Signal processing method of detection radar, living body detection system and vehicle

Abstract

The invention discloses a signal processing method of a detection radar, a living body detection system and a vehicle, the signal processing method of the detection radar comprises the following steps: obtaining a first radar echo signal of the detection radar, the first radar echo signal comprising a respiration characteristic signal and being used for living body detection; filtering the breathing characteristic signal from the first radar echo signal to obtain a second radar echo signal; and performing signal-to-noise ratio estimation of the detection radar based on the first radar echo signal and the second radar echo signal. According to the method, the complexity of signal-to-noise ratio estimation can be effectively reduced, and the utilization rate of data is enhanced, so that the method can better adapt to various vehicle application scenes.

Description

Technical Field

[0001] The present application belongs to the field of signal processing technology, and specifically relates to a signal processing method for a detection radar, a living body detection system and a vehicle, as well as an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] As vehicles become increasingly intelligent, more and more are equipped with liveness detection systems. Related technologies for liveness detection systems employ detection radars, such as ultra-wideband radars, and perform liveness detection based on the radar signals from these radars. For these ultra-wideband radars, their detection signal-to-noise ratio (SNR) is a key metric for evaluating their detection capabilities. Estimating the radar's SNR is a technical challenge that needs to be addressed. Summary of the Invention

[0003] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a signal processing method for detection radar, a liveness detection system and vehicle, as well as electronic equipment, a computer-readable storage medium, and a computer program product, which can effectively reduce the complexity of signal-to-noise ratio estimation and enhance the utilization of data resources, thereby better adapting to various vehicle application scenarios.

[0004] In a first aspect, an embodiment of the present application provides a signal processing method for a detection radar, comprising:

[0005] Acquiring a first radar echo signal of a detection radar, where the first radar echo signal includes a breathing characteristic signal and is used for liveness detection;

[0006] filtering out the breathing characteristic signal from the first radar echo signal to obtain a second radar echo signal;

[0007] A signal-to-noise ratio of the detection radar is estimated based on the first radar echo signal and the second radar echo signal.

[0008] In some embodiments, the signal-to-noise ratio estimation of the detection radar based on the first radar echo signal and the second radar echo signal includes:

[0009] Obtaining a first power value corresponding to the first radar echo signal;

[0010] Obtaining a second power value corresponding to the second radar echo signal;

[0011] A signal-to-noise ratio (SNR) of the detection radar is estimated based on the first power value and the second power value to obtain a SNR estimation result.

[0012] In some embodiments, performing the signal-to-noise ratio estimation of the detection radar based on the first power value and the second power value to obtain a signal-to-noise ratio estimation result includes:

[0013] A first difference between the first power value and the second power value is obtained, and a ratio of the first difference to the second power value is used as a signal-to-noise ratio estimation result.

[0014] In some embodiments, obtaining the first power value corresponding to the first radar echo signal includes:

[0015] A power spectrum of the first radar echo signal is acquired, and the power spectrum of the first radar echo signal is integrated to obtain a first power value corresponding to the first radar echo signal.

[0016] In some embodiments, obtaining the second power value corresponding to the second radar echo signal includes:

[0017] A power spectrum of the second radar echo signal is acquired, and the power spectrum of the second radar echo signal is integrated to obtain a second power value corresponding to the second radar echo signal.

[0018] In some embodiments, filtering the breathing characteristic signal from the first radar echo signal to obtain the second radar echo signal includes:

[0019] The first radar echo signal is subjected to band-stop filtering to filter out the respiratory characteristic signal within the respiratory frequency band, thereby obtaining a second radar echo signal.

[0020] In some embodiments, the first radar echo signal is a channel impulse response signal.

[0021] In some embodiments, before filtering out the breathing characteristic signal from the first radar echo signal to obtain the second radar echo signal, the method further includes:

[0022] Signal preprocessing is performed on the first radar echo signal.

[0023] In some embodiments, the signal preprocessing includes at least one of obtaining a modulus value, centering processing, and removing linear processing.

[0024] In some embodiments, it further includes:

[0025] Liveness detection is performed based on the first radar echo signal of the detection radar.

[0026] In some embodiments, the above-mentioned liveness detection based on the first radar echo signal includes:

[0027] Liveness detection is performed based on the first radar echo signal of the detection radar and the signal-to-noise ratio estimation result.

[0028] In some embodiments, it further includes:

[0029] Output alarm information based on the live results.

[0030] In some embodiments, before performing liveness detection based on the first radar echo signal of the detection radar, the method further includes:

[0031] Make sure the liveness detection function is enabled.

[0032] In some embodiments, before filtering out the breathing characteristic signal from the first radar echo signal, the method further includes:

[0033] Make sure the signal quality detection function is enabled.

[0034] In a second aspect, an embodiment of the present application provides a signal processing device for a detection radar, comprising:

[0035] a signal acquisition module, configured to acquire a first radar echo signal of a detection radar, the first radar echo signal including a breathing characteristic signal, and used for liveness detection;

[0036] a second signal acquisition module, configured to filter out the breathing characteristic signal from the first radar echo signal to obtain a second radar echo signal;

[0037] The signal-to-noise ratio estimation module is used to estimate the signal-to-noise ratio of the detection radar based on the first radar echo signal and the second radar echo signal.

[0038] In a third aspect, an embodiment of the present application provides a vehicle-mounted system, comprising a detection radar and a signal-to-noise ratio estimation module, wherein the signal-to-noise ratio estimation module is used to obtain a first radar echo signal of the detection radar, wherein the first radar echo includes a breathing characteristic signal and is used to perform liveness detection, filter out the breathing characteristic signal from the first radar echo signal to obtain a second radar echo signal, and perform signal-to-noise ratio estimation of the detection radar based on the first radar echo signal and the second radar echo signal.

[0039] In some embodiments, it further includes:

[0040] The liveness detection module is used to perform liveness detection based on the first radar echo signal of the detection radar.

[0041] In some embodiments, it further includes:

[0042] The application control module is used to control the startup of at least one of the signal-to-noise ratio estimation module and the living body detection module.

[0043] In a fourth aspect, an embodiment of the present application provides an electronic device comprising: a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the signal processing method for detecting radar as described in the first aspect are implemented.

[0044] In a fifth aspect, an embodiment of the present application provides a vehicle, comprising the vehicle system described in the third aspect, or the electronic device described in the fourth aspect.

[0045] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the signal processing method for detecting radar as described in the first aspect are implemented.

[0046] In a seventh aspect, an embodiment of the present application provides a computer program product, which, when executed by a vehicle's processor, implements the steps of the signal processing method for detection radar as described in the first aspect.

[0047] The technical solution provided in this application obtains a first radar echo signal from a detection radar, which includes a breathing characteristic signal and is used for liveness detection; filters out the breathing characteristic signal from the first radar echo signal to obtain a second radar echo signal; and estimates the signal-to-noise ratio of the detection radar based on the first and second radar echo signals. Because the above technical solution filters out the breathing characteristic signal from the first radar echo information capable of liveness detection, extracts the noise signal therefrom, and obtains the second radar echo signal, and uses the two radar echo signals and the first radar echo information for signal-to-noise ratio estimation based on existing software and hardware resources, it is not only easy to implement, but also can enhance data utilization and save costs, making it more adaptable to various vehicle application scenarios.

[0048] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0050] Figure 1 This is a flow chart of a signal processing method for detecting radar in an embodiment of the present application;

[0051] Figure 2 This is a schematic diagram of a detection radar position in an embodiment of the present application;

[0052] Figure 3 for Figure 1 The specific execution flow chart of step 103 shown;

[0053] Figure 4 This is a schematic diagram of a process for performing signal-to-noise ratio estimation in an embodiment of the present application;

[0054] Figure 5This is a schematic diagram of a process for performing liveness detection in an embodiment of the present application;

[0055] Figure 6 This is a schematic structural diagram of a signal processing device for detecting radar in an embodiment of the present application;

[0056] Figure 7 This is a structural diagram of a vehicle system in an embodiment of the present application;

[0057] Figure 8 This is a schematic structural diagram of a detection radar in an embodiment of the present application;

[0058] Figure 9 This is a schematic structural diagram of an electronic device according to an embodiment of the present application;

[0059] Figure 10 This is a schematic structural diagram of a vehicle in an embodiment of the present application;

[0060] Figure 11 This is a schematic structural diagram of another vehicle in an embodiment of the present application. DETAILED DESCRIPTION

[0061] The following describes embodiments of the present application in more detail with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are for illustrative purposes only and are not intended to limit the scope of protection of the present application.

[0062] It should be understood that the various steps described in the method embodiments of the present application can be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0063] As discussed in the background, most vehicles are currently equipped with liveness detection systems. However, the reliability of these systems' detection results requires further evaluation based on signal-to-noise ratio (SNR) estimation. However, existing SNR estimation methods based on radar signals are limited by specific signal processing and hardware configurations, making them difficult to implement and limited in applicability. They struggle to adapt to the complex and unique environment inside vehicles, and therefore cannot meet the needs of diverse vehicle application scenarios.

[0064] Therefore, this application provides a technical solution for a signal processing method for detecting radar. Figure 1 A flow chart of a signal processing method for detecting radar provided in an embodiment of the present application is shown as follows: Figure 1 As shown, the following steps are included:

[0065] Step 101: Acquire a first radar echo signal of a detection radar, where the first radar echo includes a breathing characteristic signal and is used for liveness detection.

[0066] The detection radar can be an ultra-wideband radar, which is a radar system that uses ultra-wideband (UWB) signals for detection and ranging. It transmits a pulse signal through a transmitter and uses a receiver to receive the echo of the pulse signal after it is reflected or scattered by the target object to detect the existence, position and motion state of the target object. The radar can measure small changes in the target object and has strong environmental anti-interference ability, and can maintain data reliability in complex scenes. The first radar echo signal is a channel impulse response signal (Channel Impulse Response Signal). Response, abbreviated as: CIR), that is, the echo signal of the pulse signal emitted by the UWB radar reflected or scattered by the target object. The above-mentioned first radar echo signal can also include the breathing characteristic signal and heartbeat characteristic signal of the living body, which can be used for living body detection; the breathing characteristic signal refers to the signal reflecting the physiological changes in the breathing process of the living body, for example, the breathing characteristic signal of living bodies such as humans and animals, which can be obtained by the detection radar. In this application, it can be the breathing frequency signal of the living body; living body detection refers to the process of judging whether there is a living body in the current environment through detection technology, such as detecting whether there is a child in a locked car. In this application, the number and placement of the above-mentioned detection radars can be set according to engineering requirements. For example, when using UWB radar for vehicle living body detection, one UWB radar can be used and placed on the roof, such as Figure 2 shown.

[0067] Step 102: filtering the breathing characteristic signal from the first radar echo signal to obtain a second radar echo signal;

[0068] After detecting with a UWB radar and obtaining a first radar echo signal, the first radar echo information is filtered to remove the respiratory characteristic signal, thereby obtaining a second radar echo signal. The second radar echo signal is a radar echo signal that does not include the respiratory characteristic signal and may include noise, heartbeat characteristic signals, etc. The noise may include noise generated by environmental interference on the detection radar, electrical noise, etc. The heartbeat characteristic signal is relatively weak and can be ignored in subsequent calculations. Filtering is a signal processing technique that improves signal quality by removing unwanted frequency components from the original signal or enhancing desired frequency components.

[0069] Step 103: Estimating the signal-to-noise ratio of the detection radar based on the first radar echo signal and the second radar echo signal.

[0070] After acquiring the first and second radar echo signals, the signal-to-noise ratio (SNR) of the detection radar can be estimated using these two signals to assess the quality of the detection radar signal. The SNR measures the relative strength of the signal to the noise.

[0071] As described above, the above method performs respiratory characteristic signal filtering processing on the first radar echo information capable of liveness detection, extracts the noise signal therefrom, and obtains the second radar echo signal. Based on the existing software and hardware resources, the above two radar echo signals and the first radar echo information are used to estimate the signal-to-noise ratio. This method is not only easy to implement, but also can enhance data utilization and save costs, thereby enabling it to better adapt to various vehicle application scenarios.

[0072] In an embodiment of the present application, the first radar echo signal may include multiple echo signals. That is, the detection radar transmits a series of periodic pulse signals to form a pulse sequence. Subsequently, a set number of echo signals are selected as a group for processing. For example, M pulse signals are selected as a group. The set number can be determined based on user needs and the computing resources of the device.

[0073] In this embodiment of the present application, before filtering out the breathing characteristic signal from the first radar echo information, it is also possible to determine whether the signal quality detection function is required in the current scenario. For example, in a vehicle scenario, when it is determined that the vehicle doors are closed and locked, and the UWB radar is activated, the vehicle signal quality detection function can be activated, that is, the signal-to-noise ratio estimation of the UWB radar can be performed. This effectively avoids wasting system resources during signal quality detection, thereby improving the intelligence and practicality of the overall system.

[0074] Specifically, Figure 3 for Figure 1 The specific execution flow chart of step 103 is as shown in FIG. Figure 3 As shown, the following steps are included:

[0075] Step 301: Obtain a first power value corresponding to a first radar echo signal;

[0076] After obtaining the first radar echo signal of the detection radar in step 101, it can be further processed for subsequent calculations. Specifically, the power spectrum of the first radar echo signal can be first obtained, and then the power spectrum can be integrated to obtain the power value of the first radar echo signal, i.e., the first power value. The power value refers to the energy per unit time of the signal received by the detection radar, indicating the strength of the signal; the power spectrum is the distribution of the signal power in the frequency domain, which is used to reflect the power of the signal at different frequency components. The radar echo signal can be processed using methods such as Fourier transform and window function to obtain the corresponding power spectrum. For example, when calculating the power spectrum of the radar echo signal using Fourier transform, the first radar echo signal is first Fourier transformed to obtain the corresponding frequency domain signal. Then, the square of the amplitude of the frequency domain signal is calculated and the square of the amplitude is divided by the signal length to obtain the power spectrum of the radar echo signal. The Fourier transform is a linear integral transform used to convert a signal from the time domain to the frequency domain.

[0077] Step 302: Obtain a second power value corresponding to the second radar echo signal;

[0078] The process for obtaining the first power value corresponding to the first radar echo signal is the same as that for obtaining the first power value corresponding to the first radar echo signal. That is, first obtain the power spectrum of the second radar echo signal, then integrate the power spectrum to obtain the second power value corresponding to the second radar echo signal. The process for obtaining the power spectrum of the second radar echo signal can be referenced to the process for obtaining the power spectrum of the first radar echo signal and is not further described here.

[0079] Step 303: Estimating the signal-to-noise ratio of the detection radar based on the first power value and the second power value to obtain a signal-to-noise ratio estimation result.

[0080] After obtaining the power values corresponding to the first radar echo signal and the second radar echo signal respectively through step 301 and step 302, the above power values can be used to perform ratio calculation to estimate the signal-to-noise ratio of the detection radar used. Specifically, the first power value and the second power value are first calculated to obtain the difference between the two power values, that is, the first difference. Then, the first difference and the second power value are calculated to obtain the signal-to-noise ratio estimation result of the detection radar. The above signal-to-noise ratio estimation result can be used to evaluate the signal quality of the detection radar. The signal-to-noise ratio estimation method of first performing the difference and then the ratio can simplify the calculation process, making it easier to implement under the existing software and hardware resources. In this way, not only can the complexity of the signal-to-noise ratio estimation be reduced, but also costs can be saved, thereby better adapting to various vehicle application scenarios and meeting the signal-to-noise ratio estimation requirements in different scenarios.

[0081] In an embodiment of the present application, when filtering out the respiratory characteristic signal from the first radar echo signal to obtain the second radar echo signal, specifically, the first radar echo signal can be subjected to band-stop filtering, thereby filtering out the respiratory characteristic signal within a certain frequency band to obtain the second radar echo signal. The above-mentioned band-stop filtering refers to allowing most frequency components in the radar echo signal to pass through, while attenuating the signal within a certain frequency range to an extremely low level, so as to achieve the purpose of filtering out the signal within the frequency range. The above-mentioned respiratory frequency band can be pre-specified, that is, it can be pre-specified according to actual application requirements. For example, for the application requirements of liveness detection, especially when it is necessary to detect the breathing of children, the children's respiratory frequency band, that is, the respiratory frequency band of 0.3Hz to 0.5Hz, can be specified. In this way, the original radar echo signal is subjected to band-stop filtering, which can effectively filter out the respiratory characteristic signal within the specified frequency band, thereby not only improving the accuracy of signal processing, but also meeting the needs of different application scenarios.

[0082] In some embodiments, before obtaining the second radar echo signal based on the first radar echo signal of the detection radar, the first radar echo signal may be preprocessed to facilitate subsequent use of the first radar echo signal for signal-to-noise ratio estimation. Specifically, the first radar echo signal may be subjected to modulus calculation, centering, and delinearization to obtain a signal with prominent periodicity and more suitable for frequency domain analysis. Since the first radar echo signal is typically represented in complex form, with its real and imaginary parts reflecting the amplitude and phase of the signal, respectively, modulus calculation can eliminate phase interference and focus on amplitude variations, such as fluctuations in reflection intensity caused by micro-motion of the human body. Centering reduces the mean of the first radar echo signal to zero to eliminate DC components in the signal, preventing them from masking minor variations, such as low-frequency fluctuations caused by breathing, and thus interfering with the determination of the respiratory characteristic signal. Delinearization eliminates baseline drift in the first radar echo signal through linear fitting. For example, a line is fitted using the least squares method and then removed from the first radar echo signal to eliminate linear components. The above-mentioned baseline drift may be caused by temperature, equipment aging and other reasons.

[0083] In the embodiment of the present application, if the acquired first radar echo signal of the detection radar does not include a breathing characteristic signal, the signal-to-noise ratio estimation process is also used to perform signal-to-noise ratio estimation on the detection radar used.

[0084] In the embodiment of the present application, when the detection radar is located inside the vehicle and the signal-to-noise ratio is estimated, the specific process is as follows: Figure 4 As shown, the following steps are included:

[0085] Step 401: Determine whether the vehicle is in a door-locked state;

[0086] After the user leaves the vehicle, the current state of the vehicle is determined, that is, whether the vehicle is currently in a state with the doors closed and locked. If the vehicle is in a state with the doors closed and locked, it is determined that the detection radar can be started and step 402 is executed. Otherwise, step 409 is executed, indicating that the vehicle in the current state does not need to start the detection radar, thereby reducing unnecessary waste of resources.

[0087] Step 402: Determine whether to enable the signal quality detection function;

[0088] After determining in the above steps that the vehicle is in the locked state with its doors closed, the process then proceeds to determine whether the signal quality detection function is enabled, i.e., whether the received radar echo signal is used to estimate the signal-to-noise ratio. If so, step 403 is executed; otherwise, step 409 is executed, terminating the process. This determination of whether the signal quality detection function is enabled can be based on pre-set rules. Specifically, the system defaults to automatically performing signal-to-noise ratio estimation when the vehicle is locked with its doors closed and the detection radar is enabled. The user can subsequently modify this setting, in which case the determination will be based on the modified rule.

[0089] Step 403: pre-process the first radar echo signal;

[0090] After the detection radar is activated in step 401, a first radar echo signal is acquired. Subsequently, the first radar echo signal is subjected to modulus calculation, centering, and linearization removal to obtain a signal that is more amenable to frequency domain analysis. For example, the first radar echo signal S1 is preprocessed to obtain a preprocessed first radar echo signal S2.

[0091] Step 404: Obtain a first power value corresponding to the first radar echo signal;

[0092] A power value is calculated for the preprocessed first radar echo signal, that is, a power spectrum of the preprocessed first radar echo signal is first obtained, and then the power spectrum is integrated to obtain a first power value. For example, the power spectrum of the radar echo signal S2 is calculated, and the power spectrum is integrated to obtain a first power value P2.

[0093] Step 405: Acquire a second radar echo;

[0094] This step is to perform band-stop filtering on the preprocessed first radar echo signal to filter out the respiratory characteristic signals within the specified respiratory frequency band, thereby obtaining a second radar echo signal. For example, the radar echo signal S2 is band-stop filtered to filter out the children's respiratory characteristic signals in the children's respiratory frequency band of 0.3Hz to 0.5Hz, thereby obtaining the radar echo signal S3.

[0095] Step 406: Obtain a second power value corresponding to the second radar echo;

[0096] The same method as step 404 is used to calculate the power value of the second radar echo signal, for example, the power value P3 of the radar echo signal S3.

[0097] Step 407: Estimating the signal-to-noise ratio of the detection radar;

[0098] In this step, the difference between the first power value and the second power value is first calculated, and then the ratio of the difference to the second power value is calculated. The result of the ratio calculation is the signal-to-noise ratio estimation result. For example, the formula The signal-to-noise ratio estimation result is obtained to evaluate the signal quality of the detection radar, where S is the signal-to-noise ratio estimation result, P2 represents the first power value, and P3 represents the second power value.

[0099] Step 408: Transmit the signal-to-noise ratio estimation result;

[0100] After obtaining the signal-to-noise ratio estimation result, the above result can be transmitted to the whole vehicle system and the liveness detection module. Subsequently, the whole vehicle system can display the signal-to-noise ratio estimation result to the liveness detection module, which can evaluate the liveness detection result of the liveness detection module so that the user can more intuitively judge the reliability of the liveness detection result.

[0101] Step 409: End the signal-to-noise ratio estimation.

[0102] After it is determined not to enable the signal quality detection function, or after the signal quality detection function is enabled and the signal-to-noise ratio estimation is completed, the process ends.

[0103] In an embodiment of the present application, the first radar echo signal obtained can be used not only for the estimation of the signal-to-noise ratio of the detection radar, but also for liveness detection. Specifically, liveness detection can be performed based on the first radar echo signal and the signal-to-noise ratio estimation result, that is, first determine whether there is a living body in the current scene based on the breathing characteristic signal in the above-mentioned first radar echo signal, and obtain a liveness detection result. Then, the liveness detection result is evaluated using the above-mentioned signal-to-noise ratio estimation result, so that the user can better judge the reliability of the liveness detection result. The above-mentioned liveness detection results include both existence and non-existence. For example, when applied to the detection of the presence of children in the car, it is possible to determine whether there is a breathing characteristic signal in the child's breathing frequency band in the first radar echo signal, that is, to determine whether there is a child's breathing frequency signal, and obtain a child presence detection result. If so, it is determined that there is a child in the car, and the calculated signal-to-noise ratio estimation value is displayed simultaneously, so that the user can judge the reliability of the child presence detection result. Otherwise, the detection is terminated. This process does not require any additional hardware equipment. Liveness detection can be achieved by using only the first radar echo signal collected by the existing detection radar. This not only enables efficient data reuse, but also saves hardware costs, making the entire detection system more economical and efficient. At the same time, the liveness detection results are evaluated through the signal-to-noise ratio results, which not only improves the accuracy of the detection, but also provides users with a more comprehensive and reliable detection experience.

[0104] In an embodiment of the present application, a variety of liveness detection methods can be used, and liveness detection can be performed based on the first radar echo signal and the signal-to-noise ratio estimation result. For example, frequency analysis, classification algorithm, neural network model and other methods can be used for liveness detection. A suitable liveness detection method can be selected according to the needs of the actual application scenario to complete the liveness detection task. When the frequency analysis method is used, the first radar echo signal can be Fourier transformed to obtain the frequency domain characteristics of the above radar echo signal. Subsequently, the above frequency domain characteristics are analyzed to determine whether there is a breathing characteristic signal within a specified frequency band in the first radar echo signal, thereby obtaining the liveness detection result of the current scene. At the same time, the liveness detection result is evaluated using the signal-to-noise ratio result. For example, if there is a child's breathing characteristic signal within the frequency band of 0.3Hz to 0.5Hz, it is determined that there is a child in the current scene. This method is simple and easy to implement, has a certain degree of universality, and can handle liveness detection tasks in different scenarios. When a classification algorithm is used, the time domain and frequency domain features of the first radar echo signal can be first extracted using Fourier transform, wavelet transform, time-frequency analysis, etc., and then the above time domain and frequency domain features are input into the classification algorithm for processing and analysis. Respiratory information such as the living person's breathing frequency, breathing depth, and breathing pattern can be output, and based on the above information, it is determined whether there is a living person in the current scene to obtain a liveness detection result, and the above liveness detection result is evaluated based on the signal-to-noise ratio result. The living person's breathing information is obtained by the classification algorithm, and then the presence of a living person is determined, which can improve the efficiency and accuracy of liveness detection. The above classification algorithm can include multiple types of algorithms, such as support vector machines, artificial neural networks, K-nearest neighbor algorithms, etc. When a neural network model is used, the first radar echo signal can be input into the neural network model for in-depth analysis and prediction, and respiratory information such as the living person's breathing frequency, breathing depth, and breathing pattern can be output. Specifically, the neural network model automatically extracts the respiratory characteristics of the first radar echo signal, and then classifies the respiratory characteristics of the living body after obtaining them, thereby obtaining the respiratory information of the living body, and judges whether there is a living body in the current scene based on the respiratory information, obtains the liveness detection result, and evaluates the liveness detection result based on the signal-to-noise ratio result. This method is highly automated and intelligent, and can greatly improve the accuracy and efficiency of liveness detection. The neural network model is obtained by training with a large amount of physiological information signal data, and includes a model based on a convolutional neural network and a model based on a recurrent neural network. The model based on the convolutional neural network can efficiently process physiological information signals with a grid structure; the model based on the recurrent neural network can well process and analyze physiological information signals in a time series.

[0105] In some embodiments, before performing liveness detection using the liveness detection method in the above embodiments, the first radar echo signal may be preprocessed, for example, by removing noise from the signal through filtering technology and performing gain adjustment to optimize the signal strength and quality. In this way, preliminary processing of the first radar echo signal in the above manner helps to reduce noise interference, multipath effects, and other factors that may negatively affect signal accuracy, thereby improving the accuracy of subsequent liveness detection.

[0106] In this embodiment of the present application, before using the first radar echo signal for liveness detection, it is also possible to determine whether the liveness detection function needs to be activated in the current scene. For example, in a vehicle scenario, when the doors are closed and the vehicle is locked, the vehicle's liveness detection function can be activated to detect the presence of a living person inside the vehicle. This strategy of first determining and then activating not only ensures the accuracy and timeliness of liveness detection, but also effectively avoids wasting system resources when detection is not necessary, thereby improving the overall intelligence and practicality of the system.

[0107] In an embodiment of the present application, after liveness detection is completed based on the first radar echo signal and the signal-to-noise ratio estimation result, and a liveness detection result is obtained, a corresponding operation can be further performed based on the liveness detection result, that is, an alarm message is generated and output based on the liveness detection result to prompt the user so that the user can take timely action. Specifically, when the liveness detection result is positive, an alarm message is automatically generated. This message can be sent to the user's mobile device, such as a mobile phone, tablet computer, or smartwatch, and the user can be notified by voice broadcast, vibration, or pop-up prompts. The user can then take timely action based on the alarm message. Otherwise, the liveness detection is terminated and no alarm message is generated to avoid unnecessary interference and false alarms. The alarm message can also be sent to the vehicle computer and digital key. The vehicle computer can perform corresponding operations based on the specific situation in the vehicle. For example, if the temperature in the vehicle is too high, the vehicle air conditioning function can be activated to adjust the temperature to a comfortable level. After receiving the alarm message, the digital key can alert the user through sound, vibration, etc. The alarm message can include information such as the specific result of the liveness detection, the signal-to-noise ratio estimation result, and the corresponding action. In this way, generating and outputting alarm information based on the liveness detection results can ensure that users receive relevant notifications in the first place, thereby promptly understanding the specific circumstances of the liveness detection and taking appropriate measures to deal with possible situations or problems.

[0108] In some embodiments, before using the first radar echo signal for liveness detection, a preliminary judgment can be made on whether there is a breathing characteristic signal of a living body in the above-mentioned first radar echo signal. Specifically, the first radar echo signal can be input into a pre-trained breathing model for in-depth analysis and classification, and finally the classification result is output. For example, when detecting the presence of a child in a vehicle scene, it is known that the child's breathing frequency band is 0.3Hz to 0.5Hz. The first radar echo received by the detection radar is input into the breathing model for analysis to determine whether there is a frequency component in the above-mentioned signal that belongs to the above-mentioned child's breathing frequency band. If it does, it is preliminarily determined that the first radar echo signal includes a child's breathing characteristic signal; continue to analyze the next group of radar echo signals until all radar echo information traversal is completed. The above-mentioned breathing model is mainly used to preliminarily judge whether there is a breathing characteristic signal in the radar echo signal of the detection radar. The model is obtained by training using a large number of breathing characteristic signals. In this application, the placement of the above-mentioned breathing model can be determined according to engineering needs. For example, as shown in 2, it is placed at the seat in the cabin.

[0109] In the embodiment of the present application, when the detection radar is located inside the vehicle and the signal-to-noise ratio estimation result is used to detect the presence of living bodies in the vehicle, the entire process is as follows: Figure 5 As shown, the following steps are included:

[0110] Step 501: Determine whether the vehicle is currently in a door-closed and locked state;

[0111] After the user leaves the vehicle, the current state of the vehicle is determined, that is, whether the vehicle is currently in a state with the doors closed and locked. If the vehicle is in a state with the doors closed and locked, it is determined that the detection radar can be started and step 502 is executed. Otherwise, step 507 is executed, indicating that the vehicle in the current state does not need to start the detection radar, thereby reducing unnecessary waste of resources.

[0112] Step 502: Start the liveness detection function;

[0113] After determining in step 501 that the vehicle is currently in a locked state with its doors closed, a liveness detection algorithm is started to perform liveness detection. Specifically, a liveness detection result is obtained based on the first radar echo signal S1 in combination with a liveness detection method.

[0114] Step 503: input the signal-to-noise ratio estimation result;

[0115] After obtaining the liveness detection result, the signal-to-noise ratio estimation result is input and the liveness detection result is evaluated using the signal-to-noise ratio estimation result so that the user can more intuitively judge the reliability of the liveness detection result.

[0116] Step 504: Transmitting the liveness detection result;

[0117] After obtaining the liveness detection result, the liveness detection result and the signal-to-noise ratio estimation result are transmitted to the vehicle system for subsequent operations. The above liveness detection results include presence and absence.

[0118] Step 505: Determine whether there is a target living body;

[0119] At this point, the vehicle system determines whether a target living being, such as a child, is present in the vehicle based on the liveness detection results. If so, step 506 is executed; otherwise, step 507 is executed. The target living being is determined based on application requirements. For example, in the case of child presence detection in a vehicle, the target living being is a child.

[0120] Step 506: Start the alarm function;

[0121] After determining in step 505 that the target living being is present in the current vehicle, the vehicle alarm function is activated and an alarm message is generated to alert the user. Specifically, the alarm message can be sent to the user's mobile device, such as a mobile phone, tablet computer, or smartwatch, and the user can be alerted by voice broadcast, vibration, or pop-up window prompts. The user can then take timely measures based on the above alarm message. At the same time, the above alarm message can also be sent to the vehicle computer and digital key. The vehicle computer can perform corresponding operations based on the specific situation in the vehicle. For example, if the temperature in the vehicle is too high at this time, the vehicle will activate the air conditioning function to adjust the temperature in the vehicle to a comfortable temperature. After receiving the above alarm message, the digital key can alert the user by sound, vibration, etc. The above alarm message may include information about the target living being, signal-to-noise ratio estimation results, and corresponding processing measures.

[0122] Step 507: End the liveness detection.

[0123] If it is determined that the vehicle is currently in another state, or the liveness detection is completed, the process ends.

[0124] In the embodiment of the present application, the above-mentioned signal-to-noise ratio estimation and liveness detection can be performed simultaneously, or the signal-to-noise ratio estimation can be performed first and then the liveness detection, or the liveness detection can be performed first and then the signal-to-noise ratio estimation.

[0125] With the above Figure 1-Figure 5 Corresponding to any of the detection radar signal processing methods shown, the present application also provides a detection radar signal processing device, Figure 6The present invention provides a schematic structural diagram of a signal processing device for a detection radar provided in an embodiment of the present invention. The device includes a first signal acquisition module 11, a second signal acquisition module 12, and a signal-to-noise ratio estimation module 13. The first signal acquisition module 11 is used to acquire a first radar echo signal of the detection radar, the first radar echo signal including a breathing characteristic signal and used for liveness detection; the second signal acquisition module 12 is used to filter out the breathing characteristic signal from the first radar echo signal to obtain a second radar echo signal; and the signal-to-noise ratio estimation module 13 is used to estimate the signal-to-noise ratio of the detection radar based on the first radar echo signal and the second radar echo signal. By processing the signal of the detection radar through the device, the first radar echo signal capable of liveness detection can be filtered out of the breathing characteristic signal based on existing software and hardware resources to obtain a noise signal, i.e., the second radar echo signal. The above two radar echo signals and the first radar echo information are used for signal-to-noise ratio estimation, which is not only easy to implement, but also can enhance data utilization and save costs, thereby enabling the device to better adapt to various vehicle application scenarios.

[0126] This application also provides a vehicle system, the architecture of which is shown in the following figure: Figure 7 As shown, the vehicle-mounted system includes a detection radar 21 and a signal-to-noise ratio estimation module 22, wherein the detection radar 21 is used to transmit a pulse signal and receive a radar echo signal; the signal-to-noise ratio estimation module 22 is used to obtain a first radar echo signal of the detection radar, the first radar echo including a breathing characteristic signal, and is used for liveness detection. Then, the breathing characteristic signal is filtered out from the first radar echo signal to obtain a second radar echo signal, and then the signal-to-noise ratio of the detection radar is estimated based on the first radar echo signal and the second radar echo signal. The above-mentioned signal-to-noise ratio estimation module can also be called a signal quality detection module. Through this vehicle-mounted system, the credible noise ratio can be estimated based on existing software and hardware resources and the first radar echo information capable of liveness detection. This not only makes it easier to achieve enhanced data utilization, but also saves costs, making the vehicle-mounted system more suitable for a variety of vehicle application scenarios.

[0127] The above detection radar 21, such as Figure 8As shown, it can be composed of an antenna 211, a waveform generator 212, a transmitter 213, a duplexer 214, a low-noise RF amplifier 215, a mixer 216, an intermediate frequency amplifier 217, a local oscillator 218, a signal processor 219, a data processor 220 and a display 221. The antenna 111 is used to receive the echo signal of the detection radar; the waveform generator 212 is used to generate a pulse waveform; the transmitter 213 is used to modulate the waveform generated by the waveform generator to the radio frequency and amplify the power of the waveform; the duplexer 214, also known as a circulator or a transceiver switch, is used to switch between transmitting radar signals and receiving radar echo signals; the low-noise RF amplifier 215 is used to preliminarily amplify the received weak echo signal while minimizing noise interference to improve signal quality; the mixer 216 mixes the amplified RF signal with the local oscillator signal to convert the signal frequency to The lower intermediate frequency band facilitates subsequent processing; the intermediate frequency amplifier 217 is used to further amplify the intermediate frequency signal to ensure that the signal strength meets the requirements of subsequent processing; the local oscillator 218 provides the local oscillator signal required by the mixer; the signal processor 219 performs pulse compression, matched filtering, Doppler filtering, integration, and motion compensation on the signal, and its output is transmitted to the system display, data processor, and other components; the data processor 220 is used to further process and analyze the received signal processor output data; and the display 221 is used to display the data processor output data. The receiver of this detection radar typically adopts a superheterodyne design. The first stage is usually a low-noise RF amplifier to maximize the preservation of signal detail and reduce noise. Subsequent one or more processing stages convert the received signal to a lower intermediate frequency and finally baseband through steps such as mixing and amplification. The baseband signal is the original signal without any carrier modulation and contains all the target information. This baseband signal is then fed into the signal processor for a series of complex signal processing operations for subsequent operation and analysis.

[0128] refer to Figure 7 The vehicle-mounted system may also include a liveness detection module 23, which is configured to perform liveness detection based on the first radar echo signal of the detection radar. Specifically, this module uses the first radar echo signal, which has been subjected to signal-to-noise ratio estimation, to perform liveness detection and obtain a liveness detection result. The signal-to-noise ratio estimation result output by the signal-to-noise ratio estimation module is then used to evaluate the liveness detection result, allowing the user to more directly determine the reliability of the liveness detection result. By integrating the liveness detection module into the vehicle-mounted system, the same radar echo signal is used for both signal-to-noise ratio estimation and liveness detection, eliminating the need for additional hardware. This approach not only achieves efficient data reuse but also saves hardware costs, thereby optimizing the entire vehicle-mounted system.

[0129] In some embodiments, the vehicle system may further include an application control module 24, a microcontroller communication module 25, a microcontroller software driver module 26, and a detection radar transceiver module software driver module 27. Figure 7 As shown, the application control module 24 is used to control the startup, shutdown, and result output of at least one of the signal-to-noise ratio estimation module and the liveness detection module, as well as the scheduling of the liveness detection algorithm. The microcontroller communication module 25, also known as the wireless communication module, is used to generate alarm information based on information such as the signal-to-noise ratio estimation result and the liveness detection result, and output it to the digital key via wireless means such as Bluetooth and WiFi. After receiving this information, the digital key can alert the user through sound, vibration, or display. The microcontroller software driver module 26 is used to drive the microcontroller's peripheral circuits to ensure the microcontroller's normal operation and communication with external devices. It includes a serial peripheral interface driver, a Bluetooth driver, a general-purpose input / output driver, a system clock driver, and a watchdog driver. The detection radar transceiver module software driver module 72 is a complex driver based on the microcontroller software driver module. It drives the detection radar, transmits and receives detection radar data, and performs hardware self-tests on the detection radar driver sensor. By integrating these modules into the vehicle system, the functionality and reliability of the vehicle system can be greatly improved, providing users with a more convenient and secure user experience.

[0130] The present application also provides an electronic device, such as Figure 9 As shown, the electronic device includes: a processor 31 and a memory 32, the memory 32 stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the following is achieved: Figure 1-Figure 5 The steps of the signal processing method of the detection radar.

[0131] The present application also provides a vehicle comprising Figure 7 The vehicle system 41, such as Figure 10 shown in, or including Figure 9 The electronic device 42 shown, such as Figure 11 As shown in the figure, this vehicle-mounted system not only effectively utilizes the radar echo signal generated by the detection radar for signal-to-noise ratio estimation, but also uses this same radar echo signal for liveness detection, thereby achieving efficient reuse of radar data. This approach not only optimizes resource utilization but also significantly enhances the overall performance and safety of the vehicle.

[0132] The present application also provides a computer-readable storage medium, wherein a program or instruction is stored on the computer-readable storage medium, and when the program or instruction is executed by a processor, the following is realized: Figure 1-Figure 5 The steps of the signal processing method of the detection radar.

[0133] The present application also provides a computer program product, which, when executed by a vehicle processor, implements the following Figure 1-Figure 5 The steps of the signal processing method of the detection radar.

[0134] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising 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 sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0135] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general-purpose hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for enabling a terminal or network-side device to execute the methods described in each embodiment of the present application.

[0136] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of this application and the scope of protection of the claims. These implementation methods are all within the protection of this application.

Claims

1. A signal processing method for a detection radar, characterized in that: include: Acquiring a first radar echo signal of a detection radar, where the first radar echo signal includes a breathing characteristic signal and is used for liveness detection; filtering out a breathing characteristic signal from the first radar echo signal to obtain a second radar echo signal; A signal-to-noise ratio of the detection radar is estimated based on the first radar echo signal and the second radar echo signal.

2. The method according to claim 1, characterized in that The estimating the signal-to-noise ratio of the detection radar based on the first radar echo signal and the second radar echo signal includes: Obtaining a first power value corresponding to the first radar echo signal; Obtaining a second power value corresponding to the second radar echo signal; A signal-to-noise ratio (SNR) of the detection radar is estimated based on the first power value and the second power value to obtain a SNR estimation result.

3. The method according to claim 2, characterized in that The performing a signal-to-noise ratio estimation of the detection radar based on the first power value and the second power value to obtain a signal-to-noise ratio estimation result includes: A first difference between the first power value and the second power value is obtained, and a ratio of the first difference to the second power value is used as the signal-to-noise ratio estimation result.

4. The method according to claim 2, characterized in that The obtaining of a first power value corresponding to the first radar echo signal includes: A power spectrum of the first radar echo signal is acquired, and the power spectrum of the first radar echo signal is integrated to obtain a first power value corresponding to the first radar echo signal.

5. The method according to claim 2, characterized in that The obtaining a second power value corresponding to the second radar echo signal includes: A power spectrum of the second radar echo signal is acquired, and the power spectrum of the second radar echo signal is integrated to obtain a second power value corresponding to the second radar echo signal.

6. The method according to claim 1, characterized in that The filtering out the breathing characteristic signal from the first radar echo signal to obtain a second radar echo signal includes: The first radar echo signal is subjected to band-stop filtering to filter out the respiratory characteristic signal within the respiratory frequency band, thereby obtaining a second radar echo signal.

7. The method according to any one of claims 1 to 6, characterized in that: The first radar echo signal is a channel impulse response signal.

8. The method according to any one of claims 1 to 6, characterized in that: Before filtering out the breathing characteristic signal from the first radar echo signal to obtain the second radar echo signal, the method further includes: Perform signal preprocessing on the first radar echo signal.

9. The method according to claim 8, characterized in that The signal preprocessing includes at least one of obtaining a modulus value, centering processing, and removing linear processing.

10. The method according to any one of claims 1 to 9, characterized in that: Also includes: Liveness detection is performed based on the first radar echo signal of the detection radar.

11. The method according to claim 10, characterized in that The performing living body detection based on the first radar echo signal includes: Liveness detection is performed based on the first radar echo signal of the detection radar and a signal-to-noise ratio estimation result.

12. The method according to claim 10, characterized in that Also includes: Output alarm information based on the live results.

13. The method according to claim 10, characterized in that Before performing liveness detection based on the first radar echo signal of the detection radar, the method further includes: Make sure the liveness detection function is enabled.

14. The method according to any one of claims 1 to 9, characterized in that: Before filtering out the breathing characteristic signal from the first radar echo signal, the method further includes: Make sure the signal quality detection function is enabled.

15. A vehicle computer system, characterized in that: It includes a detection radar and a signal-to-noise ratio estimation module. The signal-to-noise ratio estimation module is used to obtain a first radar echo signal of the detection radar, the first radar echo includes a breathing characteristic signal, and is used to perform liveness detection, filter the breathing characteristic signal from the first radar echo signal to obtain a second radar echo signal, and estimate the signal-to-noise ratio of the detection radar based on the first radar echo signal and the second radar echo signal.

16. The vehicle system according to claim 15, characterized in that: Also includes: A liveness detection module is used to perform liveness detection based on the first radar echo signal of the detection radar.

17. The vehicle system according to claim 16, characterized in that: Also includes: The application control module is used to control the startup of at least one of the signal-to-noise ratio estimation module and the living body detection module.

18. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the signal processing method of the detection radar according to any one of claims 1 to 14 are implemented.

19. A vehicle, characterized in that: Including the electronic device described in claim 18, or the vehicle system described in any one of claims 15-17.

20. A computer-readable storage medium, characterized in that The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the signal processing method for detection radar according to any one of claims 1 to 14 are implemented.

21. A computer program product, characterized in that When the program product is executed by a processor of an electronic device, the steps of the signal processing method for detecting radar according to any one of claims 1 to 14 are implemented.

Images