In-vehicle living body detection method and system

Abstract

The invention provides an in-vehicle living body detection method and system. The in-vehicle living body detection method comprises the steps that continuous multi-frame radar echo data in a vehicle is collected based on a UWB radar installed on the vehicle; for each frame of radar echo data, intercepting radar echo data of each distance unit from the radar echo data; wherein each distance unit is determined according to the vehicle information of the vehicle and the radar information of the UWB radar; extracting the phase of the radar echo data of each distance unit from the radar echo data of each distance unit, and determining the frequency spectrum information of the radar echo data of each distance unit according to the phase of the radar echo data of each distance unit; and determining whether a living body exists in the vehicle or not according to the frequency spectrum information of the radar echo data of each distance unit.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and more specifically, to a method and system for detecting a living body in a vehicle. Background Art

[0002] With the continuous development of society, the use of cars is becoming more and more widespread, and people pay more and more attention to the safety of car use in daily life. Especially after parking and locking the car, if there are still living things in the car, it will be a very dangerous thing. Therefore, how to provide a real-time detection method for whether there are living things in the car is a problem that needs to be solved urgently.

[0003] In the prior art, a camera is generally installed inside a vehicle, and then the camera is used to collect information inside the vehicle, and the presence of a living body in the vehicle is determined based on the information inside the vehicle. However, this method of collecting information inside the vehicle through a camera is not conducive to protecting the privacy of users, that is, it is easy to leak the privacy of users, and the cost is high. Summary of the invention

[0004] In view of this, the present invention provides a method and system for detecting living bodies in a vehicle, so as to solve the problems of easy leakage of user privacy and high cost in the prior art.

[0005] A first aspect of the present invention provides a method for detecting a living body in a vehicle, the method comprising:

[0006] Based on the UWB radar installed on the vehicle, continuous multi-frame radar echo data inside the vehicle is collected;

[0007] For each frame of the radar echo data, radar echo data of each distance unit is intercepted from the radar echo data; wherein each distance unit is determined according to the vehicle information of the vehicle and the radar information of the UWB radar;

[0008] Extracting the phase of the radar echo data of each of the distance units from the radar echo data of each of the distance units, and determining the frequency spectrum information of the radar echo data of each of the distance units according to the phase of the radar echo data of each of the distance units;

[0009] determining whether there is a living body in the vehicle according to the frequency spectrum information of the radar echo data of each of the distance units;

[0010] If there is a living body in the vehicle, a prompt message indicating that there is a living body in the vehicle is output.

[0011] Optionally, the radar echo data includes phase information including distance information, and the distance information includes the distance between each object in the vehicle and the UWB radar;

[0012] For each frame of the radar echo data, extracting the radar echo data of each of the distance units from the radar echo data, including:

[0013] For each frame of the radar echo data, the radar echo data of each distance unit is intercepted from the target distance information of the phase information of the radar echo data; wherein the radar echo data of the distance unit includes the target distance information; the target distance information includes the target distance between the target object and the UWB radar, and the target object is an object among each of the objects.

[0014] Optionally, extracting the phase of the radar echo data of each of the distance units from the radar echo data of each of the distance units, and determining the spectrum information of the radar echo data of each of the distance units according to the phase of the radar echo data of each of the distance units, includes:

[0015] The phase of the radar echo data of each distance unit is obtained by calculating the target distance in the radar echo function of each distance unit through a pre-constructed echo model function;

[0016] The phase of the radar echo data of each distance unit is subjected to a fast Fourier transform to obtain the frequency spectrum information of the radar echo data of each distance unit.

[0017] Optionally, determining whether there is a living body in the vehicle according to the frequency spectrum information of the radar echo data of each of the distance units includes:

[0018] Selecting target spectrum information within a preset frequency range from the spectrum information of the radar echo data of each of the distance units; wherein the target spectrum information includes target frequency energy corresponding to each frequency within the preset frequency range;

[0019] Accumulating the energy of each target spectrum in the target spectrum information of the radar echo data of each distance unit to obtain the sum of the spectrum energy of each distance unit;

[0020] If there is a distance unit whose sum of spectrum energy is greater than a preset threshold, it is determined that there is a living body among the objects in the vehicle;

[0021] If there is no distance unit whose sum of frequency energy is greater than the preset threshold, it is determined that there is no living body among the objects in the vehicle.

[0022] Optionally, before extracting the phase of the radar echo data of each of the distance units from the radar echo data of each of the distance units, the method further includes:

[0023] Preprocessing the radar echo data of each of the range units;

[0024] Correspondingly, extracting the phase of the radar echo data of each distance unit from the radar echo data of each distance unit includes:

[0025] The phase of the radar echo data of each of the distance units is extracted from the preprocessed radar echo data of each of the distance units.

[0026] Optionally, the preprocessing of the radar echo data of each of the distance units includes:

[0027] The echo data of each of the range radars is subjected to sliding average noise reduction and downsampling processing, so as to pre-process the radar echo data of each of the range units.

[0028] A second aspect of the present invention provides a system for detecting a living body in a vehicle, the system comprising:

[0029] An acquisition unit, used for acquiring continuous multi-frame radar echo data in the vehicle based on the UWB radar installed on the vehicle;

[0030] An interception unit, used for determining at least one distance unit according to the vehicle information of the vehicle and the radar information of the UWB radar, and intercepting the radar echo data of each distance unit from each frame of the radar echo data;

[0031] an extraction unit, used to extract the phase of the radar echo data of each distance unit from the radar echo data of each distance unit, and determine the frequency spectrum information of the radar echo data of each distance unit according to the phase of the radar echo data of each distance unit;

[0032] A judgment unit, used for determining whether there is a living body in the vehicle according to the frequency spectrum information of the radar echo data of each of the distance units;

[0033] The output unit outputs prompt information indicating that there is a living body in the vehicle if there is a living body in the vehicle.

[0034] Optionally, the radar echo data includes phase information including distance information, the distance information includes the distance between each object in the vehicle and the UWB radar, and the interception unit includes:

[0035] A distance unit determination unit, configured to determine a plurality of distance units according to the size of the interior space of the vehicle and the installation position of the UWB radar on the vehicle; wherein the vehicle information of the vehicle includes the size of the interior space of the vehicle, and the radar information of the UWB radar includes the installation position of the UWB radar on the vehicle;

[0036] The interception unit is used to intercept the radar echo data of each distance unit from the target distance information of the phase information of the radar echo data for each frame of the radar echo data; wherein the radar echo data of the distance unit includes the target distance information; the target distance information includes the target distance between the target object and the UWB radar, and the target object is an object among each of the objects.

[0037] Optionally, the phase extraction unit is used to calculate the target distance in the radar echo function of each distance unit by using a pre-constructed echo model function to obtain the phase of the radar echo data of each distance unit;

[0038] The fast Fourier transform unit is used to perform fast Fourier transform on the phase of the radar echo data of each distance unit to obtain the frequency spectrum information of the radar echo data of each distance unit.

[0039] Optionally, the judging unit includes:

[0040] A selection unit, configured to select target spectrum information within a preset frequency range from the spectrum information of the radar echo data of each of the distance units; wherein the target spectrum information includes target frequency energy corresponding to each frequency within the preset frequency range;

[0041] An accumulation unit, used for accumulating the energy of each target spectrum in the target spectrum information of the radar echo data of each distance unit to obtain the sum of the spectrum energy of each distance unit;

[0042] A first determination unit, configured to determine that there is a living body among the objects in the vehicle if there is a distance unit whose sum of spectrum energy is greater than a preset threshold;

[0043] The second determination unit is used to determine that there is no living body among the objects in the vehicle if there is no distance unit whose sum of frequency energy is greater than the preset threshold. The present invention provides a method and system for detecting living bodies in a vehicle, which collects continuous multiple frames of radar echo data on the vehicle based on a UWB radar installed in the vehicle; determines at least one distance unit according to the vehicle information of the vehicle and the radar information of the UWB radar, and intercepts the radar echo data of each distance unit from each frame of the radar echo data, so as to extract the phase of the radar echo data of each distance unit from the radar echo data of each distance unit, and determines the spectrum information of the radar echo data of each distance unit according to the phase of the radar echo data of each distance unit; determines whether there is a living body in the vehicle according to the spectrum information of the radar echo data of each distance unit. The technical solution provided by the present invention is to install a UWB radar on the vehicle in advance instead of installing a camera in the vehicle in the prior art, thereby achieving the purpose of reducing costs; and by extracting the phase in the radar echo data of each distance unit, and determining the frequency spectrum information of the radar echo data of the corresponding distance unit according to the extracted phase, it is judged whether there is a living body in the vehicle. Compared with signals with small changes, it is more sensitive to better identify the breathing frequency and small movement characteristics of the living body in the vehicle, thereby improving the detection rate of the living body in the vehicle, and at the same time avoiding the leakage of user privacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0045] Figure 1 A schematic diagram of a flow chart of a method for detecting a living body in a vehicle provided by an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of the structure of an in-vehicle living body detection system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0049] As can be seen from the above background technology, currently, a camera is installed inside a vehicle, and then the camera is used to collect information inside the vehicle, and then it is determined whether there is a living body inside the vehicle based on the information inside the vehicle. However, this method of collecting information inside the vehicle through a camera is not conducive to protecting the privacy of users, that is, it is easy to leak the privacy of users, and the cost is high.

[0050] In order to avoid leaking user privacy, in the existing technology, millimeter wave radar can also be installed on the vehicle to detect whether there is a living body in the car. However, this detection method requires the radar to work at 77GHz-79GHz, which cannot be widely used.

[0051] Therefore, an embodiment of the present invention provides a method for detecting living things in a vehicle. By pre-installing an ultra-wideband radar (Ultra Wide Band, UWB) on the vehicle instead of installing a camera in the vehicle in the prior art, not only can the purpose of reducing costs be achieved, but also can be widely used; and by extracting the phase in the radar echo data of each of the distance units, and determining the frequency spectrum information of the radar echo data of the corresponding distance unit according to the extracted phase, it is judged whether there is a living thing in the vehicle. Compared with signals with small changes, it is more sensitive, and can better identify the breathing frequency and small movement characteristics of the living thing in the vehicle, thereby improving the detection rate of the living thing in the vehicle, and at the same time can avoid leaking the privacy of the user.

[0052] See also Figure 1 , shows a flow chart of a method for detecting a living body in a vehicle provided by an embodiment of the present invention, which specifically includes the following steps:

[0053] S101: Collecting continuous multi-frame radar echo data in the vehicle based on the UWB radar installed on the vehicle.

[0054] In the embodiment of the present invention, a UWB radar can be pre-installed on the vehicle so that when the UWB radar is in operation, continuous multiple frames of radar echo data in the vehicle can be collected in real time through the UWB. Each frame of radar echo data is radar echo data after coherent processing; each frame of radar echo data includes phase information including target distance information, and the target distance information includes the distance between each object in the vehicle and the UWB radar.

[0055] In some embodiments, continuous multiple frames of radar echo data in the vehicle can be periodically collected based on the UWB radar installed on the vehicle. For example, 2048 frames of continuous radar echo data in the vehicle can be collected every 5 ms by the UWB radar installed on the vehicle. The corresponding period and the number of frames of collected radar echo data can be set according to actual applications, which is not limited in this embodiment of the present invention.

[0056] It should be noted that, since the electromagnetic waves reflected by the object are phase modulated, the phase information of the radar echo data after coherent processing may include not only the target distance information but also the corresponding phase information. Each object may be an object with the ability to reflect electromagnetic waves, which is not limited in this embodiment of the present invention.

[0057] It is worth noting that since the distance between each object in the vehicle and the UWB radar installed on the vehicle is different, the distance between each object and the UWB radar in the target distance information can be sorted from small to large. For example, the target distance information can be 0m, 0.3m, 0.6m, 0.9m, 1.2m, and 1.5m.

[0058] In actual application, the UWB radar may be installed on an armrest of a rear seat in a vehicle, or the UWB radar may be installed on a B-pillar of a vehicle, which is not limited in this embodiment of the present invention.

[0059] S102: For each frame of the radar echo data, extract radar echo data of each distance unit from the radar echo data; wherein each distance unit is determined according to vehicle information of the vehicle and radar information of the UWB radar.

[0060] In an embodiment of the present invention, since the sizes of the interior spaces of different types of vehicles are different, multiple distance units can be set according to the sizes of the interior spaces of different types of vehicles and the installation positions of the UWB radars on the vehicles; for each type of vehicle, a distance unit association relationship between the size of the interior space of the type of vehicle and the installation position of the UWB on the vehicle and the corresponding distance units can be set.

[0061] As an implementation method of an embodiment of the present invention, when the installation position of the UWB radar on the vehicle is the same, if the interior space of the vehicle is larger, then each distance unit associated with it can be set larger; if the interior space of the vehicle is smaller, then each distance unit associated with it can be set smaller. It can be configured according to actual application and is not limited in this embodiment of the present invention.

[0062] In some embodiments, the distance units that have a distance unit association relationship with the size of the space inside the vehicle and the installation position of the UWB radar on the vehicle can be a continuous plurality of distance units or a discontinuous plurality of distance units; for example, the distance units can be 3, 5, 8, 10, 12, or can be 3, 4, 5, 6, 7, etc., and can be set according to actual applications, and are not limited in this embodiment of the present invention.

[0063] In the specific process of executing step S102, after collecting multiple frames of radar echo data, the vehicle information of the vehicle and the radar information of the UWB radar installed on the vehicle can be obtained; wherein the vehicle information of the vehicle includes the size of the interior space of the vehicle, and the radar information of the UWB radar includes the installation position of the UWB radar on the vehicle. According to the determined relationship between the distance units corresponding to the current size of the interior space of the vehicle and the installation position of the UWB radar on the vehicle, and according to the determined relationship between the distance units, the multiple distance units corresponding to the current size of the interior space of the vehicle and the installation position of the UWB radar on the vehicle are determined from the pre-set distance units, so as to intercept the echo data of each distance unit from each frame of radar echo data.

[0064] Specifically, the process of intercepting the echo data of each distance unit from each frame of radar echo data can be specifically as follows: for each frame of radar echo data, the echo data of each distance unit can be intercepted from the target distance information of the phase information of the radar echo data, so that a part of the echo data irrelevant to the living body in the vehicle can be removed from the collected radar echo data, thereby preventing the non-detection of living bodies outside the vehicle and improving the efficiency of living body detection in the vehicle; wherein, the radar echo data of the distance unit includes target distance information; the target distance information includes the target distance between the target object and the UWB radar, and the target object is an object among each of the objects.

[0065] For example, the distance information in the phase information of the radar echo data is 0.3m, 0.4m, 0.5m, 0.6m, 1m, and 1.5m; if the distance units associated with the current vehicle's interior space size and the installation position of the UWB on the vehicle are 3, 4, and 5, then the target distance in the radar echo data with a distance unit of 3 intercepted from the distance information of the phase information of the radar echo data is 0.5m, the target distance in the radar echo data with a distance unit of 4 is 0.6m, and the target distance in the radar echo data with a distance unit of 5 is 1m.

[0066] S103: extracting the phase of the radar echo data of each distance unit from the radar echo data of each distance unit, and determining the frequency spectrum information of the radar echo data of each distance unit according to the phase of the radar echo data of each distance unit.

[0067] In the specific process of executing step S103, for each frame of radar echo data, after the radar echo data of each distance unit is cut out from the radar echo data, the phase of the radar echo data of each distance unit can be calculated according to the target distance in the radar echo data of each distance unit, and the frequency spectrum information of the radar echo data of each distance unit can be determined according to the phase of the radar echo data of each distance unit.

[0068] Optionally, in an embodiment of the present invention, a corresponding echo model function may be pre-constructed, so that the target distance in the radar echo function of each distance unit is calculated by the pre-constructed echo model function to obtain the phase of the radar echo data of each distance unit; the phase of the radar echo data of each distance unit is fast Fourier transformed to obtain the spectrum information of the radar echo data of each distance unit. The pre-constructed echo model function is shown in formula (1).

[0069]

[0070] Where s(t) is the target distance in the radar echo data of the range unit, R = R 0 +Bcos(2πf h t), R0 is the position of the target object relative to the UWB radar corresponding to the target distance, Bcos(2πf h t) is the change in relative radar distance caused by the chest fluctuation of living breathing, B is the amplitude of the chest change, and f h is the breathing frequency, is the DC component, C is the amplitude of the DC component, is the phase of the DC component, N(t) is the noise energy, j is the imaginary sign, λ is the wavelength, A is the amplitude, and exp is the exponential signal.

[0071] It should be noted that since the DC component is caused by leakage from the transmitting antenna to the receiving antenna, the DC component will not change with changes in the external environment; the DC component can be obtained by filtering the radar echo data obtained in an environment without a living body.

[0072] In practical applications, for each distance unit, the target distance in the radar echo data of the distance unit can be brought into the pre-built echo model function for calculation, and the phase 4πR of the radar echo data of the distance unit can be reversely deduced; since R = R 0 +Bcos(2πf h t), therefore, by extracting the corresponding phase from the radar echo data of the single range gate, the breathing characteristics of the object can be extracted accordingly.

[0073] It should be noted that if the target object corresponding to the target distance is a living body, the respiratory frequency in the phase calculated using the target distance is not zero; if the target object corresponding to the target distance is not a living body, the respiratory frequency in the phase calculated using the target distance is zero.

[0074] Furthermore, in an embodiment of the present invention, in order to further reduce the noise in the radar echo data and improve the computational efficiency when calculating the phase, the radar echo data of each distance unit may be preprocessed before the corresponding phase is extracted from the radar echo data of each distance unit.

[0075] Optionally, the process of preprocessing the radar echo data of each of the distance units may specifically be: performing sliding average noise reduction and downsampling processing on the echo data of each of the distance radars, so as to preprocess the radar echo data of each of the distance units, thereby achieving noise reduction and improving computing efficiency.

[0076] S104: Determine whether there is a living body in the vehicle based on the spectrum information of the radar echo data of each distance unit. If there is a living body in the vehicle, execute step S105; if there is no living body in the vehicle, return to execute step S101.

[0077] In an embodiment of the present invention, in order to further improve the accuracy of living body detection, a corresponding initial frequency range can be set according to the upper limit of the breathing frequency and the DC component of an ordinary living body; since the phase winding problem will cause the spectrum to become dispersed, the initial frequency range can be optimized to obtain a preset frequency range.

[0078] In actual application, since the DC component needs to be removed, the spectrum below 0.1 Hz can be excluded. Since the upper limit of the breathing frequency of ordinary living organisms is 0.8 Hz, but the phase winding problem will cause the spectrum to become dispersed, the upper limit can be adjusted to 1.6 Hz, so the preset frequency range can be set to 0.1 Hz ~ 1.6 Hz.

[0079] In the specific process of executing step S104, for each radar echo data, after obtaining the frequency spectrum information of the radar echo data of each distance unit intercepted from the radar echo data, for each distance unit, target frequency information located in a preset frequency range can be selected from the frequency spectrum information of the radar echo data of each distance unit, so as to determine whether there is a living body in the vehicle based on the target frequency spectrum information of the radar echo data of each of the distance units.

[0080] It should be noted that the target spectrum information includes the target frequency energy corresponding to each frequency within a preset frequency range.

[0081] Optionally, the energy of each target spectrum in the target spectrum information of the radar echo data of each distance unit is accumulated to obtain the sum of the spectrum energy of each distance unit; it is determined whether there is a distance unit whose sum of spectrum energy is greater than a preset threshold value among the distance units; if there is a distance unit whose sum of spectrum energy is greater than the preset threshold value, it is determined that there is a living body among the objects in the vehicle; if there is no distance unit whose sum of frequency energy is greater than the preset threshold value, it is determined that there is no living body among the objects in the vehicle. The method of accumulating the energy of each target spectrum in the target spectrum information of the radar echo data of each distance unit to obtain the sum of the spectrum energy of each distance unit can be referred to formula (2).

[0082]

[0083] Wherein, E is the sum of the spectrum energies of the distance unit, f is the frequency, and S(f) is the target frequency energy corresponding to the frequency f in the target spectrum information of the distance unit.

[0084] It should be noted that the preset threshold is obtained by debugging, testing and adjusting in advance based on historical radar echo data with living bodies in the vehicle and radar echo data with no living bodies in the vehicle.

[0085] In actual application, for each distance unit, if the sum of the spectrum energies obtained by accumulating the energies of each target frequency in the target frequency information of the radar echo data of the distance unit is greater than a preset threshold, it can be determined that there are living objects among the objects in the vehicle, and the target object at the target distance in the radar echo data corresponding to the distance unit can be determined as a living object.

[0086] Furthermore, in an embodiment of the present invention, after a living body is determined, a prompt message indicating the presence of a living body in the vehicle can be further sent to the central control via CAN / CANFD to remind the user that there is a living body in the vehicle, so that the user can check the vehicle in time to avoid safety accidents.

[0087] S105: Outputting prompt information indicating that there is a living body in the vehicle.

[0088] The present invention provides a method for detecting living bodies in a vehicle. The method comprises collecting continuous multiple frames of radar echo data on the vehicle based on a UWB radar installed in the vehicle; determining at least one distance unit according to vehicle information of the vehicle and radar information of the UWB radar, and intercepting radar echo data of each distance unit from each frame of the radar echo data, so as to extract the phase of the radar echo data of each distance unit from the radar echo data of each distance unit, and determining the frequency spectrum information of the radar echo data of each distance unit according to the phase of the radar echo data of each distance unit; and determining whether a living body exists in the vehicle according to the frequency spectrum information of the radar echo data of each distance unit. The technical solution provided by the present invention is to install a UWB radar on the vehicle in advance instead of installing a camera in the vehicle in the prior art, thereby achieving the purpose of reducing costs; and by extracting the phase in the radar echo data of each distance unit, and determining the frequency spectrum information of the radar echo data of the corresponding distance unit according to the extracted phase, it is judged whether there is a living body in the vehicle. Compared with signals with small changes, it is more sensitive to better identify the breathing frequency and small movement characteristics of the living body in the vehicle, thereby improving the detection rate of the living body in the vehicle, and at the same time avoiding the leakage of user privacy.

[0089] Based on the in-vehicle liveness detection method provided by the above embodiment of the present invention, the embodiment of the present invention also provides an in-vehicle liveness detection system, such as Figure 2 As shown, the system includes:

[0090] The acquisition unit 21 is used to acquire continuous multi-frame radar echo data in the vehicle based on the UWB radar installed on the vehicle;

[0091] An interception unit 22, configured to determine at least one distance unit according to the vehicle information of the vehicle and the radar information of the UWB radar, and intercept radar echo data of each distance unit from each frame of the radar echo data;

[0092] An extraction unit 23, used to extract the phase of the radar echo data of each distance unit from the radar echo data of each distance unit, and determine the frequency spectrum information of the radar echo data of each distance unit according to the phase of the radar echo data of each distance unit;

[0093] A judgment unit 24, configured to determine whether there is a living body in the vehicle according to the frequency spectrum information of the radar echo data of each of the distance units;

[0094] The output unit 25 outputs prompt information indicating that there is a living body in the vehicle if there is a living body in the vehicle.

[0095] The above-mentioned embodiment of the present invention discloses the specific principles and execution processes of each unit in the in-vehicle liveness detection system, which is the same as the in-vehicle liveness detection method disclosed in the above-mentioned embodiment of the present invention. Please refer to the corresponding parts of the in-vehicle liveness detection method disclosed in the above-mentioned embodiment of the present invention, and no further details will be given here.

[0096] The present invention provides a system for detecting living bodies in a vehicle. The system collects continuous multiple frames of radar echo data on the vehicle based on a UWB radar installed in the vehicle. At least one distance unit is determined according to vehicle information of the vehicle and radar information of the UWB radar, and radar echo data of each distance unit is intercepted from each frame of the radar echo data, so as to extract the phase of the radar echo data of each distance unit from the radar echo data of each distance unit, and determine the frequency spectrum information of the radar echo data of each distance unit according to the phase of the radar echo data of each distance unit. According to the frequency spectrum information of the radar echo data of each distance unit, it is determined whether there is a living body in the vehicle. The technical solution provided by the present invention is to install a UWB radar on the vehicle in advance instead of installing a camera in the vehicle in the prior art, thereby achieving the purpose of reducing costs; and by extracting the phase in the radar echo data of each distance unit, and determining the frequency spectrum information of the radar echo data of the corresponding distance unit according to the extracted phase, it is judged whether there is a living body in the vehicle. Compared with signals with small changes, it is more sensitive to better identify the breathing frequency and small movement characteristics of the living body in the vehicle, thereby improving the detection rate of the living body in the vehicle, and at the same time avoiding the leakage of user privacy.

[0097] Optionally, the radar echo data includes phase information including distance information, the distance information includes the distance between each object in the vehicle and the UWB radar, and the interception unit includes:

[0098] A distance unit determination unit, configured to determine a plurality of distance units according to the size of the interior space of the vehicle and the installation position of the UWB radar on the vehicle; wherein the vehicle information of the vehicle includes the size of the interior space of the vehicle, and the radar information of the UWB radar includes the installation position of the UWB radar on the vehicle;

[0099] The interception unit is used to intercept the radar echo data of each distance unit from the target distance information of the phase information of the radar echo data for each frame of the radar echo data; wherein the radar echo data of the distance unit includes the target distance information; the target distance information includes the target distance between the target object and the UWB radar, and the target object is an object among each of the objects.

[0100] Optionally, the extraction unit includes:

[0101] A phase extraction unit, configured to obtain the phase of the radar echo data of each distance unit by calculating the target distance in the radar echo function of each distance unit through a pre-constructed echo model function;

[0102] The fast Fourier transform unit is used to perform fast Fourier transform on the phase of the radar echo data of each distance unit to obtain the frequency spectrum information of the radar echo data of each distance unit.

[0103] Optionally, the judging unit includes:

[0104] A selection unit, configured to select target spectrum information within a preset frequency range from the spectrum information of the radar echo data of each of the distance units; wherein the target spectrum information includes target frequency energy corresponding to each frequency within the preset frequency range;

[0105] An accumulation unit, used for accumulating the energy of each target spectrum in the target spectrum information of the radar echo data of each distance unit to obtain the sum of the spectrum energy of each distance unit;

[0106] A first determination unit, configured to determine that there is a living body among the objects in the vehicle if there is a distance unit whose sum of spectrum energy is greater than a preset threshold;

[0107] The second determination unit is used to determine that there is no living body among the objects in the vehicle if there is no distance unit whose sum of frequency energy is greater than the preset threshold.

[0108] Optionally, the in-vehicle living body detection system provided by the embodiment of the present invention further includes:

[0109] A preprocessing unit, used for preprocessing the radar echo data of each of the distance units;

[0110] Correspondingly, the extraction unit is further used to extract the phase of the radar echo data of each of the distance units from the pre-processed radar echo data of each of the distance units.

[0111] Optional, pre-processing unit, including:

[0112] The preprocessing subunit is used to perform sliding average noise reduction and downsampling processing on the echo data of each of the range radars, so as to preprocess the radar echo data of each of the range units.

[0113] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, in which the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0114] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0115] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0116] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for detecting a living body in a vehicle, characterized in that: The method comprises: Based on the UWB radar installed on the vehicle, continuous multi-frame radar echo data inside the vehicle is collected; For each frame of the radar echo data, radar echo data of each distance unit is intercepted from the radar echo data; wherein each distance unit is determined according to the vehicle information of the vehicle and the radar information of the UWB radar; Extracting the phase of the radar echo data of each of the distance units from the radar echo data of each of the distance units, and determining the frequency spectrum information of the radar echo data of each of the distance units according to the phase of the radar echo data of each of the distance units; determining whether there is a living body in the vehicle according to the frequency spectrum information of the radar echo data of each of the distance units; If there is a living body in the vehicle, a prompt message indicating that there is a living body in the vehicle is output.

2. The method according to claim 1, characterized in that The radar echo data includes phase information including distance information, and the distance information includes the distance between each object in the vehicle and the UWB radar; For each frame of the radar echo data, extracting the radar echo data of each of the distance units from the radar echo data, including: For each frame of the radar echo data, the radar echo data of each distance unit is intercepted from the target distance information of the phase information of the radar echo data; wherein the radar echo data of the distance unit includes the target distance information; the target distance information includes the target distance between the target object and the UWB radar, and the target object is an object among each of the objects.

3. The method according to claim 2, characterized in that The extracting the phase of the radar echo data of each of the distance units from the radar echo data of each of the distance units, and determining the spectrum information of the radar echo data of each of the distance units according to the phase of the radar echo data of each of the distance units, comprises: The phase of the radar echo data of each distance unit is obtained by calculating the target distance in the radar echo function of each distance unit through a pre-constructed echo model function; The phase of the radar echo data of each distance unit is subjected to a fast Fourier transform to obtain the frequency spectrum information of the radar echo data of each distance unit.

4. The method according to claim 1, characterized in that The determining whether there is a living body in the vehicle according to the spectrum information of the radar echo data of each of the distance units comprises: Selecting target spectrum information within a preset frequency range from the spectrum information of the radar echo data of each of the distance units; wherein the target spectrum information includes target frequency energy corresponding to each frequency within the preset frequency range; Accumulating the energy of each target spectrum in the target spectrum information of the radar echo data of each distance unit to obtain the sum of the spectrum energy of each distance unit; If there is a distance unit whose sum of spectrum energy is greater than a preset threshold, it is determined that there is a living body among the objects in the vehicle; If there is no distance unit whose sum of frequency energy is greater than the preset threshold, it is determined that there is no living body among the objects in the vehicle.

5. The method according to claim 1, characterized in that Before extracting the phase of the radar echo data of each of the distance units from the radar echo data of each of the distance units, the method further includes: Preprocessing the radar echo data of each of the range units; Correspondingly, extracting the phase of the radar echo data of each distance unit from the radar echo data of each distance unit includes: The phase of the radar echo data of each of the distance units is extracted from the preprocessed radar echo data of each of the distance units.

6. The method according to claim 5, characterized in that The preprocessing of the radar echo data of each of the distance units includes: The echo data of each of the range radars is subjected to sliding average noise reduction and downsampling processing, so as to pre-process the radar echo data of each of the range units.

7. A system for detecting living things in a vehicle, characterized in that: The system comprises: An acquisition unit, used for acquiring continuous multi-frame radar echo data in the vehicle based on the UWB radar installed on the vehicle; An interception unit, used for determining at least one distance unit according to the vehicle information of the vehicle and the radar information of the UWB radar, and intercepting the radar echo data of each distance unit from each frame of the radar echo data; an extraction unit, used to extract the phase of the radar echo data of each distance unit from the radar echo data of each distance unit, and determine the frequency spectrum information of the radar echo data of each distance unit according to the phase of the radar echo data of each distance unit; A judgment unit, used for determining whether there is a living body in the vehicle according to the frequency spectrum information of the radar echo data of each of the distance units; The output unit outputs prompt information indicating that there is a living body in the vehicle if there is a living body in the vehicle.

8. The system according to claim 7, characterized in that The radar echo data includes phase information including distance information, and the distance information includes the distance between each object in the vehicle and the UWB radar. The interception unit includes: A distance unit determination unit, configured to determine a plurality of distance units according to the size of the interior space of the vehicle and the installation position of the UWB radar on the vehicle; wherein the vehicle information of the vehicle includes the size of the interior space of the vehicle, and the radar information of the UWB radar includes the installation position of the UWB radar on the vehicle; The interception unit is used to intercept the radar echo data of each distance unit from the target distance information of the phase information of the radar echo data for each frame of the radar echo data; wherein the radar echo data of the distance unit includes the target distance information; the target distance information includes the target distance between the target object and the UWB radar, and the target object is an object among each of the objects.

9. The system according to claim 8, characterized in that The phase extraction unit is used to calculate the target distance in the radar echo function of each distance unit by using a pre-constructed echo model function to obtain the phase of the radar echo data of each distance unit; The fast Fourier transform unit is used to perform fast Fourier transform on the phase of the radar echo data of each distance unit to obtain the frequency spectrum information of the radar echo data of each distance unit.

10. The system according to claim 7, characterized in that The judging unit comprises: A selection unit, configured to select target spectrum information within a preset frequency range from the spectrum information of the radar echo data of each of the distance units; wherein the target spectrum information includes target frequency energy corresponding to each frequency within the preset frequency range; An accumulation unit, used for accumulating the energy of each target spectrum in the target spectrum information of the radar echo data of each distance unit to obtain the sum of the spectrum energy of each distance unit; A first determination unit, configured to determine that there is a living body among the objects in the vehicle if there is a distance unit whose sum of spectrum energy is greater than a preset threshold; The second determination unit is used to determine that there is no living body among the objects in the vehicle if there is no distance unit whose sum of frequency energy is greater than the preset threshold.

Images