Intrusion detection method, electronic device, and computer-readable storage medium

Abstract

This application discloses an intrusion detection method, electronic device, and computer-readable storage medium. The method includes: acquiring first radiation energy collected by multiple passive infrared sensors at a current moment, wherein at least some of the passive infrared sensors are configured to detect different sub-regions within a target area; determining the current energy change of the target area at the current moment based on the first radiation energy collected by each passive infrared sensor; acquiring environmental parameters at the current moment and determining an energy change threshold based on the environmental parameters; and determining whether an intrusion target exists in the target area at the current moment based on the current energy change and the energy change threshold. This method can improve the success rate of intrusion detection in complex environments.

Description

Technical Field

[0001] This application relates to the field of detection technology, and in particular to an intrusion detection method, electronic device, and computer-readable storage medium. Background Technology

[0002] Existing intrusion detection solutions often exhibit poor success rates in complex environments with numerous interfering factors. In particular, the ability to identify intrusion behavior significantly decreases when interference is present. These external interferences not only increase the likelihood of false alarms but also cause genuine intrusions to be missed, thus significantly impacting the overall reliability and practicality of the detection system. Therefore, improving the anti-interference capability and detection accuracy in complex environments has become a critical issue that urgently needs to be addressed in the field of intrusion detection. Summary of the Invention

[0003] This application provides an intrusion detection method, an electronic device, and a computer-readable storage medium that can improve the success rate of intrusion detection in complex environments.

[0004] A first aspect of this application provides an intrusion detection method, the method comprising: acquiring a first radiation energy collected at a current moment by a plurality of passive infrared sensors, wherein at least some of the passive infrared sensors are configured to detect different sub-regions within a target area; determining the current energy change of the target area at the current moment based on the first radiation energy collected by each of the passive infrared sensors; acquiring environmental parameters at the current moment and determining an energy change threshold at the current moment based on the environmental parameters; and determining whether an intrusion target exists in the target area at the current moment based on the current energy change and the energy change threshold.

[0005] A second aspect of this application provides an electronic device including a memory and a processor interconnected, wherein the memory is used to store a computer program, which, when executed by the processor, is used to implement the method as described in any of the above embodiments.

[0006] A third aspect of this application provides a computer-readable storage medium storing a computer program that can be executed by a processor to perform the steps of the method as described in any of the above embodiments.

[0007] Unlike existing technologies, the beneficial effects of this application are as follows: This application acquires the first radiation energy collected by multiple passive infrared sensors at the current moment, then determines the current change energy of the target area at the current moment. When determining the energy change threshold at the current moment, the environmental parameters collected in real time at the current moment are used to make the energy change threshold adapt to environmental changes. Then, based on the current change energy and the energy change threshold, it is determined whether there is an intrusion object in the target area at the current moment. It will not produce the possibility of false alarms due to some environmental disturbances, thereby improving the intrusion detection success rate in some complex environments, especially under some external environmental disturbances. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein: Figure 1 This is a flowchart illustrating the intrusion detection method of this application; Figure 2 This is a schematic diagram illustrating the application of the intrusion detection method of this application in an application scenario; Figure 3 yes Figure 2 A schematic diagram of the target area projected onto the ground; Figure 4 yes Figure 1 A flowchart illustrating one embodiment of step S200; Figure 5 yes Figure 4 A flowchart illustrating one embodiment of step S210; Figure 6 yes Figure 5 A flowchart illustrating one embodiment of step S212; Figure 7 yes Figure 4 A flowchart illustrating one embodiment of step S220; Figure 8 yes Figure 7 A flowchart illustrating one embodiment of step S222; Figure 9 yes Figure 1 A flowchart illustrating one embodiment of step S300; Figure 10 yes Figure 9 A flowchart illustrating one embodiment of step S320; Figure 11 This is a schematic diagram of the structure of one embodiment of the electronic device of this application; Figure 12 This is a schematic diagram of one embodiment of the computer-readable storage medium of this application. Detailed Implementation

[0009] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0010] It should be noted that the terms "first" and "second" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0011] See Figures 1 to 3 , Figure 1 This is a flowchart illustrating the intrusion detection method of this application. Figure 2 This is a schematic diagram illustrating the application of the intrusion detection method of this application in an application scenario. Figure 3 yes Figure 2 A schematic diagram of the target area projected onto the ground. The first aspect of this application provides an intrusion detection method, which includes: S100: Acquire the first radiation energy collected at the current moment by multiple passive infrared sensors (PIR), wherein at least some of the passive infrared sensors are configured to detect different sub-regions in the target region.

[0012] Specifically, the target area refers to the area to be detected, which can also be understood as the area resulting from the superposition of the detection areas of multiple passive infrared sensors. In this scheme, the target area is divided into multiple different sub-regions, each of which is detected by at least one passive infrared sensor. Each passive infrared sensor detects at least one sub-region, and the difference in detection range of the multiple passive infrared sensors can be achieved through differences in lens structure. For example, in Figure 2In this configuration, the target area is divided into three sub-regions: D1, D2, and D3. Based on their distance from the passive infrared sensors, these sub-regions can be referred to as near-field, mid-field, and far-field, respectively. Among multiple passive infrared sensors, the first is installed to detect D1, the second to detect both D1 and D2, the third to detect D2, the fourth to detect both D2 and D3, and the fifth to detect all three. Multiple passive infrared sensors can also be used to detect the same sub-region. In other applications, the number and division of sub-regions within the target area, the number of passive infrared sensors, and the selected detection methods can all be different. The passive infrared sensor's acquisition principle is based on the pyroelectric effect and infrared radiation characteristics, achieving target detection by detecting the energy of specific wavelengths of infrared light emitted by an object. In this step, the first radiation energy collected by multiple passive infrared sensors at the current moment is directly obtained, thereby enabling the acquisition of energy data for different sub-regions within the target area.

[0013] S200: Determine the current change in energy of the target area at the current moment based on the first radiation energy collected by each passive infrared sensor.

[0014] Specifically, based on the first radiation energy collected in real time by each passive infrared sensor, and combined with the detection coverage of each passive infrared sensor, the energy data of all passive infrared sensors are superimposed, and after further data processing, the current change in energy of the target area at the current moment is obtained.

[0015] In one embodiment, see Figure 4 , Figure 4 yes Figure 1 A flowchart illustrating one embodiment of step S200, wherein step S200 includes: S210: For each passive infrared sensor, determine the corresponding energy change data of the passive infrared sensor based on the first radiation energy collected by the passive infrared sensor and the background radiation energy collected in advance by the passive infrared sensor.

[0016] Specifically, background radiation energy refers to the radiation energy of the background environment in the target area detected by multiple passive infrared sensors. This energy reflects the background radiation level of the environment under normal conditions, and therefore should not inherently contain any radiation components generated by intruding objects or sudden interference sources. In other words, background radiation energy represents the amount of radiation that remains relatively constant over a long period of time under stable conditions. Background radiation energy is collected by passive infrared sensors at an early stage, for example, during equipment installation and commissioning, or at any suitable time during system operation as needed. It should be noted that the method of collecting background radiation energy is basically the same as the method of collecting the first radiation energy described in step S100. By comparing and analyzing the real-time collected first radiation energy with the pre-acquired background radiation energy, changes in radiation levels can be effectively identified, thereby accurately determining the energy change data detected by the passive infrared sensors.

[0017] In one embodiment, see Figure 5 , Figure 5 yes Figure 4 A flowchart illustrating one embodiment of step S210, wherein step S210 includes: S211: Integrate the difference between the first radiation energy and the background radiation energy per unit time to obtain the first result.

[0018] Specifically, the difference between the first radiant energy and the background radiant energy is first calculated. This difference represents the difference between the radiant energy at the current moment and the radiant energy in the background. Then, the differences from multiple different moments within a unit time are accumulated to obtain the first result. It should be noted that a passive infrared sensor can typically collect the first radiant energy at multiple different moments within a unit time. Therefore, this step is equivalent to accumulating the differences between the first radiant energy and the background radiant energy at the current moment and all moments in the previous unit time to obtain the first result. The advantage of this processing method is that the result within a unit time (i.e., a period of time) can avoid the possibility of false detection caused by a single abnormal acquisition.

[0019] The specific formula for step S211 above is as follows: .

[0020] in, It is background radiation energy. It is the first type of radiant energy. Let t be the first result corresponding to the i-th (1≤i≤n) passive infrared sensor among n passive infrared sensors, where t is time, t1 is the current time, and t0 is the time one unit time before the current time.

[0021] Of course, in some other implementations, the difference between the first radiation energy and the background radiation energy can be directly used as the first result. The advantage of this approach is that it reduces the amount of data computation and storage.

[0022] S212: Based on the first result, obtain the energy change data.

[0023] Specifically, after obtaining the first result corresponding to each passive infrared sensor, the first results corresponding to different passive infrared sensors are then fused to obtain the energy change data corresponding to the target area, which is used for subsequent intrusion judgment in the target area.

[0024] Furthermore, in implementing step S212, this application fuses the first result with environmental parameters. Environmental parameters refer to relevant parameters in the environment where the passive infrared sensor is located. Environmental parameters may change over time. Dynamically fusing the first result with environmental parameters can make the first result adapt to the dynamic changes in the environment, thereby improving the identification of environmental changes and intrusion changes.

[0025] In one embodiment, see Figure 6 , Figure 6 yes Figure 5 A flowchart illustrating one embodiment of step S212 is provided. Multiple environmental parameters are considered. Step S212 includes: S2121: For each environmental parameter, substitute the environmental parameter into the corresponding first preset function to obtain the first target value of the environmental parameter.

[0026] Specifically, environmental parameters include ambient temperature, ambient humidity, ambient wind speed, the preliminary position of the target being detected, and the actual installation angle of the passive infrared sensor. Ambient temperature, humidity, and wind speed are collected by sensors. The preliminary position of the target is inferred based on the first radiation energy obtained in step S100. This preliminary position is only for initial inference and may be correct or incorrect; it cannot be used for intrusion detection or precise location. The actual installation angle of the passive infrared sensor is obtained through calibration during sensor installation. Therefore, ambient temperature, humidity, wind speed, and the preliminary position of the target are real-time dynamic parameters. While the actual installation angle of the passive infrared sensor is not a real-time dynamic parameter, it is still a variable parameter, depending on the installation method. In the above steps, for each environmental parameter, the specific value of the acquired environmental parameter is first substituted into a first preset function. By calculating the output of the first preset function, the first target value corresponding to that environmental parameter is obtained. This step ensures that each environmental parameter can be accurately quantified according to its characteristics.

[0027] Furthermore, the specific formulas for the normalized first preset function corresponding to each environmental parameter are as follows: The environmental parameter is ambient temperature, and the first preset function corresponding to the ambient temperature is as follows: g(T) = k T2 ×|TT ref | / T r .

[0028] Where T is the ambient temperature, T ref For reference temperature, for example, the reference temperature could be 36℃, T r This refers to the temperature detection range value. For example, if the temperature detection interval is -40℃ to 50℃, then the temperature detection range value is 90℃, k. T2 This is the temperature compensation coefficient. Generally speaking, the temperature compensation coefficient is a positive value. The greater the difference between the ambient temperature and the reference temperature, the larger the first target value.

[0029] The environmental parameter is ambient humidity, and the first preset function corresponding to the ambient humidity is as follows: g(H)=k H2 ×(HH ref ).

[0030] Where H represents ambient humidity, H ref For reference humidity, k H2 This is the humidity compensation coefficient. Generally speaking, the humidity compensation coefficient is negative. When the ambient humidity is lower than the reference humidity, it has a higher first target value.

[0031] The environmental parameter is the ambient wind speed, and the first preset function corresponding to the ambient wind speed is as follows: g(W) = k W2 ×(WW ref ).

[0032] Where W is the ambient wind speed, W ref For reference wind speed, k W2 The wind speed influence coefficient is generally positive. When the ambient wind speed is higher than the reference wind speed, the first target value is higher.

[0033] The environmental parameters represent the initial position of the target being detected, and the first preset function corresponding to the initial position of the target being detected is as follows: g(D)={(D1:k} e1 );……;(D i :k ei );……;(D n :k en )}.

[0034] The target area is divided into partitions D1 to D... nThe partitions are divided into two groups, each corresponding to a distance coefficient k. e1 To k en i takes values ​​between 1 and n, and each D i The partition has a distance coefficient k. ei Different sub-regions have different distance coefficients, which were determined by previous experimental tests.

[0035] The environmental parameter is the actual installation angle of the passive infrared sensor. The first preset function corresponding to the actual installation angle of the passive infrared sensor is as follows: g(θ) = k θ2 ×|θ-θ ref | / θ r .

[0036] Where θ is the actual installation angle of the passive infrared sensor, θ ref θ is the reference installation angle for the passive infrared sensor. r k represents the angle mounting range value for the passive infrared sensor. θ2 This is the influence coefficient of the passive infrared sensor. Generally speaking, the influence coefficient of the passive infrared sensor is negative. The greater the difference between the actual installation angle and the reference installation angle, the smaller the first target value.

[0037] S2122: Perform a weighted summation of multiple first target values ​​to determine the first sum value.

[0038] Specifically, the first target value corresponding to different environmental parameters in step S2121 above is fused and calculated to obtain the first sum value.

[0039] The specific formula for determining the first sum M is as follows: M=β T ×g(T)+β H ×g(H)+β W ×g(W)+β D ×g(D)+β θ ×g(θ).

[0040] Where, β T β is the weight of the first preset function corresponding to the ambient temperature. H β is the weight of the first preset function corresponding to ambient humidity. W β is the weight of the first preset function corresponding to the ambient wind speed. D β is the weight of the first preset function corresponding to the initial position of the target being detected. θ The weight of the first preset function corresponding to the actual installation angle of the passive infrared sensor.

[0041] S2123: Obtain energy change data based on the first sum and the first result.

[0042] Specifically, by utilizing the dynamic nature of the first sum, fluctuation characteristics are extracted from the first result to obtain energy change data. This step enables the dynamic extraction of fluctuation characteristics in the first radiant energy, thereby better adapting to dynamic environmental changes.

[0043] Determine energy change data C i The specific formula is as follows: C i =M i ×E i .

[0044] Among them, E i M represents the first result corresponding to the i-th passive infrared sensor out of n passive infrared sensors. i Let C be the first sum value corresponding to the i-th passive infrared sensor out of n passive infrared sensors. i Let C be the energy change data corresponding to the i-th passive infrared sensor out of n passive infrared sensors. i It can characterize the spatiotemporal distribution differences of energy changes in the detection area of ​​the corresponding passive infrared sensor.

[0045] Of course, in addition to step S210 described above, in some other embodiments, the energy change data corresponding to the passive infrared sensor can also be determined based on the first radiation energy collected by the passive infrared sensor at the current moment and the second radiation energy collected by the passive infrared sensor at the previous moment. The advantage of this embodiment is that it avoids the process of specifically collecting and calibrating the background radiation energy in the early stages, simplifying the system initialization process and the initial operation steps of the detection method.

[0046] Please combine Figure 4 After step S220, the following steps continue to be performed: S220: Determine the current energy change of the target area at the current moment based on the energy change data corresponding to each passive infrared sensor.

[0047] Specifically, by analyzing and processing the energy change data corresponding to different passive infrared sensors, the current energy change of the target area at the current moment can be determined, thereby determining the energy change situation of the target area.

[0048] In one embodiment, see Figure 7 , Figure 7 yes Figure 4 A flowchart illustrating one embodiment of step S220, wherein step S220 includes: S221: At least each energy change data point is weighted and summed to obtain a second sum.

[0049] Specifically, in the previous step S210, the energy change data corresponding to each passive infrared sensor has been obtained. At least by weighting and summing all the energy change data, a second sum value is obtained.

[0050] S222: Determine the current change in energy of the target region at the current moment based on the second sum.

[0051] Specifically, using the second sum as the base data, the second sum can be directly used as the current change energy of the target region at the current moment. Alternatively, the second sum can be processed to improve the accuracy of the current change energy through training.

[0052] Further reading Figure 8 , Figure 8 yes Figure 7 A flowchart illustrating one embodiment of step S222, wherein step S222 includes: S2221: Add the weights and stability coefficients corresponding to all energy change data to obtain the third sum.

[0053] Specifically, the stability coefficient is added to the weights corresponding to all energy change data to obtain a third sum, and the stability coefficient is used to control the magnitude of weight updates in subsequent steps.

[0054] S2222: Calculate the ratio of the second sum to the third sum to obtain the current change energy of the target region at the current time; wherein, the weights corresponding to all energy change data are updated through backpropagation of the loss function.

[0055] Specifically, the ratio of the second sum to the third sum is calculated to obtain the current energy change of the target area at the current moment. Weights are trained using historical intrusion data, and the weights of each energy change data point can be automatically adjusted through the backpropagation mechanism of the loss function. This improves the model's prediction accuracy and adaptability to different environmental temperatures, humidity levels, and wind speeds. The stability coefficient prevents large weight changes due to single-iteration anomalies, ensuring the robustness and generalization ability of the process.

[0056] The above step S222 specifically calculates the current energy change P. out The formula is: .

[0057] Among them, C i Let w be the energy change data corresponding to the i-th passive infrared sensor out of n passive infrared sensors. i Let ε be the weight of the energy change data corresponding to the i-th passive infrared sensor among n passive infrared sensors, and let ε be the stability coefficient, the value of which is between 10 and 10. -5~ 10-3 between.

[0058] Further reading Figure 1 After step S200, the following steps are performed: S300: Collects environmental parameters at the current moment and determines the energy change threshold at the current moment based on the environmental parameters.

[0059] Specifically, environmental parameters include ambient temperature, ambient humidity, ambient wind speed, the initial position of the target being detected, and the actual installation angle of the passive infrared sensor. These environmental parameters are collected at the current moment using sensors or other methods. The energy change threshold is then determined based on these environmental parameters. It should be understood that the energy change threshold is not a fixed threshold; it possesses dynamic characteristics of the environment. As the environment changes, the energy change threshold also changes accordingly. This adaptation of the energy change threshold to the environment improves its reliability in changing environments. It should be noted that the environmental parameters collected in this step can also be used in step S2121 above.

[0060] In one embodiment, see Figure 9 , Figure 9 yes Figure 1 A flowchart illustrating one embodiment of step S300 is provided. Multiple environmental parameters are considered. Determining the energy change threshold at the current moment based on these environmental parameters in step S300 includes: S310: For each environmental parameter, substitute the environmental parameter into the corresponding second preset function to obtain the second target value of the environmental parameter.

[0061] Specifically, for each environmental parameter, the first step is to substitute the acquired numerical value of the environmental parameter into a second preset function. By calculating the output of the second preset function, the second target value corresponding to that environmental parameter is obtained. This step ensures that each environmental parameter can be accurately quantified according to its characteristics.

[0062] Furthermore, the specific formulas for the normalized second preset functions corresponding to each environmental parameter are as follows: The environmental parameter is the ambient temperature, and the second preset function corresponding to the ambient temperature is as follows: f(T) = k T1 |TT ref | / T r .

[0063] Where T is the ambient temperature, T ref For reference temperature, for example, the reference temperature could be 36℃, T r This refers to the temperature detection range, for example, a temperature detection interval of -40℃ to 50℃, k. T1This is the temperature compensation coefficient. Generally speaking, the temperature compensation coefficient is a positive value. The greater the difference between the ambient temperature and the reference temperature, the larger the first target value.

[0064] The environmental parameter is ambient humidity, and the second preset function corresponding to the ambient humidity is as follows: f(H)=k H1 (HH ref ).

[0065] Where H represents ambient humidity, H ref For reference humidity, k H1 This is the humidity compensation coefficient. Generally speaking, the humidity compensation coefficient is negative. If the ambient humidity is lower than the reference humidity, then it has a higher second target value.

[0066] The environmental parameter is the ambient wind speed, and the second preset function corresponding to the ambient wind speed is as follows: f(W) = k W1 (WW ref ).

[0067] Where W is the ambient wind speed, W ref For reference wind speed, k W1 The wind speed influence coefficient is generally positive. If the ambient wind speed is higher than the reference wind speed, then the second target value is higher.

[0068] The environmental parameters represent the initial position of the target being detected, and the second preset function corresponding to the initial position of the target being detected is as follows: f(D) = {(D1:k} d1 );……;(D i :k di );……;(D n :k dn )}.

[0069] The target area is divided into partitions D1 to D... n The partitions are divided into two groups, each corresponding to a distance coefficient k. d1 To k dn i takes values ​​between 1 and n, and each D i The partition has a distance coefficient k. di Different sub-regions have different distance coefficients, which were determined by previous experimental tests.

[0070] The environmental parameter is the actual installation angle of the passive infrared sensor. The second preset function corresponding to the actual installation angle of the passive infrared sensor is as follows: f(θ) = k θ1 |θ-θ ref | / θ r .

[0071] Where θ is the actual installation angle of the passive infrared sensor, θ ref θ is the reference installation angle for the passive infrared sensor. r k represents the angle mounting range value for the passive infrared sensor. θ1 The influence coefficient of a passive infrared sensor is generally negative. The greater the difference between the actual installation angle and the reference installation angle, the smaller the second target value.

[0072] S320: Determine the energy change threshold at the current moment based on multiple second target values ​​and a baseline threshold.

[0073] Specifically, the baseline threshold refers to the threshold in a static environment, excluding the changing characteristics of the dynamic environment. This step combines multiple second target values ​​to obtain the energy change threshold at the current moment. The energy change threshold can change with the changes in the environment, thus providing different thresholds in different environments.

[0074] It can be seen that the first preset function and the second preset function have the same form, but they are different in setting their respective compensation coefficients, influence coefficients or distance coefficients for environmental parameters. In other words, different coefficients can be used to adapt to some more complex detection environments when dynamically extracting features and dynamically calculating thresholds.

[0075] In one embodiment, see Figure 10 , Figure 10 yes Figure 9 A flowchart illustrating one embodiment of step S320, wherein step S320 includes: S321: Perform a weighted summation of multiple second objective values ​​to determine the fourth sum.

[0076] Specifically, the fourth sum value is obtained by merging the second target values ​​corresponding to different environmental parameters in step S310 above.

[0077] S322: Obtain the energy change threshold at the current moment based on the fourth sum and the baseline threshold.

[0078] Specifically, the baseline threshold is adjusted by the dynamic characteristics of the fourth sum to obtain the energy change threshold that reflects environmental changes. The energy change threshold can be optimized based on historical data, for example, by using moving average filtering to reduce instantaneous interference.

[0079] The above determines the energy change threshold V at the current moment. d The specific formula is: V d =V base ×(α T ×f(T)+α H ×f(H)+αW ×f(W)+α D ×f(D)+α θ ×f(θ)).

[0080] Among them, V base As the baseline threshold, α T α is the weight of the second preset function corresponding to the ambient temperature. H α represents the weight of the second preset function corresponding to ambient humidity. W α is the weight of the second preset function corresponding to the ambient wind speed. D The weight α is the weight of the second preset function corresponding to the initial position of the target being detected. θ The weight of the second preset function corresponding to the actual installation angle of the passive infrared sensor.

[0081] In actual execution, the execution order of steps S300 and S200 does not need to be distinguished.

[0082] Further reading Figure 1 After step S300, the following steps are performed: S400: Based on the current energy change and the energy change threshold, determine whether there is an intrusion target in the target area at the current moment.

[0083] Specifically, by comparing the current change energy with the energy change threshold, if the current change energy is less than the energy change threshold, there is no intrusion target in the target area at the current moment; if the current change energy is not less than the energy change threshold, there is an intrusion target in the target area at the current moment.

[0084] Further, after step S400, the following is included: If an intrusion target exists in the target area at the current moment, locate the sub-area where the intrusion target is located.

[0085] Specifically, if there is an intruder in the target area at the current moment, the sub-area where the intruder is located can be determined by dividing the first radiation energy, the background radiation energy, and the detection area of ​​each passive infrared sensor.

[0086] In summary, this application acquires the first radiation energy collected by multiple passive infrared sensors at the current moment, then determines the current energy change of the target area at the current moment. When determining the energy change threshold at the current moment, the environmental parameters collected in real time at the current moment are used to make the energy change threshold adapt to environmental changes. Then, based on the current energy change and the energy change threshold, it is determined whether there is an intrusion object in the target area at the current moment. It will not produce the possibility of false alarms due to some environmental disturbances, thereby improving the intrusion detection success rate in some complex environments, especially under some external environmental disturbances.

[0087] See Figure 11 , Figure 11 This is a schematic diagram of the structure of an embodiment of the electronic device of this application. The electronic device 300 includes a processor 310 and a memory 320. The processor 310 is coupled to the memory 320. The memory 320 stores program data. The processor 310 executes the program data in the memory 320 to implement the steps in any of the above embodiments. The detailed steps can be found in the above embodiments and will not be repeated here.

[0088] Among them, electronic device 300 can be any device with algorithm capabilities, such as mobile phone, tablet computer, smartwatch, desktop computer or laptop computer, without any restrictions.

[0089] See Figure 12 , Figure 12 This is a schematic diagram of one embodiment of the computer-readable storage medium of this application. The computer-readable storage medium 400 stores a computer program 410, which can be executed by a processor to implement the steps in any of the above methods. Detailed method steps can be found in the relevant content above, and will not be repeated here.

[0090] Specifically, the computer-readable storage medium 400 can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or a device that can store the computer program 410. Alternatively, it can be a server that stores the computer program 410, which can send the stored computer program 410 to other devices for execution, or it can run the stored computer program 410 itself.

[0091] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An intrusion detection method, characterized in that, The method includes: Acquire the first radiation energy collected at the current moment by multiple passive infrared sensors, wherein at least some of the passive infrared sensors are configured to detect different sub-regions in the target region; Based on the first radiation energy collected by each of the passive infrared sensors, determine the current change in energy of the target area at the current moment; Collect environmental parameters at the current moment, and determine the energy change threshold at the current moment based on the environmental parameters; Based on the current energy change and the energy change threshold, it is determined whether there is an intrusion target in the target area at the current moment.

2. The method according to claim 1, characterized in that, The step of determining the current energy change of the target area at the current moment based on the first radiation energy collected by each of the passive infrared sensors includes: For each of the passive infrared sensors, the energy change data corresponding to the passive infrared sensor is determined based on the first radiation energy collected by the passive infrared sensor and the background radiation energy collected in advance by the passive infrared sensor. Based on the energy change data corresponding to each of the passive infrared sensors, the current energy change of the target area at the current moment is determined.

3. The method according to claim 2, characterized in that, The step of determining the energy change data corresponding to the passive infrared sensor based on the first radiation energy collected by the passive infrared sensor and the background radiation energy pre-collected by the passive infrared sensor includes: The difference between the first radiation energy and the background radiation energy is integrated over a unit time to obtain a first result; Based on the first result, the energy change data is obtained.

4. The method according to claim 3, characterized in that, The environmental parameters are multiple, and the step of obtaining the energy change data based on the first result includes: For each of the environmental parameters, the environmental parameter is substituted into the corresponding first preset function to obtain the first target value of the environmental parameter; The first sum is determined by weighted summation of multiple first target values. The energy change data is obtained based on the first sum and the first result.

5. The method according to claim 2, characterized in that, The step of determining the current energy change of the target area at the current moment based on the energy change data corresponding to each of the passive infrared sensors includes: At least each of the energy change data points is weighted and summed to obtain a second sum value; Based on the second sum, the current change energy of the target region at the current moment is determined.

6. The method according to claim 5, characterized in that, The step of determining the current change energy of the target region at the current moment based on the second sum value includes: Add the weights and stability coefficients corresponding to all the energy change data to obtain the third sum; The ratio of the second sum to the third sum is calculated to obtain the current energy change of the target region at the current time; wherein, the weights corresponding to all the energy change data are updated through backpropagation of the loss function.

7. The method according to claim 1, characterized in that, The environmental parameters are multiple, and the step of determining the energy change threshold at the current moment based on the environmental parameters includes: For each of the environmental parameters, the environmental parameter is substituted into the corresponding second preset function to obtain the second target value of the environmental parameter; The energy change threshold at the current moment is determined based on multiple second target values ​​and a benchmark threshold.

8. The method according to claim 7, characterized in that, The step of determining the energy change threshold at the current moment based on multiple second target values ​​and a benchmark threshold includes: The fourth sum is determined by weighted summation of multiple second target values. The energy change threshold at the current moment is obtained based on the fourth sum and the benchmark threshold.

9. The method according to claim 7, characterized in that, The environmental parameter is the ambient temperature, and the second preset function corresponding to the ambient temperature is as follows: f(T)=k T1 |T-T ref | / T r ; Where T is the ambient temperature, T ref For reference temperature, T r k represents the temperature detection range. T1 This is the temperature compensation coefficient; The environmental parameter is ambient humidity, and the second preset function corresponding to the ambient humidity is as follows: f(H)=k H1 (H-H ref ); Where H is the ambient humidity, H ref For reference humidity, k H1 This is the humidity compensation coefficient; The environmental parameter is the ambient wind speed, and the second preset function corresponding to the ambient wind speed is as follows: f(W)=k W1 (W-W ref ); Where W is the ambient wind speed, W ref For reference wind speed, k W1 This refers to the wind speed influence coefficient. The environmental parameters represent the initial position of the target being detected, and the second preset function corresponding to the initial position of the target being detected is as follows: f(D)={(D1:k d1 );……;(D i :k di );……;(D n :k dn )}; The target area is divided into partitions D1 to D... n The partitions are divided into two groups, each corresponding to a distance coefficient k. d1 To k dn i takes values ​​between 1 and n, and each D i The partition has a distance coefficient k. di ; The environmental parameter is the actual installation angle of the passive infrared sensor, and the second preset function corresponding to the actual installation angle of the passive infrared sensor is as follows: f(θ)=k θ1 |θ-θ ref | / θ r ; Where θ is the actual installation angle of the passive infrared sensor, θ ref θ is the reference installation angle for the passive infrared sensor. r k represents the angle installation range value of the passive infrared sensor. θ1 The influence coefficient of the passive infrared sensor is denoted as .

10. The method according to claim 1, characterized in that, After the step of determining whether an intrusion target exists in the target area at the current moment based on the current energy change and the energy change threshold, the following is included: If an intrusion target exists in the target area at the current moment, locate the sub-area where the intrusion target is located.

11. An electronic device, characterized in that, The system includes an interconnected memory and a processor, wherein the memory is used to store a computer program, which, when executed by the processor, is used to implement the method as described in any one of claims 1-10.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that can be executed by a processor to implement the steps of the method as described in any one of claims 1-10.

Images