Security method and device based on full-range feature recognition and four-dimensional trajectory tracking

Abstract

The present invention provides a security method and device based on full-range feature recognition and four-dimensional trajectory tracking, relating to the field of security technology, including: collecting a multi-modal data set of target objects in a target area through a data collection module; performing data fusion on the multi-modal data set through a feature recognition module to obtain a plurality of feature sequences, and performing individual feature matching and identity authentication to obtain the individual behavior data of each target object; performing behavior anomaly detection on each target object based on the individual behavior data through a behavior analysis module; visualizing the four-dimensional movement trajectory through a four-dimensional trajectory reconstruction module, and adding a specified mark to the four-dimensional movement trajectory of the target object with abnormal behavior; determining the level of the anomaly detection result and performing corresponding target actions through an intelligent operation linkage module. The present invention provides a technical solution that can integrate multiple data sources and support full-time and full-scenario monitoring to improve the security protection level of the park.

Description

Technical Field

[0001] The present invention relates to the field of security technologies, and in particular, to a security method and device based on full-range feature recognition and four-dimensional trajectory tracking. Background Art

[0002] In park management, traditional security systems often struggle to cope with complex and changing security challenges. Especially with the continuous expansion of park scale and the increase in population density, how to effectively identify and track the behaviors of individuals has become an urgent problem to be solved. Most of the existing security measures rely on video surveillance by fixed cameras and manual patrols, which are not only inefficient but also difficult to achieve real-time monitoring and rapid response across the entire park. In addition, in the face of emergencies, there is a lack of effective tools to quickly locate the positions and activity trajectories of suspicious persons, which limits the overall effectiveness of the security system. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a security method and device based on full-range feature recognition and four-dimensional trajectory tracking, which provides a technical solution that can integrate multiple data sources and support full-time and full-scenario monitoring to improve the security protection level of the park.

[0004] In the first aspect, the present invention provides a security method based on full-range feature recognition and four-dimensional trajectory tracking, which is applied to a security device. The security device includes a data acquisition module, a feature recognition module, a behavior analysis module, a four-dimensional trajectory reconstruction module, and an intelligent operation linkage module. The method includes:

[0005] Through the data acquisition module deployed within the target area, data is collected for one or more target objects entering the target area to obtain a multi-modal data set;

[0006] Through the feature recognition module, data fusion is performed on the multi-modal data set to obtain multiple feature sequences, and individual feature matching and identity authentication are performed on each feature sequence to obtain individual behavior data corresponding to each target object;

[0007] Through the behavior analysis module, behavior anomaly detection is performed on each target object based on the individual behavior data to obtain a behavior anomaly detection result corresponding to each target object. The behavior anomaly detection result is used to indicate whether the target object has abnormal behavior;

[0008] Through the four-dimensional trajectory reconstruction module, the four-dimensional movement trajectory of the target object within the target area is visualized, and a specified mark is added to the four-dimensional movement trajectory corresponding to the target object with abnormal behavior;

[0009] Through the intelligent operation linkage module, determine the alarm and response levels corresponding to the anomaly detection results, and execute the target actions corresponding to the alarm and response levels. The target actions include one or more of alarm actions, multi-level response actions, and device linkage disposal actions.

[0010] In one implementation, the multi-modal data set includes access control perception data, video surveillance data, and sensor data; performing data fusion on the multi-modal data set to obtain multiple feature sequences, including:

[0011] Extract the first face feature corresponding to the access control perception data and the second face feature corresponding to the video surveillance data, and perform fuzzy matching on the first face feature and the second face feature to determine the association relationship between the access control perception data and the video surveillance data;

[0012] Based on the association relationship, perform data fusion on the access control perception data, video surveillance data, and sensor data to obtain multiple feature sequences.

[0013] In one implementation, based on the association relationship, perform data fusion on the access control perception data, video surveillance data, and sensor data to obtain multiple feature sequences, including:

[0014] Match the access control perception data with the sensor data, and match the video surveillance data with the sensor data;

[0015] If there is an association relationship between the access control perception data and the video surveillance data that match the sensor data, then perform data fusion on the sensor data and its matched access control perception data and video surveillance data to obtain multiple feature sequences.

[0016] In one implementation, perform individual feature matching and identity authentication on each feature sequence to obtain the individual behavior data corresponding to each target object, including:

[0017] For any two feature sequences, determine the feature similarity between the two feature sequences, and determine that the two feature sequences belong to the same target object when the feature similarity is higher than a preset threshold;

[0018] Based on the feature sequences belonging to the same target object, determine the individual behavior data corresponding to each target object.

[0019] In one implementation, perform behavior anomaly detection on each target object based on the individual behavior data to obtain the behavior anomaly detection results corresponding to each target object, including:

[0020] Preprocess the individual behavior data corresponding to each target object, and extract the key features corresponding to each target object from the preprocessed individual behavior data. The key features include behavior frequency and behavior duration;

[0021] Based on a pre-trained behavior pattern model, and based on a plurality of pre-configured alternative behavior patterns and key features corresponding to each target object, determine the target behavior pattern to which each target object belongs;

[0022] Based on the key features corresponding to each target object and the target behavior pattern to which it belongs, perform behavior anomaly detection on each target object to obtain a behavior anomaly detection result corresponding to each target object.

[0023] In one implementation manner, based on the key features corresponding to each target object and the target behavior pattern to which it belongs, perform behavior anomaly detection on each target object to obtain a behavior anomaly detection result corresponding to each target object, including:

[0024] For any key feature corresponding to each target object, determine whether the value of the key feature is higher than the behavior threshold corresponding to the target behavior pattern to which the target object belongs, and when the judgment result is yes, determine that the target object has an abnormal behavior.

[0025] In one implementation manner, visualize the four-dimensional movement trajectory of the target object in the target area, including:

[0026] Obtain the three-dimensional coordinate data of the target object moving in the target area and its associated timestamp information, and construct a four-dimensional movement trajectory corresponding to the target object;

[0027] Establish a three-dimensional model corresponding to the target area, and map the four-dimensional movement trajectory into the three-dimensional model to realize the visualization of the four-dimensional movement trajectory.

[0028] In a second aspect, the present invention further provides a security device based on full-range feature recognition and four-dimensional trajectory tracking. The security device includes a data collection module, a feature recognition module, a behavior analysis module, a four-dimensional trajectory reconstruction module, and an intelligent operation linkage module:

[0029] The data collection module deployed inside the target area is used to: collect data on one or more target objects entering the target area to obtain a multi-modal data set;

[0030] The feature recognition module is used to: perform data fusion on the multi-modal data set to obtain a plurality of feature sequences, and perform individual feature matching and identity authentication on each feature sequence to obtain individual behavior data corresponding to each target object;

[0031] The behavior analysis module is used to: perform behavior anomaly detection on each target object based on the individual behavior data to obtain a behavior anomaly detection result corresponding to each target object, and the behavior anomaly detection result is used to characterize whether the target object has an abnormal behavior;

[0032] The four-dimensional trajectory reconstruction module is used to: visualize the four-dimensional movement trajectory of a target object within a target area, and add a specified mark to the four-dimensional movement trajectory corresponding to the target object with abnormal behavior;

[0033] The intelligent operation linkage module is used to: determine the alarm and response levels corresponding to the abnormal detection result, and execute the target actions corresponding to the alarm and response levels, where the target actions include one or more of an alarm action, a multi-level response action, and a device linkage disposal action.

[0034] Thirdly, the present invention further provides an electronic device, including a processor and a memory, where the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method according to any one of the first aspect.

[0035] Fourthly, the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to implement the method according to any one of the first aspect.

[0036] An anti-theft method and device based on full-range feature recognition and four-dimensional trajectory tracking provided by the present invention. The anti-theft device includes a data acquisition module, a feature recognition module, a behavior analysis module, a four-dimensional trajectory reconstruction module, and an intelligent operation linkage module. First, the data acquisition module deployed inside the target area collects data on one or more target objects entering the target area to obtain a multi-modal data set. Then, the feature recognition module performs data fusion on the multi-modal data set to obtain multiple feature sequences, and performs individual feature matching and identity authentication on each feature sequence to obtain the individual behavior data corresponding to each target object. Next, the behavior analysis module performs behavior anomaly detection on each target object based on the individual behavior data to obtain the behavior anomaly detection result corresponding to each target object. The behavior anomaly detection result is used to indicate whether the target object has abnormal behavior. Then, the four-dimensional trajectory reconstruction module visualizes the four-dimensional movement trajectory of the target object in the target area, and adds a specified mark to the four-dimensional movement trajectory corresponding to the target object with abnormal behavior. Finally, the intelligent operation linkage module determines the alarm and response level corresponding to the anomaly detection result, and executes the target actions corresponding to the alarm and response level. The target actions include one or more of an alarm action, a multi-level response action, and a device linkage disposal action. The above method automatically collects a multi-modal data set and analyzes the individual behavior data corresponding to each target object for behavior anomaly detection of the target object. At the same time, it accurately restores the four-dimensional movement trajectory of each target object, and adds a specified mark to the four-dimensional movement trajectory of the target object with abnormal behavior. In addition, it introduces intelligent operation linkage to realize real-time monitoring and trajectory tracking of the target personnel with abnormal behavior. The present invention provides a technical solution that can integrate multiple data sources and support full-time and full-scenario monitoring to improve the security protection level of the park and provide strong technical support for maintaining public safety.

[0037] Other features and advantages of the present invention will be described in the following specification, and in part will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention are realized and obtained by the structures specifically pointed out in the specification, the claims, and the drawings.

[0038] To make the above objectives, features, and advantages of the present invention more obvious and understandable, the following specific embodiments are given in conjunction with the accompanying drawings and described in detail as follows. Brief Description of the Drawings

[0039] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0040] Figure 1 It is a schematic flowchart of a security method based on full-range feature recognition and four-dimensional trajectory tracking provided by an embodiment of the present invention;

[0041] Figure 2 It is an overall flowchart of a security method based on full-range feature recognition and four-dimensional trajectory tracking provided by an embodiment of the present invention;

[0042] Figure 3 It is a technical framework diagram of a data acquisition module provided by an embodiment of the present invention;

[0043] Figure 4 It is a technical framework diagram of a feature recognition module provided by an embodiment of the present invention;

[0044] Figure 5 It is a technical framework diagram of a four-dimensional trajectory reconstruction module provided by an embodiment of the present invention;

[0045] Figure 6 It is a technical architecture diagram of an intelligent operation linkage module provided by an embodiment of the present invention;

[0046] Figure 7 It is a schematic structural diagram of a security device based on full-range feature recognition and four-dimensional trajectory tracking provided by an embodiment of the present invention;

[0047] Figure 8 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Specific Embodiments

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the present invention in conjunction with the embodiments. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0049] Currently, most existing security measures rely on video surveillance by fixed cameras and manual patrols. This not only has low efficiency but also makes it difficult to achieve real-time monitoring and rapid response across the entire park. In addition, in the face of emergencies, there is a lack of effective tools to quickly locate the positions and movement trajectories of suspicious personnel, which limits the overall effectiveness of the security system. In response to the above problems, the embodiments of the present invention have conducted in-depth analysis. First, the activities of individuals within the park have a high degree of uncertainty and mobility, and a method capable of real-time acquiring and processing a large number of access records is required to facilitate the timely detection of abnormal behaviors. Second, due to the complex park environment, the diversity of individual characteristics requires the security system to have the ability to perform full-range fuzzy searches and quickly locate specific targets in a large amount of data. Finally, in order to improve the speed and accuracy of security incident response, it is necessary to construct a three-dimensional map model to visually present the movement trajectories of individuals and combine intelligent analysis technologies to effectively track suspicious behaviors. Therefore, it is particularly important to develop an intelligent security system that integrates full-time and full-scenario access record query, full-range feature search, and four-dimensional trajectory reconstruction functions.

[0050] Based on this, the embodiments of the present invention provide a security method and device based on full-range feature recognition and four-dimensional trajectory tracking, providing a technical solution that can integrate multiple data sources and support full-time and full-scenario monitoring to improve the security protection level of the park.

[0051] For ease of understanding of this embodiment, first, a security method based on full-range feature recognition and four-dimensional trajectory tracking disclosed in the embodiments of the present invention will be introduced in detail. The security device includes a data acquisition module, a feature recognition module, a behavior analysis module, a four-dimensional trajectory reconstruction module, and an intelligent operation linkage module. Refer to Figure 1 the flow schematic diagram of a security method based on full-range feature recognition and four-dimensional trajectory tracking shown in

[0052] Step S102, through the data acquisition module deployed within the target area, data is acquired for one or more target objects entering the target area to obtain a multi-modal data set.

[0053] Among them, the data acquisition module may include access sensing devices, video surveillance devices, and behavior trajectory recognition sensors. The multi-modal data set includes data acquired by access sensing devices (referred to as access sensing data for short), data acquired by video surveillance devices (referred to as video surveillance data for short), and data acquired by behavior trajectory recognition sensors (referred to as sensor data for short); the target objects are employees or visitors.

[0054] Step S104: Using the feature recognition module, perform data fusion on the multimodal dataset to obtain multiple feature sequences, and perform individual feature matching and identity authentication on each feature sequence to obtain the individual behavior data corresponding to each target object.

[0055] In one example, match the access control perception data, video surveillance data, and sensor data respectively to analyze the access control perception data, video surveillance data, and sensor data that are suspected to belong to the same target object. By fusing the access control perception data, video surveillance data, and sensor data that are suspected to belong to the same target object, multiple feature sequences can be obtained; then, use the similarity between the feature sequences to identify the feature sequences that belong to the same target object, realize individual feature matching and identity authentication, and obtain the individual behavior data. The individual behavior data will include all the data of the target object (including access control perception data, video surveillance data, and sensor data).

[0056] Step S106: Using the behavior analysis module, perform behavior anomaly detection on each target object based on the individual behavior data to obtain the behavior anomaly detection result corresponding to each target object. The behavior anomaly detection result is used to characterize whether the target object has abnormal behavior.

[0057] In one example, key features such as behavior frequency and behavior duration can be extracted from the individual behavior data, and a pre-trained neural network can be used to determine the target behavior pattern to which the behavior frequency and behavior duration belong. Based on the behavior threshold, behavior frequency, and behavior duration corresponding to the behavior pattern, determine whether the target object has abnormal behavior and obtain the corresponding behavior anomaly detection result.

[0058] Step S108: Using the four-dimensional trajectory reconstruction module, visualize the four-dimensional movement trajectory of the target object in the target area, and add a specified mark to the four-dimensional movement trajectory corresponding to the target object with abnormal behavior.

[0059] Among them, the four-dimensional movement trajectory includes three-dimensional coordinate data and its associated timestamp information. In one example, a three-dimensional model corresponding to the target area can be constructed, and the four-dimensional movement trajectory can be mapped into the three-dimensional model to realize the visualization of the four-dimensional movement trajectory. Preferably, for the four-dimensional movement trajectory corresponding to the target object with abnormal behavior, specified marks such as highlighting, special colors, and magnification can be used for visualization.

[0060] Step S110: Using the intelligent operation linkage module, determine the alarm and response level corresponding to the anomaly detection result, and execute the target action corresponding to the alarm and response level. The target action includes one or more of an alarm action, a multi-level response action, and a device linkage disposal action.

[0061] In one example, the intelligent operation linkage module is configured with an alarm mechanism, a multi-level response strategy, and a linkage disposal process, and is used to execute corresponding alarm actions, multi-level response actions, and device linkage disposal actions according to the alarm and response levels corresponding to the anomaly detection results.

[0062] The security method based on full-range feature recognition and four-dimensional trajectory tracking provided by the embodiments of the present invention automatically collects multi-modal data sets and analyzes the individual behavior data corresponding to each target object, which is used to detect abnormal behaviors of the target objects. At the same time, the four-dimensional movement trajectories of each target object are accurately restored, and specified marks are added to the four-dimensional movement trajectories of the target objects with abnormal behaviors. In addition, intelligent operation linkage is introduced to realize real-time monitoring and trajectory tracking of target personnel with abnormal behaviors. The present invention provides a technical solution that can integrate multiple data sources and support full-time and full-scenario monitoring, so as to improve the security protection level of the park and provide strong technical support for maintaining public security.

[0063] For easy understanding, the embodiments of the present invention provide a specific implementation manner of a security method based on full-range feature recognition and four-dimensional trajectory tracking. Refer to Figure 2 the overall flowchart of a security method based on full-range feature recognition and four-dimensional trajectory tracking shown in

[0064] (1) Data acquisition module. The multi-modal data sets collected by the data acquisition module include access control perception data, video surveillance data, and sensor data.

[0065] As the cornerstone of the intelligent security device, the data acquisition module not only converges multiple real-time data sources, but also uses advanced algorithms to realize full-range feature recognition and four-dimensional trajectory tracking. By integrating and analyzing the data of access control, surveillance, and behavior trajectory recognition sensors, this module constructs an intelligent security system and a behavior recognition system, and at the same time provides real-time data support for subsequent decision-making.

[0066] Exemplarily, refer to Figure 3 the technical framework diagram of a data acquisition module shown in

[0067] The data sources of the data acquisition module include access control perception devices, video surveillance devices, and behavior trajectory recognition sensors. Specifically:

[0068] The access control sensing device adopts identity recognition technology: based on technologies such as face recognition and RFID (Radio Frequency Identification), it creates identity card data of employees and visitors (i.e., target objects). When the target object enters or exits the target area, it records the timestamp (T), location (L), and identity proof (ID) of the target object. Expressed by the formula: [D_{entry}={ID,L,T}].

[0069] The video surveillance device conducts real-time data collection: deploy high-definition surveillance devices to obtain real-time video streams. Set up an image recognition algorithm to detect moving targets using a convolutional neural network (CNN) and generate feature vectors (F): [F=CNN(I_t)\quad(I_t\{is the real-time video frame})]. Preferably, the storage algorithm of the video surveillance device is also improved: introduce a fast indexing algorithm, such as Hash mapping, to optimize the storage and calling speed when introducing video frames. The specific storage strategy is: [S={H(T),F}\quad(H\{is the hash function})].

[0070] The behavior trajectory recognition sensor: This sensor detects surrounding objects by emitting and receiving radio waves. The reflected signal can be transformed and analyzed to identify parameters such as the movement trajectory, speed, direction, and distance of the object. Set the received signal as R(t), then it can be expressed as: [R(t)=H(S(t))\quad(S(t)\{is the emitted signal})]. Through the stationary detection function, the sensor can judge the stationary state of the human body. The built-in algorithm of the sensor analyzes the change of the reflected signal. If there is no obvious movement, the security device will identify it as stationary and send out relevant signals.

[0071] Data processing and storage are performed on the multi-modal data set collected from the above data sources, including processes such as data preprocessing, missing value filling, data normalization, and data storage. Specifically:

[0072] Data preprocessing: Preprocess the collected data to improve the quality and usability of the data. The preprocessing steps include: Denoising: Use a high-pass or low-pass filter to remove noise signals. The denoising of E(t) can be expressed as: [E_{filtered}(t)=E(t)\asth(t)\quad(h\{is the filter response})].

[0073] Missing value filling: Apply interpolation techniques (such as linear interpolation) to fill in the missing time series data based on adjacent data points.

[0074] Data normalization: Scale the feature values between 0 and 1 for easier model processing. The formula is: $E_{norm}(i)=\frac{E(i)-E_{min}}{E_{max}-E_{min}}$.

[0075] Data storage: The storage mechanism uses a cloud database suitable for high concurrency, such as MongoDB or Cassandra, and stores the data in JSON format.

[0076] (2) Feature recognition module:

[0077] The core task of the feature recognition module is to extract high-dimensional features from data from various sources to achieve accurate individual identity recognition and behavior classification. By comprehensively using technologies such as deep learning, fuzzy matching, and multi-modal data fusion, the accuracy and efficiency of feature recognition are improved, providing reliable support for intelligent security devices. See Figure 4 The technical framework diagram of a feature recognition module shown, including processes such as a training module, feature extraction and comparison.

[0078] The embodiments of the present invention provide a specific processing flow of a feature recognition module, including:

[0079] (2.1) Extract the first face feature corresponding to the access control perception data and the second face feature corresponding to the video surveillance data.

[0080] In one example, face features are extracted from the access control perception data and the video surveillance data respectively through a convolutional neural network (CNN). CNN can automatically learn hierarchical features in the image. The convolutional operation of each layer can be represented by the following formula: $Z = f(W * X + b)$, where $Z$ is the output feature map, $W$ is the convolutional kernel, $X$ is the input image, $b$ is the bias, and $f$ is the activation function (such as ReLU). At the same time, a large-scale labeled dataset (such as LFW, VGGFace, etc.) is used in the training stage to enhance the generalization ability of the model. Data augmentation (such as random cropping, flipping, etc.) is used to further improve the robustness of the model.

[0081] (2.2) Perform fuzzy matching on the first face feature and the second face feature to determine the association relationship between the access control perception data and the video surveillance data.

[0082] In one example, by performing fuzzy matching on the first face feature and the second face feature, the recognition rate and accuracy are improved.

[0083] The processing flow of the fuzzy matching algorithm includes: calculating the similarity between feature vectors, usually applying cosine similarity or Euclidean distance: [\{CosineSimilarity}=\frac{A\cdotB}{||A||\cdot||B||}][\{EuclideanDistance}=||A - B||_2=\sqrt{\sum(A_i - B_i)^2}]. Compare between the detected image and the images in the database to determine the correlation between access control perception data and video surveillance data.

[0084] (2.3) Based on the correlation, perform data fusion on access control perception data, video surveillance data, and sensor data to obtain multiple feature sequences.

[0085] In one example, by fusing access control data (such as time, location, behavior records), video surveillance data (facial features, action recognition), and sensor data (location, behavior), a more comprehensive individual feature description is formed.

[0086] In a specific implementation, match the access control perception data and sensor data, and match the video surveillance data and sensor data; if there is a correlation between the access control perception data and video surveillance data that the sensor data matches, perform data fusion on the sensor data and its matched access control perception data and video surveillance data to obtain multiple feature sequences.

[0087] The fusion methods include the weighted average method, principal component analysis (PCA), etc.: Among them, principal component analysis reduces the high-dimensional features to a lower dimension and eliminates the correlation between features. Its transformation formula is: [Z = \{X}W], where (Z) is the feature after dimensionality reduction, (X) is the original data, and (W) is the feature weight matrix.

[0088] (2.4) For any two feature sequences, determine the feature similarity between the two feature sequences, and if the feature similarity is higher than the preset threshold, determine that the two feature sequences belong to the same target object. Based on the feature sequences belonging to the same target object, determine the individual behavior data corresponding to each target object.

[0089] In one example, the feature comparison uses the Softmax classification algorithm to calculate the feature similarity, so as to achieve the matching and identity confirmation of individual features. The Softmax formula is as follows:

[0090] [P(y_i)=\frac{e^{f(x_i)}}{\sum_{j = 1}^{K}e^{f(x_j)}}].

[0091] Among them, (P(y_i)) represents the probability that the feature vector (x_i) belongs to the identity (y_i), (f(x_i)) is the classification score of the feature vector, and (K) is the number of categories.

[0092] The classification decision basis is: if (P(y_i) > \theta) (threshold), then the identity is confirmed as (y_i); otherwise, it is determined as an unknown identity.

[0093] (III) Behavior analysis module:

[0094] Deeply analyze the monitored individual behavior patterns to identify and determine abnormal behaviors. This module is an important part of the intelligent security device. Through behavior pattern analysis, potential security hazards can be monitored in real time, and the alertness to abnormal situations can be enhanced, thus effectively protecting the safety of the park.

[0095] In specific implementation, it mainly includes the following steps:

[0096] (3.1) Preprocess the individual behavior data corresponding to each target object, and extract the key features corresponding to each target object from the preprocessed individual behavior data. The key features include behavior frequency and behavior duration.

[0097] Preprocessing: Clean and standardize the collected individual behavior data to ensure the quality and consistency of the data. This includes removing noise data, filling in missing values, and normalizing the data to a unified scale.

[0098] Feature extraction: Extract key features from the preprocessed individual behavior data, such as behavior frequency and behavior duration, etc. These features will be used as the input of the behavior pattern model. Behavior frequency is the number of times a specific behavior appears per unit time, reflecting the activity of the behavior. Behavior duration is the stay time of an individual in a certain activity state, reflecting the persistence of the behavior.

[0099] (3.2) Through a pre-trained behavior pattern model, based on multiple pre-configured alternative behavior patterns and the key features corresponding to each target object, determine the target behavior pattern to which each target object belongs.

[0100] To accurately analyze the behavior patterns of individuals, we use a long short-term memory (LSTM) neural network. This architecture based on the recurrent neural network (RNN) is especially suitable for sequence data and can effectively solve the deficiencies of traditional models in dealing with long-term dependencies.

[0101] Before executing (3.2), it is necessary to build the LSTM model, train the model, and verify and test the model.

[0102] LSTM Model Construction: Utilize deep learning frameworks such as TensorFlow or PyTorch to construct an LSTM neural network model. The model should include an input layer, an LSTM layer, a fully connected layer, and an output layer, where the LSTM layer is responsible for capturing the temporal dependencies in the behavior data.

[0103] Model Training: Use historical behavior data to train the LSTM model, and optimize the model parameters through the backpropagation algorithm to enable it to accurately predict individual behavior patterns. During the training process, methods such as cross-validation are adopted to evaluate the performance of the model and make necessary adjustments.

[0104] Model Verification and Testing: Verify the performance of the LSTM model on an independent test set to ensure that it can accurately identify and predict individual behavior patterns. At the same time, conduct robustness tests on the model to ensure that it can maintain stable performance under different scenarios and conditions.

[0105] Input multiple pre-configured alternative behavior patterns and the key features corresponding to each target object into the verified and tested LSMT model to use the LSTM model to determine the target behavior pattern to which each target object belongs. Among them, the behavior patterns can be walking, wandering, staying, etc., and these types reflect the activity status of individuals.

[0106] (3.3) Based on the key features corresponding to each target object and its target behavior pattern, conduct behavior anomaly detection on each target object to obtain the behavior anomaly detection results corresponding to each target object.

[0107] In one example, for any key feature corresponding to each target object, judge whether the value of the key feature is higher than the behavior threshold corresponding to the target behavior pattern to which the target object belongs, and determine that the target object has abnormal behavior when the judgment result is yes. The process of setting the behavior threshold is as follows: Use statistical methods (such as standard deviation) and machine learning means to set the behavior threshold. For example, define the mean and standard deviation of the behavior, and judge the anomaly based on this: [z=\frac{x-\mu}{\sigma}]; where, (z) is the standardized value, (x) is the current behavior feature, (\mu) is the sample mean, and (\sigma) is the sample standard deviation. When (z>z_{{threshold}}), it is marked as abnormal behavior.

[0108] Specifically, behavior anomaly detection is a key step in identifying potential risks. Combining with the LSTM model, the following two detection methods are performed: active detection and passive detection. Active detection: Real-time evaluation of whether an individual's behavior exceeds the set normal range. Once an abnormal behavior is detected, the security device will immediately issue an alarm and generate a log. Passive detection: When an abnormal frequency or data peak is detected in the data stream, record the relevant data and conduct a detailed analysis. In this process, the data is further analyzed through clustering algorithms or anomaly detection algorithms (such as Isolation Forest) to identify potential abnormal patterns.

[0109] (4) Four-dimensional Trajectory Reconstruction Module:

[0110] The main function of the four-dimensional trajectory reconstruction module is to effectively visualize the movement trajectory of an individual in the smart park, so as to facilitate the management personnel to monitor and analyze dynamic activities. This module helps the manager to understand the personnel flow in the park, as well as potential safety hazards and abnormal behaviors in real time through the accurate capture and analysis of individual behaviors.

[0111] In one implementation, first obtain the three-dimensional coordinate data of the target object moving in the target area and its associated timestamp information, and construct the corresponding four-dimensional movement trajectory of the target object; then establish a three-dimensional model corresponding to the target area, and map the four-dimensional movement trajectory into the three-dimensional model to achieve the visualization of the four-dimensional movement trajectory.

[0112] Specifically, in the process of collecting and processing trajectory data, first rely on various sensors and data acquisition technologies to obtain the location information of individuals. Exemplarily, refer to Figure 5 the technical framework diagram of a four-dimensional trajectory reconstruction module shown, including the processes of collecting location information, collecting trajectory data and constructing, data coordinate transformation, and trajectory dynamic visualization. The following are the key steps of trajectory reconstruction:

[0113] (4.1) Location Information Acquisition:

[0114] Through technologies such as GPS, base station signals, and Wi-Fi positioning, the geographical location of individuals in the park is obtained in real time. For indoor environments, Bluetooth positioning devices or ultra-wideband (UWB) technologies can be used. The location information presents as a timestamp and the corresponding three-dimensional coordinate data during the acquisition process, that is, ((t, x, y, z)), where (t) is the time, and (x), (y), and (z) are the spatial positions of the three-dimensional coordinates respectively.

[0115] (4.2) Trajectory Construction:

[0116] By processing the position information in the time series, a three-dimensional trajectory of an individual is constructed. The trajectory can be represented as a series of connected points, i.e.: [{trajectory}={(t_1,x_1,y_1,z_1),(t_2,x_2,y_2,z_2),\ldots,(t_n,x_n,y_n,z_n)}].

[0117] (4.3)Data cleaning and interpolation:

[0118] Remove the noise in data collection and fill in the missing data caused by unstable signals. For the missing data points, linear interpolation or spline interpolation methods can be used for completion to ensure the continuity of the trajectory.

[0119] Furthermore, 3D modeling and visualization technologies can be used to provide managers with an intuitive display of dynamic trajectories. The following are several important aspects of the visualization process:

[0120] Select a visualization tool: Use modern visualization tools such as Three.js and Unity to visualize the trajectory data as a three-dimensional model. Three.js is a Web-based 3D JavaScript library, which is very suitable for web applications, while Unity provides powerful 3D rendering and real-time interaction capabilities.

[0121] Data rendering: Map the trajectory points to a three-dimensional scene to generate a dynamic trajectory diagram. It can be represented in various ways such as particle systems, line drawing, or point cloud display. The dynamic transformation of the trajectory can display important information such as the moving direction and speed of the individual.

[0122] User interaction: Provide a user-friendly interaction interface, enabling managers to freely rotate, zoom, and observe the three-dimensional perspective, further enhancing the understanding of dynamic activities. An event trigger mechanism can also be embedded. For example, when clicking on a specific point on the trajectory, relevant information or analysis data can be popped up.

[0123] (V)Intelligent operation linkage module:

[0124] The intelligent operation linkage mechanism aims to integrate all security modules in the park to form a highly integrated security response system. This mechanism can achieve real-time data communication and collaboration among modules, not only improving the overall security efficiency but also enhancing the response ability to emergencies. Through efficient data exchange, security devices can quickly make judgments and thus implement appropriate response measures, which is conducive to building a safer park environment.

[0125] See Figure 6The technical architecture diagram of an intelligent operation linkage module shown in the figure includes the process of integrating data sources, behavior analysis modules, data input acquisition interface, behavior detection, triggering alarms and notifying relevant personnel. Please refer to the following steps for details:

[0126] (5.1) Data fusion and analysis:

[0127] Real-time data fusion: The security device integrates information from different data sources in real time, including access control systems, surveillance cameras, sensors, and alarm systems. Through deep learning and data mining algorithms, combined with feature recognition and behavior analysis data, it generates a comprehensive view and builds an individual behavior and identity template. This template can not only reflect the individual's behavioral characteristics, but also identify possible abnormal behaviors, thus providing a basis for subsequent security decisions.

[0128] Data visualization: To ensure that operators can quickly understand complex data, security devices provide a real-time monitoring interface to display the dynamics and behavior patterns of people in the area. Visualization tools display through maps, charts and dynamic graphics, which facilitates security personnel to quickly analyze and evaluate data. For example, high-risk areas can be displayed through heat maps, or individual movement paths can be displayed using dynamic trajectory maps. At the same time, security devices also allow users to customize visualization indicators to more accurately monitor key areas and targets.

[0129] (5.2) Real-time alert mechanism:

[0130] Alarm mechanism design: To ensure timely and effective response to suspicious behaviors, this mechanism adopts a hierarchical alarm system. The system divides different alarm levels according to the degree of abnormal behavior and triggers corresponding emergency response measures. For example, for low-level abnormal behaviors, the system may only record and mark them; while for high-level threats, security personnel will be notified immediately to take action. The alarm threshold can be dynamically adjusted based on historical data analysis and actual application scenarios to achieve the best response effect.

[0131] Multi-level response strategy: In addition to graded alarms, a multi-level response strategy is also designed. For example, when suspicious behavior is detected, the system will first automatically send a text message or email to alert relevant personnel to pay attention; if the situation continues to deteriorate, it will trigger a higher level of response, such as on-site sound and light warnings, remote voice warnings, etc.; in the most extreme cases, the system will directly contact the park's emergency response team or even external law enforcement agencies.

[0132] Linkage handling process: Once an alarm is triggered, the system will automatically start a series of linkage handling processes. This includes but is not limited to locking the relevant area, adjusting the viewing angle of the surveillance camera to obtain more details, launching drones for aerial reconnaissance, etc. These linkage operations can greatly improve the response efficiency and ensure that the development of the situation is controlled in the shortest time.

[0133] An embodiment of the present invention proposes an intelligent security method based on full-range feature recognition and four-dimensional trajectory tracking. By integrating advanced image recognition technology and big data analysis algorithms, this method realizes all-round monitoring of individual activities within the park. This method can automatically collect and analyze the access records of the access control system, use fuzzy matching algorithms for feature search, and accurately restore the movement trajectories of individuals with the help of three-dimensional map technology. More importantly, the present invention also introduces an intelligent operation linkage mechanism, which can automatically associate face capture information with other systems (such as feature recognition, image recognition, and access records), so as to realize real-time monitoring and trajectory tracking of the behaviors of suspicious personnel. This "tracking by the map" method greatly improves the security protection level of the park and provides strong technical support for maintaining public safety.

[0134] An embodiment of the present invention provides a specific example of a security method based on full-range feature recognition and four-dimensional trajectory tracking. An emergency occurred in a large park, and an unauthorized person tried to enter a sensitive area within the park. The security device first recorded the timestamp (T), location (L), and identity document (ID) of the person through the access control system, and captured the face image of the person through video surveillance. The feature recognition module extracted the face features through CNN and performed fuzzy matching with the identity information in the database, and found that the person had no access permission.

[0135] At this time, the behavior analysis module starts to work, analyzes the behavior pattern of the person through the LSTM neural network, and detects that the person's behavior is abnormal (such as lingering for a long time). The four-dimensional trajectory reconstruction module updates the movement trajectory of the person in real time and displays it on the visualization interface for the park security personnel to view.

[0136] The intelligent operation linkage mechanism is immediately activated. The security device automatically sends an alarm to the security personnel and reminds relevant personnel to pay attention through text messages and emails. At the same time, the security device adjusts the angle of the monitoring camera to obtain more details and starts a drone for aerial reconnaissance. Finally, the security personnel quickly lock in the person based on the information provided by the security device and take corresponding measures, successfully preventing potential security threats.

[0137] It can be seen from the above embodiments that the intelligent security method provided by the present invention can effectively improve the security management level of the park, ensure rapid response in case of emergencies, and protect the security of the park.

[0138] In summary, the technical key points of the security method based on full-range feature recognition and four-dimensional trajectory tracking provided by the embodiments of the present invention include:

[0139] (a) Full-range feature recognition and multi-modal data fusion:

[0140] Innovation points: Comprehensively utilize multiple data sources such as face recognition, RFID, and behavior trajectory recognition sensors, and perform identity verification through fuzzy matching technology. Combine multi-modal data fusion technologies (such as weighted average method, PCA) to achieve all-round feature recognition of individuals. Advantage points: Compared with single-feature recognition, the present invention can more comprehensively describe individual features, improving recognition accuracy and robustness.

[0141] (b) Four-dimensional trajectory tracking and data processing:

[0142] Innovation points: Real-time obtain individual location information through technologies such as GPS and Wi-Fi positioning, construct a four-dimensional trajectory in combination with the time dimension, and use data cleaning and interpolation technologies (such as linear interpolation) to ensure the continuity of the trajectory. Advantage points: Achieve accurate capture and analysis of individual movement trajectories, helping managers to understand the personnel flow situation and potential safety hazards in the park in real time.

[0143] (c) Real-time data fusion and intelligent analysis:

[0144] Innovation points: Perform real-time fusion of data from access control systems, surveillance cameras, sensors, and alarm systems, generate comprehensive views through deep learning and data mining algorithms, and use LSTM neural networks for behavior pattern analysis. Advantage points: Through real-time data fusion and intelligent analysis, the security device can quickly make judgments, discover abnormal behaviors in a timely manner, and improve the overall security efficiency.

[0145] (d) Four-dimensional trajectory reconstruction and dynamic visualization:

[0146] Innovation points: Use modern visualization tools (such as Three.js, Unity) to visually display the trajectory data in three dimensions and provide a user-friendly interaction interface, supporting free rotation, zooming, and observing three-dimensional perspectives. Advantage points: Provide intuitive dynamic trajectory displays for managers, enhance the understanding of dynamic activities, and assist in decision-making.

[0147] (e) Intelligent operation linkage mechanism:

[0148] Innovation points: Establish a hierarchical alarm system and design multi-level response strategies to ensure timely and effective response to suspicious behaviors. Once the alarm is triggered, the system automatically starts the linkage disposal process, including locking the area, adjusting the perspective of the surveillance camera, starting drone reconnaissance, etc. Advantage points: Through the intelligent linkage mechanism, the system can quickly respond and take appropriate countermeasures, improving the efficiency of incident handling and reducing security risks.

[0149] Based on the above technical points, the embodiments of the present invention have at least the following advantages:

[0150] Comprehensively improve security efficiency: By integrating a variety of advanced technical means, achieve all-round monitoring of personnel activities within the park, and improve the overall efficiency of security devices; Real-time response and rapid decision-making: Real-time data fusion and intelligent analysis technologies enable security devices to quickly make judgments and take appropriate countermeasures, shortening the response time; Accurate behavior recognition and anomaly detection: Utilize advanced behavior analysis technologies to accurately identify the behavior patterns of individuals, and promptly discover and handle potential security hazards; Enhance user experience and decision-making support: Through four-dimensional trajectory reconstruction and dynamic visualization technologies, provide intuitive dynamic trajectory displays for managers, enhance the understanding of dynamic activities, and assist in decision-making.

[0151] Based on the foregoing embodiments, an embodiment of the present invention provides a security device based on full-range feature recognition and four-dimensional trajectory tracking. Refer to Figure 7 the structural schematic diagram of a security device based on full-range feature recognition and four-dimensional trajectory tracking shown in

[0152] The data acquisition module 702 deployed within the target area is used to: collect data on one or more target objects entering the target area to obtain a multi-modal data set;

[0153] The feature recognition module 704 is used to: perform data fusion on the multi-modal data set to obtain multiple feature sequences, and perform individual feature matching and identity authentication on each feature sequence to obtain the individual behavior data corresponding to each target object;

[0154] The behavior analysis module 706 is used to: perform behavior anomaly detection on each target object based on the individual behavior data to obtain the behavior anomaly detection result corresponding to each target object, and the behavior anomaly detection result is used to indicate whether the target object has abnormal behavior;

[0155] The four-dimensional trajectory reconstruction module 708 is used to: visualize the four-dimensional movement trajectory of the target object within the target area, and add a specified mark to the four-dimensional movement trajectory corresponding to the target object with abnormal behavior;

[0156] The intelligent operation linkage module 710 is used to: determine the alarm and response levels corresponding to the anomaly detection result, and execute the target actions corresponding to the alarm and response levels, and the target actions include one or more of alarm actions, multi-level response actions, and device linkage disposal actions.

[0157] The security device based on full-range feature recognition and four-dimensional trajectory tracking provided by the embodiments of the present invention automatically collects multi-modal data sets and analyzes the individual behavior data corresponding to each target object for detecting abnormal behaviors of the target objects. At the same time, it accurately restores the four-dimensional movement trajectories of each target object, adds specified marks to the four-dimensional movement trajectories of the target objects with abnormal behaviors. In addition, it introduces intelligent operation linkage to achieve real-time monitoring and trajectory tracking of the target personnel with abnormal behaviors. The present invention provides a technical solution that can integrate multiple data sources and support full-time and full-scene monitoring to improve the security protection level of the park and provide strong technical support for maintaining public security.

[0158] For the device provided by the embodiments of the present invention, its implementation principle and the technical effects produced are the same as those of the foregoing method embodiments. For the sake of brief description, for the parts not mentioned in the device embodiments, reference may be made to the corresponding contents in the foregoing method embodiments.

[0159] The embodiments of the present invention provide an electronic device. Specifically, the electronic device includes a processor and a storage device; a computer program is stored on the storage device, and when the computer program is run by the processor, it executes the method according to any one of the foregoing implementation manners.

[0160] Figure 8 FIG. 10 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. The electronic device 100 includes: a processor 80, a memory 81, a bus 82, and a communication interface 83. The processor 80, the communication interface 83, and the memory 81 are connected through the bus 82. The processor 80 is used to execute an executable module stored in the memory 81, such as a computer program.

[0161] Among them, the memory 81 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 83 (which may be wired or wireless), a communication connection between the system network element and at least one other network element is realized, and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0162] The bus 82 may be an ISA bus, a PCI bus, an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 8 only a bidirectional arrow is used in FIG. 10, but it does not mean that there is only one bus or one type of bus.

[0163] Among them, the memory 81 is used to store a program. After receiving an execution instruction, the processor 80 executes the program. The method executed by the device defined by the flow process disclosed in any embodiment of the foregoing embodiments of the present invention can be applied to or implemented by the processor 80.

[0164] The processor 80 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 80 or the instructions in the form of software. The above-mentioned processor 80 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 81, and the processor 80 reads the information in the memory 81 and combines its hardware to complete the steps of the above method.

[0165] The computer program product of the readable storage medium provided by the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the foregoing method embodiments. For the specific implementation, reference can be made to the foregoing method embodiments and will not be elaborated here.

[0166] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs, Read-Only Memories), random access memories (RAMs, Random Access Memories), magnetic disks, or optical discs.

[0167] Finally, it should be noted that the above-mentioned embodiments are only specific implementation manners of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A security method based on full-range feature recognition and four-dimensional trajectory tracking, characterized in that Applied to a security device, the security device includes a data acquisition module, a feature recognition module, a behavior analysis module, a four-dimensional trajectory reconstruction module, and an intelligent operation linkage module. The method includes: Using the data acquisition module deployed within the target area to collect data on one or more target objects entering the target area, obtaining a multi-modal data set; Using the feature recognition module to perform data fusion on the multi-modal data set to obtain multiple feature sequences, and performing individual feature matching and identity authentication on each feature sequence to obtain individual behavior data corresponding to each target object; Using the behavior analysis module to perform behavior anomaly detection on each target object based on the individual behavior data, obtaining a behavior anomaly detection result corresponding to each target object, where the behavior anomaly detection result is used to indicate whether the target object has abnormal behavior; Using the four-dimensional trajectory reconstruction module to visualize the four-dimensional movement trajectory of the target object within the target area, and adding a specified mark to the four-dimensional movement trajectory corresponding to the target object with abnormal behavior; Using the intelligent operation linkage module to determine the alarm and response level corresponding to the anomaly detection result, and execute the target action corresponding to the alarm and response level, where the target action includes one or more of an alarm action, a multi-level response action, and a device linkage disposal action; The multi-modal data set includes access control perception data, video surveillance data, and sensor data; performing data fusion on the multi-modal data set to obtain multiple feature sequences includes: Extracting a first face feature corresponding to the access control perception data and a second face feature corresponding to the video surveillance data, and performing fuzzy matching on the first face feature and the second face feature to determine the association relationship between the access control perception data and the video surveillance data; Based on the association relationship, performing data fusion on the access control perception data, the video surveillance data, and the sensor data to obtain multiple feature sequences; including: matching the access control perception data and the sensor data, and matching the video surveillance data and the sensor data; if there is the association relationship between the access control perception data and the video surveillance data matched by the sensor data, then performing data fusion on the sensor data and the access control perception data and the video surveillance data it matches to obtain multiple feature sequences.

2. The security method based on full-range feature recognition and four-dimensional trajectory tracking according to claim 1, characterized in that, Performing individual feature matching and identity authentication on each feature sequence to obtain individual behavior data corresponding to each target object includes: For any two feature sequences, determining the feature similarity between the two feature sequences, and determining that the two feature sequences belong to the same target object when the feature similarity is higher than a preset threshold; Based on the feature sequences belonging to the same target object, determining the individual behavior data corresponding to each target object.

3. The security method based on full-range feature recognition and four-dimensional trajectory tracking according to claim 1, characterized in that Performing behavior anomaly detection on each target object based on the individual behavior data, obtaining a behavior anomaly detection result corresponding to each target object, includes: Preprocess the individual behavior data corresponding to each of the target objects, and extract the key features corresponding to each of the target objects from the preprocessed individual behavior data, where the key features include behavior frequency and behavior duration; Based on a pre-trained behavior pattern model, determine the target behavior pattern to which each of the target objects belongs, based on a plurality of pre-configured alternative behavior patterns and the key features corresponding to each of the target objects; Perform behavior anomaly detection on each of the target objects based on the key features corresponding to each of the target objects and the target behavior pattern to which it belongs, to obtain the behavior anomaly detection result corresponding to each of the target objects.

4. The security method based on full-range feature recognition and four-dimensional trajectory tracking according to claim 3, wherein, Perform behavior anomaly detection on each of the target objects based on the key features corresponding to each of the target objects and the target behavior pattern to which it belongs, to obtain the behavior anomaly detection result corresponding to each of the target objects, including: For any one of the key features corresponding to each of the target objects, determine whether the value of the key feature is higher than the behavior threshold corresponding to the target behavior pattern to which the target object belongs, and determine that the target object has an abnormal behavior when the determination result is yes.

5. The security method based on full-range feature recognition and four-dimensional trajectory tracking according to claim 1, wherein Visualize the four-dimensional movement trajectory of the target object in the target area, including: Obtain the three-dimensional coordinate data of the target object moving in the target area and its associated timestamp information, and construct the four-dimensional movement trajectory corresponding to the target object; Establish a three-dimensional model corresponding to the target area, and map the four-dimensional movement trajectory to the three-dimensional model to realize the visualization of the four-dimensional movement trajectory.

6. A security device based on full-range feature recognition and four-dimensional trajectory tracking, characterized in that The security device includes a data collection module, a feature recognition module, a behavior analysis module, a four-dimensional trajectory reconstruction module, and an intelligent operation linkage module: The data collection module deployed inside the target area is used to: collect data on one or more target objects entering the target area to obtain a multi-modal data set; The feature recognition module is used to: perform data fusion on the multi-modal data set to obtain a plurality of feature sequences, and perform individual feature matching and identity authentication on each of the feature sequences to obtain the individual behavior data corresponding to each of the target objects; The behavior analysis module is used to: perform behavior anomaly detection on each of the target objects based on the individual behavior data to obtain the behavior anomaly detection result corresponding to each of the target objects, and the behavior anomaly detection result is used to characterize whether the target object has an abnormal behavior; The four-dimensional trajectory reconstruction module is used to: visualize the four-dimensional movement trajectory of the target object in the target area, and add a specified mark to the four-dimensional movement trajectory corresponding to the target object with an abnormal behavior; The intelligent operation linkage module is used to: determine the alarm and response level corresponding to the anomaly detection result, and execute the target actions corresponding to the alarm and response level, where the target actions include one or more of an alarm action, a multi-level response action, and a device linkage disposal action; The multi-modal data set includes access control perception data, video surveillance data, and sensor data; specifically, the feature recognition module is used to: Extract the first face feature corresponding to the access control perception data and the second face feature corresponding to the video surveillance data, and perform fuzzy matching on the first face feature and the second face feature to determine the association relationship between the access control perception data and the video surveillance data; Based on the association relationship, perform data fusion on the access control perception data, the video surveillance data, and the sensor data to obtain multiple feature sequences; including: matching the access control perception data and the sensor data, and matching the video surveillance data and the sensor data; If there is the association relationship between the access control perception data and the video surveillance data matched by the sensor data, perform data fusion on the sensor data and the access control perception data and the video surveillance data matched thereby to obtain multiple feature sequences.

7. An electronic device, characterized in that, It includes a processor and a memory, the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer executable instructions, and when the computer executable instructions are called and executed by a processor, the computer executable instructions cause the processor to implement the method according to any one of claims 1 to 5.

Images