Personnel detection method and device, electronic device and storage medium

Abstract

The invention relates to a personnel detection method and device, an electronic device and a storage medium, and the method comprises the steps: obtaining to-be-analyzed module length data transmitted by a wireless device; wherein the wireless device and the wireless signal detection device are a pair of wireless signal receiving and transmitting devices constructed in advance; calculating the variance of the to-be-analyzed modulus length data to obtain an initial variance calculation result; calculating the variance of the initial variance calculation result to obtain a quadratic variance calculation result; performing statistics on the initial variance calculation result and the quadratic variance calculation result to obtain a target variance calculation result; and when the target variance calculation result is greater than a preset threshold value, determining that the personnel exist in the personnel detection area. According to the invention, the problems of inaccurate personnel detection and large calculation amount are solved, the accuracy of personnel detection is improved, and the calculation amount is reduced.

Description

Technical Field

[0001] The present application relates to the field of wireless sensing, and in particular to a method, device, electronic device and storage medium for detecting personnel. Background Art

[0002] Motion recognition and position estimation of human targets have been widely used in daily life, such as elderly monitoring, fitness tracking and smart home, and have attracted widespread attention from academia and industry. Traditional human target motion recognition and position estimation adopts device-based methods, such as visual devices, wearable sensors or internal sensors of mobile phones. However, such methods have certain application limitations. Vision-based systems cannot penetrate walls, require good lighting conditions, and infringe on people's privacy. Sensor-based methods use devices that are not convenient to wear in some occasions, so their scope of application is limited and the equipment is expensive.

[0003] In recent years, wireless networks have been widely deployed, leading to the rapid development of wireless-related technologies. Studies have shown that wireless LANs can not only be used to transmit data, but also to sense changes in the surrounding environment, such as human detection, activity recognition, indoor positioning, line-of-sight path, and recognition. Wireless sensing technology uses wireless signals (such as WiFi, Bluetooth, etc.) to detect and understand the surrounding environment. This technology is mainly based on the scattering, reflection, diffraction, and attenuation characteristics of wireless signals. When the transmitter transmits the wireless signal into space, before it reaches the receiver, on the electromagnetic wave propagation path, if there is a person or activity, the human body will affect the electromagnetic wave transmission, causing its signal state to change, that is, the wireless channel state to change. However, due to the interference of the complex background environment, the multipath superposition signal obtained at the receiving end will carry characteristic information reflecting the environment, resulting in low judgment accuracy. At present, indoor personnel detection is mainly carried out through neural network algorithm models. However, the detection through neural network algorithm models is computationally intensive and time-consuming, and has high requirements on device resources, which cannot meet the use requirements of embedded devices.

[0004] There is no effective solution to the problems of inaccurate personnel detection and large amount of calculation in related technologies. Summary of the invention

[0005] In this embodiment, a method, device, electronic device and storage medium for detecting a person are provided to solve the problems of inaccurate detection of a person and large amount of calculation in related technologies.

[0006] In a first aspect, a method for detecting a person is provided in this embodiment, which is used for a wireless signal detection device, wherein the wireless signal detection device is placed in a person detection area, and includes: Acquire the module length data to be analyzed sent by the wireless device; wherein the wireless device and the wireless signal detection device are a pair of wireless signal transceiver devices constructed in advance; Calculating the variance of the modulus data to be analyzed to obtain an initial variance calculation result; Calculating the variance of the initial variance calculation result to obtain a quadratic variance calculation result; Performing statistics on the initial variance calculation result and the quadratic variance calculation result to obtain a target variance calculation result; When the target variance calculation result is greater than a preset threshold, it is determined that there is a person in the person detection area.

[0007] In some embodiments, obtaining the module length data to be analyzed sent by the wireless device includes: receiving a wireless signal sent by the wireless device, determining channel state information according to the wireless signal, determining the number of subcarriers according to the channel state information, and extracting modulus length data on each subcarrier; Performing standardization processing on the modulus length data to obtain standardized modulus length data, wherein the standardized modulus length data is distributed around a value of 1; Based on a first preset sliding window for data interception, the modulus length data to be analyzed is intercepted from the standardized modulus length data.

[0008] In some of the embodiments, before extracting the modulus length data on each subcarrier, the method further includes: The channel state information is filtered and cleaned to obtain cleaned channel state information.

[0009] In some embodiments, the step of calculating the variance of the modulus data to be analyzed to obtain an initial variance calculation result includes: The variance of the to-be-analyzed modulus data is calculated for each subcarrier to obtain an initial variance calculation result.

[0010] In some embodiments, calculating the variance of the initial variance calculation result to obtain a quadratic variance calculation result includes: Obtaining the initial variance calculation result to be analyzed from the initial variance calculation result through a second preset sliding window; The variance of the initial variance result to be analyzed is calculated for each subcarrier to obtain a quadratic variance calculation result.

[0011] In some embodiments, the performing statistics on the initial variance calculation result and the quadratic variance calculation result to obtain a target variance calculation result includes: According to a preset weight coefficient for the quadratic variance calculation result, a weighted sum is performed on the initial variance calculation result and the quadratic variance calculation result to obtain a target variance calculation result.

[0012] In some embodiments, the calculation process of the preset threshold value includes: Calculating a first threshold value according to the initial variance calculation result and a preset threshold coefficient; Calculating a second threshold value according to the quadratic variance calculation result and the preset threshold coefficient; A weighted sum is performed on the first threshold value and the second threshold value to obtain the preset threshold value.

[0013] In a second aspect, a personnel detection device is provided in this embodiment, including: an acquisition module, a first calculation module, a second calculation module, a statistical module and a determination module, wherein: The acquisition module is used to acquire the module length data to be analyzed sent by the wireless device; wherein the wireless device and the wireless signal detection device are a pair of wireless signal transceiver devices constructed in advance; The first calculation module is used to calculate the variance of the modulus data to be analyzed to obtain an initial variance calculation result; The second calculation module is used to calculate the variance of the initial variance calculation result to obtain a quadratic variance calculation result; The statistical module is used to perform statistics on the initial variance calculation result and the quadratic variance calculation result to obtain a target variance calculation result; The determination module is used to determine that there is a person in the person detection area when the target variance calculation result is greater than a preset threshold.

[0014] In a third aspect, an electronic device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the personnel detection method described in the first aspect when executing the computer program.

[0015] In a fourth aspect, in this embodiment, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the personnel detection method described in the first aspect is implemented.

[0016] Compared with the related art, the personnel detection method provided in the present embodiment is used for a wireless signal detection device, and the wireless signal detection device is placed in a personnel detection area, by acquiring the modulus data to be analyzed sent by the wireless device; wherein the wireless device and the wireless signal detection device are a pair of wireless signal transceiver devices constructed in advance; the variance of the modulus data to be analyzed is calculated to obtain an initial variance calculation result; the variance of the initial variance calculation result is calculated to obtain a quadratic variance calculation result; the initial variance calculation result and the quadratic variance calculation result are statistically analyzed to obtain a target variance calculation result; when the target variance calculation result is greater than a preset threshold value, it is determined that there is a person in the personnel detection area, which solves the problems of inaccurate personnel detection and large amount of calculation, improves the accuracy of personnel detection, and reduces the amount of calculation.

[0017] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 is a hardware structure block diagram of a terminal of the personnel detection method of this embodiment; Figure 2 is a flow chart of the personnel detection method of this embodiment; Figure 3 is an example diagram of a pair of wireless transceiver devices for personnel detection in this embodiment; Figure 4 is a detection data diagram of the personnel detection method of this embodiment in an open space; Figure 5 is a flow chart of another personnel detection method of this embodiment; Figure 6 4 is a structural block diagram of the personnel detection device of this embodiment. DETAILED DESCRIPTION

[0019] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0020] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with general skills in the technical field to which this application belongs. The words "one", "a", "the", "these" and the like in this application do not indicate a quantitative limitation, and they may be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone. Generally, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0021] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 1 is a hardware structure diagram of a terminal of the personnel detection method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 and a memory 104 for storing data, wherein the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0022] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the personnel detection method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0023] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0024] In this embodiment, a method for detecting a person is provided, which is used for a wireless signal detection device. The wireless signal detection device is placed in a person detection area. Figure 2 is a flow chart of the personnel detection method of this embodiment. Figure 2 As shown, the process includes the following steps: Step S201, obtaining the module length data to be analyzed sent by the wireless device; wherein the wireless device and the wireless signal detection device are a pair of wireless signal transceiver devices constructed in advance.

[0025] Specifically, since wireless sensing technology can use wireless signals to detect and understand the surrounding environment, this embodiment improves the personnel detection method of the wireless signal detection device on the basis of the wireless sensing technology, and can detect personnel in the room where the wireless device is deployed, especially in the bedroom and toilet of the elderly living alone, so that the person falling can be detected in time. When no one is at home, it can also monitor whether there is a person intrusion in the bedroom or window in time. First, a pair of wireless signal transceiver devices are constructed, and the wireless signal transceiver device includes a wireless device and a wireless signal detection device. As the source of the wireless signal, the wireless device can be a smart phone, a tablet computer or a laptop computer, etc., which is responsible for generating a WiFi signal and sending a data packet to the receiving end. As the receiving end of the wireless signal, the wireless signal detection device receives the WiFi signal sent by the wireless device according to a preset period. When the wireless device sends less wireless signals or does not send wireless signals, the wireless signal detection device can initiate WiFi communication to detect the WiFi signal of the wireless device, that is, the wireless signal detection device sends a packet to the wireless device, and the wireless device feeds back the corresponding WiFi signal according to the received packet, and the wireless signal detection device receives the fed-back WiFi signal. Figure 3 FIG. 1 is an example diagram of a pair of wireless transceiver devices for personnel detection in this embodiment. Figure 3 As shown, the wireless signal detection device is a router, and the wireless device can send wireless signals to the router through multiple paths, including path 1: directly from the wireless device to the router. If a user appears in the middle, the wireless signal on path 1 will be affected, and the presence of a person in the personnel detection area is determined by detecting the affected wireless signal. Path 2: The wireless signal emitted by the wireless device is reflected by the wall to the router. Among them, the reception rate range of the WiFi signal used by the wireless signal detection device in this embodiment is 2Hz to 100Hz. The wireless device will determine the communication bandwidth and adjustment method according to its own capabilities and the current wireless environment, mainly dynamically adjusting the bandwidth allocation to ensure that each part of the network can obtain appropriate bandwidth resources and improve the overall network performance. According to the bandwidth used for communication, the number of collected channel state information (CSI) data is determined. For example, when the communication bandwidth is 20 MHz, there are 64 subcarriers, and each subcarrier has a CSI data to represent the channel state of this channel, and each CSI data is a complex number. From the currently available CSI data, extract the model data on each subcarrier as the model length data to be analyzed. In personnel detection, the personnel detection requirements can be met by analyzing the mode length data. Compared with other phase data, it avoids more interference factors, reduces the complexity of processing, reduces the calculation amount of equipment, and saves computing costs.

[0026] In order to ensure the effective extraction of CSI information, Orthogonal Frequency Division Multiplexing (OFDM) and Orthogonal Frequency Division Multiple Access (OFDMA) modulation methods are used. OFDM is a multi-carrier modulation technology that divides the channel into several orthogonal sub-channels, converts high-speed data signals into parallel low-speed sub-data streams, and modulates them to each sub-channel for transmission. The use of OFDM can effectively combat frequency selective fading, overcome signal inter-symbol interference, and achieve high-speed data transmission. OFDMA is a multiple access technology in wireless communication systems that allows multiple users to share the same channel resources at the same time, thereby improving spectrum utilization and system capacity. OFDMA is an evolution of OFDM technology. It divides the subcarriers in the channel into one or more groups, and each group is used as an independent resource unit (RU) to carry and transmit data. In the downlink direction, different RUs carry the received data of different terminals; in the uplink direction, RUs carry the transmitted data of different terminals.

[0027] Step S202, calculating the variance of the modulus data to be analyzed to obtain an initial variance calculation result; calculating the variance of the initial variance calculation result to obtain a quadratic variance calculation result; and performing statistics on the initial variance calculation result and the quadratic variance calculation result to obtain a target variance calculation result.

[0028] Specifically, when the detection environment is different and there are differences in the multipath conditions during the propagation of wireless signals, the energy change ratio caused by the same personnel activities will also be quite different, especially in open scenes such as halls and squares, where the multipath effect of wireless signal propagation is less, resulting in a smaller proportion of wireless signal energy change at the receiving end, and the change is not obvious, so it is impossible to accurately identify whether there are people. Therefore, in this embodiment, the variance of the acquired modulus length data to be analyzed is first calculated. Taking a pair of wireless signal transceiver devices working at a bandwidth of 20 MHz and 64 subcarriers as an example, the processing process of the modulus length data to be analyzed is as follows: (1) A modulus length data is HM, where: HM=[HM1, HM2, …HM 64 ]; (2) Obtain (n+1) module length data H demo As the model length data to be analyzed: HM demo =[HM(k), HM(k+1), …HM(k+n)], where each HM(k) contains 64 subcarrier data and k is the starting position of the acquired modulus length data.

[0029] (3) Analyze the model length data HM demo Perform variance calculation on each subcarrier to obtain the initial variance calculation result Var: Var = [V1, V2, …, V64]; Among them, V1 is the modulus length data HM to be analyzed demo The initial variance calculation result of the first subcarrier data in each mode length data in , and similarly, V2...V64 is the mode length data to be analyzed HM demo The initial variance calculation result corresponding to each subcarrier in .

[0030] (4) Obtain m wave analysis data Var_Wave_data from the initial variance calculation result Var: Var_Wave_data = [Var1, Var2, ... Varm], where Var1 is an array containing 64 values; (5) The variance of the fluctuation analysis data Var_Wave is calculated independently for each subcarrier to obtain the quadratic variance calculation result Var_Wave: Var_Wave=[VW1, VW2, …VW64]; wherein Var_Wave is an array containing 64 values, and VW1 is the quadratic variance calculation result of the No. 1 subcarrier data in each modulus data in the fluctuation analysis data Var_Wave.

[0031] (6) Perform statistics on the initial variance calculation result Var and the quadratic variance calculation result Var_Wave to obtain the target variance calculation result CV: CV=Var+a×Var_Wave, where a is the weight coefficient, which is set according to the size of the detection range.

[0032] By performing quadratic variance calculation on the modulus length data, the detection effect can be improved. Figure 4 is a detection data diagram of the personnel detection method of this embodiment in an open field; Figure 4 As shown, the orange curve is a signal diagram showing the trend of the first-order variance calculation result over time, and the blue curve is a signal diagram showing the trend of the second-order variance calculation result over time. When no one is around, the waveforms of the two are almost the same. When someone walks by 4 meters away from the wireless signal detection device, it can be seen from the figure that the change amplitude of the blue curve is significantly larger than that of the orange curve. Therefore, it can be seen that the quadratic variance calculation can amplify the personnel detection results, especially in open spaces. By amplifying the detection effect, it is easier to detect the presence of people and improve the accuracy of personnel detection.

[0033] Step S203: When the target variance calculation result is greater than a preset threshold, it is determined that there is a person in the person detection area.

[0034] Specifically, a threshold value is set in advance to determine whether there is a person in the person detection area, wherein the threshold value can be understood as the maximum value that the variance data is not allowed to exceed. When the person detection area is empty, the target variance calculation result is relatively low. When someone enters the detection area, the person's activities will cause a significant change in the wireless signal, thereby increasing the target variance calculation result. When the target variance calculation result is greater than the preset threshold value, it is determined that there is a person in the person detection area. The threshold value can be set by the measured data of person detection or the empirical value in this field.

[0035] Through the above steps S201 to S203, the modulus length data to be analyzed sent by the wireless device is obtained; wherein the wireless device and the wireless signal detection device are a pair of wireless signal transceiver devices constructed in advance; the variance of the modulus length data to be analyzed is calculated to obtain an initial variance calculation result; the variance of the initial variance calculation result is calculated to obtain a quadratic variance calculation result; the initial variance calculation result and the quadratic variance calculation result are statistically analyzed to obtain a target variance calculation result; when the target variance calculation result is greater than a preset threshold value, it is determined that there is a person in the person detection area. Compared with the prior art that performs indoor personnel detection through a sensor device or a neural network algorithm model, this embodiment obtains the modulus length data on each subcarrier to perform a variance calculation to obtain an initial variance calculation result, performs a quadratic variance calculation on the initial variance calculation result to obtain a quadratic variance calculation result, and finally combines the initial variance calculation result and the quadratic variance calculation result to obtain a target variance calculation result, compares the target variance calculation result with a preset threshold value, detects the presence of personnel in the personnel detection area, and only analyzes the modulus length data, thereby reducing the amount of calculation, detecting the presence of personnel through quadratic variance calculation, and improving the accuracy of personnel detection.

[0036] In some embodiments, obtaining the to-be-analyzed mode length data sent by the wireless device includes: Receive a wireless signal sent by a wireless device, determine channel state information according to the wireless signal, determine the number of carriers according to the channel state information, and extract modulus length data on each subcarrier; perform standardization on the modulus length data to obtain standardized modulus length data, wherein the standardized modulus length data is distributed around a value of 1; based on a first preset sliding window for data interception, intercept the modulus length data to be analyzed from the standardized modulus length data.

[0037] Specifically, after the wireless signal detection device receives the wireless signal sent by the wireless device, it determines the amount of CSI data to be collected based on the bandwidth used for communication, such as 64 subcarriers when the communication bandwidth is 20 MHz. The modulus length data on each subcarrier is extracted. In actual use, environmental changes will cause changes in signal attenuation, and the automatic gain control AGC used in wireless signal processing will also be adjusted, which will cause large differences in the modulus length of the CSI information; therefore, before performing modulus length data analysis, the modulus length data is standardized, and the standardized processing formula is as follows: ; Among them, x is the actual modulus length data, x avg is the average data of all modulus lengths; through standardization, the modulus length data is mapped to the vicinity of 1, and the period fluctuation ratio is retained. Compared with the normalization processing used in the prior art, the normalization calculation makes the calculation results distributed between [0,1], and finally causes the variance calculation results to be distributed in a very small area near 0, and no obvious difference can be seen, which is not conducive to the comparison of variance calculation results and inconvenient for later processing. This embodiment performs standardization on the modulus length data so that the processed results are distributed above and below the value 1, preventing the variance results from tending to the vicinity of 0, improving the distribution domain of subsequent variance processing results, and through standardization, the influence of parameters such as wireless signal transmission power, distance attenuation, and AGC of wireless signal extraction is removed for the subsequent variance calculation results, and the stability of the wireless signal detection device is improved in the time domain; the subsequent variance calculation results only retain the energy change ratio caused by the change in wireless signal propagation caused by personnel activities, thereby improving the accuracy of personnel detection.

[0038] Through the first preset sliding window, through the preset window length (n+1), the modulus length data HM to be analyzed is obtained from the data set analyzed for the kth time demo : HM demo =[HM(k), HM(k+1),…HM(k+n)], Each HM(k) contains 64 subcarrier data.

[0039] In another embodiment, before extracting the modulus length data on each subcarrier, the method further includes: The channel state information is filtered and cleaned to obtain cleaned channel state information.

[0040] Specifically, the CSI data collected by the wireless signal detection device will contain a large amount of noise data, and the abnormal data needs to be cleaned; the moving window processing method is used for cleaning to obtain the cleaned channel state information. The specific processing algorithm can use a hampel filter, a low-pass filter, etc., and this embodiment does not make specific limitations on this.

[0041] In some embodiments, calculating the variance of the modulus data to be analyzed to obtain an initial variance calculation result includes: The variance of the modulus data to be analyzed is calculated for each subcarrier to obtain an initial variance calculation result.

[0042] Specifically, the model length data HM to be analyzed demo The variance calculation is performed independently for each subcarrier in to obtain the initial variance calculation result Var: HM demo =[HM(k), HM(k+1),…HM(k+n)], Each HM(k) contains 64 subcarrier data, and k is the starting position of the acquired modulus length data; Var = [V1, V2, …, V64]; Among them, V1 is the modulus length data HM to be analyzed demo The initial variance calculation result of the first subcarrier data in each mode length data in , and similarly, V2...V64 is the mode length data to be analyzed HM demo The initial variance calculation result corresponding to each subcarrier in .

[0043] In another embodiment, calculating the variance of the initial variance calculation result to obtain the secondary variance calculation result includes: The initial variance calculation result to be analyzed is obtained from the initial variance calculation result through the second preset sliding window; the variance of the initial variance result to be analyzed is calculated according to each subcarrier to obtain a quadratic variance calculation result.

[0044] Specifically, m pieces of fluctuation analysis data Var_Wave_data are obtained from the initial variance calculation result Var through the second preset sliding window: Var_Wave_data=[Var1, Var2,…Varm], Among them, Var1 is an array containing 64 values; The variance of the fluctuation analysis data Var_Wave is calculated independently for each subcarrier to obtain the quadratic variance calculation result Var_Wave: Var_Wave=[VW1, VW2,…VW64]; Among them, Var_Wave is an array containing 64 numerical values, and VW1 is the quadratic variance calculation result of the No. 1 subcarrier data in each modulus data in the fluctuation analysis data Var_Wave.

[0045] In some embodiments, statistics are performed on the initial variance calculation result and the quadratic variance calculation result to obtain the target variance calculation result, including: According to the preset weight coefficient for the quadratic variance calculation result, the initial variance calculation result and the quadratic variance calculation result are weighted and summed to obtain the target variance calculation result.

[0046] Specifically, the weight coefficient a is set for the quadratic variance calculation result according to the detection environment. In a small range environment such as indoors, a is set near 1; in an open environment, the weight of the quadratic variance calculation result is increased by increasing the value of a to expand the detection range. The initial variance calculation result Var and the quadratic variance calculation result Var_Wave are statistically analyzed to obtain the target variance calculation result CV: CV=Var+a×Var_Wave, Among them, a is the weight coefficient, which is set according to the size of the detection range.

[0047] By performing quadratic variance calculation on the modulus length data and taking statistics on the linear variance calculation results and the quadratic variance calculation results, the weight of the quadratic variance calculation result is increased by adjusting the weight coefficient a in an open environment, thereby expanding the detection range and improving the accuracy of personnel detection.

[0048] In another embodiment, the calculation process of the preset threshold value includes: A first threshold value is calculated based on the initial variance calculation result and the preset threshold coefficient; a second threshold value is calculated based on the quadratic variance calculation result and the preset threshold coefficient; and the first threshold value and the second threshold value are weightedly summed to obtain the preset threshold value.

[0049] Specifically, in order to improve the accuracy of the personnel detection result, the present embodiment also combines the initial variance calculation result and the quadratic variance calculation result to obtain a preset threshold value for the threshold value, wherein: The formula for calculating the first threshold value Jvar based on the initial variance calculation result and the preset threshold coefficient is as follows: Jvar=K1×V1+K2×V2+…+K64×V64; Among them, [V1, V2, ..., V64] is the initial variance calculation result, K1, K2 ... K64 are coefficient values ​​determined in the development stage, and their specific values ​​are determined according to the differences in subcarrier sensitivities.

[0050] The second threshold value J is calculated based on the quadratic variance calculation result and the preset threshold coefficient var-wave The formula is as follows: J var-wave =K1×VW1+K2×VW2+…+K64×VW64; Among them, [VW1, VW2, ... VW64] are the results of quadratic variance calculation, K1, K2 ... K64 are coefficient values ​​determined in the development stage, and their specific values ​​are determined according to the differences in subcarrier sensitivities.

[0051] The weight coefficient a is set for the second threshold value according to the detection environment. In a small range environment such as indoors, a is set near 1. In detection in an open environment, the value of a is increased to make the threshold value correspond to the quadratic variance calculation result synchronously. The weight coefficient a set for the second threshold value is the same as the weight coefficient set for the quadratic variance calculation result. The first threshold value and the second threshold value are weighted and summed to obtain the preset threshold value J. cv The formula is as follows: J cv =J var +a×J var_wave .

[0052] This embodiment also provides a method for detecting a person. Figure 5 is a flow chart of another personnel detection method of this embodiment. Figure 5 As shown, the process includes the following steps: Step S501, receiving a wireless signal sent by a wireless device, determining channel state information according to the wireless signal, determining the number of subcarriers according to the channel state information, filtering and cleaning the channel state information to obtain the cleaned channel state information, and extracting the modulus length data on each subcarrier.

[0053] Step S502, normalizing the modulus length data to obtain normalized modulus length data, wherein the normalized modulus length data is distributed around a value of 1; Step S503, based on a first preset sliding window for data interception, intercepting the modulus length data to be analyzed from the standardized modulus length data; Step S504, calculating the variance of the modulus length data to be analyzed according to each subcarrier, and obtaining an initial variance calculation result; Step S505, obtaining the initial variance calculation result to be analyzed from the initial variance calculation result through the second preset sliding window; calculating the variance of each subcarrier for the initial variance result to be analyzed, and obtaining the quadratic variance calculation result; Step S506, performing weighted summation on the initial variance calculation result and the quadratic variance calculation result according to the preset weight coefficient for the quadratic variance calculation result, to obtain a target variance calculation result; Step S507, calculating a first threshold value according to the initial variance calculation result and a preset threshold coefficient; calculating a second threshold value according to the quadratic variance calculation result and a preset threshold coefficient; performing weighted summation on the first threshold value and the second threshold value to obtain a preset threshold value; Step S508: When the target variance calculation result is greater than a preset threshold, it is determined that there is a person in the person detection area.

[0054] Through the above steps S501 to S508, compared with the indoor personnel detection through the sensor device or the neural network algorithm model in the prior art, this embodiment extracts the modulus length data on each subcarrier according to the current channel state information data, and performs standardization processing on the modulus length data to obtain a standardized processing result, wherein the standardized processing result is distributed near the value 1; the standardized modulus length number is subjected to two variance calculations to obtain an initial variance calculation result and a quadratic variance calculation result; the initial variance calculation result and the quadratic variance calculation structure are combined to obtain a target variance calculation result; then the first threshold value is calculated by the initial variance calculation result, and the second threshold value is calculated by the quadratic variance calculation result; the first threshold value and the second threshold value are combined to obtain the target threshold value; when the target variance calculation result is greater than the target threshold value, it is determined that there is a person in the detection area. Among them, compared with the traditional normalization processing, the normalization processing makes the processing results distributed between [0, 1], and finally basically tends to be near 0, and the observation effect of data fluctuation is not obvious. By standardizing the modulus data, the calculation results are distributed near the value 1, the distribution domain of the variance calculation results is improved, the detection effect is improved, and the accuracy of personnel detection is improved. In addition, the final variance result is obtained after two variance calculations, which expands the detection range. The final variance result is compared with the threshold value to determine whether someone has entered, thereby improving the accuracy of the personnel detection result. In addition, this embodiment only needs to calculate and analyze the modulus data in the detection channel state information, which reduces the amount of calculation.

[0055] In this embodiment, a personnel detection device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made are omitted. The terms "module", "unit", "subunit" and the like used below may be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0056] Figure 6 : is a structural block diagram of the personnel detection device of this embodiment, such as Figure 6 As shown, the device 60 includes: an acquisition module 61, a first calculation module 62, a second calculation module 63, a statistical module 64 and a determination module 65, wherein: The acquisition module 61 is used to acquire the mode length data to be analyzed sent by the wireless device; wherein the wireless device and the wireless signal detection device are a pair of wireless signal transceiver devices constructed in advance; The first calculation module 62 is used to calculate the variance of the modulus data to be analyzed and obtain an initial variance calculation result; A second calculation module 63 is used to calculate the variance of the initial variance calculation result to obtain a quadratic variance calculation result; A statistical module 64 is used to perform statistics on the initial variance calculation result and the quadratic variance calculation result to obtain a target variance calculation result; The determination module 65 is used to determine that there is a person in the person detection area when the target variance calculation result is greater than a preset threshold.

[0057] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0058] In this embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0059] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0060] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program: S1, obtaining the module length data to be analyzed sent by the wireless device; wherein the wireless device and the wireless signal detection device are a pair of wireless signal transceiver devices constructed in advance; S2, calculating the variance of the modulus data to be analyzed and obtaining the initial variance calculation result; S3, calculating the variance of the initial variance calculation result to obtain a quadratic variance calculation result; S4, performing statistics on the initial variance calculation result and the quadratic variance calculation result to obtain the target variance calculation result; S5: When the target variance calculation result is greater than a preset threshold, it is determined that there is a person in the person detection area.

[0061] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0062] In addition, in combination with the personnel detection method provided in the above embodiments, a storage medium may be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by a processor, any one of the personnel detection methods in the above embodiments is implemented.

[0063] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0064] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0065] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0066] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0067] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A method for detecting a person, characterized in that: Used for wireless signal detection equipment, the wireless signal detection equipment is placed in a personnel detection area, and includes: Acquire the module length data to be analyzed sent by the wireless device; wherein the wireless device and the wireless signal detection device are a pair of wireless signal transceiver devices constructed in advance; Calculating the variance of the modulus data to be analyzed to obtain an initial variance calculation result; Calculating the variance of the initial variance calculation result to obtain a quadratic variance calculation result; Performing statistics on the initial variance calculation result and the quadratic variance calculation result to obtain a target variance calculation result; When the target variance calculation result is greater than a preset threshold, it is determined that there is a person in the person detection area.

2. The method for detecting people according to claim 1, characterized in that: The obtaining of the module length data to be analyzed sent by the wireless device comprises: receiving a wireless signal sent by the wireless device, determining channel state information according to the wireless signal, determining the number of subcarriers according to the channel state information, and extracting modulus length data on each subcarrier; Performing standardization processing on the modulus length data to obtain standardized modulus length data, wherein the standardized modulus length data is distributed around a value of 1; Based on a first preset sliding window for data interception, the modulus length data to be analyzed is intercepted from the standardized modulus length data.

3. The method for detecting people according to claim 2, characterized in that: Before extracting the modulus length data on each subcarrier, the method further includes: The channel state information is filtered and cleaned to obtain cleaned channel state information.

4. The method for detecting people according to claim 1, characterized in that: The calculating the variance of the modulus data to be analyzed to obtain an initial variance calculation result includes: The variance of the to-be-analyzed modulus data is calculated for each subcarrier to obtain an initial variance calculation result.

5. The method for detecting people according to claim 1, characterized in that: The calculating the variance of the initial variance calculation result to obtain the quadratic variance calculation result includes: Obtaining the initial variance calculation result to be analyzed from the initial variance calculation result through a second preset sliding window; The variance of the initial variance result to be analyzed is calculated for each subcarrier to obtain a quadratic variance calculation result.

6. The method for detecting people according to claim 1, characterized in that: The performing statistics on the initial variance calculation result and the quadratic variance calculation result to obtain a target variance calculation result includes: According to a preset weight coefficient for the quadratic variance calculation result, a weighted sum is performed on the initial variance calculation result and the quadratic variance calculation result to obtain a target variance calculation result.

7. The method for detecting people according to claim 1, characterized in that: The calculation process of the preset threshold value includes: Calculating a first threshold value according to the initial variance calculation result and a preset threshold coefficient; Calculating a second threshold value according to the quadratic variance calculation result and the preset threshold coefficient; A weighted sum is performed on the first threshold value and the second threshold value to obtain the preset threshold value.

8. A person detection device, characterized in that: include: An acquisition module, a first calculation module, a second calculation module, a statistical module and a determination module, wherein: The acquisition module is used to acquire the module length data to be analyzed sent by the wireless device; wherein the wireless device and the wireless signal detection device are a pair of wireless signal transceiver devices constructed in advance; The first calculation module is used to calculate the variance of the modulus data to be analyzed to obtain an initial variance calculation result; The second calculation module is used to calculate the variance of the initial variance calculation result to obtain a quadratic variance calculation result; The statistical module is used to perform statistics on the initial variance calculation result and the quadratic variance calculation result to obtain a target variance calculation result; The determination module is used to determine that there is a person in the person detection area when the target variance calculation result is greater than a preset threshold.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the person detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the person detection method according to any one of claims 1 to 7 are implemented.

Images