Human presence detection method, system, terminal device and storage medium

Abstract

The present invention provides a method, system, terminal device and storage medium for detecting the presence of a human body. The method comprises: collecting radar echo signals fed back by radar detection signals in a scene to be tested, filtering the radar echo signals to obtain filtered signals when the number of radar echo signals meets the detection conditions; generating a scale deviation signal according to the filtered signals, performing discrete difference processing on the radar echo signals to obtain discrete difference signals; performing sliding average processing on the discrete difference signals to obtain a timing deviation signal, generating a human body distance sequence according to the timing deviation signal and the scale deviation signal; generating a human body presence detection result according to the human body presence distance in the human body distance sequence. The present invention can effectively characterize the distance between the detected human body and the corresponding signal source of the radar detection signal based on the human body distance sequence, and can effectively detect whether there is a human body in the scene to be tested based on the human body presence distance in the human body distance sequence, so as to generate a corresponding human body presence detection result.

Description

Technical Field

[0001] The present invention relates to the field of human body detection technology, and in particular to a human body presence detection method, system, terminal device and storage medium. Background Art

[0002] Human behavior detection is a technology that uses computer technology to automatically detect, analyze and understand body movements. It is widely used in emerging fields such as smart homes, security monitoring, medical rehabilitation, and human-computer interaction. Human behavior detection can generally be divided into two categories: contact and non-contact. Wearable devices are the key carriers of contact behavior detection systems, but they have many limitations such as expensive equipment, inconvenience for users to wear, and distraction. Non-contact behavior detection includes human presence detection and human gesture detection. Since human presence recognition can provide device-free perception services and friendly user interaction, it has received widespread attention from users.

[0003] Existing human presence detection methods all use infrared detection to detect human presence in the detection scene. However, since infrared detection detects human presence based on changes in energy distribution in the infrared band in the environment to be detected, when a human body enters the monitoring range, a sudden change in infrared energy in the environment caused by human body temperature can trigger presence detection judgment. However, when the human body is in a stationary state, the infrared energy change in the environment is small, resulting in the inability to detect human presence, thereby reducing the accuracy of human presence detection. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a human presence detection method, system, terminal device and storage medium, aiming to solve the problem of low accuracy of human presence detection in the existing human presence detection process due to the use of infrared detection for human presence detection.

[0005] The embodiment of the present invention is implemented as follows: a method for detecting the presence of a human body, the method comprising:

[0006] Collecting radar echo signals fed back by radar detection signals in the scene to be tested, and when the number of the radar echo signals meets the detection condition, filtering the radar echo signals to obtain filtered signals;

[0007] generating a scale deviation signal according to the filtered signal, and performing discrete difference processing on the radar echo signal to obtain a discrete difference signal;

[0008] Performing sliding average processing on the discrete difference signal to obtain a time series deviation signal, and generating a human body distance sequence according to the time series deviation signal and the scale deviation signal;

[0009] A human presence detection result is generated according to the human presence distance in the human body distance sequence.

[0010] Furthermore, filtering the radar echo signal to obtain a filtered signal includes:

[0011] Acquire the time series characteristics of each radar echo signal respectively, and generate a time series sequence according to the acquired time series characteristics;

[0012] The time series is averaged to obtain an average sequence, and the average sequence is high-pass filtered and low-pass filtered to obtain a high-pass filtered signal and a low-pass filtered signal.

[0013] Furthermore, generating a scale deviation signal according to the filtered signal includes:

[0014] Determining an absolute deviation between the high-pass filter signal and the low-pass filter signal, and normalizing the absolute deviation to obtain a sequence deviation signal;

[0015] Performing filtering processing on the sequence deviation signal to obtain a first scale deviation signal, and performing sliding average processing on the sequence deviation signal to obtain a second scale deviation signal;

[0016] The scale deviation signal includes the first scale deviation signal and the second scale deviation signal.

[0017] Furthermore, the calculation formula used to generate the human body distance sequence according to the timing deviation signal and the scale deviation signal is:

[0018]

[0019] Wherein, R is the human body presence determination value in the human body distance sequence, are respectively the first scale deviation signal, the second scale deviation signal and the timing deviation signal, and β is a preset attenuation rate.

[0020] Furthermore, generating a human presence detection result according to the human presence distance in the human body distance sequence includes:

[0021] Acquire a maximum human body existence distance in the human body distance sequence, and determine the maximum human body existence distance as a relevant distance and a relevant determination value;

[0022] Determine the difference between the relevant judgment value and the first threshold value to obtain a distance difference value, and when the distance difference value is less than or equal to the second threshold value, perform phase detection and preprocessing on the relevant distance, and obtain a discrimination value by low-complexity calculation such as accumulation, averaging, sliding average, variance, or by transferring to the frequency domain for feature calculation;

[0023] If the discrimination value is greater than the third threshold, the accumulated value of human body presence is accumulated and calculated, and the accumulated value of no human body presence is cleared to zero, and when the accumulated value of human body presence after accumulation is greater than the fourth threshold, it is determined that there is a human body in the scene to be tested;

[0024] If the discrimination value is less than or equal to the third threshold, the accumulated value indicating no human presence is accumulated and calculated, the accumulated value indicating human presence is cleared, and when the accumulated value indicating no human presence is greater than the fifth threshold, it is determined that there is no human body in the scene to be tested.

[0025] Furthermore, the performing phase detection and preprocessing on the relevant distance to obtain a discrimination value includes:

[0026] Generate a phase detection range according to the relevant distance and the preset interval distance, and perform micro-motion detection within the phase detection range to obtain the displacement at the current moment;

[0027] The displacement at the current moment is preprocessed, and low-complexity calculations such as accumulation, averaging, sliding average, variance, etc. are performed or transferred to the frequency domain for feature calculation to obtain the discriminant value.

[0028] Furthermore, after determining the difference between the correlation determination value and the first threshold value to obtain the distance difference, the method further includes:

[0029] If the distance difference is greater than the second threshold, it is determined that a human body exists in the scene to be detected.

[0030] Another object of an embodiment of the present invention is to provide a human presence detection system, the system comprising:

[0031] A signal filtering module, used for collecting radar echo signals fed back by radar detection signals in the scene to be tested, and filtering the radar echo signals when the number of the radar echo signals meets the detection condition to obtain a filtered signal;

[0032] A discrete difference processing module, used for generating a scale deviation signal according to the filtered signal, and performing discrete difference processing on the radar echo signal to obtain a discrete difference signal;

[0033] A sliding average module, used for performing sliding average processing on the discrete difference signal to obtain a timing deviation signal, and generating a human body distance sequence according to the timing deviation signal and the scale deviation signal;

[0034] The detection result generating module is used to generate a human presence detection result according to the human presence distance in the human body distance sequence.

[0035] Another object of an embodiment of the present invention is to provide a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0036] Another object of an embodiment of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0037] In an embodiment of the present invention, a radar echo signal is filtered to obtain a filtered signal, and a scale deviation signal is generated according to the filtered signal. Based on the scale deviation signal, the scale deviation of the detected human body under different filtering states can be effectively characterized. A discrete difference signal is obtained by performing discrete difference processing on the radar echo signal, and a timing deviation signal is obtained by performing sliding average processing on the discrete difference signal. Based on the timing deviation signal, the deviation of the detected human body in the timing characteristics can be effectively characterized. A human body distance sequence is generated according to the timing deviation signal and the scale deviation signal. Based on the human body distance sequence, the distance between the detected human body and the signal source corresponding to the radar detection signal can be effectively characterized. Based on the human body existence distance in the human body distance sequence, it can be effectively detected whether there is a human body in the scene to be tested to generate a corresponding human body existence detection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a flow chart of a human presence detection method provided by a first embodiment of the present invention;

[0039] Figure 2 is a flow chart of a method for detecting human presence provided by a second embodiment of the present invention;

[0040] Figure 3 yes Figure 2 A schematic diagram of the presence reflection scoring results provided in the embodiment;

[0041] Figure 4 yes Figure 2 A flowchart of specific implementation steps of step S40 provided in the embodiment;

[0042] Figure 5 is a structural schematic diagram of a human presence detection system provided by a third embodiment of the present invention;

[0043] Figure 6 It is a schematic diagram of the structure of a terminal device provided in the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0045] In order to illustrate the technical solution of the present invention, a specific embodiment is provided below for illustration.

[0046] Embodiment 1

[0047] See also Figure 1 , is a flow chart of a human presence detection method provided by a first embodiment of the present invention. The human presence detection method can be applied to any terminal device. The human presence detection method comprises the steps of:

[0048] Step S10, collecting radar echo signals fed back by radar detection signals in the scene to be tested, and when the number of the radar echo signals meets the detection condition, filtering the radar echo signals to obtain filtered signals;

[0049] Among them, at least one millimeter-wave radar is arranged in the scene to be tested, and the millimeter-wave radar is used to transmit the radar detection signal in the scene to be tested, and the terminal device receives the radar echo signal fed back by the radar detection signal in the scene to be tested in real time. The installation height and detection range of the millimeter-wave radar can be set according to the needs. Preferably, the installation height is 3 meters and the detection range is 2.5 meters. Furthermore, in the scene to be tested without people and interference, the millimeter-wave radar can be controlled to perform envelope detection according to the high transmission power configuration, and the gradient range to which the farthest envelope peak detected belongs is the installation height of the millimeter-wave radar.

[0050] In this step, the detection condition can be set according to the demand. For example, the detection condition can be set to determine whether the number of received radar echo signals is greater than or equal to a preset number. If the number of received radar echo signals is greater than or equal to the preset number, it is determined that the number of radar echo signals meets the detection condition. If the number of received radar echo signals is less than the preset number, it is determined that the number of radar echo signals does not meet the detection condition. In this step, if the number of received radar echo signals is greater than or equal to the preset number, the currently received radar echo signal is filtered to obtain a filtered signal.

[0051] Optionally, in this step, filtering the radar echo signal to obtain a filtered signal includes:

[0052] Acquire the time series characteristics of each radar echo signal respectively, and generate a time series sequence according to the acquired time series characteristics;

[0053] Among them, the generated time series is A N ={A 1 ,…A n}, A n is the time sequence feature of the nth radar echo signal. In this step, the preset number in the detection condition is set to n.

[0054] Performing average processing on the time series to obtain an average sequence, and performing high-pass filtering and low-pass filtering on the average sequence to obtain a high-pass filtered signal and a low-pass filtered signal;

[0055] Among them, the average sequence is S m =mean(A N ), respectively for the average sequence S m =mean(A N ) to perform high-pass filtering and low-pass filtering to obtain the high-pass filtering signal and the low-pass filtering signal, the filtering parameters used by the high-pass filtering and the low-pass filtering are α hp ,α lp ∈(0,1);

[0056] In this step, the high-pass filtered signal is:

[0057]

[0058] The low-pass filtered signal is:

[0059]

[0060] Step S20, generating a scale deviation signal according to the filtered signal, and performing discrete difference processing on the radar echo signal to obtain a discrete difference signal;

[0061] According to the absolute deviation between the high-pass filter signal and the low-pass filter signal, the scale deviation signal is generated. In this step, according to the characteristic that human body micro-motion will not produce drastic fluctuations in a small space and scale range, each group A N Make K discrete differences between the time series and take the average value in the full time and space domain scale. Then, normalize according to the number of discrete differences K to eliminate the transmission error and get the discrete difference signal.

[0062] Optionally, in this step, generating a scale deviation signal according to the filtered signal includes:

[0063] Determining an absolute deviation between the high-pass filter signal and the low-pass filter signal, and normalizing the absolute deviation to obtain a sequence deviation signal;

[0064] The absolute deviation includes the absolute value of the signal difference between the high-pass filter signal and the low-pass filter signal at the same time. By normalizing the absolute deviation, the absolute value of the signal difference corresponding to different times can be effectively mapped to a specified range to obtain the sequence deviation signal.

[0065] The sequence deviation signal is:

[0066]

[0067] Performing filtering processing on the sequence deviation signal to obtain a first scale deviation signal, and performing sliding average processing on the sequence deviation signal to obtain a second scale deviation signal;

[0068] The scale deviation signal includes a first scale deviation signal and a second scale deviation signal. In this step, the scale deviation signal is filtered according to the preset filtering parameters. Performing low-pass filtering on the sequence deviation signal to obtain the first scale deviation signal, where the first scale deviation signal is a large time scale deviation;

[0069] The large time scale deviation is:

[0070]

[0071] In this step, the step of performing sliding average processing on the sequence deviation signal includes:

[0072] Performing standard deviation processing on the time series to obtain the standard deviation sequence, and performing sliding average processing on the standard deviation sequence to obtain the second scale deviation signal;

[0073] The standard deviation sequence is:

[0074]

[0075] The filtering parameters used for the sliding average processing of the standard deviation series are: The second scale deviation signal is a small time scale deviation.

[0076] Step S30, performing sliding average processing on the discrete difference signal to obtain a time series deviation signal, and generating a human body distance sequence according to the time series deviation signal and the scale deviation signal;

[0077] Among them, the preset sliding parameter α vs , for discrete difference signals Perform sliding average processing to obtain the timing deviation signal In this step, based on the timing deviation signal and the first scale deviation signal and the second scale deviation signal to generate a human body distance sequence corresponding to the radar echo signal, the human body distance sequence is used to characterize the human body existence determination value and the human body existence distance corresponding to the detected human body at different times, the human body existence determination value is used to characterize whether there is a human body in the scene to be tested, and the human body existence distance is used to characterize the distance between the detected human body and the millimeter wave radar in the scene to be tested;

[0078] Optionally, in this step, the calculation formula used to generate the human body distance sequence according to the timing deviation signal and the scale deviation signal is:

[0079]

[0080] Wherein, R is the human body presence determination value in the human body distance sequence, are respectively the first scale deviation signal, the second scale deviation signal and the timing deviation signal, and β is a preset attenuation rate.

[0081] Step S40, generating a human presence detection result according to the human presence distance in the human distance sequence;

[0082] The human body presence distance in the human body distance sequence is compared with a first threshold, and the human body presence detection result is generated according to the comparison result. The first threshold can be set according to demand.

[0083] Optionally, in this embodiment, if the RAM and computing power of the hardware device on the terminal device are sufficient, FFT can be used to convert to the frequency domain for spectrum subtraction or relative spectrum method to complete the above-mentioned high-pass and low-pass filtering and background noise estimation related algorithms, which effectively improves the accuracy and timeliness of the results in terms of algorithm time complexity.

[0084] In this embodiment, the radar echo signal is filtered to obtain a filtered signal, and a scale deviation signal is generated according to the filtered signal. Based on the scale deviation signal, the scale deviation of the detected human body under different filtering states can be effectively characterized. By performing discrete difference processing on the radar echo signal, a discrete difference signal is obtained, and a sliding average processing is performed on the discrete difference signal to obtain a timing deviation signal. Based on the timing deviation signal, the deviation of the detected human body in the timing characteristics can be effectively characterized. By generating a human body distance sequence according to the timing deviation signal and the scale deviation signal, the distance between the detected human body and the signal source corresponding to the radar detection signal can be effectively characterized based on the human body distance sequence. Based on the human body existence distance in the human body distance sequence, it can be effectively detected whether there is a human body in the scene to be tested to generate a corresponding human body existence detection result.

[0085] Embodiment 2

[0086] See also Figures 2 to 4 , is a flow chart of a human presence detection method provided by a second embodiment of the present invention, and this embodiment is used to further refine step S40, including the steps of:

[0087] Step S41, obtaining the maximum human body existence distance in the human body distance sequence, and determining the maximum human body existence distance as the relevant distance and the relevant determination value;

[0088] Among them, the determined relevant judgment value is R;

[0089] Step S42, determining the difference between the relevant determination value and the first threshold value to obtain a distance difference value, and when the distance difference value is less than or equal to a second threshold value, performing phase detection and preprocessing on the relevant distance to obtain a determination value;

[0090] Among them, the first threshold (Thres R ) and the second threshold (vag) can be set according to the requirements, and the distance difference is obtained by determining the difference between the relevant determination value and the first threshold. Based on the size comparison between the distance difference and the second threshold, it is determined whether phase detection is required for the relevant distance;

[0091] In this step, if the distance difference is greater than the second threshold, it is directly determined that a human body exists in the scene to be measured, and a human body existence prompt is sent to prompt the user that a human body exists in the current scene to be measured.

[0092] Furthermore, in this step, if the distance difference is less than or equal to the second threshold, and the relevant determination value is less than or equal to the first threshold, it is directly determined that there is no human body in the scene to be tested, and a prompt indicating that there is no human body is sent.

[0093] Optionally, in this step, performing phase detection and preprocessing on the relevant distance to obtain a discrimination value includes:

[0094] Generate a phase detection range according to the relevant distance and the preset interval distance, and perform micro-motion detection within the phase detection range to obtain the displacement at the current moment;

[0095] The displacement at the current moment is preprocessed, and a discriminant value is obtained by low-complexity calculations such as accumulation, averaging, sliding average, variance, etc., or by transferring to the frequency domain for feature calculation;

[0096] According to the preset interval distance a and the correlation distance D, a phase detection range L∈(Da,D+a) is generated, and micro-motion detection is performed within the range of L∈(Da,D+a) to obtain a number of time-continuous IQ complex signals z n =a+bi, according to z n Get the micro-motion data at the current moment:

[0097]

[0098] In this step, the displacement at the current moment is accumulated and calculated to obtain the discrimination value, such as the accumulated micro-motion data Δ Acc =∑Δ n Alternatively, the accumulated micro-motion values ​​within a certain time window may be averaged, moved averaged, or varied by one or more of the above methods.

[0099] Step S43, if the discrimination value is greater than the third threshold, the human body presence cumulative value is cumulatively calculated, the human body absence cumulative value is cleared, and when the human body presence cumulative value after cumulative calculation is greater than the fourth threshold, it is determined that a human body exists in the test scene;

[0100] When the discrimination value Δ is greater than the third threshold, there is an accumulation value (C exist ) is accumulated and calculated, and the preset accumulated value used for the accumulated value of the human body can be set according to the demand. The preset accumulated value in this step is set to 1, that is, when the discrimination value is greater than the third threshold value, C exist +1, and accumulate value for no human presence (C void ) is cleared, and when C exist The value after +1 is greater than the fourth threshold (Thres p ), it is determined that there is a human body in the scene to be tested, and a human body presence prompt is sent to prompt the user that there is a human body in the current scene to be tested. Optionally, in this step, the third threshold and the fourth threshold can be set according to requirements.

[0101] Step S44, if the discrimination value is less than or equal to the third threshold, the accumulated value indicating no human body is accumulated, the accumulated value indicating human body is cleared, and when the accumulated value indicating no human body is greater than the fifth threshold, it is determined that there is no human body in the scene to be tested;

[0102] If the discrimination value is less than or equal to the third threshold, the accumulated value C is void Perform cumulative calculations, and add the value C when there is no human body. voidThe cumulative calculation is performed in the same way as the cumulative value of the human body. The preset cumulative value used can be set according to the needs. The preset cumulative value in this step is set to 1, that is, if the discrimination value is less than or equal to the third threshold, then C void +1, and the cumulative value C for the human body exist Clear the process, and C void If the value after +1 is greater than the fifth threshold, it is determined that there is no human body in the scene to be tested.

[0103] In this embodiment, the distance difference is obtained by determining the difference between the relevant judgment value and the first threshold, and based on the size comparison between the distance difference and the second threshold, it is determined whether phase detection is required for the relevant distance. In this embodiment, if the distance difference is greater than the second threshold, or if the accumulated value of the human body presence after cumulative calculation is greater than the fourth threshold, it is determined that there is a human body in the scene to be tested; when the accumulated value of no human body presence after cumulative calculation is greater than the fifth threshold, it is determined that there is no human body in the scene to be tested.

[0104] Embodiment 3

[0105] See also Figure 5 , is a schematic diagram of the structure of a human presence detection system 100 provided in a third embodiment of the present invention, comprising: a signal filtering module 10, a discrete difference processing module 11, a sliding average module 12 and a detection result generating module 13, wherein:

[0106] The signal filtering module 10 is used to collect radar echo signals fed back by radar detection signals in the scene to be tested, and when the number of the radar echo signals meets the detection condition, filter the radar echo signals to obtain filtered signals.

[0107] The signal filtering module 10 is further used to: respectively obtain the time series characteristics of each radar echo signal, and generate a time series sequence according to the obtained time series characteristics;

[0108] The time series is averaged to obtain an average sequence, and the average sequence is high-pass filtered and low-pass filtered to obtain a high-pass filtered signal and a low-pass filtered signal.

[0109] The discrete difference processing module 11 is used to generate a scale deviation signal according to the filtered signal, and perform discrete difference processing on the radar echo signal to obtain a discrete difference signal.

[0110] The discrete difference processing module 11 is further used to: determine the absolute deviation between the high-pass filter signal and the low-pass filter signal, and perform normalization processing on the absolute deviation to obtain a sequence deviation signal;

[0111] Performing filtering processing on the sequence deviation signal to obtain a first scale deviation signal, and performing sliding average processing on the sequence deviation signal to obtain a second scale deviation signal;

[0112] The scale deviation signal includes the first scale deviation signal and the second scale deviation signal.

[0113] The sliding average module 12 is used to perform sliding average processing on the discrete difference signal to obtain a time series deviation signal, and generate a human body distance sequence according to the time series deviation signal and the scale deviation signal.

[0114] Wherein, the calculation formula used to generate the human body distance sequence according to the timing deviation signal and the scale deviation signal is:

[0115]

[0116] Wherein, R is the human body presence determination value in the human body distance sequence, are respectively the first scale deviation signal, the second scale deviation signal and the timing deviation signal, and β is a preset attenuation rate.

[0117] The detection result generating module 13 is used to generate a human presence detection result according to the human presence distance in the human body distance sequence.

[0118] The detection result generating module 13 is further used to: obtain the maximum human body existence distance in the human body distance sequence, and determine the maximum human body existence distance as the relevant distance and the relevant determination value;

[0119] Determine the difference between the relevant determination value and the first threshold to obtain a distance difference, and when the distance difference is less than or equal to a second threshold, perform phase detection and preprocessing on the relevant distance to obtain a determination value;

[0120] If the discrimination value is greater than the third threshold, the accumulated value of human body presence is accumulated and calculated, and the accumulated value of no human body presence is cleared to zero, and when the accumulated value of human body presence after accumulation is greater than the fourth threshold, it is determined that there is a human body in the scene to be tested;

[0121] If the discrimination value is less than or equal to the third threshold, the accumulated value indicating no human presence is accumulated and calculated, the accumulated value indicating human presence is cleared, and when the accumulated value indicating no human presence is greater than the fifth threshold, it is determined that there is no human body in the scene to be tested.

[0122] Optionally, the detection result generating module 13 is further used to: generate a phase detection range according to the relevant distance and the preset interval distance, and perform micro-motion detection within the phase detection range to obtain the displacement at the current moment;

[0123] The displacement at the current moment is preprocessed, and low-complexity calculations such as accumulation, averaging, sliding average, variance, etc. are performed or transferred to the frequency domain for feature calculation to obtain the discriminant value.

[0124] Furthermore, the detection result generating module 13 is further configured to: if the distance difference is greater than the second threshold, determine that a human body exists in the scene to be detected.

[0125] In this embodiment, the radar echo signal is filtered to obtain a filtered signal, and a scale deviation signal is generated according to the filtered signal. Based on the scale deviation signal, the scale deviation of the detected human body under different filtering states can be effectively characterized. By performing discrete difference processing on the radar echo signal, a discrete difference signal is obtained, and a sliding average processing is performed on the discrete difference signal to obtain a timing deviation signal. Based on the timing deviation signal, the deviation of the detected human body in the timing characteristics can be effectively characterized. By generating a human body distance sequence according to the timing deviation signal and the scale deviation signal, the distance between the detected human body and the signal source corresponding to the radar detection signal can be effectively characterized based on the human body distance sequence. Based on the human body existence distance in the human body distance sequence, it can be effectively detected whether there is a human body in the scene to be tested to generate a corresponding human body existence detection result.

[0126] Embodiment 4

[0127] Figure 6 2 is a block diagram of a terminal device 2 provided in the fourth embodiment of the present application. Figure 6 As shown, the terminal device 2 of this embodiment includes: a processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the processor 20, such as a program of a human presence detection method. When the processor 20 executes the computer program 23, the steps in each embodiment of the above-mentioned human presence detection method are implemented, such as Figure 1 S10 to S40 as shown, or Figure 2 Alternatively, the processor 20 implements the above when executing the computer program 22 Figure 5 The functions of each unit in the corresponding embodiment are, for example, Figure 5 For details on the functions of units 10 to 13, please refer to Figure 5 The relevant descriptions in the corresponding embodiments are not repeated here.

[0128] Exemplarily, the computer program 22 may be divided into one or more units, which are stored in the memory 21 and executed by the processor 20 to complete the present application. The one or more units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 22 in the terminal device 2. For example, the computer program 22 may be divided into a signal filtering module 10, a discrete difference processing module 11, a sliding average module 12, and a detection result generation module 13, and the specific functions of each unit are as described above.

[0129] The terminal device may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will appreciate that Figure 6 It is only an example of the terminal device 2 and does not constitute a limitation of the terminal device 2. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0130] The processor 20 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0131] The memory 21 may be an internal storage unit of the terminal device 2, such as a hard disk or memory of the terminal device 2. The memory 21 may also be an external storage device of the terminal device 2, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 2. Further, the memory 21 may also include both an internal storage unit and an external storage device of the terminal device 2. The memory 21 is used to store the computer program and other programs and data required by the terminal device. The memory 21 may also be used to temporarily store data that has been output or is to be output.

[0132] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0133] If the integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium can be non-volatile or volatile. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in computer-readable storage media can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable storage media do not include electrical carrier signals and telecommunications signals.

[0134] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting the presence of a human body, characterized in that: The method comprises: Collecting radar echo signals fed back by radar detection signals in the scene to be tested, and when the number of the radar echo signals meets the detection condition, filtering the radar echo signals to obtain filtered signals; generating a scale deviation signal according to the filtered signal, and performing discrete difference processing on the radar echo signal to obtain a discrete difference signal; Performing sliding average processing on the discrete difference signal to obtain a time series deviation signal, and generating a human body distance sequence according to the time series deviation signal and the scale deviation signal; generating a human presence detection result according to the human presence distance in the human presence distance sequence; The filtering of the radar echo signal to obtain a filtered signal includes: Acquire the time series characteristics of each radar echo signal respectively, and generate a time series sequence according to the acquired time series characteristics; Performing average processing on the time series to obtain an average sequence, and performing high-pass filtering and low-pass filtering on the average sequence to obtain a high-pass filtered signal and a low-pass filtered signal; The step of generating a scale deviation signal according to the filtered signal comprises: Determining an absolute deviation between the high-pass filter signal and the low-pass filter signal, and normalizing the absolute deviation to obtain a sequence deviation signal; Performing filtering processing on the sequence deviation signal to obtain a first scale deviation signal, and performing sliding average processing on the sequence deviation signal to obtain a second scale deviation signal; Wherein, the scale deviation signal includes the first scale deviation signal and the second scale deviation signal; The calculation formula used to generate the human body distance sequence according to the timing deviation signal and the scale deviation signal is: Wherein, R is the human body presence determination value in the human body distance sequence, are the first scale deviation signal, the second scale deviation signal and the timing deviation signal respectively, and β is a preset attenuation rate; The step of generating a human presence detection result according to the human presence distance in the human body distance sequence includes: Acquire a maximum human body existence distance in the human body distance sequence, and determine the maximum human body existence distance as a relevant distance and a relevant determination value; Determine the difference between the relevant determination value and the first threshold to obtain a distance difference, and when the distance difference is less than or equal to a second threshold, perform phase detection and preprocessing on the relevant distance to obtain a determination value; If the discrimination value is greater than the third threshold, the accumulated value of human body presence is accumulated and calculated, and the accumulated value of no human body presence is cleared to zero, and when the accumulated value of human body presence after accumulation is greater than the fourth threshold, it is determined that there is a human body in the scene to be tested; If the discrimination value is less than or equal to the third threshold, the accumulated value indicating no human presence is accumulated and calculated, the accumulated value indicating human presence is cleared, and when the accumulated value indicating no human presence is greater than the fifth threshold, it is determined that there is no human body in the scene to be tested.

2. The method for detecting the presence of a human body as claimed in claim 1, wherein: The performing phase detection and preprocessing on the relevant distance to obtain a discrimination value includes: Generate a phase detection range according to the relevant distance and the preset interval distance, and perform micro-motion detection within the phase detection range to obtain the displacement at the current moment; The displacement at the current moment is preprocessed, and low-complexity calculations such as accumulation, averaging, sliding average, variance, etc. are performed or transferred to the frequency domain for feature calculation to obtain the discriminant value.

3. The method for detecting the presence of a human body as claimed in claim 1, wherein: After determining the difference between the correlation determination value and the first threshold value to obtain the distance difference, the method further includes: If the distance difference is greater than the second threshold, it is determined that a human body exists in the scene to be detected.

4. A human presence detection system, characterized in that: The system comprises: A signal filtering module, used for collecting radar echo signals fed back by radar detection signals in the scene to be tested, and filtering the radar echo signals when the number of the radar echo signals meets the detection condition to obtain a filtered signal; A discrete difference processing module, used for generating a scale deviation signal according to the filtered signal, and performing discrete difference processing on the radar echo signal to obtain a discrete difference signal; A sliding average module, used for performing sliding average processing on the discrete difference signal to obtain a timing deviation signal, and generating a human body distance sequence according to the timing deviation signal and the scale deviation signal; A detection result generating module, used for generating a human presence detection result according to the human presence distance in the human body distance sequence; The signal filtering module is also used to: respectively obtain the time series characteristics of each radar echo signal, and generate a time series sequence according to the obtained time series characteristics; Performing average processing on the time series to obtain an average sequence, and performing high-pass filtering and low-pass filtering on the average sequence to obtain a high-pass filtered signal and a low-pass filtered signal; The discrete difference processing module is also used to: determine the absolute deviation between the high-pass filter signal and the low-pass filter signal, and perform normalization processing on the absolute deviation to obtain a sequence deviation signal; Performing filtering processing on the sequence deviation signal to obtain a first scale deviation signal, and performing sliding average processing on the sequence deviation signal to obtain a second scale deviation signal; The calculation formula used to generate the human body distance sequence according to the timing deviation signal and the scale deviation signal is: Wherein, R is the human body presence determination value in the human body distance sequence, are the first scale deviation signal, the second scale deviation signal and the timing deviation signal respectively, and β is a preset attenuation rate; The detection result generation module is also used to: obtain the maximum human body existence distance in the human body distance sequence, and determine the maximum human body existence distance as the relevant distance and the relevant determination value; Determine the difference between the relevant determination value and the first threshold to obtain a distance difference, and when the distance difference is less than or equal to a second threshold, perform phase detection and preprocessing on the relevant distance to obtain a determination value; If the discrimination value is greater than the third threshold, the accumulated value of human body presence is accumulated and calculated, and the accumulated value of no human body presence is cleared to zero, and when the accumulated value of human body presence after accumulation is greater than the fourth threshold, it is determined that there is a human body in the scene to be tested; If the discrimination value is less than or equal to the third threshold, the accumulated value indicating no human presence is accumulated and calculated, the accumulated value indicating human presence is cleared, and when the accumulated value indicating no human presence is greater than the fifth threshold, it is determined that there is no human body in the scene to be tested.

5. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images