Invasive object track detection system based on wireless local area network signal
By analyzing the intensity changes of wireless LAN signals and data correlation algorithms, the problems of complex and easy destruction of intrusion detection equipment in the existing technology are solved, and the concealment and stability of intrusion object detection of wireless LAN signals are realized, and the installation of traditional sensors is avoided. Complexity.
Patent Information
- Application Number
- CN202411190000.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-12-06
AI Technical Summary
The existing intrusion detection technology relies on infrared and video sensors, and is complex in installation, cumbersome wiring, and is easily damaged, with insufficient stability and concealment.
The invading object trajectory detection system based on wireless LAN signals is adopted to judge object intrusion by analyzing the intensity changes of wireless LAN signals, and the position and trajectory of invading objects are determined by using function models and data association algorithms to realize detection without special sensors.
It realizes the concealment and stability of intrusion detection, and does not affect wireless LAN communication, and has the advantages of being simple, concealed and does not require special sensors.
Smart Images

Figure CN119091557A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the field of intrusion object detection, positioning and security, and relates to an intrusion object trajectory detection system based on wireless local area network signals. Background Art
[0002] Intrusion detection is the discovery and monitoring of intrusion behavior. It is to discover and detect people or objects entering a specific area through monitoring means. Intrusion object detection is the main function of security systems. At present, the relevant technologies used for intrusion detection are mainly infrared and video sensors for detection. This type of detection method requires the installation of a large number of sensors and various wiring settings. In addition, this type of detection method is easy to be discovered and destroyed, and lacks stability and concealment. Summary of the invention
[0003] In view of this, the purpose of the present invention is to provide an intrusion object trajectory detection system based on wireless LAN signals. It utilizes the characteristic that the received signal strength changes due to the obstruction of the wireless LAN signal propagation path by an object. Under the premise of not affecting the wireless LAN network communication, by analyzing the changes in the strength values of multiple wireless LAN signals in the monitoring area, it is determined whether there is an intrusion in the monitoring area, and the detection estimation and trajectory detection of the intrusion object are realized by solving the established function model; this method does not need to use special intrusion detection sensors (infrared and video sensors, etc.) for intrusion object detection, and can use the existing wireless LAN network and slightly modify it, which has the advantages of simplicity and strong concealment.
[0004] In order to achieve the above object, the present invention provides the following technical solutions:
[0005] A wireless local area network signal-based intrusion object trajectory detection system comprises: a plurality of wireless local area network signal transmitting devices, a plurality of wireless local area network signal receiving devices and at least one wireless local area network signal analyzing device.
[0006] The transmitting device and the receiving device are used to transmit and receive wireless local area network signals, and the transmitting device and the receiving device transmit the characteristics of the transmitted wireless local area network signals and the characteristics of the received wireless local area network signals to the signal analysis device respectively. The signal analysis device determines whether there is an object intrusion by analyzing the characteristics of the transmitted signal sent by the transmitting device and the characteristics of the received signal sent by the corresponding receiving device. If the signal analysis device determines that there is an object intrusion according to the signal strength change between the transmitted signal characteristics and the corresponding received signal characteristics is greater than a threshold value, otherwise it is considered that there is no object intrusion;
[0007] Among them, when an object invades, the signal analysis device determines the target position point according to the connection lines between a plurality of transmitting devices and receiving devices, and further determines the target trajectory according to the plurality of target position points.
[0008] Furthermore, the signal transmission relationship between a plurality of transmitting devices and a plurality of receiving devices is in a grid shape, wherein a transmitting device can not only send wireless LAN signals but also serve as a wireless LAN signal receiving device for other transmitting devices; a receiving device can not only receive wireless LAN signals but also serve as a transmitting device to send wireless LAN signals to other receiving devices; one transmitting device can send wireless LAN signals to multiple receiving devices, and one receiving device can receive wireless LAN signals sent by multiple transmitting devices.
[0009] Furthermore, in the event of an intrusion, the signal analysis device obtains, based on its grid-like signal network, several groups of lines between the transmitting device and the receiving device whose signal strength changes are greater than a threshold value. If it is detected that several groups of lines whose signal strength changes are greater than the threshold value all intersect at one point, the target position point is determined by the simultaneous linear equations. If it is detected that several groups of lines whose signal strength changes are greater than the threshold value do not intersect at one point, all lines whose signal changes are caused by the intrusion object are analyzed, and a distance function from the intrusion object to all the changed signal lines is established. The position of the intrusion object is estimated by the least squares method to obtain the position point. Then, several intrusion object position sequences with a time interval of T are determined according to the time sequence, and the intrusion trajectory is determined.
[0010] Furthermore, the signal analysis device determines whether the intruding object is single or multiple according to the number of target point data scanned by the signal analysis device at each moment. If there is only a single intrusion trajectory point at each moment, it is a single object invasion; if multiple intrusion trajectory points are scanned at each moment, it is necessary to perform threshold filtering on the data according to prior knowledge, wherein the prior knowledge is the spatial distribution of the intrusion location; then the distance between the filtered trajectory point and the trajectory point at the previous moment is measured, and the similarity between the trajectory points is determined according to the prior threshold, and then the intrusion object is determined to be a single target or multiple targets according to the similarity between the trajectory points. When only a single object invades, the signal analysis device connects several position points in time series to obtain the invasion trajectory; if there are multiple objects invading, the signal analysis device first obtains several intrusion object position sequences, and then associates the object position data with its corresponding trajectory through the data association algorithm, and then obtains the invasion trajectory of each object respectively.
[0011] Furthermore, when the signal analysis device identifies multiple intrusion object trajectories, the signal analysis device includes the following steps:
[0012] First, the data is preprocessed, in which the location points that do not meet the spatial constraints are filtered out by establishing a spatial constraint model;
[0013] The corresponding association tracking gate is selected according to actual needs. The association tracking gates include at least: an elliptical association gate, a circular association gate, a ring-shaped association gate and a sector-shaped association gate; among them, for targets whose movement speed and direction uncertainty are both lower than the corresponding threshold, an elliptical association gate is used; for targets evenly distributed in all directions, a circular association gate is used; for targets with random movement directions and position uncertainty higher than the threshold, a ring-shaped tracking gate is used; for targets with specific movement direction, a sector-shaped association gate is used.
[0014] The data association method is used to compare the position data of the intruding objects falling into the associated tracking gate with the associated object trajectory to obtain the respective detection points of the objects, and then the respective detection points of the objects are connected to obtain the respective trajectories of the objects.
[0015] Furthermore, the data association algorithm adopted by the signal analysis device is a global nearest neighbor algorithm, which calculates the sum of squares of the distances between the intruding object position data under all association possibilities and the existing current multi-association tracking gate center, and then associates the target observation position with the minimum distance square sum value with the current target position, specifically:
[0016] Assume that before the Kth observation, N trajectories have been established, and the Kth new observation is Z j (k),j=1,2,…,N,Z j (k) Within the association gate of track i, the difference vector between observation j and track i is defined as the difference between the measured value and the predicted value:
[0017]
[0018] Where X i (k|k-1) is the next step prediction equation for state estimation, Where A is the state transfer matrix and H is the observation matrix;
[0019] Let S(k) be e ij (k), the square of the statistical distance is:
[0020]
[0021] The global nearest neighbor association target is:
[0022]
[0023] Using the above associated objective function, the intrusion trajectory of the intruding object is finally determined.
[0024] The beneficial effects of the present invention are:
[0025] The present invention uses a wireless LAN signal analysis device to analyze the wireless LAN signal received by the wireless LAN signal receiving device, and uses the wireless LAN signal whose signal strength change is greater than a threshold to determine the position information of the transceiver, and then determine the straight line where the intruding object is located. A model is established and analyzed based on the above straight line to determine the position of the intruding object, and the trajectory detection of the intruding object is achieved through multiple scanning detections. The present invention realizes the detection and positioning of the intruding object by analyzing the strength change characteristics of the wireless LAN. Compared with the traditional intrusion detection method, the present invention has the advantages of not affecting the network communication function of the original system and good concealment.
[0026] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:
[0028] Figure 1 A simplified structural diagram of an intrusion object trajectory detection system of the present invention;
[0029] Figure 2 A workflow diagram for the trajectory association of multiple object intrusions;
[0030] Figure 3 The signal strength of the wireless LAN changes due to the obstruction of intruding objects;
[0031] Figure 4 Schematic diagram for locating trajectory points using distance and function;
[0032] Figure 5 Schematic diagram of the correction of trajectory points for the spatial constraint model;
[0033] Figure 6 Schematic diagram of various associated gates;
[0034] Figure 7 Schematic diagram of the trajectory association process of two objects;
[0035] Figure 8 It is the final trajectory of the two intruding objects after the trajectory data are associated. DETAILED DESCRIPTION
[0036] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.
[0037] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.
[0038] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "front", "rear", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.
[0039] See also Figures 1 to 8 , which is an intrusion object trajectory detection system based on wireless LAN signals.
[0040] Example
[0041] This example shows Figure 1 The intrusion object trajectory detection system shown includes a plurality of wireless LAN signal transceiver devices and at least one wireless LAN signal analysis device. In this embodiment, the system is composed of six wireless LAN signal transceiver devices and one wireless LAN signal analysis device. The wireless LAN signal sending device and the wireless LAN signal receiving device are used to transmit and receive wireless LAN signals, and transmit the received wireless LAN signals to the wireless LAN signal analysis device. The system uses the wireless LAN signal analysis device to analyze the wireless LAN signal received by the wireless LAN signal receiving device, and uses the wireless LAN signal whose signal strength change is greater than the threshold to determine the location information of the transceiver, determine the straight line where the object is located, and then determine the trajectory point of the object.
[0042] First, determine whether the intruding object is single or multiple based on the number of target point data scanned at each moment; if there is only a single intrusion trajectory point at each moment, it is a single object invasion; if multiple intrusion trajectory points are scanned at each moment, it is necessary to perform threshold filtering on the data based on prior knowledge (such as the spatial distribution of the intrusion location) to eliminate noise interference, and then measure the distance between the filtered trajectory points and the trajectory points at the previous moment, and determine the similarity between the trajectory points based on the prior threshold to determine whether it is a single target trajectory or a multi-target trajectory.
[0043] When a single object intrusion process occurs, the system can directly fit the trajectory data of the intruding object according to the order of scanning time; when multiple objects intrusion process occurs, the trajectory of the intruding object needs to be determined through the position association algorithm, such as Figure 2 The specific operation process of the system is as follows:
[0044] The wireless LAN analysis device stores the device characteristic information such as the number and location of each wireless LAN transceiver device, and analyzes and processes the wireless LAN signal according to a certain method to detect the trajectory of the intruding object. The wireless LAN analysis device adopts a certain method (polling) to receive the characteristic information such as the strength of the wireless LAN signal transmitted by each wireless LAN transmitting device from the wireless LAN signal receiving device at every time interval T, and analyzes whether the change in its strength is greater than the set threshold.
[0045] When an object intrusion occurs, the strength of the wireless LAN signal received by the corresponding wireless LAN receiving device will change due to the object's blocking of the wireless LAN signal. Figure 3 As shown, when the change is greater than the set threshold, the wireless LAN analysis device can determine that the intruding object is on the connection line determined by the wireless LAN signal receiving device that receives the signal and the wireless LAN signal transmitting device that transmits the signal.
[0046] Since the system is constructed in a network, when an object intrusion occurs, changes in the strength of several groups of wireless LAN signal lines can be detected. If the lines that detect changes in the strength of the wireless LAN signal all intersect at one point, the position of the intruding object can be determined by the simultaneous linear equations. If the lines that detect changes in the strength of the wireless LAN signal do not intersect at one point, all the lines that cause signal changes caused by the intruding object are analyzed, and a distance function from the intruding object to all the changed signal lines is established. The position estimate of the intruding object is obtained using the least squares method. That is, assuming that the position of the intruding object is point A, the point with the shortest sum of the distances from point A to the above straight lines is obtained using the least squares method, which is the estimated position of the intruding object, such as Figure 4 shown.
[0047] When a single object intrusion occurs, the above method can be used to obtain a single intrusion object position sequence with a time interval of t, and the object intrusion trajectory can be constructed. When multiple objects intrusion occur, the above method can be used to obtain multiple intrusion object position sequences with a time interval of t, but it is impossible to determine which object the trajectory point at each moment belongs to. The object position data needs to be associated with the object trajectory through a data association algorithm.
[0048] Before data association, the data can be preprocessed to remove possible outliers and noise; using information such as building floor plans or layouts, a spatial constraint model can be established to ensure that the subsequent associated trajectory data is true and reasonable, and to improve the accuracy and reliability of trajectory association. Figure 5 As shown, the trajectory points calculated by the least squares method may not meet actual expectations, and spatial constraints need to be corrected to limit the solution space of the least squares method to the solution space under actual spatial constraints, and adjust the trajectory points that do not meet expectations.
[0049] According to actual needs, select the corresponding correlation tracking gate, such as Figure 6 As shown, the associated tracking gates include at least: an elliptical associated gate, a circular associated gate, a ring-shaped associated gate and a sector-shaped associated gate. Among them, when performing intrusion trajectory detection on objects with small changes in speed and direction, such as intruder trajectory detection, an elliptical associated gate can be used; when performing intrusion trajectory detection on targets that may be evenly distributed in all directions, such as animal intrusion trajectory detection, a circular associated gate can be used; when performing intrusion trajectory detection on targets with high position uncertainty and random movement directions, such as drone swarm intrusion trajectory detection, a ring-shaped associated gate can be used; when performing intrusion trajectory detection on targets with specific directionality of movement, such as aircraft intrusion trajectory detection in pipeline space, a sector-shaped associated gate can be used. Using the data association method, the position data of the intruding object that falls into the associated tracking gate is compared with the associated object trajectory to obtain the detection points of each object, such as Figure 7 If the global nearest neighbor algorithm is used, the sum of the squares of the distances between the intruding object position data and the existing current multi-association tracking gate center under all association possibilities is calculated, and then the target observation position with the minimum sum of squares is associated with the current target position.
[0050] Assume that before the Kth observation, N trajectories have been established, and the Kth new observation is Z j (k), j = 1, 2, ..., N In the association gate of the ith track, the difference vector between observation j and track i is defined as the difference between the measured value and the predicted value:
[0051]
[0052] Where X i(k|k-1) is the next step prediction equation for state estimation, Where A is the state transfer matrix, H is the observation matrix, and S(k) is e ij (k), the square of the statistical distance is:
[0053]
[0054] The global nearest neighbor association target is:
[0055]
[0056] Using the above associated objective function, the intrusion trajectories of the two intrusion objects are finally determined, such as Figure 8 shown.
[0057] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.
Claims
1. An intrusion object trajectory detection system based on wireless local area network signals, characterized in that: It includes: Several wireless local area network signal transmitting devices, several wireless local area network signal receiving devices and at least one wireless local area network signal analyzing device, The transmitting device and the receiving device are used to transmit and receive wireless local area network signals, and the transmitting device and the receiving device transmit the characteristics of the transmitted wireless local area network signals and the characteristics of the received wireless local area network signals to the signal analysis device respectively. The signal analysis device determines whether there is an object intrusion by analyzing the characteristics of the transmitted signal sent by the transmitting device and the characteristics of the received signal sent by the corresponding receiving device. If the signal analysis device determines that there is an object intrusion according to the signal strength change between the transmitted signal characteristics and the corresponding received signal characteristics is greater than a threshold value, otherwise it is considered that there is no object intrusion; Among them, when an object invades, the signal analysis device determines the target position point according to the connection lines between a plurality of transmitting devices and receiving devices, and further determines the target trajectory according to the plurality of target position points.
2. The intrusion object trajectory detection system based on wireless local area network signals according to claim 1, characterized in that: The signal transmission relationship between a plurality of transmitting devices and a plurality of receiving devices is in a grid shape, wherein the transmitting device can not only send wireless LAN signals, but also serve as a wireless LAN signal receiving device for other transmitting devices; the receiving device can not only receive wireless LAN signals, but also serve as a transmitting device to send wireless LAN signals to other receiving devices; one transmitting device can send wireless LAN signals to multiple receiving devices, and one receiving device can receive wireless LAN signals sent by multiple transmitting devices.
3. The intrusion object trajectory detection system based on wireless local area network signals according to claim 2 is characterized in that: In the case of an intrusion, the signal analysis device obtains a number of groups of lines between the transmitting device and the receiving device whose signal strength changes are greater than a threshold value according to its grid-shaped signal network. If it is detected that a number of groups of lines whose signal strength changes are greater than the threshold value intersect at one point, the target position point is determined by simultaneous linear equations; If it is detected that several groups of lines with signal strength changes greater than the threshold do not intersect at one point, all lines of signal changes caused by the intrusion object are analyzed, and a distance function from the intrusion object to all the changed signal lines is established. The position of the intrusion object is estimated using the least squares method to obtain the position point; Then, a number of intrusion object position sequences with a time interval of T are determined according to the time sequence, and then the intrusion trajectory is determined.
4. The intrusion object trajectory detection system based on wireless local area network signals according to claim 3 is characterized in that: The signal analysis device determines whether the intruding object is single or multiple according to the number of target point data scanned at each moment; If there is only a single intrusion trajectory point at each moment, it is a single object intrusion; If multiple intrusion trajectory points are scanned at each moment, it is necessary to perform threshold filtering on the data based on prior knowledge, where the prior knowledge is the spatial distribution of the intrusion location; then the distance between the filtered trajectory points and the trajectory points at the previous moment is measured, and the similarity between the trajectory points is determined based on the prior threshold, and then the intrusion object is determined to be a single target or multiple targets based on the similarity between the trajectory points; When only a single object invades, the signal analysis device connects several position points in time series to obtain the invasion trajectory; When there are multiple intruding objects, the signal analysis device first obtains a sequence of positions of several intruding objects, then associates the object position data with its corresponding trajectory through a data association algorithm, and then obtains the intrusion trajectory of each object.
5. The intrusion object trajectory detection system based on wireless local area network signals according to claim 4 is characterized in that: When the signal analysis device identifies multiple intrusion object trajectories, the signal analysis device includes the following steps: First, the data is preprocessed, in which the location points that do not meet the spatial constraints are filtered out by establishing a spatial constraint model; Select the corresponding association tracking gate according to actual needs. The association tracking gate includes at least: elliptical association gate, circular association gate, ring association gate and fan association gate; among them, for targets whose movement speed and direction uncertainty are both lower than the corresponding threshold, the elliptical association gate is used; for targets evenly distributed in all directions, the circular association gate is used; for targets with random movement directions and position uncertainty higher than the threshold, the ring tracking gate is used; for targets with specific movement directions, the fan association gate is used; The data association method is used to compare the position data of the intruding objects falling into the associated tracking gate with the associated object trajectory to obtain the respective detection points of the objects, and then the respective detection points of the objects are connected to obtain the respective trajectories of the objects.
6. The intrusion object trajectory detection system based on wireless local area network signals according to claim 5, characterized in that: The data association algorithm used by the signal analysis device is a global nearest neighbor algorithm, which calculates the sum of the squares of the distances between the intruder position data and the existing current multi-association tracking gate center under all association possibilities, and then associates the target observation position with the minimum distance square sum value with the current target position, specifically: Assume that before the Kth observation, N trajectories have been established, and the Kth new observation is Z j (k),j=1,2,…,N,Z j (k) Within the association gate of track i, the difference vector between observation j and track i is defined as the difference between the measured value and the predicted value: Where X i (k|k-1) is the next step prediction equation for state estimation, Where A is the state transfer matrix and H is the observation matrix; Let S(k) be e ij (k), the square of the statistical distance is: The global nearest neighbor association target is: Using the above associated objective function, the intrusion trajectory of the intruding object is finally determined.
