Living object detection method, passenger detection method, related device, vehicle and medium

Abstract

The invention relates to a living object detection method, a passenger detection method, a related device, a vehicle and a medium. The living object detection method comprises the following steps: controlling a loudspeaker to emit a first sound wave signal in a preset space; controlling a microphone to collect a second sound wave signal in the preset space, wherein the second sound wave signal is generated based on the first sound wave signal; determining channel state information corresponding to the second sound wave signal according to the first sound wave signal and the second sound wave signal; and according to the channel state information corresponding to the second sound wave signal, determining whether there is a living object in the preset space. Therefore, the detection of the living object is realized through the signals transmitted and received by the microphone and the loudspeaker, no additional equipment is needed, and the accurate detection of the living object can be realized on the basis of not increasing the hardware cost. In addition, detection of living things can be achieved only through the microphone and the loudspeaker which are low in cost, and therefore the applicability of the method is high.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle technology, and in particular to a living thing detection method, a passenger detection method, related devices, a vehicle and a medium. Background Art

[0002] With the development of intelligence, the smart cockpit of vehicles is becoming more and more intelligent. In the smart cockpit, identifying whether there are passengers in the car is crucial for intelligent decision-making in the smart cockpit. For example, when identifying the presence of passengers in the car, the smart cockpit can make decisions based on data detected by other perception systems, such as whether to turn on the air conditioning in the smart cockpit, whether to remind the driver to fasten the seat belt, etc.

[0003] At present, the related technologies mostly detect whether there is a passenger in the seat by detecting the pressure value of the pressure sensor installed on the seat. However, this method will detect the object placed on the seat as a passenger, which may lead to wrong decision-making of the smart cockpit. In order to improve the accuracy of passenger detection in the car, it is also necessary to identify whether the object in the car is alive. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a living thing detection method, a passenger detection method, related devices, a vehicle and a medium.

[0005] According to a first aspect of an embodiment of the present disclosure, a method for detecting living things is provided, the method comprising:

[0006] Controlling the loudspeaker to emit a first sound wave signal in a preset space;

[0007] Controlling the microphone to collect a second sound wave signal in the preset space, where the second sound wave signal is generated based on the first sound wave signal;

[0008] Determine, according to the first sound wave signal and the second sound wave signal, channel state information corresponding to the second sound wave signal;

[0009] Determine whether there is a living thing in the preset space according to the channel state information corresponding to the second sound wave signal.

[0010] According to a second aspect of an embodiment of the present disclosure, a passenger detection method is provided, the method comprising:

[0011] Determine whether the seats in the cabin are occupied;

[0012] When the seat is in the occupied state and the living thing detection result in the vehicle cabin indicates that a living thing exists, determining that a passenger exists in the vehicle cabin;

[0013] Among them, the living thing detection result in the cabin is obtained according to the living thing detection method as described in the first aspect of the present disclosure.

[0014] According to a third aspect of an embodiment of the present disclosure, there is provided a living thing detection device, the living thing detection device comprising:

[0015] A first control module is configured to control the speaker to emit a first sound wave signal in a preset space;

[0016] A second control module is configured to control the microphone to collect a second sound wave signal in the preset space, where the second sound wave signal is generated based on the first sound wave signal;

[0017] A first determining module is configured to determine channel state information corresponding to the second sound wave signal according to the first sound wave signal and the second sound wave signal;

[0018] The second determination module is configured to determine whether there is a living thing in the preset space according to the channel state information corresponding to the second sound wave signal.

[0019] According to a fourth aspect of an embodiment of the present disclosure, a passenger detection device is provided, the device comprising:

[0020] a seventh determination module, configured to determine whether a seat in the vehicle cabin is in an occupied state;

[0021] An eighth determination module is configured to determine that there is a passenger in the cabin when the seat is in the occupied state and a living thing detection result in the cabin indicates that there is a living thing;

[0022] Among them, the living thing detection result in the cabin is obtained according to the living thing detection method as described in the first aspect of the present disclosure.

[0023] According to a fifth aspect of an embodiment of the present disclosure, a vehicle is provided, comprising:

[0024] A processor, a speaker, and a microphone, wherein the processor is connected to the speaker and the microphone respectively;

[0025] a memory for storing processor-executable instructions;

[0026] Wherein, the processor is configured to execute the living thing detection method as described in the first aspect of the present disclosure, or to execute the passenger detection method as described in the second aspect of the present disclosure.

[0027] According to a sixth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the living thing detection method provided in the first aspect of the present disclosure are implemented, or the steps of the passenger detection method provided in the second aspect of the present disclosure are implemented.

[0028] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0029] By adopting the above technical solution, the speaker is controlled to emit a first sound wave signal in a preset space, and the microphone is controlled to collect signals to obtain a second sound wave signal. Then, according to the first sound wave signal and the second sound wave signal, the channel state information corresponding to the second sound wave signal is determined. Finally, according to the channel state information, it is determined whether there is a living thing in the preset space. In this way, the detection of living things is achieved through the sound wave signals received and sent by the microphone and the speaker, without the need for additional equipment, and accurate detection of living things can be achieved without increasing hardware costs. In addition, only low-cost microphones and speakers are needed to detect living things, which makes the method more applicable.

[0030] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0032] Figure 1 The figure is a flow chart of a living thing detection method according to an exemplary embodiment.

[0033] Figure 2 The present invention is a flowchart showing a method for determining a target dynamic or static state of an object in a preset space according to an exemplary embodiment.

[0034] Figure 3 According to an exemplary embodiment, Figure 2 Schematic diagram of the process of step S22.

[0035] Figure 4 The invention is a flow chart showing a method for determining breathing information in a preset space according to an exemplary embodiment.

[0036] Figure 5 The figure is a flow chart of another method for detecting living things according to an exemplary embodiment.

[0037] Figure 6 The figure is a flow chart of a passenger detection method according to an exemplary embodiment.

[0038] Figure 7 The figure is a block diagram of a living thing detection device according to an exemplary embodiment.

[0039] Figure 8 It is a block diagram of a passenger detection device according to an exemplary embodiment.

[0040] Fig. 9 is a block diagram of a vehicle according to an exemplary embodiment.

[0041] Fig.10 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0042] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0043] It should be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located, and with the authorization given by the owner of the corresponding device.

[0044] Common living thing detection technologies currently include: 1. Identifying whether there are living things from images collected by the camera. However, there are serious privacy issues and it is easily affected by lighting conditions or occlusions. A single camera cannot cover the entire area due to seat occlusions. 2. Using a thermal sensor to sense whether there is a changing heat source to determine whether there is a moving object. It can only determine whether there is an object with a heat source, and a thermal sensor needs to be installed. The target cannot be detected when the object is stationary. 3. Sense whether there is an object through the reflection of electromagnetic waves. For moving objects, it can be judged by extracting the speed, but the cost is relatively high. 4. Determine whether there is a moving object through the fluctuation of the WiFi signal. However, since the extraction of the channel state information currently used for perception will affect the communication capability of WiFi, the use of this technology is limited.

[0045] In view of this, the present disclosure provides a living thing detection method, a passenger detection method, related devices, a vehicle and a medium, which realize the detection of living things through the sound wave signals received and sent by a microphone and a speaker, without the need for additional equipment, and can realize accurate detection of living things without increasing hardware costs. In addition, the method has strong applicability.

[0046] Figure 1 FIG. 1 is a flow chart of a method for detecting living things according to an exemplary embodiment. Figure 1 As shown, the method includes the following steps.

[0047] In step S11, the speaker is controlled to emit a first sound wave signal in a preset space.

[0048] In step S12, the microphone is controlled to collect a second sound wave signal in a preset space, where the second sound wave signal is generated based on the first sound wave signal.

[0049] In the present disclosure, the preset space may be any space, for example, the preset space may be a room equipped with a speaker and a microphone. For another example, the preset space may be a vehicle cabin equipped with a speaker and a microphone. In the case where the preset space is a vehicle cabin, the solution provided by the present disclosure can detect living things in the vehicle cabin. In this way, when the owner leaves the vehicle and the windows are closed, the living thing detection method provided by the present disclosure can detect whether there are passengers left in the closed vehicle cabin, thereby ensuring the safety of the passengers.

[0050] The second sound wave signal may be a signal generated after a preset space performs at least one of reflection, diffraction, and scattering operations on the first sound wave signal.

[0051] It should be understood that the number of the speaker and the microphone may be one or more, and the number of the speaker and the microphone may be the same or different, and the present disclosure does not specifically limit this.

[0052] In step S13, channel state information corresponding to the second sound wave signal is determined according to the first sound wave signal and the second sound wave signal.

[0053] In step S14, it is determined whether there is a living thing in the preset space according to the channel state information corresponding to the second sound wave signal.

[0054] The channel state information can reflect the changes in the channel for transmitting the sound wave signal. If there is a living thing, the movement of the living thing will cause the channel to change, that is, cause the change in the channel state information. Therefore, in the present disclosure, it can be determined whether there is a living thing in the preset space based on the channel state information corresponding to the second sound wave signal.

[0055] By adopting the above technical solution, the speaker is controlled to emit a first sound wave signal in a preset space, and the microphone is controlled to collect signals to obtain a second sound wave signal. Then, according to the first sound wave signal and the second sound wave signal, the channel state information corresponding to the second sound wave signal is determined. Finally, according to the channel state information, it is determined whether there is a living thing in the preset space. In this way, the detection of living things is achieved through the sound wave signals received and sent by the microphone and the speaker, without the need for additional equipment, and accurate detection of living things can be achieved without increasing hardware costs. In addition, only low-cost microphones and speakers are needed to detect living things, which makes the method more applicable.

[0056] In order to facilitate those skilled in the art to better understand the living thing detection method provided by the present disclosure, the living thing detection method is described below with a complete embodiment.

[0057] In the present disclosure, the first sound wave signal emitted by the speaker is a specific sound wave signal. In one embodiment, the first sound wave signal can be generated by:

[0058] First, a plurality of frames of first baseband signals whose autocorrelation values ​​are greater than a second preset threshold are generated.

[0059] In the present disclosure, the multiple frames of first baseband signals may be the same baseband signal.

[0060] For example, considering that the autocorrelation of the ZC (Zadoff-Chu) sequence is good, the first baseband signal can be a ZC sequence. The ZC sequence is usually represented by a complex number. Therefore, in this example, the first baseband signal is a set of complex signal values. Preferably, the length of the first baseband signal can be 85.

[0061] It should be understood that, in practical applications, the first baseband signal may also be other sequences with good autocorrelation, and the present disclosure does not make any specific limitation to this.

[0062] Afterwards, the multiple frames of first baseband signals are modulated into ultrasonic frequency band signals, and the ultrasonic frequency band signals are determined as first sound wave signals.

[0063] It should be understood that the first baseband signal is a low-frequency signal. In order to avoid interference to the user caused by the signal emitted by the speaker heard by the human ear, in the present disclosure, the low-frequency first baseband signal can be modulated into an ultrasonic frequency band signal, and the ultrasonic frequency band signal can be determined as the first sound wave signal.

[0064] For example, multiple first baseband signals can be modulated into an ultrasonic frequency range of 18kHz to 20kHz, and the human ear can hardly hear the sound waves in this frequency range emitted by the speaker. In addition, for a sound wave with a sampling rate of 48kHz, the length of the modulated signal will change from the original 85 to 2048, that is, the length of a frame of modulated data is 2048.

[0065] It should be understood that if the first baseband signal is a set of complex signal values, the modulated ultrasonic frequency band signal is also a set of complex signal values, that is, the first ultrasonic signal is a set of complex signal values. When playing, the speaker only plays the real part of the complex signal value, and accordingly, the microphone also receives a set of real part values.

[0066] Considering that the movement of the object is a continuous action, in order to improve the accuracy of the determined dynamic and static state of the object, it is necessary to determine the dynamic and static state of the object based on the channel state information within a period of time, that is, it is necessary to determine the dynamic and static state of the object based on the channel state information corresponding to multiple frames of data. Therefore, in one embodiment, the first sound wave signal and the second sound wave signal both include multiple frames of data, that is, the channel state information corresponding to the second sound wave signal includes the channel state information corresponding to the multiple frames of data.

[0067] In the present disclosure, each frame of data included in the first sound wave signal is generated based on the first baseband signal corresponding to each frame, that is, the first baseband signal is adjusted to generate a frame of data. Among them, multiple frames of data can be generated based on the same first baseband signal, that is, the first baseband signal corresponding to each frame of data is the same.

[0068] In one embodiment of the present disclosure, the specific implementation method of step S13 determining the channel state information corresponding to the second sound wave signal according to the first sound wave signal and the second sound wave signal is as follows: first, according to the cross-correlation between the first sound wave signal and the second sound wave signal, multiple frames of data included in the second sound wave signal are identified. Finally, for each frame of data, the frame data is demodulated to obtain a second baseband signal corresponding to the frame data, and the channel state information corresponding to the frame data is determined according to the second baseband signal and the first baseband signal corresponding to the frame data.

[0069] It should be understood that the second sound wave signal received by the microphone includes multiple frames of data, but it is impossible to determine which of the received data belongs to one frame of data. Therefore, in the present disclosure, it is necessary to identify the multiple frames of data included in the second sound wave signal based on the cross-correlation between the first sound wave signal and the second sound wave signal. That is, multiple frames of complete data are divided from the received data sequence. Afterwards, for each frame of data, the frame data is demodulated to obtain the second baseband signal corresponding to the frame data, and finally, the channel state information corresponding to the frame data is determined based on the second baseband signal and the first baseband signal corresponding to the frame data.

[0070] Optionally, determining the channel state information corresponding to the frame data according to the second baseband signal and the first baseband signal corresponding to the frame data may include:

[0071] Determining a frequency response of a baseband signal according to the second baseband signal and a first baseband signal corresponding to the frame data;

[0072] The frequency response of the baseband signal is determined as the channel state information corresponding to the frame data.

[0073] For example, the second baseband signal and the first baseband signal corresponding to the frame data are converted from the time domain to the frequency domain, and then the second baseband signal in the frequency domain is divided by the first baseband signal in the frequency domain to obtain the frequency response of the baseband signal.

[0074] In one possible manner, the frequency response of the baseband signal can be used to characterize the channel state information, that is, the quotient of the frequency domain of the second baseband signal corresponding to the frame data and the frequency domain of the first baseband signal corresponding to the frame data is determined as the channel state information corresponding to the frame data.

[0075] In another possible manner, considering that the channel impulse response can characterize the length of the channel, in this manner, the channel impulse response can also be used to characterize the channel state information, that is, the channel impulse response is determined according to the frequency response of the baseband signal; and the channel impulse response is determined as the channel state information corresponding to the frame data. For example, the frequency response of the baseband signal can be converted into the channel impulse response by inverse Fourier transform.

[0076] It should be understood that, in this manner, the channel impulse response is determined as the channel state information corresponding to the frame data, so that the length of the channel state information corresponding to the frame data is the same as the length or sampling point of the frame data.

[0077] In this disclosure, Figure 1 The specific implementation of step S14 is: determining the target dynamic and static state of the object in the preset space according to the channel state information corresponding to the multi-frame data; if the target dynamic and static state of the object is a moving state, determining that there is a living thing in the preset space.

[0078] It should be understood that if the object in the preset space is in motion, the position of the object may be different at different times, which will affect the data transmission channel, that is, the channel state information will change. Therefore, in this embodiment, the target dynamic and static state of the object in the preset space can be determined based on the channel state information corresponding to the transmitted multi-frame data.

[0079] In one embodiment, the speaker sends out multiple frames of data sequentially, that is, the speaker sends out the multiple frames of data sequentially at different times. Figure 2 FIG. 1 is a flow chart showing a method for determining the target dynamic and static state of an object in a preset space according to an exemplary embodiment. Figure 2 As shown, the method for determining the target dynamic and static state of an object in a preset space may include the following steps.

[0080] In step S21, based on the channel state information corresponding to each frame of data in the multiple frames of data, the change amount of the channel state information corresponding to each frame of data is determined.

[0081] For example, assume that the multiple frames of data are N frames of data, and the i-th frame of data is transmitted at time ti, the value range of i is [1, N], each frame of data includes M sampling points, each sampling point is a data, that is, each frame of data includes M data, preferably, M=85.

[0082] As shown in the following matrix, c1, c2...cM are sampling points, that is, the data included in each frame of data. Each element in the matrix represents the channel state information corresponding to each data transmitted. For example, s{t1,c1} represents the channel state information corresponding to the first data of the first frame of data, and s{tN,cM} represents the channel state information corresponding to the Mth data of the Nth frame of data. In the following matrix, the i-th column represents the channel state information corresponding to the i-th frame of data, and the value range of i is [1,N].

[0083]

[0084] In this embodiment, determining the change amount of the channel state information corresponding to each frame of data refers to determining the change amount of each column element in the above matrix.

[0085] In one manner of this embodiment, the change amount of the channel state information corresponding to each frame of data may be the difference between the maximum channel state information and the minimum channel state information in each column.

[0086] In another way of this embodiment, the amount of change in the channel state information corresponding to each frame of data may also be the variance of the channel state information in each column. That is, for each column in the above matrix, the variance of the channel state information of the column is calculated, and the variance is determined as the amount of change in the channel state information corresponding to the frame data of the column. For example, the variance of the channel state information of the first column is determined as the amount of change in the channel state information corresponding to the first frame of data, the variance of the channel state information of the Nth column is determined as the amount of change in the channel state information corresponding to the Nth frame of data, and so on.

[0087] In another method of this embodiment, each frame of data includes M data, and the M data are transmitted on M channels respectively, M is an integer greater than 1, and the specific method for determining the change amount of the channel state information corresponding to each frame of data is: for each channel, according to the channel state information corresponding to each frame of data on the channel and a preset step size, determine the difference in channel state information corresponding to different frame data on the channel to obtain a deviation value of the channel state information corresponding to each frame of data on each channel; for each frame of data, according to the deviation value of the channel state information corresponding to the frame of data on each channel, determine the variance of the deviation value, and determine the variance as the change amount of the channel state information corresponding to the frame of data.

[0088] For example, continuing to take the above matrix as an example, in the above matrix, each row can represent a channel. First, for each row of the above matrix, the difference of the channel state information corresponding to different frame data on the channel is determined according to a preset step size to obtain the deviation value of the channel state information corresponding to each frame data on each channel.

[0089] For example, if the preset step size is 2, the difference between s{t3,c1} and s{t1,c1} is determined as the deviation value of the channel state information corresponding to the first frame data on the first channel, the difference between s{t4,c1} and s{t2,c1} is determined as the deviation value of the channel state information corresponding to the second frame data on the first channel, ..., the difference between s{tN,c1} and s{t(N-2),c1} is determined as the deviation value of the channel state information corresponding to the N-2 frame data on the first channel, the difference between s{t1,c1} and s{t(N-1),c1} is determined as the deviation value of the channel state information corresponding to the N-1 frame data on the first channel, and the difference between s{t2,c1} and s{tN,c1} is determined as the deviation value of the channel state information corresponding to the N-1 frame data on the first channel. It should be understood that the difference described here refers to the amplitude difference of two complex numbers.

[0090] Finally, for each frame of data, the variance of the deviation value of the channel state information corresponding to the frame of data on each channel is calculated to obtain the amount of change of the channel state information corresponding to the frame of data. For example, after calculating the deviation value of the channel state information corresponding to each frame of data on each channel, it is represented in a matrix form, and the deviation value of the channel state information corresponding to each frame of data on each channel is located in a column, so that the deviation value matrix of the channel state information is obtained, and thus, the variance of each column is calculated to obtain the amount of change of the channel state information corresponding to the frame data corresponding to the column.

[0091] In step S22, for each frame of data, the first target dynamic and static state of the object when the frame of data is transmitted is determined according to the change amount of the channel state information corresponding to the frame of data.

[0092] First of all, it should be understood that the preset space can be in the cabin, and multiple microphones are usually arranged in the cabin, and the positions of the multiple microphones are different. In this way, the channels for transmitting the frame data received by each microphone are also different, and accordingly, the channel state information corresponding to the multiple frames of data received by each microphone is also different. Therefore, in the case where there are multiple microphones, step S13 determines the channel state information corresponding to the second sound wave signal according to the first sound wave signal and the second sound wave signal, which may include: for each microphone, determining the channel state information corresponding to the multiple frames of data received by the microphone according to the first sound wave signal and the second sound wave signal collected by the microphone.

[0093] Secondly, it should be understood that due to the different positions of the microphones, the attenuation of the data in the second sound wave signal received by different microphones is different, that is, the channel state information corresponding to the multi-frame data received by different microphones is different. Therefore, in the case of multiple microphones, the target dynamic and static state of the object in the preset space is determined according to the channel state information corresponding to the multi-frame data received by the multiple microphones. Among them, the channel state information corresponding to the multi-frame data received by each microphone can be represented in the form of the above matrix.

[0094] Accordingly, Figure 3 According to an exemplary embodiment, Figure 2 Schematic diagram of the process of step S22 in FIG. Figure 2 As shown, step S22 may further include step S221 and step S222 for each frame of data, determining the first target dynamic and static state of the object when transmitting the frame of data according to the change amount of the channel state information corresponding to the frame of data.

[0095] In step S221, for each microphone, according to the change amount of the channel state information corresponding to the multiple frames of data received by the microphone, the second target dynamic and static state of the object when transmitting each frame of data received by the microphone is determined.

[0096] For example, for each microphone, it is determined that the second target dynamic and static state of the object is a moving state when the change in the transmission channel state information is greater than the first preset threshold frame data, and it is determined that the second target dynamic and static state of the object is a stationary state when the change in the transmission channel state information is not greater than the first preset threshold frame data.

[0097] As described above, the channel state information corresponding to the multiple frames of data received by each microphone can be represented in the form of the above-mentioned matrix. That is, for each microphone, the variance of each column in the deviation value matrix can be further calculated according to the method of determining the change in the channel state information described above, and the change in the channel state information corresponding to the frame data corresponding to each column can be obtained.

[0098] It should be understood that the volatility of the channel state information corresponding to the frame data corresponding to each column can be determined based on the variance of each column. If the variance is large, it indicates that the volatility of the channel state information corresponding to the frame data is large, that is, it is determined that the second target dynamic state of the object is in motion when the frame data is transmitted. If the variance is small, it indicates that the volatility of the channel state information corresponding to the frame data is small, that is, it is determined that the second target dynamic state of the object is in a stationary state when the frame data is transmitted.

[0099] For example, assuming that the microphones include microphone 1, microphone 2, microphone 3, microphone 4 and microphone 5, and the multi-frame data includes five frames of data, and the five frames of data are transmitted in sequence at time t1, time t2, time t3, time t4 and time t5, respectively. The second target dynamic and static state of the object when each frame of data received by each microphone is transmitted is shown in Table 1. In Table 1, the second to sixth rows respectively represent the second target dynamic and static state of the object when each frame of data received by each microphone is transmitted. Among them, "dynamic" in Table 1 represents that the second target dynamic and static state is a moving state, and "static" represents that the second target dynamic and static state is a static state.

[0100] Table 1

[0101] t1 t2 t3 t4 t5 Microphone 1 move move move move move Microphone 2 move quiet quiet quiet quiet Microphone 3 move quiet move quiet move Microphone 4 quiet quiet quiet quiet move Microphone 5 quiet move move move quiet

[0102] In step S222, for each frame of data, the first target dynamic and static state of the object when transmitting the frame of data is determined according to the second target dynamic and static state of the object when transmitting the frame of data received by each microphone.

[0103] For example, taking the above Table 1 as an example, the second to sixth columns in Table 1 represent the first frame data, the second frame data, the third frame data, the fourth frame data, and the fifth frame data, respectively. For example, for the second frame data, according to the second target dynamic and static state of the object when transmitting the second frame data received by each microphone shown in the third column, the first target dynamic and static state of the object when transmitting the second frame data is determined.

[0104] In the present disclosure, a voting method can be used to determine the first target motion state of an object when transmitting the frame data. Accordingly, an implementation of step S222 is: if the number of second target motion states that are in motion is greater than the number of second target motion states that are in stillness, then the third target motion state of the object when transmitting the frame data is determined to be in motion, and, if the number of second target motion states that are in motion is not greater than the number of second target motion states that are in stillness, then the third target motion state of the object when transmitting the frame data is determined to be in stillness; based on the third target motion state of the object when transmitting the frame data, the first target motion state of the object when transmitting the frame data is determined.

[0105] Continuing with Table 1 as an example, for the first frame of data, the number of second target dynamic and static states that are in motion is greater than the number of second target dynamic and static states that are in static state, then it is determined that the third target dynamic and static state of the object is in motion when the first frame of data is transmitted. Similarly, it is determined that the third target dynamic and static state of the object is in static state when the second frame of data is transmitted, it is determined that the third target dynamic and static state of the object is in motion when the third frame of data is transmitted, it is determined that the third target dynamic and static state of the object is in static state when the fourth frame of data is transmitted, and it is determined that the third target dynamic and static state of the object is in motion when the fifth frame of data is transmitted. Among them, the third target dynamic and static state of the object when the above five frames of data are transmitted is as shown in Table 2.

[0106] Table 2

[0107] t1 t2 t3 t4 t5 The third target dynamic and static state move quiet move quiet move

[0108] Another implementation of step S222 is: if the number of second target dynamic and static states that are motion states is greater than a preset number, then it is determined that the third target dynamic and static state of the object is a motion state when transmitting the frame data; otherwise, it is determined that the third target dynamic and static state of the object is a static state when transmitting the frame data; based on the third target dynamic and static state of the object when transmitting the frame data, the first target dynamic and static state of the object when transmitting the frame data is determined.

[0109] In this embodiment, a preset number is set in advance. For each frame of data, as long as the number of motion states is greater than the preset number, it can be determined that the third target dynamic state of the object when transmitting the frame of data is a motion state, without determining the size relationship between the number of motion states and the number of static states.

[0110] In one possible manner, the specific implementation method of determining the first target dynamic and static state of the object when transmitting the frame data based on the third target dynamic and static state of the object when transmitting the frame data is as follows: the third target dynamic and static state of the object when transmitting the frame data is determined as the first target dynamic and static state of the object when transmitting the frame data.

[0111] In a possible manner, considering the detection error, the third target motion state determined above can be subjected to state filtering processing, and then the first target motion state can be determined based on the third target motion state after the state filtering processing. That is, the specific implementation method of determining the first target motion state of the object when transmitting the frame data based on the third target motion state of the object when transmitting the frame data is as follows: the third target motion state of the object when transmitting the frame data is subjected to state filtering processing, and the third target motion state after the state filtering processing is determined as the first target motion state of the object when transmitting the frame data.

[0112] In this method, the state filtering processing is specifically that when the third target dynamic and static state of the object when transmitting the frame data is inconsistent with the third target dynamic and static state of the two adjacent frame data before and after the transmission of the frame data, the third target dynamic and static state of the object when transmitting the frame data is updated with the third target dynamic and static state of the two adjacent frame data before and after the transmission of the frame data.

[0113] For example, taking Table 2 as an example, for the first frame data, the third target dynamic and static state of the object when transmitting the first frame data is different from the third target dynamic and static state of the object when transmitting the second frame data, but it is the same as the third target dynamic and static state of the object when transmitting the fifth frame data, that is, it is not updated. For the second frame data, since the third target dynamic and static state of the object when transmitting the second frame data is different from the corresponding third target dynamic and static state when transmitting the first frame data and the second frame data, it is necessary to update the third target dynamic and static state of the object when transmitting the second frame data to the motion state. Similarly, for the third frame data, since the third target dynamic and static state of the object when transmitting the second frame data is updated to the motion state, the third target dynamic and static state of the object when transmitting the third frame data is the same as the third target dynamic and static state of the object when transmitting the second frame data, and then it is not updated. For the fourth frame data, the third target dynamic and static state of the object when transmitting the third frame data is updated to the motion state. It is not updated for the fifth frame data either. In this way, the third target dynamic and static state after state filtering can be obtained, and it is determined as the first target dynamic and static state of the object when transmitting the frame data.

[0114] In another embodiment, determining the target dynamic and static state of an object in a preset space based on channel state information corresponding to multiple frames of data may also include: performing mean filtering on the change in the channel state information corresponding to each frame of data to obtain the processed change; accordingly, the above-mentioned determining, for each frame of data, the first target dynamic and static state of the object when transmitting the frame of data based on the change in the channel state information corresponding to the frame data may include: determining, for each frame of data, the first target dynamic and static state of the object when transmitting the frame of data based on the processed change in the channel state information corresponding to the frame data.

[0115] In this embodiment, after calculating the change amount of the channel state information corresponding to each frame of data, the obtained change amount is subjected to mean filtering. For example, the mean filtering process is performed with a sliding window, for example, the sliding window size is 5, then the mean of the change amount of the channel state information corresponding to the first frame of data to the second frame of data is calculated, and the mean is determined as the processed change amount of the channel state information corresponding to the first frame of data, similarly, the mean of the change amount of the channel state information corresponding to the second frame of data to the sixth frame of data is calculated, and the mean is determined as the processed change amount of the channel state information corresponding to the second frame of data, and so on, respectively, the processed change amount of the channel state information corresponding to each frame of data is calculated, and then for each frame of data, according to the processed change amount of the channel state information corresponding to the frame of data, the first target dynamic and static state of the object when the frame of data is transmitted is determined.

[0116] It should be noted that, in this embodiment, the specific implementation method of determining the first target dynamic and static state of the object when transmitting the frame data based on the processed change in the channel state information corresponding to the frame data is similar to the method described in the above step S22, and the present disclosure will not go into details about this.

[0117] return Figure 2 , Figure 2 As shown, the method for determining the target dynamic and static state of an object in a preset space may include step S23.

[0118] In step S23, the target dynamic and static state of the object in the preset space is determined according to the first target dynamic and static state of the object when each frame of data is transmitted.

[0119] In one embodiment, the target dynamic and static state of the object in the space can be determined based on all frame data included in the sound wave signal, that is, the target dynamic and static state of the object in the space can be determined based on the first target dynamic and static state of the object when each frame data in all frame data is transmitted.

[0120] For example, based on the first target dynamic and static state of the object when transmitting each frame of all frame data, if the number of motion states is greater than the number of static states, the target dynamic and static state of the object in the space is determined to be a motion state; otherwise, the target dynamic and static state of the object in the space is determined to be a static state.

[0121] Considering that in actual applications, the number of frames of data included in the sound wave signal is relatively large, if the target dynamic and static state of the object in the space is determined based on all the frame data included in the sound wave signal, the amount of calculation is relatively large. Therefore, in another embodiment, the target dynamic and static state of the object in the space can be determined based on part of the frame data in each cycle of living thing detection. The specific implementation of step S23 can be: determining a first preset number of first target frame data from multiple frames of data; determining the target dynamic and static state of the object in the preset space based on the first target dynamic and static state of the object when transmitting each first target frame data.

[0122] For example, a sliding window may be used to select a first preset number of first target frame data from all frame data, wherein the height of the sliding window is M, and the width is the value of the first preset number. For example, assuming that the first preset number is 30, then in the first cycle of live object detection, the first target motion state of the object when transmitting the first frame data to the thirtieth frame data may be used to determine the target motion state of the object in the preset space, and in the second cycle of live object detection, the first target motion state of the object when transmitting the second frame data to the thirty-first frame data may be used to determine the target motion state of the object in the preset space, and so on.

[0123] In this example, according to the first target dynamic and static state of the object when transmitting each first target frame data, if the number of motion states is greater than the number of static states, the target dynamic and static state of the object in the space is determined to be a motion state; otherwise, the target dynamic and static state of the object in the space is determined to be a static state.

[0124] In this way, the detection of living things can be achieved through the signals received and sent by the microphone and the speaker, without the need for additional equipment, and accurate detection of living things can be achieved without increasing hardware costs.

[0125] Considering that the object may be in a static state such as sleeping, if only the dynamic and static state of the object is used to detect whether there is a living thing in the preset space, it may result in missed detection. Therefore, in order to further improve the accuracy of living thing detection, in the present disclosure, Figure 1 The specific implementation method of step S14 can also be: if the target dynamic or static state of the object is not a moving state, then the breathing information in the preset space is determined according to the channel state information corresponding to the multi-frame data; if the breathing information indicates that there is breathing behavior in the preset space, then it is determined that there is a living thing in the preset space; if the breathing information indicates that there is no breathing behavior in the preset space, then it is determined that there is no living thing in the preset space.

[0126] It should be understood that if there is breathing behavior in the preset space, the breathing action of the object will cause the chest movement of the object, that is, the relative position of the chest of the object and the microphone and speaker will change at different times, which will in turn affect the data transmission channel, that is, the channel state information will change. Therefore, in the present disclosure, the breathing information in the preset space can be determined based on the channel state information corresponding to the transmitted multi-frame data.

[0127] In this way, the breathing information in the preset space is determined according to the channel state information corresponding to the multi-frame data, and no additional equipment is required. The breathing information in the preset space can be detected without increasing the hardware cost, and the method has strong applicability. In addition, when the target dynamic state of the object is not in a moving state, the breathing information in the preset space is further detected to determine whether there is a living thing in the preset space, thereby improving the accuracy of the detection of living things.

[0128] In one embodiment, if the target dynamic and static state of the object is not a motion state, the specific implementation method of determining the breathing information in the preset space according to the channel state information corresponding to the multi-frame data is as follows: if the target dynamic and static state of the object is not a motion state, the channel state information corresponding to the multi-frame data is filtered to obtain the channel state information corresponding to the multi-frame data after filtering; the breathing information in the preset space is determined according to the channel state information corresponding to the multi-frame data after filtering.

[0129] Taking into account that the breathing amplitude of the object is usually relatively small, that is, the movement amplitude of the chest cavity caused by breathing is small, and the impact on the channel is also small, that is, the impact of breathing on the channel state information corresponding to the multi-frame data is not obvious. Therefore, in this embodiment, the channel state information corresponding to the obtained multi-frame data can also be filtered to filter out errors, and then the breathing information in the preset space is determined based on the channel state information corresponding to the multi-frame data after filtering.

[0130] For example, since the speaker continuously sends multiple frames of data, a hampel filter can be used to filter out abnormal values ​​in the channel state information that is continuously determined and changes over time. In addition, a Savitzky-Golay filter can also be used to filter noise in the channel state information to obtain smooth channel state information.

[0131] By adopting the above technical solution, the channel state information corresponding to the obtained multi-frame data is filtered to obtain relatively accurate channel state information corresponding to the multi-frame data. Then, the respiratory information in the preset space is determined based on the accurate channel state information, which improves the accuracy of the determined respiratory information and further improves the accuracy of living thing detection.

[0132] Figure 4is a flow chart of a method for determining respiratory information in a preset space according to an exemplary embodiment. In this embodiment, each frame of data includes M data, and the M data are transmitted on M channels respectively, where M is an integer greater than 1. Figure 2 As shown, the method for determining breathing information in a preset space may include the following steps.

[0133] In step S41, the breathing detection related parameters corresponding to each channel are determined according to the channel state information corresponding to the multiple frames of data.

[0134] In step S42, if there is a first target channel whose breathing detection related parameters meet the preset threshold conditions, it is determined that there is breathing behavior in the preset space.

[0135] In step S43, if there is no first target channel whose breathing detection related parameters meet the preset threshold condition, it is determined that there is no breathing behavior in the preset space.

[0136] The channel state information corresponding to the multi-frame data on each channel can be used to characterize the change of the channel at different times, that is, to characterize the influence of breathing on the channel at different times. For example, if there is no breathing behavior, the environment of each channel does not change at different times, and each channel remains unchanged at different times, that is, the corresponding channel state information of each channel remains unchanged. If there is breathing behavior, the environment of at least some channels changes at different times, and at least some channels change at different times, that is, the corresponding channel state information on at least some channels changes. Therefore, in an embodiment, it can be determined that there is breathing behavior in the preset space based on the breathing detection related parameters corresponding to each channel.

[0137] For example, the multi-frame data is N frames of data, and the corresponding channel state information is exemplified by the above matrix. In the above matrix, the channel state information located in the same row is recorded as the channel state information corresponding to the N frames of data on the channel. In step S21, the respiration detection related parameters corresponding to each channel are determined, that is, for each row in the above matrix, the respiration detection related parameters corresponding to the row are determined according to the channel state information of the row.

[0138] By adopting the above technical scheme, the breathing detection related parameters corresponding to each channel are determined according to the channel state information corresponding to the multi-frame data, and whether there is breathing behavior is determined according to the breathing detection related parameters. In this way, compared with the detection of breathing in the prior art, this scheme realizes the detection of breathing through the sound wave signals received and sent by the microphone and the speaker. No additional equipment is required, and it can realize accurate detection of breathing without increasing the hardware cost, thereby making the method more applicable.

[0139] In the case where there are multiple microphones, in one implementation, the specific implementation of step S41 determining the breathing detection related parameters corresponding to each channel according to the channel state information corresponding to the multiple frames of data is as follows: determining the breathing detection related parameters corresponding to each channel according to the channel state information corresponding to the multiple frames of data received by the multiple microphones. For example, if the number of microphones is 5, then 5 matrices similar to the above matrix can be obtained in the above manner, and the breathing detection related parameters corresponding to each row in the 5 matrices are calculated respectively.

[0140] Considering that if the breathing detection related parameters corresponding to each channel of each microphone are determined based on the channel state information corresponding to the multi-frame data received by all microphones, it will lead to a large amount of calculation and a slow breathing detection rate. Therefore, in another embodiment, a target microphone for breathing detection can be determined from multiple microphones, and then the breathing detection related parameters corresponding to each channel can be determined based on the channel state information corresponding to the multi-frame data received by the target microphone. By way of example, the specific implementation method of step S41 determining the breathing detection related parameters corresponding to each channel based on the channel state information corresponding to the multi-frame data is as follows: for each microphone, according to the channel state information corresponding to the multi-frame data received by the microphone, determine the change amount of the channel state information corresponding to the multi-frame data received by the microphone on each channel; determine the microphone with the largest change amount of the channel state information as the target microphone; and determine the breathing detection related parameters corresponding to each channel based on the channel state information corresponding to the multi-frame data received by the target microphone.

[0141] Since the breathing amplitude is usually relatively small, the change in channel state information caused by it is usually not obvious. Therefore, in this embodiment, in order to improve the accuracy of breathing detection, the microphone with the largest change in channel state information can be determined as the target microphone, and then the breathing information in the preset space is determined only based on the channel state information corresponding to the multiple frames of data received by the target microphone.

[0142] The following describes a method for determining the amount of change in channel state information corresponding to multiple frames of data on each channel.

[0143] In one embodiment, for each channel, according to the channel state information corresponding to the multi-frame data on the channel, the difference between the maximum channel state information and the minimum channel state information corresponding to the multi-frame data on the channel is determined, and the difference is determined as the change amount of the channel state information corresponding to the multi-frame data on the channel. In this way, the change amount of the channel state information corresponding to the multi-frame data on each channel is obtained.

[0144] In another manner, for each channel, according to the channel state information corresponding to the multi-frame data on the channel, the variance of the channel state information corresponding to the multi-frame data on the channel is determined, and the variance is determined as the amount of change in the channel state information corresponding to the multi-frame data on the channel. For example, taking the above matrix as an example, for each row in the above matrix, the variance of the channel state information of the row is calculated, and the variance is determined as the amount of change in the channel state information corresponding to the multi-frame data on the channel.

[0145] In accordance with the above method, the change in channel state information corresponding to the multi-frame data received by each microphone on each channel is determined, and then the microphone with the largest change in channel state information is determined as the target microphone, and the breathing detection related parameters corresponding to each channel are determined based on the channel state information corresponding to the multi-frame data received by the target microphone.

[0146] It should be understood that after the target microphone for performing breathing detection is determined, subsequent operations are performed according to the channel state information corresponding to the multiple frames of data received by the target microphone.

[0147] In the present disclosure, the breathing detection related parameter may be a parameter related to breathing. For example, the breathing detection related parameter may include a change in the channel state information used to characterize the impact of the amplitude of chest cavity changes caused by breathing on the channel, and / or an autocorrelation value of the channel state information used to characterize the periodicity of breathing.

[0148] For example, the breathing detection related parameters include the autocorrelation value of the channel state information, and accordingly, the preset threshold condition includes that the autocorrelation value of the channel state information is greater than a first preset threshold; and / or, the breathing detection related parameters include the change amount of the channel state information, and accordingly, the preset threshold condition includes that the change amount of the channel state information is greater than a second preset threshold.

[0149] In one embodiment, the breathing detection related parameters include the change amount of the channel state information. Accordingly, Figure 4 In step S41, the specific implementation method of determining the respiration detection related parameters corresponding to each channel according to the channel state information corresponding to the multi-frame data is as follows: for each channel, the variance of the channel state information is determined according to the channel state information corresponding to the multi-frame data on the channel, and the variance is determined as the change in the channel state information corresponding to the multi-frame data on the channel.

[0150] The specific manner of determining the variance of the channel state information has been described in the above embodiment of determining the target microphone for performing breathing detection, and will not be repeated here.

[0151] In this embodiment, after determining the amount of change in channel state information corresponding to the multi-frame data on each channel, the channel whose amount of change in channel state information is greater than the second preset threshold is determined as the first target channel. If the first target channel exists, it is determined that there is breathing behavior in the preset space, otherwise it is determined that there is no breathing behavior in the preset space.

[0152] In another embodiment, the breathing detection related parameter includes an autocorrelation value of the channel state information. Accordingly, Figure 4 In step S41, the specific implementation method of determining the respiration detection related parameters corresponding to each channel according to the channel state information corresponding to the multi-frame data is as follows: for each channel, according to the channel state information corresponding to the multi-frame data on the channel, determine the autocorrelation function of the channel state information, and determine the autocorrelation value of the channel state information corresponding to the multi-frame data on the channel according to the autocorrelation function.

[0153] It should be understood that, since breathing is periodic, the autocorrelation function of the channel state information is also approximately periodic. In this embodiment, breathing behavior can be detected based on the autocorrelation value of the channel state information. For example, after determining the autocorrelation function of the channel state information, in the autocorrelation represented by the autocorrelation function, the mean of a preset number of alternating peak and trough values ​​is determined as the autocorrelation value of the channel state information corresponding to the multi-frame data on the channel. For example, the mean of the first 6 alternating peak and trough values ​​in the autocorrelation is determined as the autocorrelation value of the channel state information corresponding to the multi-frame data on the channel.

[0154] In this embodiment, after determining the autocorrelation value of the channel state information corresponding to the multi-frame data on each channel, the channel whose autocorrelation value is greater than the first preset threshold is determined as the first target channel. If the first target channel exists, it is determined that there is a breathing behavior in the preset space, otherwise it is determined that there is no breathing behavior in the preset space.

[0155] In yet another embodiment, the breathing detection related parameters include the autocorrelation value of the channel state information and the change amount of the channel state information, and the preset threshold conditions include that the autocorrelation value of the channel state information is greater than a first preset threshold and the change amount of the channel state information is greater than a second preset threshold.

[0156] In this embodiment, the autocorrelation value and the variation of the channel state information corresponding to the multi-frame data on each channel are determined respectively in the manner described in the above embodiment. Afterwards, the channel whose autocorrelation value is greater than the first preset threshold and whose variation is greater than the second preset threshold is determined as the first target channel. If the first target channel exists, it is determined that there is a breathing behavior in the preset space, otherwise it is determined that there is no breathing behavior in the preset space.

[0157] Considering that in actual applications, the number of frames of data included in the sound wave signal is relatively large, if the respiratory information in the preset space is determined based on all the frame data included in the sound wave signal, the amount of calculation is relatively large. Therefore, in one way, the respiratory information in the preset space can be determined based on part of the frame data in each breathing detection cycle. Accordingly, the specific implementation method of determining the respiratory information in the preset space based on the channel state information corresponding to the multiple frames of data is: determining a first preset number of first target frame data from the multiple frames of data; and determining the respiratory information in the preset space based on the channel state information corresponding to the first target frame data.

[0158] For example, a sliding window may be used to select a first preset number of first target frame data from all frame data, wherein the height of the sliding window is M and the width is the value of the first preset number. For example, assuming that the first preset number is 30, in the first breathing detection cycle, the breathing information in the preset space is determined according to the channel state information corresponding to the first frame data to the thirtieth frame data, and in the second breathing detection cycle, the breathing information in the preset space is determined according to the channel state information corresponding to the second frame data to the thirty-first frame data, and so on.

[0159] In one embodiment, when it is determined that there is breathing behavior in the preset space, the breathing frequency of the living thing can be further determined. For example, the living thing detection method provided by the present disclosure can also include:

[0160] Determine the first target channel with the largest change in channel state information as the second target channel for this detection;

[0161] The breathing frequency of the living thing in the preset space is determined according to the autocorrelation function of the channel state information corresponding to the multi-frame data on the second target channel detected this time.

[0162] In the present disclosure, the channel with a larger change in channel state information can better characterize the breathing behavior of the living thing, and therefore, the breathing frequency of the living thing can be determined based on the corresponding channel state information on the second target channel with the largest change in channel state information. In addition, as shown above, the autocorrelation value of the channel state information can characterize the breathing cycle, and therefore, the autocorrelation function of the channel state information corresponding to the second target channel detected in this detection of multiple frames of data is used to determine the breathing frequency of the living thing existing in the preset space.

[0163] For example, according to the autocorrelation function of the channel state information corresponding to the second target channel, each cycle is calculated according to adjacent peaks and troughs in the autocorrelation function, and the average value of each cycle is determined as the breathing cycle, thereby determining the breathing frequency. For example, the time difference between the first peak and the first trough is determined as the first cycle, the time difference between the first trough and the second peak is determined as the second cycle, and the time difference between the second peak and the second trough is determined as the third cycle, and then the average value of the first cycle, the second cycle and the third cycle is determined as the breathing cycle.

[0164] It should be understood that in the embodiment in which the breathing information in the preset space can be determined according to part of the frame data in each breathing detection cycle, the second target channel for this detection can be determined for each breathing detection cycle.

[0165] In another embodiment, the living thing detection method provided by the present disclosure may further include:

[0166] Determine the second target channel detected last time, and the current breathing detection related parameters corresponding to the second target channel detected last time;

[0167] If the current breathing detection related parameters corresponding to the second target channel still meet the preset threshold conditions, the breathing frequency of the living thing in the preset space is determined according to the current autocorrelation function of the channel state information corresponding to the second target channel detected last time by the multi-frame data.

[0168] It should be understood that different detection cycles use different data frames, and thus the channel state information used to determine the breathing detection related parameters corresponding to each channel is not completely the same. Therefore, in different detection cycles, the breathing detection related parameters corresponding to the same channel are different. That is, the current breathing detection related parameters corresponding to the second target channel detected last time may be different from the breathing detection related parameters corresponding to the last detection.

[0169] In this embodiment, if the current breathing detection related parameters corresponding to the second target channel detected last time still meet the preset threshold conditions, the breathing frequency of the living thing in the preset space is determined directly based on the period of the autocorrelation function of the channel state information corresponding to the multi-frame data on the second target channel detected last time.

[0170] Accordingly, determining the first target channel with the largest change in channel state information as the second target channel for this detection includes:

[0171] Determining that the current breathing detection related parameter corresponding to the second target channel detected last time does not meet the preset threshold condition;

[0172] The first target channel with the largest change in channel state information is determined as the second target channel for this detection.

[0173] In this embodiment, the current respiration detection related parameters corresponding to the second target channel detected last time still meet the preset threshold conditions, and the respiration frequency of the living thing existing in the preset space is determined according to the autocorrelation function of the channel state information corresponding to the second target channel detected last time by the multi-frame data, and when the current respiration detection related parameters corresponding to the second target channel detected last time no longer meet the preset threshold conditions, the first target channel with the largest change in channel state information is determined as the second target channel detected this time. In this way, switching back and forth of the determined second target channel is avoided.

[0174] In the present disclosure, the living thing detection method may further include:

[0175] Display and / or report the determination result for indicating whether there is a living thing in the preset space.

[0176] For example, the determination result is displayed to achieve visualization. For another example, the determination result is reported to the application layer so that the application layer combines the data detected by other sensors with the determination result to perform corresponding actions.

[0177] The following is a complete example of a method for detecting living things provided by the present disclosure. Figure 5 FIG. 1 is a flow chart of another method for detecting living things according to an exemplary embodiment. Figure 5 As shown, the living thing detection method may include the following steps.

[0178] In step S51, a first sound wave signal is generated, and at least one speaker is controlled to emit the first sound wave signal in a preset space.

[0179] In step S52, at least one microphone is controlled to collect a second sound wave signal in a preset space, where the second sound wave signal is generated based on the first sound wave signal.

[0180] In step S53, channel state information corresponding to the multiple frames of data is determined according to the first sound wave signal and the second sound wave information.

[0181] In step S54, the target dynamic and static states of the objects in the preset space are determined according to the channel state information corresponding to the multiple frames of data.

[0182] In step S55 , if the target static / dynamic state of the object is a moving state, it is determined that there is a living thing in the preset space.

[0183] In step S56, if the target dynamic and static state of the object is not a moving state, the breathing information in the preset space is determined according to the channel state information corresponding to the multiple frames of data.

[0184] In step S57 , if the breathing information indicates that there is breathing behavior in the preset space, it is determined that there is a living thing in the preset space.

[0185] In step S58, the determination result indicating the presence of a living thing is displayed and / or reported.

[0186] Regarding each step in the above embodiment, the specific method of each step has been described in detail in the above embodiment and will not be elaborated here.

[0187] Based on the same inventive concept, the present disclosure also provides a passenger detection method. Figure 6 FIG. 1 is a flow chart of a passenger detection method according to an exemplary embodiment. Figure 6 As shown, the passenger detection method may include the following steps.

[0188] In step S61, it is determined whether the seat in the vehicle cabin is in an occupied state.

[0189] In step S62, when the seat is in an occupied state and the result of the living thing detection in the cabin is that a living thing exists, it is determined that there is a passenger in the cabin.

[0190] Among them, according to the living thing detection method provided by the present disclosure, the living thing detection result in the vehicle cabin is obtained.

[0191] In the present disclosure, a pressure sensor disposed on the seat can be used to detect whether the seat in the vehicle cabin is in an occupied state. For example, a pressure signal of the seat in the vehicle cabin is obtained; if the pressure value represented by the pressure signal is within a preset range, it is determined that the seat is in an occupied state. The preset range is determined according to the weight range of the passenger.

[0192] It should be understood that if the presence of a passenger on the seat is detected only by the pressure value detected by the pressure sensor arranged on the seat, the object placed on the seat will be mistakenly detected as a passenger, which will lead to the smart cockpit outputting an erroneous decision. Therefore, in the present disclosure, in order to improve the accuracy of passenger detection, when the seat is determined to be occupied according to the pressure signal detected by the pressure sensor, it is further determined whether the object placed on the seat is a living thing according to the living thing detection method provided by the present disclosure. If it is a living thing, it is determined that the object on the seat is a passenger, that is, it is determined that there is a passenger in the cabin, otherwise it is determined that there is no passenger in the cabin.

[0193] By adopting the above technical solution, when the seat is occupied, the presence of passengers in the cabin can be determined in combination with the results of living thing detection in the cabin, thereby effectively improving the efficiency of passenger detection in the cabin and enhancing the user experience.

[0194] In addition, after determining that there is a passenger in the cabin, the passenger detection method may also include at least one of the following steps: outputting prompt information; controlling the vehicle in which the cabin is located to power on; and starting the air conditioner in the cabin.

[0195] For example, after determining that there is a passenger in the cabin, a prompt message is output, wherein the prompt message may be a prompt message to the driver that there is a passenger left in the cabin, or a message to the passenger to fasten the seat belt, etc. This disclosure does not specifically limit this.

[0196] For another example, after determining that there are passengers in the cabin, the vehicle in which the cabin is located is controlled to be powered on. In this way, after the vehicle is powered on, the passenger can use the power on the vehicle to meet their needs, for example, turn on the air conditioner in the car, charge a mobile phone, or start the vehicle, etc.

[0197] For another example, after determining that there are passengers in the cabin, the cabin air conditioner is started. In this way, when the vehicle is in a closed state and the driver is not in the vehicle, after determining that there are passengers in the cabin, the cabin air conditioner is automatically started to prevent the passengers left in the cabin from suffocating and ensure the safety of the passengers in the cabin.

[0198] The adoption of the above technical solution further improves the intelligence level of the passenger detection method and further enhances the user experience.

[0199] Based on the same inventive concept, the present disclosure also provides a living thing detection device. Figure 7 FIG. 1 is a block diagram of a living thing detection device according to an exemplary embodiment. Figure 7 As shown, the living thing detection device 700 may include:

[0200] The first control module 701 is configured to control the speaker to emit a first sound wave signal in a preset space;

[0201] A second control module 702 is configured to control the microphone to collect a second sound wave signal in the preset space, where the second sound wave signal is generated based on the first sound wave signal;

[0202] A first determining module 703 is configured to determine channel state information corresponding to the second sound wave signal according to the first sound wave signal and the second sound wave signal;

[0203] The second determination module 704 is configured to determine whether there is a living thing in the preset space according to the channel state information corresponding to the second sound wave signal.

[0204] Optionally, both the first sound wave signal and the second sound wave signal include multiple frames of data; accordingly, the channel state information corresponding to the second sound wave signal includes the channel state information corresponding to the multiple frames of data.

[0205] Optionally, the second determining module 704 includes:

[0206] A first determination submodule is configured to determine a target dynamic or static state of an object in the preset space according to channel state information corresponding to the multiple frames of data;

[0207] The second determination submodule is configured to determine that there is a living thing in the preset space if the target static and dynamic state of the object is a moving state.

[0208] Optionally, the speaker sends out the multiple frames of data in sequence; and the first determining submodule includes:

[0209] a change amount determination submodule, configured to determine a change amount of the channel state information corresponding to each frame of data according to the channel state information corresponding to each frame of data in the multiple frames of data;

[0210] A first target dynamic and static state determination submodule is configured to determine, for each frame of data, a first target dynamic and static state of the object when the frame of data is transmitted according to a change amount of the channel state information corresponding to the frame of data;

[0211] The target motion state determination submodule is configured to determine the target motion state of the object in the preset space according to the first target motion state of the object when each frame of data is transmitted.

[0212] Optionally, there are multiple microphones; the first determination module 703 is configured to: for each microphone, determine the channel state information corresponding to the multiple frames of data received by the microphone according to the first sound wave signal and the second sound wave signal collected by the microphone;

[0213] Correspondingly, the first target dynamic and static state determination submodule is configured as: for each of the microphones, determining the second target dynamic and static state of the object when transmitting each frame of data received by the microphone based on the change in channel state information corresponding to the multiple frames of data received by the microphone; for each frame of data, determining the first target dynamic and static state of the object when transmitting the frame data based on the second target dynamic and static state of the object when transmitting the frame data received by each of the microphones.

[0214] Optionally, the first target motion / still state determination submodule is configured as follows: if the number of the second target motion / still state being a moving state is greater than the number of the second target motion / still state being a stationary state, then determining that the third target motion / still state of the object is a moving state when transmitting the frame data; and, if the number of the second target motion / still state being a moving state is not greater than the number of the second target motion / still state being a stationary state, then determining that the third target motion / still state of the object is a stationary state when transmitting the frame data; and determining the first target motion / still state of the object when transmitting the frame data based on the third target motion / still state of the object when transmitting the frame data.

[0215] Optionally, the first target motion and still state determination submodule is configured to: determine the third target motion and still state of the object when transmitting the frame data as the first target motion and still state of the object when transmitting the frame data; or, perform state filtering processing on the third target motion and still state of the object when transmitting the frame data, and determine the third target motion and still state after the state filtering processing as the first target motion and still state of the object when transmitting the frame data.

[0216] Optionally, the first target motion / still state determination submodule is configured to: determine that the second target motion / still state of the object is a motion state when the change in the transmission channel state information is greater than the frame data of a first preset threshold, and determine that the second target motion / still state of the object is a stationary state when the change in the transmission channel state information is not greater than the frame data of the first preset threshold.

[0217] Optionally, each frame of data includes M data, and the M data are transmitted on M channels respectively, where M is an integer greater than 1; the change amount determination submodule is configured to: for each channel, determine the difference in channel state information corresponding to different frame data on the channel according to the channel state information corresponding to each frame of data on the channel and a preset step size, so as to obtain a deviation value of the channel state information corresponding to each frame of data on each channel; for each frame of data, determine the variance of the deviation value according to the deviation value of the channel state information corresponding to the frame data on each channel, and determine the variance as the change amount of the channel state information corresponding to the frame data.

[0218] Optionally, the first determining submodule further includes:

[0219] The filtering processing submodule is configured to perform mean filtering on the variation of the channel state information corresponding to each frame of data to obtain a processed variation;

[0220] The first target dynamic and static state determination submodule is configured to: for each frame of data, determine the first target dynamic and static state of the object when transmitting the frame of data according to the processed change amount of the channel state information corresponding to the frame of data.

[0221] Optionally, the target dynamic and static state determination submodule is configured to: determine a first preset number of first target frame data from multiple frames of data; and determine the target dynamic and static state of the object in the preset space based on the first target dynamic and static state of the object when transmitting each of the first target frame data.

[0222] Optionally, the second determining module 704 further includes:

[0223] A third determination submodule is configured to determine the breathing information in the preset space according to the channel state information corresponding to the multiple frames of data if the target dynamic and static state of the object is not a motion state;

[0224] The fourth determination submodule is configured to determine that there is a living thing in the preset space if the breathing information indicates that there is breathing behavior in the preset space; and determine that there is no living thing in the preset space if the breathing information indicates that there is no breathing behavior in the preset space.

[0225] Optionally, each frame of data includes M data, and the M data are transmitted on M channels respectively, where M is an integer greater than 1; and the third determining submodule includes:

[0226] a fifth determination submodule, configured to determine a respiration detection related parameter corresponding to each channel according to the channel state information corresponding to the multiple frames of data;

[0227] a sixth determination submodule, configured to determine that there is a breathing behavior in the preset space if there is a first target channel whose breathing detection related parameters meet a preset threshold condition;

[0228] The seventh determination submodule is configured to determine that there is no breathing behavior in the preset space if there is no first target channel whose breathing detection related parameters meet the preset threshold condition.

[0229] Optionally, the breathing detection related parameter includes an autocorrelation value of the channel state information, and accordingly, the preset threshold condition includes that the autocorrelation value of the channel state information is greater than a first preset threshold; and / or

[0230] The breathing detection related parameter includes a change amount of channel state information. Accordingly, the preset threshold condition includes that the change amount of the channel state information is greater than a second preset threshold.

[0231] Optionally, the breathing detection related parameters include the autocorrelation value of the channel state information; the fifth determination submodule is configured to: for each channel, determine the autocorrelation function of the channel state information according to the channel state information corresponding to the multiple frames of data on the channel, and determine the autocorrelation value of the channel state information corresponding to the multiple frames of data on the channel according to the autocorrelation function.

[0232] Optionally, the breathing detection related parameters include the change in the channel state information; the fifth determination submodule is configured to: for each channel, determine the variance of the channel state information according to the channel state information corresponding to the multi-frame data on the channel, and determine the variance as the change in the channel state information corresponding to the multi-frame data on the channel.

[0233] Optionally, the living thing detection device 700 may further include:

[0234] A third determination module is configured to determine the first target channel with the largest change in channel state information as the second target channel for this detection;

[0235] The fourth determination module is configured to determine the breathing frequency of the living thing existing in the preset space according to the autocorrelation function of the channel state information corresponding to the multiple frames of data on the second target channel detected this time.

[0236] Optionally, the living thing detection device 700 may further include:

[0237] a fifth determination module, configured to determine a second target channel detected last time, and current breathing detection related parameters corresponding to the second target channel detected last time;

[0238] a sixth determination module, configured to determine the breathing frequency of the living being in the preset space according to the autocorrelation function of the channel state information corresponding to the multi-frame data on the second target channel detected last time, if the current breathing detection related parameter corresponding to the second target channel detected last time still meets the preset threshold condition;

[0239] Accordingly, the third determination module is configured to: determine that the current breathing detection related parameters corresponding to the second target channel detected last time do not meet the preset threshold condition; and determine the first target channel with the largest change in channel state information as the second target channel detected this time.

[0240] Optionally, there are multiple microphones, and the channel state information corresponding to the multi-frame data includes the channel state information corresponding to the multi-frame data received by each of the multiple microphones; the fifth determination submodule is configured to: for each microphone, determine the change in channel state information corresponding to the multi-frame data received by the microphone on each channel according to the channel state information corresponding to the multi-frame data received by the microphone; determine the microphone with the largest change in channel state information as the target microphone; and determine the breathing detection related parameters corresponding to each channel according to the channel state information corresponding to the multi-frame data received by the target microphone.

[0241] Optionally, the third determination submodule is configured as follows: if the target dynamic or static state of the object is not a motion state, filtering the channel state information corresponding to the multiple frames of data to obtain the channel state information corresponding to the multiple frames of data after filtering; and determining the breathing information within the preset space based on the channel state information corresponding to the multiple frames of data after filtering.

[0242] Optionally, the living thing detection device 700 may further include:

[0243] The processing module is configured to display and / or report a determination result indicating whether there is a living thing in the preset space.

[0244] Optionally, each frame data included in the first sound wave signal is generated based on the first baseband signal corresponding to it; the first determination module 703 is configured to: identify multiple frames of data included in the second sound wave signal according to the cross-correlation between the first sound wave signal and the second sound wave signal; for each frame data, demodulate the frame data to obtain the second baseband signal corresponding to the frame data, and determine the channel state information corresponding to the frame data according to the second baseband signal and the first baseband signal corresponding to the frame data.

[0245] Optionally, the first determination module 703 is configured to: determine a frequency response of a baseband signal according to the second baseband signal and a first baseband signal corresponding to the frame data; and determine the frequency response of the baseband signal as channel state information corresponding to the frame data.

[0246] Optionally, the first determination module 703 is further configured to: determine a channel impulse response according to a frequency response of the baseband signal; and determine the channel impulse response as channel state information corresponding to the frame data.

[0247] Optionally, the first sound wave signal is generated in the following manner:

[0248] Generate a plurality of frames of first baseband signals having autocorrelation values ​​greater than a third preset threshold;

[0249] The multiple frames of first baseband signals are modulated into ultrasonic frequency band signals, and the ultrasonic frequency band signals are determined as first sound wave signals.

[0250] Based on the same inventive concept, the present disclosure also provides a passenger detection device. Figure 8 FIG. 1 is a block diagram of a passenger detection device according to an exemplary embodiment. Figure 8 As shown, the passenger detection device 800 may include:

[0251] The seventh determination module 801 is configured to determine whether a seat in the vehicle cabin is occupied;

[0252] An eighth determination module 802 is configured to determine that there is a passenger in the cabin when the seat is in the occupied state and the living thing detection result in the cabin indicates that there is a living thing;

[0253] Among them, the living thing detection result in the cabin is obtained according to the living thing detection method described in the present disclosure.

[0254] Optionally, the seventh determination module 801 is configured to: obtain a pressure signal of a seat in the vehicle cabin; if a pressure value represented by the pressure signal is within a preset range, determine that the seat is in an occupied state.

[0255] Optionally, after determining that there is a passenger in the cabin, the passenger detection device 800 further includes:

[0256] The execution module is configured to execute at least one of the following after determining that there is a passenger in the cabin: output a prompt message; control the vehicle where the cabin is located to power on; and start the air conditioner of the cabin.

[0257] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0258] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the steps of the living thing detection method provided by the present disclosure, or implement the steps of the living thing detection method provided by the present disclosure.

[0259] Fig. 9 900 is a block diagram of a vehicle according to an exemplary embodiment. For example, vehicle 900 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. Vehicle 900 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0260] Reference Fig. 9, the vehicle 900 may include various subsystems, for example, an infotainment system 910, a perception system 920, a decision control system 930, a drive system 940, and a computing platform 950. The vehicle 900 may also include more or fewer subsystems, and each subsystem may include multiple components. In addition, each subsystem and each component of the vehicle 900 may be interconnected by wire or wireless means.

[0261] In some embodiments, the infotainment system 910 may include a communication system, an entertainment system, and a navigation system, etc.

[0262] The perception system 920 may include several sensors for sensing information about the environment around the vehicle 900. For example, the perception system 920 may include a global positioning system (the global positioning system may be a GPS system, or a Beidou system or other positioning systems), an inertial measurement unit (IMU), a laser radar, a millimeter wave radar, an ultrasonic radar, and a camera.

[0263] The decision control system 930 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0264] The drive system 940 may include components that provide powered motion for the vehicle 900. In one embodiment, the drive system 940 may include an engine, an energy source, a transmission system, and wheels. The engine may be a combination of one or more of an internal combustion engine, an electric motor, and an air compression engine. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0265] Some or all functions of the vehicle 900 are controlled by a computing platform 950. The computing platform 950 may include at least one processor 951 and a memory 952, and the processor 951 may execute instructions 953 stored in the memory 952.

[0266] The processor 951 may be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable Gate Array, FPGA), a system on chip (System on Chip, SOC), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or a combination thereof.

[0267] The memory 952 may be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0268] In addition to instructions 953 , memory 952 may also store data, such as road maps, route information, vehicle location, direction, speed, etc. The data stored in memory 952 may be used by computing platform 950 .

[0269] In the embodiment of the present disclosure, the processor 951 may execute instruction 953 to complete all or part of the steps of the above-mentioned living thing detection method or passenger detection method.

[0270] Fig.10 1 is a block diagram of an electronic device according to an exemplary embodiment. For example, the electronic device 1000 may be provided as a server. Fig.10 , the electronic device 1000 includes a processing component 1022, which further includes one or more processors, and a memory resource represented by a memory 1032 for storing instructions that can be executed by the processing component 1022, such as an application. The application stored in the memory 1032 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1022 is configured to execute instructions to perform the above-mentioned living thing detection method or the above-mentioned passenger detection method. The electronic device 1000 may also include a power supply component 1026 configured to perform power management of the device 1000, a wired or wireless network interface 1050 configured to connect the electronic device 1000 to a network, and an input / output interface 1058. The electronic device 1000 can operate based on an operating system stored in the memory 1032.

[0271] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned living thing detection method or the above-mentioned passenger detection method when executed by the programmable device.

[0272] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0273] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for detecting living things, characterized in that: include: Controlling the loudspeaker to emit a first sound wave signal in a preset space; Controlling the microphone to collect a second sound wave signal in the preset space, where the second sound wave signal is generated based on the first sound wave signal; Determine, according to the first sound wave signal and the second sound wave signal, channel state information corresponding to the second sound wave signal; Determine whether there is a living thing in the preset space according to the channel state information corresponding to the second sound wave signal.

2. The method for detecting living things according to claim 1, characterized in that: The first sound wave signal and the second sound wave signal both include multiple frames of data; accordingly, the channel state information corresponding to the second sound wave signal includes the channel state information corresponding to the multiple frames of data.

3. The method for detecting living things according to claim 2, characterized in that: The determining, according to the channel state information corresponding to the second sound wave signal, whether there is a living thing in the preset space includes: Determining a target dynamic or static state of an object in the preset space according to channel state information corresponding to the multiple frames of data; If the target dynamic and static state of the object is a moving state, it is determined that there is a living thing in the preset space.

4. The method for detecting living things according to claim 3, characterized in that: The speaker sends out the multiple frames of data in sequence; and determining the target dynamic and static state of the object in the preset space according to the channel state information corresponding to the multiple frames of data includes: Determine, according to the channel state information corresponding to each frame of data in the multiple frames of data, a change amount of the channel state information corresponding to each frame of data; For each frame of data, determining a first target dynamic or static state of the object when transmitting the frame of data according to a change amount of the channel state information corresponding to the frame of data; The target dynamic and static state of the object in the preset space is determined according to the first target dynamic and static state of the object when each frame of data is transmitted.

5. The method for detecting living things according to claim 4, characterized in that: The number of the microphones is multiple; and the determining, according to the first sound wave signal and the second sound wave signal, the channel state information corresponding to the second sound wave signal comprises: For each of the microphones, determining channel state information corresponding to multiple frames of data received by the microphone according to the first sound wave signal and the second sound wave signal collected by the microphone; Correspondingly, for each frame of data, determining the first target dynamic and static state of the object when transmitting the frame of data according to the change amount of the channel state information corresponding to the frame of data includes: For each of the microphones, determining a second target dynamic and static state of the object when transmitting each frame of data received by the microphone according to a change amount of the channel state information corresponding to the multiple frames of data received by the microphone; For each frame of data, the first target dynamic and static state of the object when transmitting the frame of data is determined according to the second target dynamic and static state of the object when transmitting the frame of data received by each microphone.

6. The method for detecting living things according to claim 5, characterized in that: The determining, according to the second target dynamic and static state of the object when transmitting the frame data received by each microphone, the first target dynamic and static state of the object when transmitting the frame data comprises: If the number of the second target motion-static state being the moving state is greater than the number of the second target motion-static state being the stationary state, determining that the third target motion-static state of the object is the moving state when the frame data is transmitted, and if the number of the second target motion-static state being the moving state is not greater than the number of the second target motion-static state being the stationary state, determining that the third target motion-static state of the object is the stationary state when the frame data is transmitted; The first target motion state of the object when transmitting the frame data is determined according to the third target motion state of the object when transmitting the frame data.

7. The method for detecting living things according to claim 6, characterized in that: The determining, according to the third target motion state of the object when transmitting the frame data, the first target motion state of the object when transmitting the frame data comprises: determining the third target motion / still state of the object when transmitting the frame data as the first target motion / still state of the object when transmitting the frame data; or A state filtering process is performed on the third target motion and still state of the object when the frame data is transmitted, and the third target motion and still state after the state filtering process is determined as the first target motion and still state of the object when the frame data is transmitted.

8. The method for detecting living things according to claim 5, characterized in that: The determining, according to the change amount of the channel state information corresponding to the multiple frames of data received by the microphone, the second target dynamic and static state of the object when transmitting each frame of data received by the microphone comprises: Determine that the second target dynamic and static state of the object is a moving state when the change in the transmission channel state information is greater than the frame data of the first preset threshold, and determine that the second target dynamic and static state of the object is a stationary state when the change in the transmission channel state information is not greater than the frame data of the first preset threshold.

9. The method for detecting living things according to claim 4, characterized in that: Each frame of data includes M data, and the M data are transmitted on M channels respectively, where M is an integer greater than 1; The determining, according to the channel state information corresponding to each frame of data in the multiple frames of data, a change amount of the channel state information corresponding to each frame of data, comprises: For each channel, according to the channel state information corresponding to each frame of data on the channel and a preset step size, determine the difference of the channel state information corresponding to different frames of data on the channel, so as to obtain a deviation value of the channel state information corresponding to each frame of data on each channel; For each frame of data, the variance of the deviation value is determined according to the deviation value of the channel state information corresponding to the frame of data on each channel, and the variance is determined as the change amount of the channel state information corresponding to the frame of data.

10. The method for detecting living things according to claim 4, characterized in that: The determining, according to the channel state information corresponding to the multiple frames of data, the target dynamic and static state of the object in the preset space also includes: Performing mean filtering on the variation of the channel state information corresponding to each frame of data to obtain the processed variation; The determining, for each frame of data, according to a change amount of channel state information corresponding to the frame of data, a first target dynamic and static state of the object when the frame of data is transmitted, includes: For each frame of data, a first target dynamic or static state of the object when the frame of data is transmitted is determined according to a processed change amount of the channel state information corresponding to the frame of data.

11. The method for detecting living things according to claim 4, characterized in that: The determining the target dynamic and static state of the object in the preset space according to the first target dynamic and static state of the object when transmitting each frame of data includes: Determine a first preset number of first target frame data from the multiple frame data; The target dynamic and static states of the objects in the preset space are determined according to the first target dynamic and static states of the objects when the first target frame data are transmitted.

12. The method for detecting living things according to claim 3, characterized in that: The determining whether there is a living thing in the preset space according to the channel state information corresponding to the second sound wave signal also includes: If the target static / dynamic state of the object is not a moving state, determining the breathing information in the preset space according to the channel state information corresponding to the multiple frames of data; If the breathing information indicates that there is breathing behavior in the preset space, it is determined that there is a living thing in the preset space; If the breathing information indicates that there is no breathing behavior in the preset space, it is determined that there is no living thing in the preset space.

13. The method for detecting living things according to claim 12, characterized in that: Each frame of data includes M data, and the M data are transmitted on M channels respectively, where M is an integer greater than 1; and determining the breathing information in the preset space according to the channel state information corresponding to the multiple frames of data includes: Determine breathing detection related parameters corresponding to each channel according to channel state information corresponding to the multiple frames of data; If there is a first target channel whose breathing detection related parameters meet the preset threshold conditions, determining that there is breathing behavior in the preset space; If there is no first target channel whose breathing detection related parameters meet the preset threshold conditions, it is determined that there is no breathing behavior in the preset space.

14. The method for detecting living things according to claim 13, characterized in that: The breathing detection related parameter includes an autocorrelation value of the channel state information, and accordingly, the preset threshold condition includes that the autocorrelation value of the channel state information is greater than a first preset threshold; and / or The breathing detection related parameter includes a change amount of channel state information. Accordingly, the preset threshold condition includes that the change amount of the channel state information is greater than a second preset threshold.

15. The method for detecting living things according to claim 13, characterized in that: The respiration detection related parameter includes an autocorrelation value of the channel state information; and determining the respiration detection related parameter corresponding to each channel according to the channel state information corresponding to the multiple frames of data includes: For each channel, an autocorrelation function of the channel state information corresponding to the multiple frames of data on the channel is determined, and an autocorrelation value of the channel state information corresponding to the multiple frames of data on the channel is determined based on the autocorrelation function.

16. The method for detecting living things according to claim 13, characterized in that: The respiration detection related parameter includes a change amount of the channel state information; and determining the respiration detection related parameter corresponding to each channel according to the channel state information corresponding to the multiple frames of data includes: For each channel, the variance of the channel state information corresponding to the multiple frames of data on the channel is determined, and the variance is determined as a change in the channel state information corresponding to the multiple frames of data on the channel.

17. The method for detecting living things according to claim 13, characterized in that: The method further comprises: Determine the first target channel with the largest change in channel state information as the second target channel for this detection; The breathing frequency of the living thing in the preset space is determined according to the autocorrelation function of the channel state information corresponding to the multiple frames of data on the second target channel detected this time.

18. The method for detecting living things according to claim 17, characterized in that: The method further comprises: Determine the second target channel detected last time, and the current breathing detection related parameters corresponding to the second target channel detected last time; If the current breathing detection related parameter corresponding to the second target channel detected last time still meets the preset threshold condition, determining the breathing frequency of the living thing existing in the preset space according to the current autocorrelation function of the channel state information corresponding to the multi-frame data on the second target channel detected last time; Determining the first target channel with the largest change in the channel state information as the second target channel for this detection includes: Determining that the current breathing detection related parameter corresponding to the second target channel detected last time does not meet the preset threshold condition; The first target channel with the largest change in channel state information is determined as the second target channel for this detection.

19. The method for detecting living things according to claim 13, characterized in that: There are multiple microphones, and the channel state information corresponding to the multiple frames of data includes channel state information corresponding to the multiple frames of data received by each of the multiple microphones; The determining, according to the channel state information corresponding to the multiple frames of data, the breathing detection related parameters corresponding to each channel includes: For each microphone, determining, according to the channel state information corresponding to the multiple frames of data received by the microphone, a change amount of the channel state information corresponding to the multiple frames of data received by the microphone on each channel; The microphone with the largest change in channel state information is determined as the target microphone; The breathing detection related parameters corresponding to each channel are determined according to the channel state information corresponding to the multiple frames of data received by the target microphone.

20. The method for detecting living things according to claim 12, characterized in that: If the target static and dynamic state of the object is not a moving state, determining the breathing information in the preset space according to the channel state information corresponding to the multiple frames of data includes: If the target static / dynamic state of the object is not a moving state, filtering the channel state information corresponding to the multiple frames of data to obtain the channel state information corresponding to the multiple frames of data after filtering; The breathing information in the preset space is determined according to the channel state information corresponding to the multiple frames of data after filtering.

21. The method for detecting living things according to any one of claims 1 to 20, characterized in that: The method further comprises: Display and / or report a determination result indicating whether there is a living thing in the preset space.

22. The method for detecting living things according to any one of claims 2 to 20, characterized in that: Each frame of data included in the first sound wave signal is generated based on the first baseband signal corresponding to the first sound wave signal; and determining the channel state information corresponding to the second sound wave signal according to the first sound wave signal and the second sound wave signal, including: identifying, according to the cross-correlation between the first sound wave signal and the second sound wave signal, a plurality of frames of data included in the second sound wave signal; For each frame of data, the frame data is demodulated to obtain a second baseband signal corresponding to the frame data, and channel state information corresponding to the frame data is determined based on the second baseband signal and a first baseband signal corresponding to the frame data.

23. The method for detecting living things according to claim 22, characterized in that: The determining, according to the second baseband signal and the first baseband signal corresponding to the frame data, the channel state information corresponding to the frame data includes: determining a frequency response of a baseband signal according to the second baseband signal and a first baseband signal corresponding to the frame data; The frequency response of the baseband signal is determined as the channel state information corresponding to the frame data.

24. The method for detecting living things according to claim 23, characterized in that: The determining, according to the second baseband signal and the first baseband signal corresponding to the frame data, the channel state information corresponding to the frame data further includes: determining a channel impulse response according to a frequency response of the baseband signal; The channel impulse response is determined as channel state information corresponding to the frame data.

25. The method for detecting living things according to any one of claims 1 to 20, characterized in that: The first sound wave signal is generated by: Generate a plurality of frames of first baseband signals having autocorrelation values ​​greater than a third preset threshold; The multiple frames of first baseband signals are modulated into ultrasonic frequency band signals, and the ultrasonic frequency band signals are determined as first sound wave signals.

26. A passenger detection method, characterized in that: The method comprises: Determine whether the seats in the cabin are occupied; When the seat is in the occupied state and the living thing detection result in the vehicle cabin indicates that a living thing exists, determining that a passenger exists in the vehicle cabin; Wherein, the living thing detection result in the cabin is determined according to the living thing detection method according to any one of claims 1-25.

27. The passenger detection method according to claim 26, characterized in that: The determining whether a seat in the vehicle cabin is in an occupied state comprises: Obtain pressure signals of seats in the vehicle cabin; If the pressure value represented by the pressure signal is within a preset range, it is determined that the seat is in an occupied state.

28. The passenger detection method according to claim 26 or 27, characterized in that: After determining that there is a passenger in the vehicle cabin, the method further includes at least one of the following steps: Output prompt information; Controlling the vehicle where the cabin is located to power on; The air conditioning of the cabin is activated.

29. A living thing detection device, characterized in that: The living thing detection device comprises: A first control module is configured to control the speaker to emit a first sound wave signal in a preset space; A second control module is configured to control the microphone to collect a second sound wave signal in the preset space, where the second sound wave signal is generated based on the first sound wave signal; A first determining module is configured to determine channel state information corresponding to the second sound wave signal according to the first sound wave signal and the second sound wave signal; The second determination module is configured to determine whether there is a living thing in the preset space according to the channel state information corresponding to the second sound wave signal.

30. A passenger detection device, characterized in that: The passenger detection device comprises: a seventh determination module, configured to determine whether a seat in the vehicle cabin is in an occupied state; An eighth determination module is configured to determine that there is a passenger in the cabin when the seat is in the occupied state and a living thing detection result in the cabin indicates that there is a living thing; Wherein, the living thing detection result in the cabin is obtained according to the living thing detection method according to any one of claims 1 to 25.

31. A vehicle, characterized in that: include: A processor, a speaker, and a microphone, wherein the processor is connected to the speaker and the microphone respectively; a memory for storing processor-executable instructions; The processor is configured to execute the living thing detection method as described in any one of claims 1 to 25, or to execute the passenger detection method as described in any one of claims 26 to 28.

32. A computer readable storage medium having computer program instructions stored thereon, characterized in that When the program instructions are executed by a processor, the steps of the method described in any one of claims 1 to 25 are implemented. Alternatively, implement the passenger detection method as described in any one of claims 26-28.

Images