Vehicle-mounted living body detection method and device, vehicle, storage medium and product

Abstract

The present disclosure relates to a vehicle-mounted living body detection method and device, a vehicle, a computer readable storage medium and a computer program product, and relates to the technical field of intelligent cockpit. The vehicle-mounted living body detection method comprises: acquiring a UWB response signal; performing Fourier transform on the UWB response signal to obtain a response spectrum signal; determining a target signal peak according to the signal energy of the response spectrum signal; in response to the frequency of the target signal peak not being located in a breathing frequency band, determining that the target signal peak corresponds to an interference signal; performing signal cancellation processing on the UWB response signal based on the interference signal to obtain a target response signal; and performing living body detection based on the target response signal to determine whether there is a living body in the vehicle cabin. The method suppresses the strong Doppler component generated by the moving object in the cabin by performing cancellation processing based on the identified interference signal, significantly improves the accuracy and robustness of the in-vehicle living body detection, and effectively reduces the false positive and false negative risks.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent cockpit technology, and more specifically, to an in-vehicle liveness detection method, device, vehicle, computer-readable storage medium, and computer program product. Background Technology

[0002] With the continuous improvement of automotive intelligence, in-vehicle occupant safety monitoring technology has received increasing attention. Especially in scenarios such as vehicle parking, rest, or changes in cabin space, accurately detecting the presence of occupants or left-behind children or pets has become a crucial research direction for in-vehicle safety systems. Traditional liveness detection solutions primarily rely on visual sensors or infrared thermal imaging technology, determining the presence of living beings inside the vehicle through image recognition or temperature distribution. However, in practical applications, these solutions are easily affected by factors such as changes in lighting conditions, obstructions, and fluctuations in ambient temperature, leading to unstable detection performance and posing safety hazards to living beings within the cabin. Summary of the Invention

[0003] To overcome the problems existing in related technologies, this disclosure provides a vehicle-mounted liveness detection method, device, vehicle, computer-readable storage medium, and computer program product.

[0004] According to a first aspect of the present disclosure, a vehicle-mounted liveness detection method is provided, the method comprising: acquiring a UWB response signal; the UWB response signal being a response signal based on a UWB pulse signal transmitted to a vehicle cabin by a UWB radar; performing a Fourier transform on the UWB response signal to obtain a response spectrum signal; determining at least one target signal peak based on the signal energy of the response spectrum signal; determining that the target signal peak corresponds to an interference signal because its frequency is not located in the breathing frequency band; performing signal cancellation processing on the UWB response signal based on the interference signal to obtain a target response signal; and performing liveness detection based on the target response signal to determine whether a live person exists in the vehicle cabin.

[0005] In some exemplary embodiments of this disclosure, the step of performing a Fourier transform on the UWB response signal to obtain a response spectrum signal includes: performing a spatial domain transformation on the UWB response signal to obtain a spatial domain response signal; obtaining a target region response signal from the spatial domain response signal according to a preset target region; and performing a Fourier transform on the target region response signal to obtain the response spectrum signal.

[0006] In some exemplary embodiments of this disclosure, the step of performing signal cancellation processing on the UWB response signal based on the interference signal to obtain a target response signal includes: obtaining signal parameters of the interference signal according to the interference signal; aligning the interference signal with the UWB response signal; and compensating the UWB response signal based on the signal parameters of the interference signal to obtain the target response signal.

[0007] In some exemplary embodiments of this disclosure, the step of performing signal cancellation processing on the UWB response signal based on the interference signal to obtain the target response signal includes: filtering the UWB response signal based on the breathing frequency band to obtain the target response signal.

[0008] In some exemplary embodiments of this disclosure, the step of performing signal cancellation processing on the UWB response signal based on the interference signal to obtain the target response signal includes: filtering the UWB response signal through an adaptive filter to obtain the target response signal; wherein the adaptive filter uses the interference signal as a reference input.

[0009] In some exemplary embodiments of this disclosure, the method further includes: in response to receiving a cockpit drive signal, the UWB radar transmitting the UWB pulse signal to the vehicle cockpit; the cockpit drive signal is used to drive the vehicle cockpit to switch from a first spatial state to a second spatial state.

[0010] In some exemplary embodiments of this disclosure, the cockpit drive signal is used to drive the lifting roof of the vehicle cockpit to rise or fall.

[0011] In some exemplary embodiments of this disclosure, the liveness detection based on the target response signal includes: acquiring cabin space calibration information corresponding to the first space state; and performing liveness detection based on the target response signal and the cabin space calibration information.

[0012] In some exemplary embodiments of this disclosure, the liveness detection based on the target response signal includes: determining the displacement amplitude of at least one target object according to the target response signal; and determining the presence of a live object in the vehicle cabin in response to the displacement amplitude of the target object being greater than an amplitude threshold.

[0013] In some exemplary embodiments of this disclosure, the liveness detection based on the target response signal includes: performing differential processing on the target response signal to obtain a differential response signal; extracting a micro-motion response signal from the target response signal based on the displacement amplitude of the differential response signal; extracting micro-motion change features based on the micro-motion response signal; and performing liveness detection based on the micro-motion change features to determine whether a live body exists in the vehicle cabin.

[0014] In some exemplary embodiments of this disclosure, the step of performing liveness detection based on the micro-motion change features to determine whether a living person exists in the vehicle cabin includes: performing feature recognition on the micro-motion change features using a pre-trained respiratory wave model to determine whether a living person exists in the vehicle cabin.

[0015] According to a second aspect of the present disclosure, an in-vehicle liveness detection device is provided, comprising: a response signal acquisition unit for acquiring a UWB response signal; the UWB response signal being a response signal based on a UWB pulse signal transmitted to a vehicle cabin by a UWB radar; a spectrum conversion unit for performing a Fourier transform on the UWB response signal to obtain a response spectrum signal; a peak determination unit for determining at least one target signal peak based on the signal energy of the response spectrum signal; an interference signal determination unit for determining that the target signal peak corresponds to an interference signal in response to the frequency of the target signal peak not being located in the breathing frequency band; a cancellation processing unit for performing signal cancellation processing on the UWB response signal based on the interference signal to obtain a target response signal; and a liveness detection unit for performing liveness detection based on the target response signal to determine whether a live person exists in the vehicle cabin.

[0016] In some exemplary embodiments of this disclosure, the spectrum conversion unit is further configured to perform spatial domain conversion on the UWB response signal to obtain a spatial domain response signal; obtain a target region response signal from the spatial domain response signal according to a preset target region; and perform Fourier transform on the target region response signal to obtain the response spectrum signal.

[0017] In some exemplary embodiments of this disclosure, a UWB transmitting unit is configured to transmit a UWB pulse signal to the vehicle cabin in response to receiving a cabin drive signal; the cabin drive signal is configured to drive the vehicle cabin to switch from a first spatial state to a second spatial state.

[0018] In some exemplary embodiments of this disclosure, the liveness detection unit is further configured to acquire cabin space calibration information corresponding to the first space state; and perform liveness detection based on the target response signal and the cabin space calibration information.

[0019] In some exemplary embodiments of this disclosure, the liveness detection unit is further configured to perform differential processing on the target response signal to obtain a differential response signal; extract a micro-motion response signal from the target response signal based on the displacement amplitude of the differential response signal; extract micro-motion change features based on the micro-motion response signal; and perform liveness detection based on the micro-motion change features to determine whether a live body exists in the vehicle cabin.

[0020] According to a third aspect of the present disclosure, a vehicle is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to: implement the steps of any of the vehicle-mounted liveness detection methods.

[0021] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, which, when instructions in the storage medium are executed by a processor of a mobile terminal, enables the mobile terminal to perform any of the vehicle-mounted liveness detection methods described in the present disclosure.

[0022] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the vehicle-mounted liveness detection methods described above.

[0023] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects: This disclosure provides a vehicle-mounted liveness detection method, comprising: acquiring a UWB response signal; performing a Fourier transform on the UWB response signal to obtain a response spectrum signal; determining at least one target signal peak based on the signal energy of the response spectrum signal; determining that the target signal peak corresponds to an interference signal since the frequency of the target signal peak is not located in the breathing frequency band; performing signal cancellation processing on the UWB response signal based on the interference signal to obtain a target response signal; and performing liveness detection based on the target response signal to determine whether a live person exists in the vehicle cabin. This method, by performing cancellation processing based on the identified interference signal, suppresses the strong Doppler component generated by moving objects in the cabin, significantly improving the accuracy and robustness of in-vehicle liveness detection and effectively reducing the risk of false alarms and false negatives.

[0024] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0025] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0026] Figure 1This is a flowchart of an on-board liveness detection method according to an exemplary embodiment of the present disclosure. Figure 1 .

[0027] Figure 2 This is a flowchart illustrating a spectrum signal transformation process according to an exemplary embodiment of the present disclosure.

[0028] Figure 3 This is a flowchart of an on-board liveness detection method according to an exemplary embodiment of the present disclosure. Figure 2 .

[0029] Figure 4 This is a flowchart of a liveness detection method illustrated according to an exemplary embodiment of the present disclosure. Figure 1 .

[0030] Figure 5 This is a flowchart of a liveness detection method illustrated according to an exemplary embodiment of the present disclosure. Figure 2 .

[0031] Figure 6 This is a block diagram illustrating an on-board liveness detection device according to an exemplary embodiment of the present disclosure.

[0032] Figure 7 This is a functional block diagram of a vehicle according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0033] Exemplary embodiments of this disclosure will be described in detail herein, examples of which are illustrated in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. Various changes, modifications, and equivalents of the methods, apparatus, and / or systems described herein will become apparent upon understanding this disclosure. For example, the order of operations described herein is merely illustrative and is not limited to those orders set forth herein, but can be changed as will become apparent upon understanding this disclosure, except for operations that must be performed in a particular order. Furthermore, for clarity and brevity, descriptions of features known in the art may be omitted.

[0034] The embodiments described below, which are examples of some of the embodiments of this disclosure, do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0035] The steps of the method in the exemplary embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings and examples.

[0036] Figure 1This is a flowchart of an on-board liveness detection method according to an exemplary embodiment of the present disclosure. Figure 1 The method described in this embodiment can be applied to electronic devices, including vehicles.

[0037] like Figure 1 As shown, in some embodiments, the vehicle-mounted liveness detection method of this disclosure includes: In step S110, a UWB response signal is acquired; the UWB response signal is a response signal based on the UWB pulse signal transmitted from the UWB radar to the vehicle cockpit.

[0038] This disclosure provides a scheme for detecting the presence of a living person inside a vehicle cabin. The scheme primarily utilizes the transmission and echo of Ultra Wide Band (UWB) pulse signals within the vehicle cabin for detection. UWB radar transmits UWB pulse signals into the vehicle cabin, and the echoes (UWB response signals) after reflection or scattering of these pulse signals by objects (such as seats, pop-up bed panels, roof inner walls, and human bodies) are received. The presence of a living person inside the vehicle cabin is determined by analyzing the echo disturbances. Specifically, the received Channel Impulse Response (CIR) data is used to detect surrounding objects and their motion. This CIR data contains distance and amplitude information for each reflection path, reflecting the structural characteristics and dynamic changes of the vehicle's interior space. The motion state of the living person is estimated by analyzing changes in the CIR data, thereby achieving liveness detection.

[0039] In step S120, the UWB response signal is subjected to Fourier transform to obtain the response spectrum signal.

[0040] In this embodiment, the acquired UWB response signal is subjected to Fourier transform processing to obtain a response spectrum signal. Since the original CIR data acquired by the UWB radar is reflection information S(t) in the time domain, a Fourier transform of the UWB response signal is required to facilitate subsequent analysis of the frequency characteristics in the signal, resulting in the corresponding response spectrum signal S(f). This response spectrum signal reflects the energy distribution of each frequency component in the UWB response signal, where different frequencies correspond to different motion speeds.

[0041] For example, a slow-time Fast Fourier Transform (FFT) can be performed on the UWB response signal to obtain the response spectrum signal. Here, slow time refers to the time series formed by the radar continuously observing the same spatial location during multiple pulse transmissions, with the sampling interval being the time difference between adjacent pulses, used to capture the dynamic information of the target changing over time.

[0042] In step S130, at least one target signal peak is determined based on the signal energy of the response spectrum signal.

[0043] While UWB radar can detect minute displacement changes such as those caused by human respiration, it faces challenges during detection. For example, a vehicle's pop-up roof might be rising or falling, or the vehicle might be vibrating due to engine noise. In such cases, the moving object introduces a strong Doppler frequency component into the echo signal. This strong interference signal has energy far exceeding the millimeter-level minute movements produced by human respiration, causing the respiratory characteristics to be completely submerged in the motion interference and unable to be effectively extracted. This can lead to false alarms or missed detections in liveness detection.

[0044] In this embodiment of the disclosure, to address the aforementioned problems, at least one target signal peak is determined based on the signal energy distribution of the response spectrum signal. Generally, higher energy frequency components indicate more significant motion corresponding to that speed. By performing energy analysis on the response spectrum signal, one or more signal peaks with higher energy are extracted as target signal peaks. Multiple target signal peaks can be determined by setting a set energy threshold. Alternatively, the peak with the highest energy can be selected as the target signal peak. These peaks may correspond to different types of motion sources: for example, the movement of a rising roof, vehicle vibration, or large-scale human movement.

[0045] In step S140, in response to the fact that the frequency of the target signal peak is not located in the breathing frequency band, it is determined that the target signal peak corresponds to an interference signal.

[0046] In this embodiment, the chest cavity fluctuations caused by respiration in a living organism typically conform to certain physiological characteristics. For example, the respiratory rate is within a certain frequency range (e.g., 0.1-0.8 Hz), the amplitude of movement is usually on the millimeter level, the movement cycle is continuous, and the amplitude of movement is consistent. Based on this, the system determines whether the frequency of the target signal peak falls within the respiratory frequency band (e.g., 0.1-0.8 Hz) using a preset respiratory frequency band. If the frequency of the target signal peak is within the respiratory frequency band, then the peak may correspond to a human respiratory signal. If the frequency of the target signal peak is not within the respiratory frequency band, it indicates that the motion source corresponding to the peak is not a living organism. That is, the target signal peak is determined to correspond to an interference signal.

[0047] In step S150, the UWB response signal is subjected to signal cancellation processing based on the interference signal to obtain the target response signal.

[0048] In this embodiment, the system performs signal cancellation processing on the UWB response signal based on the identified interference signal to suppress interference components and obtain the target response signal. Since interference signals typically have high energy and may mask the respiratory signal used for liveness detection, signal processing methods are needed to suppress the interference signal, thereby highlighting the respiratory signal portion of the response signal. Cancellation processing refers to the process of removing interference components from the received signal through signal subtraction, filtering compensation, or adaptive algorithms to highlight the target signal.

[0049] It should be noted that, depending on the characteristics of the interference signal, various signal cancellation processing methods can be used to suppress the strong Doppler component in the response signal. Regardless of the signal cancellation processing method used, it should be considered within the protection scope of this disclosure.

[0050] In some exemplary embodiments, the target object inside the vehicle (such as a human body or other objects) may undergo overall movement. For example, this could involve the movement of the pop-up roof or adjustment of the seat posture. Such macroscopic movements generate significant Doppler frequency components in the radar echo signal, thus creating interference signals in the response signal. To reduce the impact of these interference signals on the target response signal, the following signal cancellation methods can be employed: Based on the interference signal, obtain the signal parameters of the interference signal; Align the interference signal with the UWB response signal; The UWB response signal is compensated based on the signal parameters of the interference signal to obtain the target response signal.

[0051] In this embodiment, when performing cancellation processing on the UWB response signal, the signal parameters of the identified interference signal are first obtained. These signal parameters may include the peak frequency of the interference signal, the amplitude information of the interference signal, and the phase change characteristics, and may also include the radial velocity of the target object corresponding to the interference signal. The interference signal is then aligned with the UWB response signal to ensure phase consistency during compensation. Subsequently, the UWB response signal is compensated based on the signal parameters of the interference signal. When the motion frequency is relatively stable, the system can use frequency shift compensation or phase ramp compensation methods to construct a demodulated signal based on the estimated Doppler frequency offset, and perform complex demodulation on the original signal to eliminate the linear phase drift caused by the overall motion. Through the above frequency compensation or phase correction processing, the interference signal components are effectively suppressed, and the low-frequency drift introduced by them is significantly eliminated.

[0052] In some exemplary embodiments, factors such as vehicle vibration and environmental interference typically introduce low-frequency motion components into the radar echo signal, thus forming interference signals in the response signal. To reduce the impact of such interference signals on the target response signal, the following signal cancellation methods can be employed: The UWB response signal is filtered based on the breathing frequency band to obtain the target response signal.

[0053] In this embodiment, the micro-motion signals generated by human respiration are typically located in a relatively stable low-frequency range. Therefore, the UWB response signal can be filtered based on appropriate filter parameters set according to the breathing frequency band corresponding to human respiration, thereby suppressing low-frequency or abnormal frequency components and weakening the influence of large-scale motion or environmental disturbances. After filtering, the effective micro-motion signals (corresponding to the micro-motion signals of respiration) in the signal are preserved, while the interference components are significantly weakened, which helps to improve the reliability of subsequent liveness detection.

[0054] In some exemplary embodiments, in complex scenarios, there may be multiple motion sources inside the vehicle, such as vehicle structural vibration, changes in external environmental reflections, or the movement of other non-target objects. These interference signals may superimpose with the target signal, thereby affecting the liveness detection effect. These interference signals may have a certain degree of randomness and cannot be canceled by preset feature parameters. To reduce the impact of such interference signals on the target response signal, the following signal cancellation method can be adopted: The UWB response signal is filtered by an adaptive filter to obtain the target response signal; wherein the adaptive filter uses the interference signal as a reference input.

[0055] In this embodiment, an adaptive filter can be introduced to filter interference signals with a certain degree of randomness. Specifically, the interference signal is used as a reference input, and an adaptive filtering model is constructed to estimate and cancel the relevant interference components in the UWB response signal. During the filtering process, the adaptive algorithm dynamically adjusts the filter parameters according to the real-time characteristics of the interference signal, gradually weakening the interference components in the UWB response signal and thus highlighting the target micro-motion signal components in the UWB response signal. This approach can adapt to complex environmental changes without relying on fixed parameters, thereby enhancing the signal cancellation adaptability.

[0056] In step S160, a liveness detection is performed based on the target response signal to determine whether a live person exists in the vehicle cabin.

[0057] In this embodiment, after the aforementioned step S150 to cancel out interference signals in the response signal, a target response signal with enhanced respiratory signal is obtained. Based on this, a liveness detection is performed on the target response signal using signal analysis to determine whether a living person exists in the vehicle cabin. Specifically, signal characteristics of the target response signal can be obtained through signal analysis, and these signal characteristics can be matched with the physiological characteristics corresponding to live respiration to determine whether a living person exists in the vehicle cabin. These signal characteristics may include: signal frequency, frequency stability, signal-to-noise ratio, and phase shift amplitude, etc.

[0058] In an exemplary embodiment, to improve detection accuracy, a respiratory fluctuation model can be pre-trained to identify subtle changes in the target response signal to determine the presence of a living being in the vehicle cabin. This respiratory fluctuation model is trained on respiratory samples from multiple scenarios and poses using a lightweight deep learning network (such as 1D-CNN+RNN), effectively distinguishing respiratory signals from non-periodic noise. Furthermore, the respiratory fluctuation model can be used to further score the judgment result, outputting a liveness confidence score. This liveness confidence score allows for a more refined determination of whether a living being exists in the cabin.

[0059] In an exemplary embodiment, based on the aforementioned liveness detection results, a "live body present" or "no live body present" status information can be output to the ECU or central control module. The ECU or central control module then triggers corresponding safety policies or alarm mechanisms based on this status information to provide safety assurance for any live bodies within the cockpit.

[0060] This disclosure provides a vehicle-mounted liveness detection method, comprising: acquiring a UWB response signal; performing a Fourier transform on the UWB response signal to obtain a response spectrum signal; determining at least one target signal peak based on the signal energy of the response spectrum signal; determining that the target signal peak corresponds to an interference signal since the frequency of the target signal peak is not located in the breathing frequency band; performing signal cancellation processing on the UWB response signal based on the interference signal to obtain a target response signal; and performing liveness detection based on the target response signal to determine whether a live person exists in the vehicle cabin. This method, by performing cancellation processing based on the identified interference signal, suppresses the strong Doppler component generated by moving objects in the cabin, significantly improving the accuracy and robustness of in-vehicle liveness detection and effectively reducing the risk of false alarms and false negatives.

[0061] Figure 2 This is a flowchart illustrating a spectrum signal transformation process according to an exemplary embodiment of the present disclosure. Figure 2 As shown, the aforementioned step S120 may include the following steps.

[0062] In step S210, the UWB response signal is spatially converted to obtain a spatial domain response signal.

[0063] In this embodiment, due to the large space in the vehicle cabin, the UWB response signal may include many echo signals generated by interfering objects, thus affecting the final liveness detection. In some application scenarios, the vehicle may only focus on whether a live object exists in a local area of ​​the cabin space. For example, when the vehicle's pop-up roof is rising or falling, the vehicle focuses on whether a live object exists in the area around the pop-up roof to avoid the risk of accidental trapping. Therefore, the UWB response signal can be preprocessed to extract the response signal corresponding to the target area before subsequent signal analysis and processing.

[0064] In this embodiment, since the raw CIR data acquired by the UWB radar is reflection information S(t) in the time domain, it is necessary to perform a spatial domain transformation on the UWB response signal to convert it into a corresponding spatial domain response signal. Specifically, a range FFT can be performed on the UWB response signal to convert the round-trip time corresponding to each sampling point into the corresponding distance value, thereby constructing a range-dimensional response signal. Furthermore, an angle FFT can be performed on the UWB response signal to convert the phase information corresponding to each sampling point into the corresponding angle information, thereby constructing a direction-dimensional response signal. Using the aforementioned range-dimensional and direction-dimensional response signals, the spatial position corresponding to each sampling point can be constructed, thus forming a spatial domain response signal.

[0065] In step S220, the target region response signal is obtained from the spatial domain response signal according to the preset target region.

[0066] In this embodiment of the disclosure, based on pre-calibrated cabin space information, a target area response signal can be extracted from the spatial domain response signal according to a preset target area (ROI). For example, when the vehicle's pop-up roof is in the process of rising or falling, the area around the pop-up roof is determined as the target area based on the pre-calibrated relative positional relationship between the pop-up roof and the UWB radar. The system selects the corresponding preset target area according to the current pop-up roof status (such as opening angle, roof position), and extracts data within that distance range from the spatial domain response signal to form the target area response signal.

[0067] It should be noted that the vehicle can pre-calibrate multiple target areas according to functional requirements. When the vehicle receives a corresponding function trigger command, it can determine the corresponding target area based on the function trigger command and obtain the corresponding target area response signal from the spatial domain response signal.

[0068] In step S230, the target region response signal is subjected to Fourier transform to obtain the response spectrum signal.

[0069] In this embodiment, the obtained target region response signal is subjected to Fourier transform processing to obtain the corresponding response spectrum signal of the target region. The related process is similar to the aforementioned step S120, and will not be described again here.

[0070] This disclosure provides an on-vehicle liveness detection method. By converting UWB response signals into spatial domain response signals, the method can filter the response signals based on a preset target region according to spatial dimensions, extracting the response signals of the key target region and filtering out response information from other regions. This spatial dimension-based filtering improves the efficiency of subsequent signal analysis and processing, while also increasing the accuracy of liveness detection.

[0071] Figure 3 This is a flowchart of an on-board liveness detection method according to an exemplary embodiment of the present disclosure. Figure 2 .

[0072] In this embodiment of the disclosure, Figure 3 Steps S310, S320, S330, S340, S350, and S360 in the vehicle-mounted liveness detection method shown are... Figure 1 The steps S110, S120, S130, S140, S150, and S160 in the vehicle-mounted liveness detection method shown correspond to each other and will not be repeated here.

[0073] In this embodiment of the disclosure, Figure 1 Based on the vehicle-mounted liveness detection method shown, the method may further include the following steps.

[0074] In step S300, in response to receiving a cockpit drive signal, the UWB radar transmits a UWB pulse signal to the vehicle cockpit; the cockpit drive signal is used to drive the vehicle cockpit to switch from a first spatial state to a second spatial state.

[0075] In this embodiment, the UWB radar can respond to receiving a cockpit drive signal and trigger the transmission of a UWB pulse signal to the vehicle cockpit. This cockpit drive signal is used to switch the vehicle cockpit from a first spatial state to a second spatial state. For example, a pop-up roof control command drives the pop-up roof to rise or fall, thereby switching the cockpit space from a single-level spatial state to a two-level spatial state, or from a two-level spatial state to a single-level spatial state, or changing the cockpit height. Another example is a seat position adjustment command, which drives the seat to change position or posture, thereby changing the position of objects within the cockpit space. Based on this cockpit drive signal, on the one hand, the displacement of the driven object may pose a safety hazard to surrounding living beings; on the other hand, the displacement of the driven object may also introduce strong Doppler frequency components into the echo signal, thus interfering with the relevant liveness detection. Therefore, it is necessary to respond to the cockpit drive signal to control the UWB radar to transmit a UWB pulse signal to the vehicle cockpit for liveness detection as disclosed in this invention.

[0076] In an exemplary embodiment, the cockpit drive signal is used to drive the lifting roof of the vehicle cockpit to rise or fall. Based on this, the UWB radar transmits UWB pulse signals to the vehicle cockpit to detect the presence of living beings in the area surrounding the lifting roof. To improve liveness detection in the area surrounding the lifting roof, the UWB radar can be positioned on the top of the vehicle cockpit, so that the transmitted UWB pulse signals can cover the second-level cockpit space after the lifting roof is raised.

[0077] In some exemplary embodiments, such as Figure 3 As shown, the aforementioned step S160 may include the following steps.

[0078] In step S361, the cabin space calibration information corresponding to the first space state is obtained.

[0079] In this embodiment, the in-vehicle reflective environment varies significantly under different spatial states within the cabin. Therefore, during liveness detection, the spatial positions of various objects within the cabin can be pre-calibrated. Data comparison is then performed based on the cabin space calibration information to obtain more accurate liveness detection results. This cabin space calibration information refers to reference data pre-collected or calibrated for the vehicle cabin under different spatial states, used to assist in signal analysis and judgment during liveness detection. As mentioned earlier, the cabin drive signal is used to drive the vehicle cabin from a first spatial state to a second spatial state. Therefore, during liveness detection, the cabin space calibration information corresponding to the first spatial state can be used as the reference calibration data.

[0080] In an exemplary embodiment, UWB echo data corresponding to different spatial states of the cockpit can be collected in advance to obtain cockpit space calibration information. For example, UWB echo data for different opening angles of the roof can be collected for each state, and background features for each state can be extracted to form a space calibration database. The calibration information may include: static reflection intensity templates for each distance unit, distance range of the target area (ROI), background noise threshold, etc. In practical applications, the first spatial state is determined according to the state switching direction indicated by the current cockpit drive signal, and the corresponding cockpit space calibration information is read from the memory.

[0081] In step S362, liveness detection is performed based on the target response signal and the cockpit space calibration information.

[0082] In this embodiment, based on the target response signal obtained after signal cancellation processing, and combined with the cabin space calibration information acquired in step S361, liveness detection is performed to determine whether a living person exists in the vehicle cabin. The target response signal is a signal extracted after suppressing motion interference, which may contain micro-motion signals generated by the breathing of a living person. Since relying solely on the target response signal for liveness detection without considering the spatial position information corresponding to the initial space state of the cabin may lead to misjudgment, it is necessary to combine the cabin space calibration information corresponding to the first space state for liveness detection, thereby enhancing the ability to capture micro-motion signals generated by breathing and improving the accuracy of liveness detection results.

[0083] This disclosure provides an on-board liveness detection method that links liveness detection to cockpit drive signals. The cockpit drive signals trigger a UWB radar to emit UWB pulse signals for liveness detection. However, this cockpit drive signal presents several challenges. First, the displacement of the driven object may pose a safety hazard to surrounding live objects. Second, the displacement may introduce strong Doppler frequency components into the echo signal, thus interfering with liveness detection. Simultaneously, by pre-calibrating the cockpit space under various spatial states, basic spatial calibration information is provided for subsequent liveness detection. Combining cockpit space calibration information with liveness detection enhances the ability to capture micro-motion signals generated by breathing, improving the accuracy of liveness detection results.

[0084] Figure 4 This is a flowchart of a liveness detection method illustrated according to an exemplary embodiment of the present disclosure. Figure 1 .like Figure 4 As shown, the aforementioned step S160 may include the following steps.

[0085] In step S410, the displacement amplitude of at least one target object is determined based on the target response signal.

[0086] In this embodiment of the disclosure, by performing signal analysis on the target response signal, individual objects in space can be separated using distance or angle information, thereby identifying the various target objects present in space. These target objects may be seats, items, or living beings within a cockpit. By comparing and analyzing consecutive frames of the target response signal, it can be determined whether each target object has displacement, and thus the magnitude of that displacement can be determined.

[0087] For example, by comparing and analyzing consecutive frames of the target response signal, the phase change of the target object is extracted. Using the relationship between the phase difference and radial displacement, the displacement amplitude of the target object is calculated. The system can then report the radial distance information of each target object based on a preset detection cycle, thereby determining the displacement amplitude.

[0088] In step S420, in response to the displacement amplitude of the target object being greater than an amplitude threshold, it is determined that a living person exists in the vehicle cabin.

[0089] In this embodiment of the disclosure, when a living object moves significantly, it may produce displacement on the order of centimeters or even larger. Therefore, a pre-set amplitude threshold can be used to determine whether a target object is making significant displacement in the cabin space, thus serving as the basis for determining whether a living object exists. When the displacement amplitude of a target object exceeds the amplitude threshold, it is determined that a living object exists in the current vehicle cabin, and the corresponding status information regarding the presence or absence of a living object is then output to the ECU or central control module.

[0090] Figure 5 This is a flowchart of a liveness detection method illustrated according to an exemplary embodiment of the present disclosure. Figure 2 .like Figure 5 As shown, the aforementioned step S160 may include the following steps.

[0091] In step S510, the target response signal is differentially processed to obtain a differential response signal.

[0092] In this embodiment of the disclosure, during the liveness detection process, the target response signal is first subjected to differential processing to obtain a differential response signal. The core of differential processing is to remove static components from the signal by subtracting signals between adjacent time frames, thereby highlighting the dynamic components. In this differential response signal, reflections from stationary objects (such as seats or fixed interior trim) are significantly suppressed, while signal changes caused by breathing, heartbeat, or subtle body movements are significantly enhanced. Through differential processing, the system can effectively improve the signal-to-noise ratio of weak subtle movement signals, making breathing fluctuations that were originally submerged in a static background more prominent.

[0093] In an exemplary embodiment, the aforementioned can be used first. Figure 4 The liveness detection method shown determines whether there is a large displacement of the target object. If no large displacement is detected, then... Figure 5 The liveness detection method based on micro-motion features is shown.

[0094] In step S520, a micro-motion response signal is extracted from the target response signal based on the displacement amplitude of the differential response signal.

[0095] In this embodiment, the differential response signal reflects the change of the signal over time, and its displacement amplitude corresponds to the displacement amplitude of the target object in the radar radial direction. Since the displacement amplitude caused by breathing is typically on the order of millimeters and is periodic, the system can set a displacement amplitude threshold to retain only signal components whose displacement amplitude is within the typical range of breathing, thereby further extracting the micro-motion response signal that may be generated by breathing. Through this extraction process, the system can separate the micro-motion components related to breathing from the target response signal, remove large-amplitude motion residues and small-amplitude noise interference, and provide a high-quality input signal for subsequent feature extraction.

[0096] In step S530, micro-motion change features are extracted based on the micro-motion response signal.

[0097] In this embodiment, the micro-motion response signal may include physiological features such as respiration and heartbeat. However, these features present complex waveforms in the time domain, requiring further analysis to extract micro-motion change features suitable for liveness detection. Many physiological features can be used for liveness detection. For example, respiratory rate is within a certain frequency range (e.g., 0.1-0.8 Hz), motion amplitude is typically in the millimeter range, motion period is continuous, and motion amplitude is consistent. Therefore, this disclosure does not specifically limit the type and method of feature extraction.

[0098] In an exemplary embodiment, in the time domain, the system can calculate statistical characteristics of the signal, such as peak intervals and amplitude distribution, to evaluate the periodicity and stability of the waveform.

[0099] In an exemplary embodiment, in the frequency domain, the system can extract features such as the signal's frequency, peak energy, and signal-to-noise ratio.

[0100] In an exemplary embodiment, the micro-motion response signal can be de-trending to eliminate baseline shifts caused by temperature drift or slow environmental changes. A bandpass filter can be used to preserve the signal components within the breathing frequency band, highlighting the regularity of human respiration while suppressing vehicle vibration interference and high-frequency random noise. Frequency domain transformation can be performed on the micro-motion response signal to obtain its spectral distribution, extracting features such as peak frequency, peak energy, and signal-to-noise ratio within the breathing frequency band.

[0101] In step S540, a liveness detection is performed based on the micro-motion change characteristics to determine whether a live person exists in the vehicle cabin.

[0102] In this embodiment, the extracted micro-motion change features can be compared with pre-set signal features corresponding to the physiological laws of human respiration. When the micro-motion change features match the physiological features corresponding to human respiration, it is determined that a living person exists in the vehicle cabin, and then the corresponding status information on the presence or absence of a living person is output to the ECU or central control module.

[0103] In an exemplary embodiment, to improve detection accuracy, a respiratory fluctuation model can be pre-trained to identify subtle changes in the target response signal to determine the presence of a living being in the vehicle cabin. This respiratory fluctuation model is trained on respiratory samples from multiple scenarios and poses using a lightweight deep learning network (such as 1D-CNN+RNN), effectively distinguishing respiratory signals from non-periodic noise. Furthermore, the respiratory fluctuation model can be used to further score the judgment result, outputting a liveness confidence score. This liveness confidence score allows for a more refined determination of whether a living being exists in the cabin.

[0104] This disclosure provides a vehicle-mounted liveness detection method that can perform liveness detection based on target response signals in multiple ways. It can determine the presence of a large-scale moving object within the cabin based on the displacement amplitude of the target object, thereby determining the presence of a live person. Even when no large displacement is detected, liveness detection can also be performed based on micro-motion features. By comparing the extracted micro-motion change features with the physiological characteristics of a live person, the presence of a live person can be further determined.

[0105] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0106] Figure 6 This is a block diagram illustrating an on-board liveness detection device according to an exemplary embodiment of this disclosure. Figure 6 As shown, the vehicle-mounted liveness detection device 600 may include: a response signal acquisition unit 610, a spectrum conversion unit 620, a peak determination unit 630, an interference signal determination unit 640, a cancellation processing unit 650, and a liveness detection unit 660.

[0107] The response signal acquisition unit 610 is used to acquire the UWB response signal; the UWB response signal is a response signal based on the UWB pulse signal transmitted from the UWB radar to the vehicle cabin.

[0108] The spectrum conversion unit 620 is used to perform Fourier transform on the UWB response signal to obtain the response spectrum signal.

[0109] The peak determination unit 630 is used to determine at least one target signal peak based on the signal energy of the response spectrum signal.

[0110] The interference signal determination unit 640 is used to determine that the target signal peak corresponds to an interference signal in response to the fact that the frequency of the target signal peak is not located in the breathing frequency band.

[0111] The cancellation processing unit 650 is used to perform signal cancellation processing on the UWB response signal based on the interference signal to obtain the target response signal.

[0112] The liveness detection unit 660 is used to perform liveness detection based on the target response signal to determine whether there is a live person in the vehicle cabin.

[0113] In some exemplary embodiments of this disclosure, the spectrum conversion unit 620 is further configured to perform spatial domain conversion on the UWB response signal to obtain a spatial domain response signal; obtain a target region response signal from the spatial domain response signal according to a preset target region; and perform Fourier transform on the target region response signal to obtain the response spectrum signal.

[0114] In some exemplary embodiments of this disclosure, the cancellation processing unit 650 is further configured to: obtain signal parameters of the interference signal based on the interference signal; align the interference signal with the UWB response signal; and compensate the UWB response signal based on the signal parameters of the interference signal to obtain the target response signal.

[0115] In some exemplary embodiments of this disclosure, the cancellation processing unit 650 is further configured to filter the UWB response signal based on the breathing frequency band to obtain the target response signal.

[0116] In some exemplary embodiments of this disclosure, the cancellation processing unit 650 is further configured to filter the UWB response signal using an adaptive filter to obtain the target response signal; wherein the adaptive filter uses the interference signal as a reference input.

[0117] In some exemplary embodiments of this disclosure, a UWB transmitting unit is configured to transmit a UWB pulse signal to the vehicle cabin in response to receiving a cabin drive signal; the cabin drive signal is configured to drive the vehicle cabin to switch from a first spatial state to a second spatial state.

[0118] In some exemplary embodiments of this disclosure, the cockpit drive signal is used to drive the lifting roof of the vehicle cockpit to rise or fall.

[0119] In some exemplary embodiments of this disclosure, the liveness detection unit 660 is further configured to acquire cabin space calibration information corresponding to the first space state; and perform liveness detection based on the target response signal and the cabin space calibration information.

[0120] In some exemplary embodiments of this disclosure, the liveness detection unit 660 is further configured to determine the displacement amplitude of at least one target object based on the target response signal; and to determine the presence of a live body in the vehicle cabin in response to the displacement amplitude of the target object being greater than an amplitude threshold.

[0121] In some exemplary embodiments of this disclosure, the liveness detection unit 660 is further configured to perform differential processing on the target response signal to obtain a differential response signal; extract a micro-motion response signal from the target response signal based on the displacement amplitude of the differential response signal; extract micro-motion change features based on the micro-motion response signal; and perform liveness detection based on the micro-motion change features to determine whether a live body exists in the vehicle cabin.

[0122] In some exemplary embodiments of this disclosure, the liveness detection unit 660 is further configured to perform feature recognition on the micro-motion change features using a pre-trained respiratory fluctuation model to determine whether a live body exists in the vehicle cabin.

[0123] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0124] It should be noted that the acquisition, storage, use, and processing of data in this disclosed technical solution all comply with the relevant provisions of national laws and regulations.

[0125] Figure 7 This is a functional block diagram of a vehicle according to an exemplary embodiment of the present disclosure. For example, vehicle 700 can be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. Vehicle 700 can be an intelligent driving vehicle, a semi-intelligent driving vehicle, or a non-intelligent driving vehicle.

[0126] Reference Figure 7The vehicle 700 may include various subsystems, such as an infotainment system 710, a perception system 720, a decision control system 730, a drive system 740, and a computing platform 750. The vehicle 700 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of the vehicle 700 can be interconnected via wired or wireless means.

[0127] In some embodiments, the infotainment system 710 may include a communication system, an entertainment system, and a navigation system, etc.

[0128] The perception system 720 may include several sensors for sensing information about the environment surrounding the vehicle 700. For example, the perception system 720 may include a global positioning system (which may be GPS, BeiDou, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0129] The decision control system 730 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0130] The drive system 740 may include components that provide powered motion to the vehicle 700. In one embodiment, the drive system 740 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0131] Some or all of the functions of vehicle 700 are controlled by computing platform 750. Computing platform 750 may include at least one processor 751 and memory 752, and processor 751 may execute instructions 753 stored in memory 752.

[0132] Processor 751 can be any conventional processor, such as a commercially available CPU. Processors may also include graphics processing units (GPUs), field-programmable gate arrays (FPGAs), systems-on-chips (SoCs), application-specific integrated circuits (ASICs), or combinations thereof.

[0133] The memory 752 can be implemented by any type of volatile or non-volatile 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 storage, flash memory, magnetic disk or optical disk.

[0134] In addition to instruction 753, memory 752 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in memory 752 can be used by computing platform 750.

[0135] In this embodiment of the disclosure, processor 751 may execute instruction 753 to complete all or part of the steps of the above-described vehicle-mounted liveness detection method.

[0136] In some embodiments of this disclosure, a non-transitory computer-readable storage medium is provided, which, when the instructions in the storage medium are executed by the processor of a mobile terminal, enables the mobile terminal to perform all or part of the steps of the above-described vehicle-mounted liveness detection method.

[0137] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0138] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A vehicle-mounted liveness detection method, characterized in that, The method includes: Acquire the UWB response signal; the UWB response signal is a response signal based on the UWB pulse signal transmitted from the UWB radar to the vehicle cockpit; Perform a Fourier transform on the UWB response signal to obtain the response spectrum signal; Based on the signal energy of the response spectrum signal, at least one target signal peak is determined; In response to the fact that the frequency of the target signal peak is not located in the breathing frequency band, it is determined that the target signal peak corresponds to an interference signal; Based on the interference signal, the UWB response signal is subjected to signal cancellation processing to obtain the target response signal; Liveness detection is performed based on the target response signal to determine whether there is a living person in the vehicle cabin.

2. The method according to claim 1, characterized in that, The step of performing a Fourier transform on the UWB response signal to obtain the response spectrum signal includes: The UWB response signal is spatially transformed to obtain a spatial domain response signal; Based on the preset target area, the target area response signal is obtained from the spatial domain response signal; The response signal of the target region is subjected to Fourier transform to obtain the response spectrum signal.

3. The method according to claim 1, characterized in that, The step of performing signal cancellation processing on the UWB response signal based on the interference signal to obtain the target response signal includes: Based on the interference signal, obtain the signal parameters of the interference signal; Align the interference signal with the UWB response signal; The UWB response signal is compensated based on the signal parameters of the interference signal to obtain the target response signal.

4. The method according to claim 1, characterized in that, The step of performing signal cancellation processing on the UWB response signal based on the interference signal to obtain the target response signal includes: The UWB response signal is filtered based on the breathing frequency band to obtain the target response signal.

5. The method according to claim 1, characterized in that, The step of performing signal cancellation processing on the UWB response signal based on the interference signal to obtain the target response signal includes: The UWB response signal is filtered by an adaptive filter to obtain the target response signal; wherein the adaptive filter uses the interference signal as a reference input.

6. The method according to claim 1, characterized in that, The method further includes: In response to receiving a cockpit drive signal, the UWB radar transmits a UWB pulse signal to the vehicle cockpit; the cockpit drive signal is used to drive the vehicle cockpit to switch from a first spatial state to a second spatial state.

7. The method according to claim 6, characterized in that, The cockpit drive signal is used to drive the lifting roof of the vehicle cockpit to rise or fall.

8. The method according to claim 6, characterized in that, The liveness detection based on the target response signal includes: Obtain the cockpit space calibration information corresponding to the first spatial state; Liveness detection is performed based on the target response signal and the cabin space calibration information.

9. The method according to claim 1 or 8, characterized in that, The liveness detection based on the target response signal includes: Based on the target response signal, determine the displacement amplitude of at least one target object; In response to the displacement amplitude of the target object being greater than an amplitude threshold, it is determined that a living person exists in the vehicle cabin.

10. The method according to claim 1 or 8, characterized in that, The liveness detection based on the target response signal includes: The target response signal is differentially processed to obtain a differential response signal; Based on the displacement amplitude of the differential response signal, the micro-motion response signal is extracted from the target response signal; Based on the micro-motion response signal, extract the micro-motion change features; Liveness detection is performed based on the micro-motion change characteristics to determine whether there are living beings inside the vehicle cabin.

11. The method according to claim 10, characterized in that, The step of performing liveness detection based on the micro-motion change characteristics to determine whether a living being exists in the vehicle cabin includes: The micro-motion change features are identified by a pre-trained respiratory fluctuation model to determine whether there is a living person in the vehicle cabin.

12. A vehicle-mounted liveness detection device, characterized in that, include: The response signal acquisition unit is used to acquire the UWB response signal; The UWB response signal is a response signal based on the UWB pulse signal transmitted from the UWB radar to the vehicle cockpit. The spectrum conversion unit is used to perform a Fourier transform on the UWB response signal to obtain the response spectrum signal; A peak determination unit is used to determine at least one target signal peak based on the signal energy of the response spectrum signal; An interference signal determination unit is configured to determine that the target signal peak corresponds to an interference signal in response to the fact that the frequency of the target signal peak is not located in the breathing frequency band. The cancellation processing unit is used to perform signal cancellation processing on the UWB response signal based on the interference signal to obtain the target response signal; A liveness detection unit is used to perform liveness detection based on the target response signal to determine whether there is a live person in the vehicle cabin.

13. The vehicle-mounted liveness detection device according to claim 12, characterized in that, The spectrum conversion unit is further configured to perform spatial domain conversion on the UWB response signal to obtain a spatial domain response signal; obtain a target region response signal from the spatial domain response signal according to a preset target region; and perform Fourier transform on the target region response signal to obtain the response spectrum signal.

14. The vehicle-mounted liveness detection device according to claim 12, characterized in that, The device further includes: The UWB transmitting unit is used to transmit the UWB pulse signal to the vehicle cockpit in response to receiving a cockpit drive signal; the cockpit drive signal is used to drive the vehicle cockpit to switch from a first spatial state to a second spatial state.

15. The vehicle-mounted liveness detection device according to claim 14, characterized in that, The liveness detection unit is also used to acquire cabin space calibration information corresponding to the first space state; and to perform liveness detection based on the target response signal and the cabin space calibration information.

16. The vehicle-mounted liveness detection device according to claim 12 or 15, characterized in that, The liveness detection unit is further configured to perform differential processing on the target response signal to obtain a differential response signal; extract a micro-motion response signal from the target response signal based on the displacement amplitude of the differential response signal; and extract micro-motion change features based on the micro-motion response signal. Liveness detection is performed based on the micro-motion change characteristics to determine whether there are living beings inside the vehicle cabin.

17. A vehicle, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to implement the steps of the vehicle-mounted liveness detection method according to any one of claims 1 to 11.

18. A non-transitory computer-readable storage medium, wherein when instructions in the storage medium are executed by a processor of a mobile terminal, the mobile terminal is enabled to perform the vehicle-mounted liveness detection method according to any one of claims 1 to 11.

19. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the vehicle-mounted liveness detection method as described in any one of claims 1 to 11.

Images