessment index fin, providing reliable data support for the preliminary intrusion assessment. The movement analysis module further analyzes the evolution of the target's movement on the basis of the preliminary assessment, obtains the movement evolution analysis index pat, and combines the path offset and the change of the movement trajectory of the target to provide a more accurate judgment basis for the in-depth intrusion behavior assessment. By dynamically evaluating the nature of the target behavior, combining the intrusion judgment assessment index fin and the movement evolution analysis index pat, and performing summary calculations, the comprehensive behavior assessment index zxp is obtained, ensuring the timeliness and accuracy of the alarm, avoiding false judgments caused by environmental impacts or target path deviations, and thus realizing efficient intrusion prevention and security management. Description of the Drawings

[0068] Figure 1 Schematic diagram of the process of an anti-intrusion alarm system based on laser ranging technology according to the present invention;

[0069] Figure 2 Operating principle diagram of an anti-intrusion alarm system based on laser ranging technology according to the present invention;

[0070] Figure 3 Line graph schematic diagram for in-depth intrusion behavior assessment according to the present invention. Detailed Implementation Modes

[0071] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0072] Embodiment 1

[0073] Please refer to Figure 1 , the present invention provides an anti-intrusion alarm system based on laser ranging technology. To achieve the above objectives, the present invention is realized through the following technical solutions: including a data acquisition module, a data processing module, a feature extraction module, an intrusion analysis module, and a movement analysis module;

[0074] The data acquisition module is used to monitor the dynamic movement trajectory, dynamic video, and environmental data of the target in real time based on laser ranging technology, a high-definition camera, and a sensor group;

[0075] The data processing module is used to construct a two-dimensional coordinate system and an image processing platform, process the dynamic movement trajectory of the target in the two-dimensional coordinate system, and process the dynamic video through the image processing platform to obtain the target movement data and target frame pictures;

[0076] The feature extraction module is used to construct a target recognition model, input the target frame pictures into the target recognition model to obtain a target image set, obtain target feature data after feature extraction, and then preprocess the environmental data, target movement data, and target feature data to obtain a target risk data group;

[0077] The intrusion analysis module is used to perform feature analysis, movement analysis, and environmental impact analysis based on the target risk data group, and perform fitting based on the analysis results to obtain an intrusion judgment evaluation index fin for preliminary intrusion behavior evaluation;

[0078] The movement analysis module is used to perform target movement evolution analysis when the preliminary intrusion behavior evaluation conforms to the intrusion characteristics, and perform fitting with the intrusion judgment evaluation index fin based on the analysis results to obtain a comprehensive behavior evaluation index zxp for in-depth intrusion behavior evaluation.

[0079] In this embodiment, the data acquisition module uses laser ranging, high-definition cameras, and sensor groups to monitor the dynamic movement trajectory, dynamic video, and environmental data of the target in real time, effectively solving the problems of low monitoring accuracy and slow response of traditional systems in complex environments. At the same time, the data processing module converts the dynamic behavior of the target into accurate target movement data and target frame pictures by constructing a two-dimensional coordinate system and processing the movement trajectory, providing high-quality data support for subsequent feature extraction and behavior evaluation. The feature extraction module adopts an advanced target recognition model, extracts features from the target frame pictures, analyzes the size, color, and texture features of the target, and comprehensively evaluates the target risk in combination with the environmental data. The innovation of this module is to improve the accuracy of target recognition and the judgment accuracy of intrusion behavior through efficient data preprocessing and feature fusion, avoiding the common misjudgment and missed judgment problems of traditional methods in complex scenarios. The intrusion analysis module further uses the target risk data group for feature analysis, motion analysis, and environmental impact analysis, accurately identifies potential intrusion behaviors through multi-dimensional analysis means, and generates an intrusion judgment evaluation index fin, providing strong decision-making support for the alarm mechanism of the system. The movement analysis module further analyzes the behavior pattern of the target and calculates the comprehensive behavior evaluation index zxp through the analysis of the evolution of the target movement on the basis of the preliminary intrusion assessment. By combining with the intrusion judgment evaluation index fin, this module enables the system to more accurately distinguish normal behaviors from potential intrusion behaviors, significantly improving the anti-interference ability of the system and the control of false alarm rate. Compared with traditional anti-intrusion systems based on single data sources or simple threshold judgments, the present invention not only improves the accuracy and reliability of intrusion detection through multi-dimensional risk assessment and behavior evolution analysis, but also achieves significant improvements in real-time performance and intelligence, providing a more comprehensive and efficient solution for modern security management and control.

[0080] Embodiment 2

[0081] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 , specifically: the data acquisition module includes a laser monitoring unit and a data acquisition unit;

[0082] The laser monitoring unit is used to use laser ranging technology in the security management and control area to monitor the dynamic movement trajectory of the target in real time;

[0083] The laser ranging technology emits laser beams to the surrounding environment in real time by installing a near-infrared laser rangefinder with a protection standard higher than IP65 in the security management and control area, and monitors the area within a straight line of 100 meters outward from the security management and control area in real time;

[0084] The data acquisition unit is used to monitor the dynamic video and environmental data of the target in the security management and control area in real time according to the installed high-definition cameras and sensor groups;

[0085] The high-definition camera is a high-definition camera with a resolution of not less than 1080p, a field of view angle between 90° and 120°, and a frame rate of not less than 30 frames per second. The installation positions of the high-definition camera and the near-infrared laser rangefinder are aligned in the same coordinate system. The sensor group includes a wind speed sensor and a light sensor.

[0086] In this embodiment, the data acquisition module provides all-round dynamic monitoring capabilities by combining the laser ranging unit and the data acquisition unit, significantly improving the accuracy and response speed of target detection. The laser ranging technology uses a near-infrared laser rangefinder with a protection standard higher than IP65, which can perform real-time monitoring up to one hundred meters outward in the security control area, effectively covering a large area and ensuring the accurate capture of the target movement trajectory. At the same time, the high-definition camera and the laser rangefinder are aligned through the same coordinate system, ensuring the high-precision cooperation of image and distance data, and further improving the reliability of monitoring. The wind speed and light sensors in the sensor group provide additional environmental data support, which can obtain environmental changes in real time and assist in evaluating the impact of the target's behavior. The design of this module enables the system to provide stable and accurate monitoring under complex environmental conditions, reduces the errors of traditional systems in dynamic scenarios, and significantly improves the system's adaptability to environmental changes, providing strong data support for subsequent intrusion analysis and risk assessment.

[0087] Embodiment 3

[0088] This embodiment is an explanatory description based on Embodiment 2. Please refer to Figure 1 , specifically: The data processing module includes a two-dimensional model construction unit, a laser processing unit, and an image processing unit;

[0089] The two-dimensional model construction unit is used to construct a two-dimensional coordinate system for each near-infrared laser rangefinder according to the Cartesian coordinate system. The two-dimensional coordinate system uses the east-west direction as the x-axis, the north-south direction as the y-axis, and the near-infrared laser rangefinder as the origin;

[0090] The laser processing unit is used to process the dynamic movement trajectory of the target detected by the near-infrared laser rangefinder in real time to obtain target movement data. The target movement data includes target speed v, movement angle θ, target acceleration a, and target direction deviation Δθ;

[0091] Based on the pulsed laser emitted by the near-infrared laser rangefinder and measuring the time interval jt from its emission to the reception of the reflected light, the distance jl between the target and the near-infrared laser rangefinder is calculated in combination with the speed of light c. Specifically: After obtaining the distance jl, combined with the laser emission angle β, calculate the target coordinates (x, y), specifically: (x, y) = (jl * cosβ, jl * sinβ). Continuously monitor the target coordinates (x t , y t ) and (x t+1 , y t+1 ) at time t and t + 1 by the near-infrared laser rangefinder, and calculate the target speed v and the motion angle θ respectively, specifically: and In the formula, Δt represents the time interval from time t to time t + 1, arctan represents the arctangent function. Then, calculate the target acceleration a and the target direction deviation Δθ by continuously obtaining the target speed v and the motion angle θ, specifically: Δθ = θ t+1 -θ t , where θ t+1 and θ t represent the motion angles θ at time t + 1 and time t respectively, v t+1 and v t represent the target speeds v at time t + 1 and time t respectively;

[0092] The image processing unit is used to build an image processing platform, and send the target dynamic video captured by the high-definition camera in real time to the image processing platform through the video transmission protocol RTSP. After the image processing platform uses the video capture tool to open the target dynamic video, use the video processing library to read the content of the target dynamic video frame by frame, and read the frame picture of each frame of the video. Then, perform image denoising and image enhancement processing on the frame picture to obtain the target frame picture;

[0093] The image denoising is performed by convolving and smoothing the frame picture using the Gaussian function. The image enhancement is performed by linearly transforming the pixel values of the frame picture to increase the brightness of the bright area of the frame picture and reduce the darkness of the dark area of the frame picture, enhancing the difference between the bright and dark areas in the image.

[0094] In this embodiment, the two-dimensional model construction unit constructs an accurate coordinate system for the laser rangefinder based on the Cartesian coordinate system, enabling the system to accurately locate the position and movement trajectory of the target; the laser processing unit accurately calculates the speed v, acceleration a, movement angle θ, and target direction deviation Δθ of the target by processing the target distance data obtained by the near-infrared laser rangefinder in real time, combining the time interval and the laser emission angle, thereby providing more accurate movement data; the image processing unit effectively improves the image quality and detail recognition ability by processing each frame of the target dynamic video and combining denoising and image enhancement techniques, ensuring that the target features can be accurately identified even in complex environments. The cooperation of these three units not only greatly improves the accuracy and reliability of target detection, but also achieves significant optimization in terms of real-time performance and environmental adaptability, enabling the intrusion prevention alarm system to quickly respond in various complex scenarios and greatly enhancing the intelligent level of intrusion detection.

[0095] Embodiment 4

[0096] This embodiment is an explanatory description carried out in Embodiment 3. Please refer to Figure 1 , specifically: The feature extraction module includes a model training unit, a feature extraction unit, and a data preprocessing unit;

[0097] The model training unit is used to construct a target recognition model based on the convolutional neural network CNN as the model framework, collect a large number of intrusion target images after annotating the targets, input them into the target recognition model, perform iterative training on the target recognition model, input the target frame pictures obtained in real time into the target recognition model, automatically identify the target position and target boundary in the target frame pictures, and then use an image segmentation algorithm to segment the target from the background to obtain a target image set;

[0098] The feature extraction unit is used to extract features from the target image set to obtain target feature data;

[0099] Use camera calibration software to calibrate the physical size of pixels in the target image set, and then use a region calculation algorithm to calculate the image size tc of the target for the calibrated physical size of pixels, and combine the distance jl obtained by laser ranging technology and the camera focal length f to calculate the actual target size mj. Specifically:

[0100] Convert the target image set from the RGB color space to the HSV color space through an image processing library, statistically analyze the color of each pixel in the image in the HSV space, then extract the statistical features of the color through a color histogram, and quantify the color mean through statistics to obtain the target color feature ys. The color feature affects the laser reflection and absorption, and thus affects the accuracy of laser measurement;

[0101] After obtaining the color features, the target image set is converted into a grayscale image by the weighted average method, and the gray value of each pixel in the image is compared with that of its adjacent pixels to form a co-occurrence matrix. The entropy of the target image set is calculated through the co-occurrence matrix to obtain the target texture feature wl, which describes the complexity of the image texture information. The higher the entropy, the more complex the texture of the image, which will increase the laser scattering effect, intensity change and transmission effect, thus affecting the accuracy of laser measurement.

[0102] The data preprocessing unit is used to perform dimensionless processing, denoising, outlier processing and rate-of-change analysis on environmental data, target movement data and target feature data to obtain a target risk data group;

[0103] The dimensionless processing is carried out by the Max-Min method to eliminate the dimensional influence of the stacking impact data and the material stacking data. The denoising decomposes the signals at different frequency scales through wavelet transform technology to eliminate the noise influence in the data. The outlier processing detects and processes the outliers existing in the stacking impact data and the material stacking data by using the interquartile range method;

[0104] The rate-of-change analysis is used to calculate the acceleration rate of change based on the target acceleration a obtained in real time Specifically: In the formula, a t+1 and a t respectively represent the target acceleration a at time t + 1 and time t, and Δt represents the time interval from time t to time t + 1;

[0105] The target risk data group includes an intrusion recognition data group, a dynamic data group and an environmental data group;

[0106] The intrusion recognition data group includes the laser ranging value jl, the target size mj, the target color feature ys and the target texture feature wl;

[0107] The dynamic data group includes the velocity v, the acceleration a, the acceleration rate of change and the target direction deviation Δθ;

[0108] The environmental data group includes the wind speed fs and the light intensity gz.

[0109] In this embodiment, the feature extraction module significantly improves the accuracy and reliability of target recognition by combining the convolutional neural network CNN with advanced image processing algorithms. By training the target recognition model, the target position and boundary in the target frame image can be automatically identified and segmented, effectively reducing the problem of misidentification caused by complex background or target morphology changes in traditional methods. At the same time, the feature extraction unit accurately calculates the actual size, color and texture features of the target, and takes into account the influencing factors of laser ranging, such as the influence of target color on laser reflection and absorption, thereby improving the accuracy of laser measurement. The data preprocessing unit effectively improves the quality of the data through dimensionless processing, denoising and outlier processing technologies, ensuring the accuracy and stability of the risk assessment data group. Through these innovative algorithms and processing methods, the present invention greatly improves the accuracy of target intrusion identification and the anti-interference ability of the system, and optimizes the real-time response and intrusion warning effect of the system.

[0110] Example 5

[0111] This embodiment is explained in Example 4. Please refer to Figure 1 ,Specifically: the intrusion analysis module includes an intrusion analysis unit and an intrusion judgment unit;

[0112] The intrusion analysis unit is used to perform feature analysis, motion analysis and environmental impact analysis respectively according to the acquired target risk data group;

[0113] The feature analysis is used to perform summary calculations based on the acquired intrusion identification data group to obtain a multi-dimensional intrusion identification index inv, which is used to analyze whether the target has intrusion features. The specific formula is as follows:

[0114]

[0115] In the formula, log represents the logarithmic function, k represents the reflection coefficient of the target, which is used to describe the intensity of the laser beam reflected from the target surface. It is determined by the surface material of the target. The reflection coefficients of different materials are obtained through the material database. Used to correct measurement errors caused by changes in object reflection coefficient and distance. The distance jl and reflection coefficient k of the target are corrected by logarithmic terms to ensure a reasonable response for targets with a long distance and a small reflection coefficient;

[0116] The motion analysis is used to perform summary calculations based on the acquired dynamic data group to obtain the dynamic motion evaluation index mot, which is used to determine whether there is an intrusion behavior. The specific formula is as follows:

[0117]

[0118] Wherein, e represents the exponential function, α represents the relationship coefficient, which is used to adjust the influence of speed and acceleration on intrusion determination, and Δθ represents the target direction deviation, that is, the change in the movement direction of the target relative to the original path. The change in acceleration is corrected by an exponential decay function.

[0119] The environmental impact analysis is used to perform summary calculations based on the obtained environmental data set to obtain the environmental interference correction index sbg, which is used to correct the influence of environmental factors on the laser ranging accuracy. The specific formula is as follows:

[0120]

[0121] Wherein, exp represents the exponential decay function. It is used to correct the combined influence of wind speed and light intensity through a non-linear exponential function. It is used to dynamically adjust the influence of environmental interference on intrusion determination.

[0122] The intrusion judgment unit includes a comprehensive analysis unit and an intrusion evaluation unit.

[0123] The comprehensive analysis unit is used to perform summary calculations based on the obtained multi-dimensional intrusion recognition index inv, dynamic motion evaluation index mot, and environmental interference correction index sbg to obtain the intrusion judgment evaluation index fin. The specific formula is as follows:

[0124]

[0125] Wherein, It is used to balance the relationship between the multi-dimensional intrusion recognition index inv, dynamic motion evaluation index mot, and environmental interference correction index sbg. Through a non-linear combination term, the influence of the intrusion characteristics and motion state of the target is associated, and at the same time, comprehensive correction is performed through environmental interference.

[0126] The intrusion evaluation unit is used to calculate the mean value of the historical intrusion judgment evaluation index fin based on all historical intrusion judgment evaluation indexes fin that meet the intrusion characteristics and normal behaviors. Based on the mean value, a preset intrusion alarm threshold M is set, and a preliminary intrusion behavior evaluation is performed with the obtained intrusion judgment evaluation index fin. The specific evaluation scheme is as follows:

[0127] When the intrusion judgment evaluation index fin > the intrusion alarm threshold M, it indicates that the target behavior conforms to the intrusion characteristics. At this time, the target movement trend evolution analysis is performed.

[0128] When the intrusion judgment evaluation index fin ≤ the intrusion alarm threshold M, it indicates that the target behavior is normal, and continuous monitoring is maintained.

[0129] In this embodiment, the intrusion analysis module significantly improves the accuracy and reliability of the anti-intrusion system through multi-dimensional data fusion analysis. First, through the comprehensive application of feature analysis, motion analysis, and environmental impact analysis, the system can comprehensively evaluate whether the target has intrusion features. In particular, by correcting the ranging error of the target through the reflection coefficient, accurate detection of long-distance and low-reflection targets is ensured. Second, through the introduction of an exponential decay function in motion analysis, the influence of acceleration changes on intrusion determination is dynamically corrected, further enhancing the accurate identification of the target's motion state. Environmental impact analysis corrects the interference of wind speed and light intensity on laser ranging, effectively dealing with errors in complex environments, thereby enhancing the stability of the system in different environments. Finally, the intrusion judgment unit comprehensively analyzes the multi-dimensional intrusion recognition index inv, the dynamic motion evaluation index mot, and the environmental interference correction index sbg, performs summary calculations, obtains the intrusion judgment evaluation index fin, and presets the intrusion alarm threshold M based on historical data, achieving accurate intrusion behavior recognition and effective false alarm control. Overall, through multi-level and multi-dimensional analysis and correction, the present invention significantly improves the intelligence, accuracy, and stability of the anti-intrusion system, providing a more refined and reliable solution for modern security monitoring.

[0130] Embodiment 6

[0131] This embodiment is an explanatory description based on Embodiment 5. Please refer to Figure 1 , specifically: when the preliminary intrusion behavior assessment is determined to conform to the intrusion characteristics, the movement trend analysis module is used to perform target movement trend evolution analysis, which specifically includes a path acquisition unit, a movement trend evolution analysis unit, and a movement trend intrusion assessment unit;

[0132] The path acquisition unit is used to calculate the target offset based on continuously monitoring the target coordinates (x t , y t ) and (x t+1 , y t+1 ) at time t and t + 1 by a near-infrared laser rangefinder, including the displacement offset Δh of the target on the x-axis and the displacement offset Δz on the y-axis. Specifically: Δh = x t+1 - x t , Δz = y t+1 - y t ;

[0133] The movement trend evolution analysis unit is used to perform summary calculations based on the obtained target offset to obtain the movement trend evolution analysis index pat, quantifying the offset of the target path and the change of the movement trajectory. The specific formula is as follows;

[0134]

[0135] Wherein, T represents the total detection time interval, Δh(t) and Δz(t) respectively represent the displacement offsets of the target relative to the x-axis and y-axis at time t, e represents the exponential function, α represents the time decay coefficient, t represents the time variable, and dt represents the time differential quantity.

[0136] The movement intrusion evaluation unit includes a comprehensive movement analysis unit and a comprehensive behavior evaluation unit;

[0137] The comprehensive movement analysis unit is used to perform summary calculations based on the obtained intrusion judgment evaluation index fin and movement evolution analysis index pat to obtain the comprehensive behavior evaluation index zxp. The specific formula is as follows;

[0138]

[0139] Wherein, w1 represents the adjustment coefficient of the movement evolution analysis index pat on the influence of the comprehensive behavior evaluation, and w2 represents the control coefficient of the attenuation speed of the intrusion judgment evaluation index fin on the final score.

[0140] The comprehensive behavior evaluation unit is used to preset the intrusion trajectory behavior threshold B according to the security standards in the field of intrusion detection, and conduct in-depth intrusion behavior evaluation with the obtained comprehensive behavior evaluation index zxp. The specific evaluation scheme is as follows;

[0141] When the comprehensive behavior evaluation index zxp > the intrusion trajectory behavior threshold B, it indicates that the target has an intrusion behavior. At this time, an alarm message is generated and transmitted to the control center through the wireless network to notify relevant personnel to drive away the intrusion target, and the control center controls the horn to continuously play "You are about to enter the controlled area. Please leave immediately";

[0142] When the comprehensive behavior evaluation index zxp ≤ the intrusion trajectory behavior threshold B, it indicates that the target has strayed in. At this time, a straying-in message is generated and transmitted to the control center through the wireless network. The control center controls the horn to continuously play "You are about to enter the controlled area. Please leave immediately", and continuously monitors the target. When the intrusion analysis module still monitors that the target behavior conforms to the intrusion characteristics after 5 minutes, the no-misjudgment instruction is executed.

[0143] In this embodiment, the dynamic analysis module brings significant improvement in intelligence and efficiency to the anti-intrusion alarm system through precise path acquisition, target dynamic evolution analysis, and comprehensive behavior evaluation. First, the path acquisition unit can calculate the displacement offsets of the target on the x-axis and y-axis in real time, thereby accurately tracking the movement trajectory of the target; the dynamic evolution analysis unit further enhances the dynamic analysis ability of the target behavior by quantifying the changes in the target trajectory. The combination of the comprehensive dynamic analysis unit and the comprehensive behavior evaluation unit enables the system to comprehensively consider the mutual influence of the intrusion judgment evaluation index fin and the dynamic evolution analysis index pat, thereby generating a more accurate comprehensive behavior evaluation index zxp. Through this comprehensive evaluation, the system can not only accurately determine whether the target is an intrusion behavior, but also effectively distinguish between accidental entry and real intrusion, greatly reducing the risks of false alarms and missed alarms. Finally, the system can trigger an alarm in real time according to the evaluation results, notifying relevant personnel to carry out emergency handling, thereby significantly improving the accuracy and response efficiency of intrusion detection. This innovation significantly enhances the adaptability and reliability of the existing anti-intrusion system in complex environments.

[0144] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An anti-intrusion alarm system based on laser ranging technology, characterized in that: It includes data acquisition module, data processing module, feature extraction module, intrusion analysis module and trend analysis module; The data acquisition module is used to monitor the target dynamic motion trajectory, dynamic video and environmental data in real time based on laser ranging technology, high-definition camera and sensor group; The data processing module is used to construct a two-dimensional coordinate system and an image processing platform, process the dynamic motion trajectory of the target in the two-dimensional coordinate system and process the dynamic video through the image processing platform to obtain the target movement data and the target frame image; The feature extraction module is used to build a target recognition model, input the target frame image into the target recognition model, obtain the target image set, obtain the target feature data after feature extraction, and then pre-process the environmental data, target movement data and target feature data to obtain the target risk data group; The intrusion analysis module is used to perform feature analysis, motion analysis and environmental impact analysis based on the target risk data group, and to perform fitting based on the analysis results to obtain the intrusion judgment evaluation index fin for preliminary intrusion behavior evaluation; The trend analysis module is used to perform target trend evolution analysis when the preliminary intrusion behavior is assessed to be consistent with the intrusion characteristics, and to fit the analysis results with the intrusion judgment evaluation index fin to obtain the comprehensive behavior evaluation index zxp for in-depth intrusion behavior evaluation.

2. The anti-intrusion alarm system based on laser ranging technology according to claim 1 is characterized in that: The data acquisition module includes a laser monitoring unit and a data acquisition unit; The laser monitoring unit is used to use laser ranging technology in the security control area to monitor the dynamic motion trajectory of the target in real time; The laser ranging technology installs a near-infrared laser rangefinder with a protection standard higher than IP65 in the safety control area to emit a laser beam to the surrounding environment in real time, and conducts real-time monitoring of a straight line of 100 meters outward from the safety control area; The data acquisition unit is used to monitor the dynamic video and environmental data of the target in the security control area in real time based on the installed high-definition camera and sensor group; The high-definition camera has a resolution of not less than 1080p, a field of view of between 90° and 120°, and a frame rate of not less than 30 frames per second, and the installation positions of the high-definition camera and the near-infrared laser rangefinder are aligned in the same coordinate system. The sensor group includes a wind speed sensor and a light sensor.

3. The anti-intrusion alarm system based on laser ranging technology according to claim 2 is characterized in that: The data processing module includes a two-dimensional model building unit, a laser processing unit and an image processing unit; The two-dimensional model construction unit is used to construct a two-dimensional coordinate system for each near-infrared laser rangefinder according to a Cartesian coordinate system, wherein the two-dimensional coordinate system is based on the east-west direction as the x-axis, the north-south direction as the y-axis, and the near-infrared laser rangefinder as the origin; The laser processing unit is used to process the dynamic motion trajectory of the target detected by the near-infrared laser rangefinder in real time to obtain target movement data, wherein the target movement data includes target speed v, movement angle θ, target acceleration a and target direction deviation Δθ; Based on the pulse laser emitted by the near-infrared laser rangefinder and measuring the time interval jt from emission to reception of reflected light, the distance jl between the target and the near-infrared laser rangefinder is calculated in combination with the speed of light c, specifically: After obtaining the distance jl, the target coordinates (x, y) are calculated in combination with the laser emission angle β, specifically: (x, y) = (jl*cosβ, jl*sinβ). The target coordinates (x) at time t and time t+1 are continuously monitored by the near-infrared laser rangefinder. t ,y t ) and (x t+1 ,y t+1 ), calculate the target speed v and motion angle θ respectively, specifically: and In the formula, Δt represents the time interval from time t to time t+1, arctan represents the inverse tangent function, and the continuously acquired target velocity v and motion angle θ are used to calculate the target acceleration a and the target direction deviation Δθ, which are specifically: Δθ=θ t+1 -θ t , where θ t+1 and θ t represents the motion angle θ at time t+1 and time t, respectively. t+1 and v t Represent the target speed v at time t+1 and time t respectively; The image processing unit is used to build an image processing platform, and sends the target dynamic video captured in real time by a high-definition camera to the image processing platform through the video transmission protocol RTSP. After the image processing platform uses a video capture tool to open the target dynamic video, it uses a video processing library to read the target dynamic video content frame by frame, and reads the frame image of each frame of the video, and then performs image denoising and image enhancement processing on the frame image to obtain the target frame image; The image denoising is performed by convolving and smoothing the frame image using a Gaussian function, and the image enhancement is performed by linearly transforming the pixel values ​​of the frame image to increase the brightness of the bright area of ​​the frame image and reduce the darkness of the dark area of ​​the frame image.

4. The anti-intrusion alarm system based on laser ranging technology according to claim 3 is characterized in that: The feature extraction module includes a model training unit, a feature extraction unit and a data preprocessing unit; The model training unit is used to build a target recognition model based on the convolutional neural network CNN as a model framework, collect a large number of intrusion target images after the target is annotated and input them into the target recognition model, iteratively train the target recognition model, input the target frame images obtained in real time into the target recognition model, automatically identify the target position and target boundary in the target frame image, and then use the image segmentation algorithm to segment the target from the background to obtain a target image set; The feature extraction unit is used to extract features from the target image set to obtain target feature data; Use the camera calibration software to calibrate the physical size of the pixels in the target image set, and then use the area calculation algorithm to calculate the target image size tc based on the calibrated pixel physical size, and combine the distance jl obtained by the laser ranging technology and the camera focal length f to calculate the actual target size mj, specifically: The target image set is converted from RGB color space to HSV color space through the image processing library, and the color of each pixel in the image is counted in HSV space. The statistical features of the color are extracted through the color histogram, and the color mean is quantified through the statistical method to obtain the target color feature ys; After obtaining the color features, the target image set is converted into a grayscale image by the weighted average method, and the grayscale values ​​of each pixel in the image are compared with those of its adjacent pixels to form a co-occurrence matrix. The entropy of the target image set is calculated through the co-occurrence matrix to obtain the target texture feature wl.

5. The anti-intrusion alarm system based on laser ranging technology according to claim 4 is characterized in that: The data preprocessing unit is used to perform dimensionless processing, denoising, outlier processing and change rate analysis on the environmental data, target movement data and target feature data to obtain a target risk data group; The dimensionless processing uses the Max-Min method to eliminate the dimensional influence of the stacking influence data and the material stacking data. The denoising uses the wavelet transform technology to decompose the signals at different frequency scales to eliminate the noise influence in the data. The outlier processing uses the interquartile range method to detect and process the outliers in the stacking influence data and the material stacking data. The change rate analysis is used to calculate the acceleration change rate based on the target acceleration a obtained in real time Specifically: In the formula, a t+1 and a t They represent the target acceleration a at time t+1 and time t respectively, and Δt represents the time interval from time t to time t+1; The target risk data group includes an intrusion identification data group, a dynamic data group and an environmental data group; The intrusion identification data set includes a laser range value jl, a target size mj, a target color feature ys and a target texture feature wl; The dynamic data set includes velocity v, acceleration a, acceleration change rate and target direction deviation Δθ; The environmental data set includes wind speed fs and light intensity gz.

6. The anti-intrusion alarm system based on laser ranging technology according to claim 5 is characterized in that: The intrusion analysis module includes an intrusion analysis unit and an intrusion judgment unit; The intrusion analysis unit is used to perform feature analysis, motion analysis and environmental impact analysis respectively according to the acquired target risk data group; The feature analysis is used to perform summary calculation based on the acquired intrusion identification data group to obtain a multi-dimensional intrusion identification index inv. The specific formula is as follows: In the formula, log represents the logarithmic function, k represents the reflection coefficient of the target; The motion analysis is used to perform summary calculations based on the acquired dynamic data group to obtain a dynamic motion evaluation index mot, and the specific formula is as follows: In the formula, e represents the exponential function, and α represents the relationship coefficient; The environmental impact analysis is used to perform summary calculations based on the acquired environmental data group to obtain the environmental interference correction index sbg. The specific formula is as follows: Where exp represents the exponential decay function.

7. The anti-intrusion alarm system based on laser ranging technology according to claim 6 is characterized in that: The intrusion judgment unit includes a comprehensive analysis unit and an intrusion assessment unit; The comprehensive analysis unit is used to perform summary calculation based on the obtained multi-dimensional intrusion identification index inv, dynamic motion evaluation index mot and environmental interference correction index sbg to obtain the intrusion judgment evaluation index fin. The specific formula is as follows: The intrusion assessment unit is used to calculate the mean of the historical intrusion judgment assessment index fin based on all the historical intrusion judgment assessment indexes fin that meet the intrusion characteristics and have normal behaviors, preset the intrusion alarm threshold M based on the mean, and perform a preliminary intrusion behavior assessment with the obtained intrusion judgment assessment index fin. The specific assessment scheme is as follows; When the intrusion judgment evaluation index fin> the intrusion alarm threshold M, it means that the target behavior meets the intrusion characteristics, and the target trend evolution analysis is performed at this time; When the intrusion judgment evaluation index fin ≤ the intrusion alarm threshold M, it means that the target behavior is normal and continuous monitoring is maintained.

8. The anti-intrusion alarm system based on laser ranging technology according to claim 7 is characterized in that: The trend analysis module is used to perform target trend evolution analysis when the preliminary intrusion behavior is evaluated as meeting the intrusion characteristics, and specifically includes a path acquisition unit, a trend evolution analysis unit and a trend intrusion assessment unit; The path acquisition unit is used to continuously monitor the target coordinates (x) at time t and time t+1 by a near-infrared laser rangefinder. t ,y t ) and (x t+1 ,y t+1 ), calculate the target offset, including the target displacement offset Δh on the x-axis and the y-axis displacement offset Δz, specifically: Δh = x t+1 -x t , Δz=y t+1 -y t ; The trend evolution analysis unit is used to perform summary calculation based on the obtained target offset, obtain the trend evolution analysis index pat, and quantify the offset of the target path and the change of the motion trajectory. The specific formula is as follows; Where T represents the total detection time interval, Δh(t) and Δz(t) represent the displacement of the target relative to the x-axis and y-axis at time t, respectively, e represents the exponential function, α represents the time attenuation coefficient, t represents the time variable, and dt represents the time calculus.

9. The anti-intrusion alarm system based on laser ranging technology according to claim 8, characterized in that: The trend intrusion assessment unit includes a comprehensive trend analysis unit and a comprehensive behavior assessment unit; The comprehensive trend analysis unit is used to perform summary calculation based on the acquired intrusion judgment evaluation index fin and trend evolution analysis index pat to obtain the comprehensive behavior evaluation index zxp. The specific formula is as follows: Where w1 represents the adjustment coefficient of the trend evolution analysis index pat on the comprehensive behavior evaluation, and w2 represents the control coefficient of the intrusion judgment evaluation index fin on the attenuation speed of the final score.

10. The anti-intrusion alarm system based on laser ranging technology according to claim 9, characterized in that: The comprehensive behavior evaluation unit is used to perform a preset intrusion trajectory behavior threshold B according to the security standards in the field of intrusion detection, and perform a deep intrusion behavior evaluation with the obtained comprehensive behavior evaluation index zxp. The specific evaluation scheme is as follows; When the comprehensive behavior evaluation index zxp>intrusion trajectory behavior threshold B, it means that the target has intrusion behavior. At this time, an alarm message is generated and transmitted to the control center through the wireless network to notify relevant personnel to drive away the intruder target; When the comprehensive behavior evaluation index zxp ≤ the intrusion trajectory behavior threshold B, it means that the target is mis-entered. At this time, mis-entry information is generated and transmitted to the control center through the wireless network.

Images