WO2022166649A1 - 车内生命探测方法、装置、设备和存储介质 - Google Patents

车内生命探测方法、装置、设备和存储介质 Download PDF

Info

Publication number
WO2022166649A1
WO2022166649A1 PCT/CN2022/073491 CN2022073491W WO2022166649A1 WO 2022166649 A1 WO2022166649 A1 WO 2022166649A1 CN 2022073491 W CN2022073491 W CN 2022073491W WO 2022166649 A1 WO2022166649 A1 WO 2022166649A1
Authority
WO
WIPO (PCT)
Prior art keywords
preset
range
signal
confidence
phase
Prior art date
Application number
PCT/CN2022/073491
Other languages
English (en)
French (fr)
Inventor
包红燕
耿文涛
刘坤明
樊听
尹学良
张昆
秘石
任玉东
秦屹
Original Assignee
森思泰克河北科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 森思泰克河北科技有限公司 filed Critical 森思泰克河北科技有限公司
Publication of WO2022166649A1 publication Critical patent/WO2022166649A1/zh

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications

Definitions

  • the present application belongs to the technical field of smart cars, and in particular relates to a method, device, device and storage medium for detecting life in a car.
  • life detection equipment mainly includes infrared detectors, ultrasonic radars and cameras.
  • the embodiments of the present application provide an in-vehicle life detection method, device, device and storage medium to solve the problem of lack of an in-vehicle life detection method with good detection effect and wide application scenarios in the prior art.
  • a first aspect of the embodiments of the present application provides a method for detecting life in a vehicle, including:
  • Obtaining step obtaining the x-th radar frame signal collected by the preset millimeter-wave radar in the vehicle, where x is a natural number greater than or equal to 2;
  • Sampling transformation step demodulation sampling and time-frequency transformation are performed on the xth radar frame signal to obtain a first range-dimension signal array, where the first range-dimension signal array includes time-dimension signal values of a plurality of range-dimension sampling points;
  • Filtering step filtering the first range-dimensional signal array to obtain a second range-dimensional signal array
  • Extracting step extracting the phase and confidence of the preset detection point in the second range-dimensional signal array
  • Iterative step performing iterative filtering on the phase and confidence of the preset detection point of the x-th radar frame signal according to the phase and confidence of the pre-extracted x-1 radar frame signal to obtain the x-th radar frame signal.
  • the filtering results of the preset detection points of each radar frame signal;
  • Detection step in the case that the filtering result is greater than the preset threshold, it is determined that the preset detection point has life.
  • a second aspect of the embodiments of the present application provides an in-vehicle life detection device, including:
  • an acquisition module used for acquiring the xth radar frame signal collected by the preset millimeter-wave radar in the vehicle, where x is a natural number greater than or equal to 2;
  • a sampling transformation module used for demodulating sampling and time-frequency transformation on the xth radar frame signal to obtain a first range-dimensional signal array, where the first range-dimensional signal array includes time-dimension signal values of a plurality of range-dimensional sampling points;
  • a filtering module used for filtering the first range-dimensional signal array to obtain a second range-dimensional signal array
  • an extraction module for extracting the phase and confidence of the preset detection point in the second range-dimensional signal array
  • the iterative module is used to iteratively filter the phase and confidence of the preset detection point of the x-th radar frame signal according to the phase and confidence of the preset detection point of the pre-extracted x-1 radar frame signal to obtain The filtering result of the preset detection point of the xth radar frame signal;
  • the detection module is used to determine that the preset detection point has life when the filtering result is greater than the preset threshold.
  • a third aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method described in the first aspect when the processor executes the computer program A step of.
  • a fourth aspect of the embodiments of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.
  • the embodiment of the present application can acquire the xth radar frame signal collected by the preset millimeter wave radar in the vehicle, and then perform demodulation sampling and time-frequency transformation on the xth radar frame signal to obtain a first range-dimensional signal array.
  • the first range-dimensional signal array can be filtered to obtain a second range-dimensional signal array, and then the phase and confidence of the preset detection points can be extracted from the second range-dimensional signal array, and then the pre-extracted Phase and confidence of the preset detection points of x-1 radar frame signals, iteratively filter the phase and confidence of the preset detection points of the xth radar frame signal, and obtain the preset detection of the xth radar frame signal filter result of points.
  • the filtering result is greater than the preset threshold, it can be determined that the preset detection point has life. Since the millimeter-wave radar can be applied to a variety of scenarios, based on the detection signal of the millimeter-wave radar, combined with the above detection algorithm, the breathing micro-moving target in the car, that is, the life in the car, can be accurately identified. In this way, it can be widely used. It is applied to in-vehicle life detection in various scenarios, and has a good detection effect.
  • FIG. 1 is a flowchart of steps of a method for detecting life in a vehicle provided by an embodiment of the present application
  • FIG. 2 is a block diagram of a radar system provided by an embodiment of the present application.
  • FIG. 3 is a schematic diagram of an antenna provided by an embodiment of the present application.
  • FIG. 4 is a schematic diagram of an in-vehicle life detection device provided by an embodiment of the present application.
  • FIG. 5 is a schematic diagram of an electronic device according to an embodiment of the present application.
  • the existing life detection equipment has limited application scenarios, cannot complete detection well, and has poor detection effect.
  • the infrared detector finds the target according to the difference between the target and the background, or the temperature difference and thermal radiation difference between the various parts of the target.
  • the infrared detector is easily disturbed by strong light and temperature, and different surfaces of the measured object return The light intensity is different, and the data returned by black is much lower than that of white, so the accuracy of the infrared detector is greatly affected by the scene, and it is difficult to be applied in practice.
  • ultrasonic radar is based on the principle of sound waves, with a small field of view (FOV) and strong directivity.
  • FOV field of view
  • multiple ultrasonic radar sensor probes are required for the wide-angle in-vehicle scene.
  • the penetration of ultrasonic radar The ceiling capacity is poor and must be installed exposed, which will cause the interior ceiling to be cut and damaged.
  • the speed of sound is greatly affected by temperature, and the distance correction needs to be performed according to the temperature. Therefore, the detection accuracy of ultrasonic radar is poor, and it is not suitable for the micro-motion detection of breathing micro-moving targets, such as children in deep sleep.
  • visual analysis technologies such as cameras
  • the recognition effect drops sharply in complex light and shadow scenarios such as backlight or night vision.
  • the complex environment in the car it is easy to be blocked by seats and interfered by objects in the car.
  • the privacy effect of cameras is also poor, and car manufacturers are very cautious about the application of in-vehicle visual products.
  • the embodiments of the present application provide a method, device, device, and storage medium for detecting life in a vehicle.
  • the following first introduces the in-vehicle life detection method provided by the embodiments of the present application.
  • millimeter-wave radar technology has a strong ability to penetrate fog, smoke, and dust, is not affected by climate, temperature, and light, and can be used in all weather and all day. It can work, and has less attenuation than light waves, can penetrate clothing, and then accurately detect living targets in complex spaces in the car.
  • the millimeter-wave radar has a wide FOV, a large effective bandwidth, and high detection accuracy. Using a special high-frequency signal processing algorithm, it can identify breathing micro-moving targets, and electromagnetic waves can penetrate the ceiling material. It can be installed in a hidden way without destroying it. The interior shape of the vehicle maintains the integrity and aesthetics of the vehicle shape. Based on the above advantages of the millimeter-wave radar, the embodiments of the present application provide a method for detecting life in a vehicle based on the millimeter-wave radar.
  • the execution subject of the in-vehicle life detection method may be an in-vehicle life detection device, and the in-vehicle life detection device may be an electronic device with data processing capability, such as in-vehicle electronic device, wearable device, server, network attached storage (Network Attached Storage) Storage, NAS) or a personal computer (personal computer, PC), etc., which are not specifically limited in this embodiment of the present application.
  • in-vehicle electronic device wearable device
  • server network attached storage (Network Attached Storage) Storage, NAS) or a personal computer (personal computer, PC), etc.
  • the in-vehicle life detection method may include the following steps:
  • Step S110 Acquire the xth radar frame signal collected by the preset millimeter wave radar in the vehicle.
  • a preset millimeter-wave radar may be pre-installed in the vehicle, for example, a millimeter-wave radar with a frequency range of 60GHz-64GHz.
  • the preset millimeter wave radar can detect the life in the vehicle by transmitting millimeter waves and receiving the reflected millimeter waves.
  • the in-vehicle life detection device can acquire the x-th radar frame signal collected by the preset millimeter-wave radar in the vehicle, where x is a natural number greater than or equal to 2.
  • the preset millimeter-wave radar can use a highly integrated MMIC (Monolithic The Microwave Integrated Circuit) solution can be interconnected with the vehicle network through CAN (Controller Area Network) communication.
  • the default millimeter-wave radar can use a multiple-input multiple-output (MIMO) antenna design scheme with 3 transmitters and 4 receivers, which can further improve the angular resolution and reduce the size of the radar on the basis of conventional radar.
  • the core RF (Radio Frequency, radio frequency) part can use high-performance millimeter-wave radar chips, such as AWR6843 chips, with a frequency range of 60 ⁇ 64GHz, that is, it has high integration, including RF front-end and signal processing modules and rich peripheral interfaces. chip.
  • a radar system block diagram of a preset millimeter-wave radar is shown, in which the realization of the radar signal processing algorithm can be completed in whole or in part in the AWR6843 chip, and the detection results are sent to the vehicle body through CAN communication controller to implement sleep wake-up function.
  • the inlet of the power supply unit is designed with functions such as anti-reverse connection, EMC (electromagnetic compatibility) suppression, and surge protection. circuit) voltage conversion, and output a variety of low ripple voltages for the back-end processor, where the ripple voltage (Ripple Voltage) refers to the industrial frequency (Industrial Frequency) AC component contained in the output DC voltage.
  • the core processor AWR6843 is an integrated single-chip mmWave (millimeter wave) sensor based on FMCW (Frequency Modulated Continuous Wave) radar technology, capable of operating in the 60GHz to 64GHz frequency band, using a low-power 45-nm RFCMOS (radio frequency Complementary Metal Oxide Semiconductor) process, which can realize RF signal generation, transmission, reception, filtering, A/D (analog and digital signal conversion) sampling, complex signal processing and data processing.
  • the voltage acquisition unit realizes power monitoring and temperature monitoring, preventing radar abnormalities caused by abnormal power supply and abnormal overheating, and effectively improving system stability.
  • FIG. 3 a schematic diagram of an antenna is shown.
  • the antenna can support a 4GHz bandwidth with an operating frequency of 60 ⁇ 64GHz.
  • the distance between R0 ⁇ R5 is Half wavelength
  • the distance between T1 and T3 is twice the wavelength
  • the height difference between T1 and T2 is half wavelength
  • the scale of each transceiver antenna is 7*1
  • the beam width is 70°*20°.
  • the array element design comprehensively balances the beam
  • the two indicators of range and antenna gain that is, to meet the needs of the detection range, and also obtain a higher transmit gain.
  • the antenna design can achieve spatial 3D resolution, that is, the distance and spatial angle of the target relative to the radar.
  • the combination of transmitter T1 and T2 achieves elevation angle resolution, and the combination of T1 and T3 achieves azimuth angle resolution.
  • the radar supports the ranging capability, so as to realize the spatial 3D recognition of the target, which lays the foundation for the accurate positioning of the target.
  • the receiving end R0 and R5 are false antennas, which can achieve the effect of expanding the field of view.
  • the radar installation angle needs to be adjusted to focus the beam on the detection area, which requires sufficient installation space at the top of the car, but due to the narrow head space in the actual car, the conventional design is difficult to achieve tilt.
  • beamforming technology can be used to design the broadband antenna to be offset from 15° to 36°, and horizontal installation can achieve the effect of inclined installation, saving installation space.
  • the software design part can include the heterogeneous design of two platforms of ARM (Advanced RISC Machine, 32-bit reduced instruction set processor) and DSP (Digital Signal Processing, digital signal processing) dual-core.
  • ARM Advanced RISC Machine, 32-bit reduced instruction set processor
  • DSP Digital Signal Processing, digital signal processing
  • the ARM platform can implement the basic underlying driver initialization thread, the MMWave module initialization thread, the control link configuration thread, and the mailbox information transmission thread in response to user commands based on the SYS/BIOS operating system.
  • DSP amortization can realize radar algorithm and data processing.
  • SYS/BIOS operating system There are also multiple threads based on SYS/BIOS operating system: basic module initialization configuration thread, mailbox information processing thread, MMWave module configuration thread, real-time data link signal processing thread, radar Implementation of signal processing algorithms, transmission of target information to terminals, configuration events, frame start events, Chirp (chirp) events, etc.
  • the SYS/BIOS operating system is a scalable real-time operating system with very fast response time (shorter delays in interrupts and task switching), deterministic response time, strong preemption system, optimized Features such as memory allocation and stack management.
  • Step S120 demodulating, sampling and time-frequency transforming the xth radar frame signal to obtain a first range-dimensional signal array.
  • the in-vehicle life detection apparatus may perform demodulation sampling and time-frequency transformation on the xth radar frame signal to obtain a first range-dimensional signal array.
  • the first distance-dimensional signal array may include time-dimensional signal values of a plurality of distance-dimensional sampling points.
  • the first distance-dimensional signal array may be:
  • Si represents the time dimension signal value of each distance dimension sampling point
  • Si [SS1, SS2...SSj...SSm], i ⁇ [1,n], j ⁇ [1,m], k ⁇ [1,p ]
  • n is the distance dimension sampling point
  • m is the time dimension sampling point
  • p is the space dimension sampling point.
  • Step S130 Perform filtering processing on the first range-dimensional signal array to obtain a second range-dimensional signal array.
  • the in-vehicle life detection device may perform filtering processing on the first range-dimensional signal array to obtain a second range-dimensional signal array. In this way, static interference clutter can be eliminated. interference.
  • step S130 may be as follows: calculating the average value of the time-dimension signal values of each distance-dimension sampling point; A second range-dimensional signal array is obtained.
  • a method of calculating an average value along the time dimension for each distance sampling point may be used to perform filtering processing on the first range-dimensional signal array to obtain the second range-dimensional signal array.
  • the second range-dimensional signal array can be obtained in the following manner:
  • SSj' represents the time dimension signal value of each distance dimension sampling point after filtering.
  • step S130 may also be as follows: calculate the average value of the time-dimension signal values of each distance-dimension sampling point; subtract the average value from the time-dimension signal value of each distance-dimension sampling point in the first distance-dimension signal array; , obtain the transition distance dimensional signal array; according to the direction of arrival positioning technology, the direction of arrival of the transition distance dimensional signal array is estimated, and the second distance dimensional signal array is obtained.
  • the interior space of the vehicle is often small, the interiors are numerous, and the dielectric constant is complex, which may easily cause electromagnetic waves to be interfered by clutter, and the micro-moving targets are not easily detected.
  • the DOA can be estimated by combining with the adaptive beamforming technology (Direction Of Arrival, DOA) to improve the target detection performance.
  • Adaptive beamforming technology also known as direction of arrival positioning technology, obtains the distance information and azimuth information of the target by processing the received echo signals.
  • each Ri array element can be shaped and weighted, and within a unit frame time, for example, within 100 milliseconds, the antenna array beam can be steered in one direction, and the desired signal can be steered to obtain the maximum output power.
  • Directional spatial domain filtering estimation in this way, the power of the signal in the specified direction can be enhanced, and the side lobes of the antenna can be cancelled at the same time to reduce the clutter interference.
  • the antenna side lobes refer to: the antenna pattern usually has two or more lobes, of which the lobe with the largest radiation intensity is called the main lobe, and the remaining lobes are called side lobes or side lobes.
  • Step S140 Extract the phase and confidence of the preset detection point in the second range-dimensional signal array.
  • the in-vehicle life detection apparatus may extract the phase and confidence level of the preset detection point in the second range-dimensional signal array. Confidence refers to the probability that the true value occurs within a certain range, centered on the measured value.
  • the region of interest can be set according to the vehicle space, and the phase and confidence of the pre-screened target points can be extracted.
  • the general vehicle rear space is 1.5m
  • the phase and confidence of the pre-screened target points within 1.5m can be extracted.
  • Step S150 Perform iterative filtering on the phase and confidence of the preset detection point of the x-th radar frame signal according to the pre-extracted phase and confidence of the x-1 th radar frame signal, to obtain the x-th radar frame signal.
  • the filtering results of the preset detection points of each radar frame signal.
  • the in-vehicle life detection device may extract the preset detection point of the x-1th radar frame signal according to the pre-extracted
  • the phase and confidence of the xth radar frame signal are iteratively filtered for the phase and confidence of the preset detection point of the xth radar frame signal, and the filtering result of the preset detection point of the xth radar frame signal is obtained.
  • the process of step S150 may be as follows: obtaining the phase of the preset detection point of the x-1 th radar frame signal and the first multiplication value of the first phase filter coefficient, and the preset detection point of the x th radar frame signal.
  • the second multiplication value of the phase and the second phase filter coefficient, the confidence of the preset detection point of the x-1 radar frame signal and the third multiplication value of the first confidence filter coefficient, the x-th radar frame signal The confidence of the preset detection point and the fourth multiplication value of the second confidence filter coefficient; the sum of the first multiplication value and the second multiplication value, and the sum of the third multiplication value and the fourth multiplication value are determined as The filtering result of the preset detection point of the xth radar frame signal.
  • the above-mentioned iterative filtering method may be called ⁇ - ⁇ loop iterative filtering, wherein 1- ⁇ is the first phase filter coefficient, ⁇ is the first phase filter coefficient, and 1- ⁇ is the first confidence filter coefficient, ⁇ is the second confidence filter coefficient, wherein the first phase filter coefficient is smaller than the second phase filter coefficient, and the first confidence filter coefficient is smaller than the second confidence filter coefficient.
  • the phase of the preset detection point of the xth radar frame signal after iterative filtering 0.9*the phase of the preset detection point of the xth radar frame signal+0.1*xth - the phase of the preset detection point of 1 radar frame signal;
  • the confidence level of the preset detection point of the xth radar frame signal after iterative filtering 0.8*the confidence level of the preset detection point of the xth radar frame signal + 0.2*The confidence of the preset detection point of the x-1th radar frame signal.
  • Step S160 In the case that the filtering result is greater than the preset threshold, it is determined that the preset detection point has life.
  • a predetermined threshold may be used to define whether there is life at a predetermined detection point. Specifically, if the filtering result is greater than the preset threshold, it can be considered that there is life at the preset detection point. In this way, when the filtering result is greater than the preset threshold, it can be determined that the preset detection point has life.
  • step S160 may be as follows: when the sum of the first multiplication value and the second multiplication value is greater than the first preset threshold, and the sum of the third multiplication value and the fourth multiplication value is greater than the second preset threshold , it is determined that there is life at the preset detection point.
  • the filtering result of the preset detection point of the xth radar frame signal may include two parts, one part is the sum of the first multiplication value and the second multiplication value, and this part may be called the phase filtering result; the other is the phase filtering result; A part is the sum of the third multiplication value and the fourth multiplication value, and this part may be called the confidence filter result.
  • the preset threshold of the phase filtering result may be referred to as the first preset threshold
  • the preset threshold of the confidence filtering result may be referred to as the second preset threshold.
  • phase filtering result and the confidence filtering result are both greater than the corresponding preset thresholds, that is, the sum of the first multiplication value and the second multiplication value is greater than the first preset threshold, and the third multiplication value and The sum of the fourth multiplication value is greater than the second preset threshold, and at this time, it can be determined that the preset detection point has life.
  • alarm information may be generated, for example, it may be sound information, light information or instant information, or sound information, light information Any two combinations of information and instant information can also be three combinations of sound information, light information and instant information to remind the user that there are children or pets left in the car.
  • the x-th radar frame signal collected by the preset millimeter-wave radar in the vehicle may be acquired, and then the x-th radar frame signal is demodulated and sampled and time-frequency transformed to obtain the first distance dimension signal array.
  • the first range-dimensional signal array can be filtered to obtain a second range-dimensional signal array, and then the phase and confidence of the preset detection points can be extracted from the second range-dimensional signal array, and then the pre-extracted Phase and confidence of the preset detection points of x-1 radar frame signals, iteratively filter the phase and confidence of the preset detection points of the xth radar frame signal, and obtain the preset detection of the xth radar frame signal filter result of points.
  • the filtering result is greater than the preset threshold, it can be determined that the preset detection point has life. Since the millimeter-wave radar can be applied to a variety of scenarios, based on the detection signal of the millimeter-wave radar, combined with the above detection algorithm, the breathing micro-moving target in the car, that is, the life in the car, can be accurately identified. In this way, it can be widely used. It is applied to in-vehicle life detection in various scenarios, and has a good detection effect.
  • the millimeter-wave radar has the characteristics of strong penetrating fog, smoke and dust, not affected by climate temperature and light, can work all day long, has less attenuation than light waves, and can penetrate clothing to accurately detect living targets in complex spaces inside the car, etc.
  • the millimeter-wave radar can be installed in the car in a hidden way, so that the integrity and aesthetics of the vehicle shape can be maintained without destroying the interior shape of the vehicle.
  • the present application also provides a specific implementation manner of an in-vehicle life detection device applied to the in-vehicle life detection method. See the examples below.
  • an in-vehicle life detection device which includes:
  • an acquisition module 410 configured to acquire the xth radar frame signal collected by the preset millimeter-wave radar in the vehicle, where x is a natural number greater than or equal to 2;
  • the sampling transformation module 420 is used for demodulating sampling and time-frequency transformation on the xth radar frame signal to obtain a first range-dimensional signal array, where the first range-dimensional signal array includes time-dimension signal values of a plurality of range-dimensional sampling points;
  • a filtering module 430 configured to perform filtering processing on the first range-dimensional signal array to obtain a second range-dimensional signal array
  • an extraction module 440 configured to extract the phase and confidence of the preset detection point in the second range-dimensional signal array
  • the iterative module 450 is configured to iteratively filter the phase and confidence of the preset detection point of the x-th radar frame signal according to the phase and confidence of the preset detection point of the x-1 th radar frame signal, which are pre-extracted, Obtain the filtering result of the preset detection point of the xth radar frame signal;
  • the detection module 460 is configured to determine that there is life at the preset detection point when the filtering result is greater than the preset threshold.
  • filtering processing is performed on the first range-dimensional signal array to obtain a second range-dimensional signal array, including:
  • the average value of the time-dimension signal value of each distance-dimension sampling point in the first range-dimension signal array is subtracted to obtain a second range-dimension signal array.
  • filtering processing is performed on the first range-dimensional signal array to obtain a second range-dimensional signal array, including:
  • the direction of arrival is estimated for the transition range-dimensional signal array, and the second range-dimensional signal array is obtained.
  • iterative filtering is performed on the phase and confidence of the preset detection point of the xth radar frame signal to obtain the filtering result of the preset detection point of the xth radar frame signal, including:
  • the multiplication value, the confidence of the preset detection point of the x-1th radar frame signal and the third multiplication value of the filter coefficient of the first confidence degree, the confidence degree and the second confidence of the preset detection point of the xth radar frame signal The fourth multiplication value of the degree filter coefficient;
  • the first phase filter coefficient is smaller than the second phase filter coefficient
  • the first confidence filter coefficient is smaller than the second confidence filter coefficient
  • determining that there is life at the preset detection point includes:
  • the method further includes:
  • alarm information is generated; the alarm information includes at least one of sound information, light information and instant information.
  • the preset frequency range of the millimeter-wave radar is 60GHz-64GHz.
  • the in-vehicle life detection device provided by the present application can realize the same step function and the same technical effect as the above-mentioned in-vehicle life detection method, and the in-vehicle life detection method is not repeated in the in-vehicle life detection device. should be deemed to have been clearly stated in the description.
  • the x-th radar frame signal collected by the preset millimeter-wave radar in the vehicle may be acquired, and then the x-th radar frame signal is demodulated and sampled and time-frequency transformed to obtain the first distance dimension signal array.
  • the first range-dimensional signal array can be filtered to obtain a second range-dimensional signal array, and then the phase and confidence of the preset detection points can be extracted from the second range-dimensional signal array, and then the pre-extracted Phase and confidence of the preset detection points of x-1 radar frame signals, iteratively filter the phase and confidence of the preset detection points of the xth radar frame signal, and obtain the preset detection of the xth radar frame signal filter result of points.
  • the filtering result is greater than the preset threshold, it can be determined that the preset detection point has life. Since the millimeter-wave radar can be applied to a variety of scenarios, based on the detection signal of the millimeter-wave radar, combined with the above detection algorithm, the breathing micro-moving target in the car, that is, the life in the car, can be accurately identified. In this way, it can be widely used. It is applied to in-vehicle life detection in various scenarios, and has a good detection effect.
  • the millimeter-wave radar has the characteristics of strong penetrating fog, smoke and dust, not affected by climate temperature and light, can work all day long, has less attenuation than light waves, and can penetrate clothing to accurately detect living targets in complex spaces inside the car, etc.
  • the millimeter-wave radar can be installed in the car in a hidden way, so that the integrity and aesthetics of the vehicle shape can be maintained without destroying the interior shape of the vehicle.
  • FIG. 5 is a schematic diagram of an electronic device provided by an embodiment of the present application.
  • the electronic device 5 of this embodiment includes a processor 50 , a memory 51 , and a computer program 52 stored in the memory 51 and executable on the processor 50 .
  • the processor 50 executes the computer program 52, the steps in each of the above embodiments of the in-vehicle life detection method are implemented.
  • the processor 50 executes the computer program 52, the functions of the modules/units in the foregoing apparatus embodiments are implemented.
  • the computer program 52 may be divided into one or more modules/units, which are stored in the memory 51 and executed by the processor 50 to complete the present application.
  • One or more modules/units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 52 in the electronic device 5 .
  • the computer program 52 can be divided into an acquisition module, a sampling transformation module, a filtering module, an extraction module, an iterative module, and a detection module.
  • the specific functions of each module are as follows:
  • an acquisition module used for acquiring the xth radar frame signal collected by the preset millimeter-wave radar in the vehicle, where x is a natural number greater than or equal to 2;
  • a sampling transformation module used for demodulating sampling and time-frequency transformation on the xth radar frame signal to obtain a first range-dimensional signal array, where the first range-dimensional signal array includes time-dimension signal values of a plurality of range-dimensional sampling points;
  • a filtering module used for filtering the first range-dimensional signal array to obtain a second range-dimensional signal array
  • an extraction module for extracting the phase and confidence of the preset detection point in the second range-dimensional signal array
  • the iterative module is used to iteratively filter the phase and confidence of the preset detection point of the x-th radar frame signal according to the phase and confidence of the preset detection point of the pre-extracted x-1 radar frame signal to obtain The filtering result of the preset detection point of the xth radar frame signal;
  • the detection module is used to determine that the preset detection point has life when the filtering result is greater than the preset threshold.
  • the electronic device 5 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
  • the electronic device may include, but is not limited to, the processor 50 and the memory 51 .
  • FIG. 5 is only an example of the electronic device 5, and does not constitute a limitation to the electronic device 5. It may include more or less components than the one shown, or combine some components, or different components
  • the electronic device may also include input and output devices, network access devices, buses, and the like.
  • the processor 50 may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, Digital Signal Processors (Digital Signal Processors, DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (Field-Programmable Gate Arrays) Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general purpose processor may be a microprocessor or it may be any conventional processor or the like.
  • the memory 51 may be an internal storage unit of the electronic device 5 , for example, a hard disk or a memory of the electronic device 5 .
  • the memory 51 can also be an external storage device of the electronic device 5, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a Secure Digital (Secure Digital, SD) card, a flash memory card ( Flash Card), etc.
  • the memory 51 may also include both an internal storage unit of the electronic device 5 and an external storage device.
  • the memory 51 is used to store computer programs and other programs and data required by the electronic device.
  • the memory 51 can also be used to temporarily store data that has been output or is to be output.
  • the disclosed apparatus/terminal device and method may be implemented in other manners.
  • the apparatus/terminal device embodiments described above are only illustrative.
  • the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units. Or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • Units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.
  • the integrated modules/units if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer-readable storage medium.
  • this application can implement all or part of the processes in the methods of the above embodiments, and can also be completed by instructing relevant hardware through a computer program.
  • the computer program can be stored in a computer-readable storage medium. When executed by the processor, the steps of the foregoing method embodiments may be implemented.
  • the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate forms, and the like.
  • Computer-readable storage media may include: any entity or device capable of carrying computer program codes, recording media, U disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random storage Access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable storage medium may be appropriately increased or decreased in accordance with the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to the legislation and patent practice, the computer-readable storage medium Electric carrier signals and telecommunication signals are not included.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

提供了一种车内生命探测方法、装置、电子设备和计算机可读存储介质，适用于智能汽车技术领域。其中，该方法包括：获取由车内的预设毫米波雷达采集的第x个雷达帧信号（S110）；对第x个雷达帧信号进行解调采样和时频变换，得到第一距离维信号阵列（S120）；对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列（S130）；在第二距离维信号阵列中提取预设探测点的相位和置信度（S140）；根据预先提取的第x-1个雷达帧信号的预设探测点的相位和置信度，对第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到第x个雷达帧信号的预设探测点的滤波结果（S150）；在滤波结果大于预设阈值的情况下，确定预设探测点存在生命（S160）。本方法可以适用于各种场景下的车内生命探测，且探测效果较好。

Description

车内生命探测方法、装置、设备和存储介质
本专利申请要求于2021年2月3日提交的中国专利申请No.CN202110149511.X的优先权。在先申请的公开内容通过整体引用并入本申请。
技术领域
本申请属于智能汽车技术领域，尤其涉及一种车内生命探测方法、装置、设备和存储介质。
 背景技术
随着车辆的普及，儿童或者宠物被遗留在车内致死的事故也逐步增多。在这些惨痛的教训面前，配置生命探测设备刻不容缓。目前，生命探测设备主要有红外探测仪、超声波雷达和摄像头。
然而，现有的生命探测设备应用场景受限，无法较好地完成探测，探测效果较差。因此，目前亟需一种探测效果较好且应用场景广泛的车内生命探测方法。
 技术问题
本申请实施例提供了一种车内生命探测方法、装置、设备和存储介质，以解决现有技术中缺少一种探测效果较好且应用场景广泛的车内生命探测方法的问题。
 技术解决方案
本申请实施例的第一方面提供了一种车内生命探测方法，包括：
获取步骤：获取由车内的预设毫米波雷达采集的第x个雷达帧信号，x为大于或者等于2的自然数；
采样变换步骤：对第x个雷达帧信号进行解调采样和时频变换，得到第一距离维信号阵列，第一距离维信号阵列包括多个距离维采样点的时间维信号值；
滤波步骤：对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列；
提取步骤：在第二距离维信号阵列中提取预设探测点的相位和置信度；
迭代步骤：根据预先提取的第x-1个雷达帧信号的预设探测点的相位和置信度，对第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到第x个雷达帧信号的预设探测点的滤波结果；
探测步骤：在滤波结果大于预设阈值的情况下，确定预设探测点存在生命。
本申请实施例的第二方面提供了一种车内生命探测装置，包括：
获取模块，用于获取由车内的预设毫米波雷达采集的第x个雷达帧信号，x为大于或者等于2的自然数；
采样变换模块，用于对第x个雷达帧信号进行解调采样和时频变换，得到第一距离维信号阵列，第一距离维信号阵列包括多个距离维采样点的时间维信号值；
滤波模块，用于对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列；
提取模块，用于在第二距离维信号阵列中提取预设探测点的相位和置信度；
迭代模块，用于根据预先提取的第x-1个雷达帧信号的预设探测点的相位和置信度，对第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到第x个雷达帧信号的预设探测点的滤波结果；
探测模块，用于在滤波结果大于预设阈值的情况下，确定预设探测点存在生命。
本申请实施例的第三方面提供了一种电子设备，包括存储器、处理器以及存储在存储器中并可在处理器上运行的计算机程序，处理器执行计算机程序时实现如第一方面所述方法的步骤。
本申请实施例的第四方面提供了一种计算机可读存储介质，计算机可读存储介质存储有计算机程序，计算机程序被处理器执行时实现如第一方面所述方法的步骤。
 有益效果
本申请实施例与现有技术相比存在的有益效果是：
本申请实施例可以获取由车内的预设毫米波雷达采集的第x个雷达帧信号，然后对第x个雷达帧信号进行解调采样和时频变换，得到第一距离维信号阵列。之后，可以对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列，然后可以在第二距离维信号阵列中提取预设探测点的相位和置信度，接着可以根据预先提取的第x-1个雷达帧信号的预设探测点的相位和置信度，对第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到第x个雷达帧信号的预设探测点的滤波结果。如果滤波结果大于预设阈值，则可以确定预设探测点存在生命。由于毫米波雷达可以应用于多种场景，因此，基于毫米波雷达的探测信号，再结合上述探测算法，可以准确地识别出车内的呼吸微动目标，即车内生命，如此，可以广泛地应用于各个场景下的车内生命探测，且具有较好的探测效果。
 附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的一种车内生命探测方法的步骤流程图；
图2为本申请实施例提供的一种雷达系统框图；
图3为本申请实施例提供的一种天线示意图；
图4为本申请实施例提供的一种车内生命探测装置的示意图；
图5为本申请实施例提供的一种电子设备的示意图。
本申请的实施方式
以下描述中，为了说明而不是为了限定，提出了诸如特定系统结构、技术之类的具体细节，以便透彻理解本申请实施例。然而，本领域的技术人员应当清楚，在没有这些具体细节的其它实施例中也可以实现本申请。在其它情况中，省略对众所周知的系统、装置、电路以及方法的详细说明，以免不必要的细节妨碍本申请的描述。
为了说明本申请所述的技术方案，下面通过具体实施例来进行说明。
如背景技术所描述的，现有的生命探测设备应用场景受限，无法较好地完成探测，探测效果较差。
比如，红外探测仪是根据目标与背景，或者目标各部分之间的温差、热辐射差来发现目标，但是，红外探测仪极易受强光和温度干扰，而且被测对象的不同面返回的光线强度不一样，黑色返回的数据要比白色低许多，故而红外探测仪的准确度受场景影响非常明显，很难在实际中得以应用。
再比如，超声波雷达基于声波原理，视场角（Field of View，FOV）较小，指向性强，然而，针对车内广角需求场景需要多个超声波雷达的传感器探头，此外，超声波雷达的穿透顶棚能力差，必须外露式安装，这将导致车内顶棚被切割破坏。另外，声速受温度影响变化较大，需要根据温度进行距离修正，故而超声波雷达的探测精度差，不适合呼吸微动目标的微动探测，如熟睡时的儿童。
再比如，视觉分析技术，如摄像头，摄像头具有光线依赖性，在逆光或夜视等光影复杂情景下识别效果急剧下降，针对车内复杂的环境，易受座椅遮挡以及车内物品的干扰。此外，摄像头的隐私效果也较差，车厂对车内视觉产品的应用十分慎重。
故而，现有的生命探测设备应用场景受限，无法较好地完成探测，探测效果较差，亟需一种探测效果较好且应用场景广泛的车内生命探测方法。
为了解决现有技术问题，本申请实施例提供了一种车内生命探测方法、装置、设备和存储介质。下面首先对本申请实施例所提供的车内生命探测方法进行介绍。
申请人经过研究发现，毫米波雷达技术与红外探测仪、超声波雷达、视觉技术相比，毫米波雷达技术穿透雾、烟、灰尘的能力强，不受气候温度光线影响，能够全天候全天时工作，且比光波的衰减小，能够穿透衣物，进而准确探测车内复杂空间中的活体目标。此外，毫米波雷达的FOV广，有效带宽较大，检测精度高，利用特殊的高频信号处理算法，能够识别呼吸微动目标，且电磁波能够穿透顶棚材质，可以通过隐藏式安装，无需破坏车内造型，保持了车辆造型的完整性和美观化。基于毫米波雷达的上述优点，本申请实施例提供了一种基于毫米波雷达的车内生命探测方法。
车内生命探测方法的执行主体，可以是车内生命探测装置，该车内生命探测装置可以是具备数据处理能力的电子设备，例如车载电子设备、可穿戴设备、服务器、网络附属存储器（Network Attached Storage，NAS）或者个人计算机（personal computer，PC）等，本申请实施例不作具体限定。
如图1所示，本申请实施例提供的车内生命探测方法可以包括以下步骤：
步骤S110、获取由车内的预设毫米波雷达采集的第x个雷达帧信号。
在一些实施例中，车内可以预先安装预设毫米波雷达，例如频率范围为60GHz-64GHz的毫米波雷达。具体的，预设毫米波雷达可以通过发射毫米波，并接收反射回来的毫米波的方式，实现对车内生命的探测。如此，车内生命探测装置可以获取由车内的预设毫米波雷达采集的第x个雷达帧信号，其中，x为大于或者等于2的自然数。
具体的，预设毫米波雷达可以采用高集成化MMIC（Monolithic Microwave Integrated Circuit，微波集成电路）方案，可以通过CAN（Controller Area Network，控制器局域网络）通信方式与整车网络互联互通。预设毫米波雷达可以采用3发4收的多输入多输出（Multiple-Input Multiple-Output，MIMO）天线设计方案，可在常规雷达的基础上进一步提高角度分辨率，并且缩小雷达尺寸。此外，核心RF（Radio Frequency，射频）部分可以采用高性能毫米波雷达芯片，例如AWR6843芯片，频段范围60~64GHz，即具有高集成度，包含射频前端和信号处理模块以及丰富的外设接口的芯片。
如图2所示，示出了一种预设毫米波雷达的雷达系统框图，其中，雷达信号处理算法的实现可以全部或者部分在AWR6843芯片内完成，并将检测结果通过CAN通信方式发送到车身控制器，以实现休眠唤醒功能。电源单元入口设计了防反接、EMC（电磁兼容性）抑制、浪涌保护等功能，可以将12V输入电压经过DCDC（直流变直流）开关电源的降压和PMIC（Power Management IC，集成电源管理电路）电压转换，输出多种低纹波电压，供后端处理器使用，其中，纹波电压（Ripple Voltage）指的是输出直流电压中含有的工频（Industrial Frequency）交流成分。核心处理器AWR6843是一种基于FMCW（Frequency Modulated Continuous Wave，调频连续波）雷达技术的集成单芯片mmWave（毫米波）传感器，能够在60GHz到64GHz频段运行，采用低功耗45-nm RFCMOS（射频互补金属氧化半导体）工艺，可以实现射频信号产生、发射、接收、滤波、A/D（模拟信号和数字信号转换）采样、复杂信号处理和数据处理。电压采集单元实现电源监控和温度监控，防止因供电异常和过热异常导致的雷达异常，有效提高了系统稳定性。
以3发4收的MIMO天线为例，如图3所示，示出了一种天线示意图，该天线可以支持60~64GHz工作频率的4GHz带宽，其中，R0~R5两两之间的间距为半波长，T1和T3的间距为两倍波长，T1和T2的高度差为半波长，每一收发天线规模为7*1，波束宽度为70°*20°，该阵元设计综合平衡了波束范围和天线增益两项指标，即满足探测范围的需求，也获得了较高的发射增益。该天线设计能够实现空间3D分辨能力，即目标相对于雷达所处的距离、空间立体角度，其中发射端T1和T2组合实现俯仰向角度分辨能力，T1和T3组合实现方位向角度分辨能力，同时雷达支持测距能力，从而实现目标的空间3维识别，对于目标精准定位奠定了基础。接收端R0和R5为虚假天线，可以达到扩展视场角的作用。此外，为了达到较好的探测效果，需要调整雷达安装角度，从而将波束集中指向探测区域，这就要求车内顶部有足够的安装空间，但由于实际车内顶部空间狭小，常规设计难以实现倾斜安装，可以采用波束赋形技术，以将宽带天线设计为偏置15°~36°形式，水平安装即可达到倾斜安装的效果，节约安装空间。
另外，软件设计部分可以包括ARM（Advanced RISC Machine，32位精简指令集处理器）和DSP（Digital Signal Processing，数字信号处理）双核两个平台的异构设计。其中，ARM平台可以基于SYS/BIOS操作系统实现基础底层驱动初始化线程、MMWave模块初始化线程、控制链路配置线程、响应用户命令邮箱信息传递线程。DSP平摊可以实现雷达算法和数据处理，同样有多个基于SYS/BIOS操作系统的线程：基本模块的初始化配置线程、邮箱信息处理线程、MMWave模块配置线程、实时数据链路信号处理线程、雷达信号处理算法的实现、将目标信息传输至终端、配置事件、帧开始事件、Chirp（线性调频信号）事件等。其中，SYS/BIOS操作系统是一个可扩展的实时的操作系统，具有非常快速的响应时间（在中断和任务切换时达到较短的延迟），响应时间的确定性，强壮的抢占系统，优化的内存分配和堆栈管理等特点。
步骤S120、对第x个雷达帧信号进行解调采样和时频变换，得到第一距离维信号阵列。
在一些实施例中，车内生命探测装置在获取到第x个雷达帧信号后，可以对第x个雷达帧信号进行解调采样和时频变换，得到第一距离维信号阵列。
具体的，该第一距离维信号阵列可以包括多个距离维采样点的时间维信号值，例如，第一距离维信号阵列可以为：
Z=[S1、S2…Si…Sn]k；
其中，Si表示每个距离维采样点的时间维信号值，Si=[SS1、SS2…SSj…SSm]，i∈[1,n]，j∈[1,m]，k∈[1,p]，n为距离维采样点，m为时间维采样点，p为空间维采样点。
步骤S130、对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列。
在一些实施例中，车内生命探测装置在得到第一距离维信号阵列后，可以对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列，如此，可以剔除静态干扰杂波的干扰。
示例性地，步骤S130的处理可以如下：计算各个距离维采样点的时间维信号值的平均值；将第一距离维信号阵列中每个距离维采样点的时间维信号值减去平均值，得到第二距离维信号阵列。
在一些实施例中，可以采用对每个距离采样点沿时间维计算平均值的方式，对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列。
具体的，可以采用如下方式得到第二距离维信号阵列：
Smean=[Smean1、Smean2…Smeani...Smeann]k，SSj’=SSj-Smeani；
其中，SSj’表示滤波后每个距离维采样点的时间维信号值。
示例性地，步骤S130的处理还可以如下：计算各个距离维采样点的时间维信号值的平均值；将第一距离维信号阵列中每个距离维采样点的时间维信号值减去平均值，得到过渡距离维信号阵列；根据波达方向定位技术对过渡距离维信号阵列进行波达方向估计，得到第二距离维信号阵列。
在一些实施例中，车内空间往往狭小且内饰物杂多，介电常数复杂，容易导致电磁波受杂波干扰，且微动目标不易被探测。此时，可以在采用对每个距离采样点沿时间维计算平均值的方式后，再结合自适应波束形成技术（Direction Of Arrival，DOA）进行DOA估计，提高目标探测性能。自适应波束形成技术也就是波达方向定位技术，通过处理接收到的回波信号，获取目标的距离信息和方位信息。
具体的，可以将各Ri阵元进行赋形加权，在单位帧时间内，例如100毫秒内，将天线阵列波束导向到一个方向上，对期望信号得到最大输出功率的导向位置，做出波达方向空域滤波估计，如此，可以增强指定方向信号的功率，同时对天线旁瓣相消，降低杂波干扰。例如，可以设特定方向θ的导向矢量α、各Ri阵元空时采样数据的协方差矩阵R¬，则最优权系数W=μRα，其中μ为常数，然后寻找min(WHRW)时的θ，即为最佳目标来向。该方法增强指定方向信号的功率，同时对天线旁瓣相消，降低杂波干扰。其中，天线旁瓣指的是：天线方向图通常都有两个或多个瓣，其中辐射强度最大的瓣称为主瓣，其余的瓣称为副瓣或旁瓣。
步骤S140、在第二距离维信号阵列中提取预设探测点的相位和置信度。
在一些实施例中，车内生命探测装置在得到第二距离维信号阵列后，可以在第二距离维信号阵列中提取预设探测点的相位和置信度。置信度指的是以测量值为中心，在一定范围内，真值出现在该范围内的几率。
具体的，可以依据车辆空间，设定感兴趣区域，对预筛选的目标点提取相位和置信度。例如，一般车辆后排空间1.5m，可以设置雷达检测距离L=1.5m，对1.5m内的预筛选目标点进行相位和置信度的提取。
步骤S150、根据预先提取的第x-1个雷达帧信号的预设探测点的相位和置信度，对第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到第x个雷达帧信号的预设探测点的滤波结果。
在一些实施例中，车内生命探测装置在提取到第x个雷达帧信号的预设探测点的相位和置信度后，可以根据预先提取的第x-1个雷达帧信号的预设探测点的相位和置信度，对第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到第x个雷达帧信号的预设探测点的滤波结果。
示例性地，步骤S150的处理可以如下：获取第x-1个雷达帧信号的预设探测点的相位和第一相位滤波系数的第一乘值、第x个雷达帧信号的预设探测点的相位和第二相位滤波系数的第二乘值、第x-1个雷达帧信号的预设探测点的置信度和第一置信度滤波系数的第三乘值、第x个雷达帧信号的预设探测点的置信度和第二置信度滤波系数的第四乘值；将第一乘值和第二乘值的和值，以及第三乘值和第四乘值的和值，确定为第x个雷达帧信号的预设探测点的滤波结果。
在一些实施例中，上述迭代滤波的方式可以称为α-β循环迭代滤波，其中，1-α为第一相位滤波系数，α为第一相位滤波系数，1-β为第一置信度滤波系数，β为第二置信度滤波系数，其中，第一相位滤波系数小于第二相位滤波系数，第一置信度滤波系数小于第二置信度滤波系数。
例如，α=0.9，β=0.8，如此，迭代滤波后的第x个雷达帧信号的预设探测点的相位=0.9*第x个雷达帧信号的预设探测点的相位+0.1*第x-1个雷达帧信号的预设探测点的相位；迭代滤波后的第x个雷达帧信号的预设探测点的置信度=0.8*第x个雷达帧信号的预设探测点的置信度+0.2*第x-1个雷达帧信号的预设探测点的置信度。
步骤S160、在滤波结果大于预设阈值的情况下，确定预设探测点存在生命。
在一些实施例中，预设阈值可以用于界定预设探测点处是否存在生命。具体的，如果滤波结果大于预设阈值，则可以认为预设探测点处存在生命。如此，在滤波结果大于预设阈值的情况下，可以确定预设探测点存在生命。
示例性地，步骤S160的处理可以如下：当第一乘值和第二乘值的和值大于第一预设阈值，且第三乘值和第四乘值的和值大于第二预设阈值时，确定预设探测点存在生命。
在一些实施例中，第x个雷达帧信号的预设探测点的滤波结果可以包括两部分，一部分是第一乘值和第二乘值的和值，该部分可称为相位滤波结果；另一部分是第三乘值和第四乘值的和值，该部分可称为置信度滤波结果。相应的，相位滤波结果的预设阈值可称为第一预设阈值，置信度滤波结果的预设阈值可称为第二预设阈值。
在一些实施例中，当相位滤波结果和置信度滤波结果同时大于相应的预设阈值时，即第一乘值和第二乘值的和值大于第一预设阈值，且第三乘值和第四乘值的和值大于第二预设阈值，此时，可以确定预设探测点存在生命。
在一些实施例中，在确定预设探测点存在生命之后，如果检测到车辆锁闭信号，则可以生成报警信息，例如，可以是声音信息、光信息或者即时信息，也可以是声音信息、光信息和即时信息中的任意两种组合，还可以是声音信息、光信息和即时信息的三种组合，以提醒用户车内遗留有儿童或者宠物。
在本申请实施例中，可以获取由车内的预设毫米波雷达采集的第x个雷达帧信号，然后对第x个雷达帧信号进行解调采样和时频变换，得到第一距离维信号阵列。之后，可以对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列，然后可以在第二距离维信号阵列中提取预设探测点的相位和置信度，接着可以根据预先提取的第x-1个雷达帧信号的预设探测点的相位和置信度，对第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到第x个雷达帧信号的预设探测点的滤波结果。如果滤波结果大于预设阈值，则可以确定预设探测点存在生命。由于毫米波雷达可以应用于多种场景，因此，基于毫米波雷达的探测信号，再结合上述探测算法，可以准确地识别出车内的呼吸微动目标，即车内生命，如此，可以广泛地应用于各个场景下的车内生命探测，且具有较好的探测效果。
此外，由于毫米波雷达具备穿透雾烟灰尘强、不受气候温度光线影响、能够全天候全天时工作、比光波的衰减小、能够穿透衣物准确探测车内复杂空间中的活体目标等特点，可以将毫米波雷达采用隐藏式安装在车内，从而可以无需破坏车内造型，保持车辆造型的完整性和美观化。
基于上述实施例提供的车生命探测方法，相应地，本申请还提供了应用于该车内生命探测方法的车内生命探测装置的具体实现方式。请参见以下实施例。
如图4所示，本申请实施例提供了一种车内生命探测装置，该装置包括：
获取模块410，用于获取由车内的预设毫米波雷达采集的第x个雷达帧信号，x为大于或者等于2的自然数；
采样变换模块420，用于对第x个雷达帧信号进行解调采样和时频变换，得到第一距离维信号阵列，第一距离维信号阵列包括多个距离维采样点的时间维信号值；
滤波模块430，用于对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列；
提取模块440，用于在第二距离维信号阵列中提取预设探测点的相位和置信度；
迭代模块450，用于根据预先提取的第x-1个雷达帧信号的预设探测点的相位和置信度，对第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到第x个雷达帧信号的预设探测点的滤波结果；
探测模块460，用于在滤波结果大于预设阈值的情况下，确定预设探测点存在生命。
在一些实施例中，对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列，包括：
计算各个距离维采样点的时间维信号值的平均值；
将第一距离维信号阵列中每个距离维采样点的时间维信号值减去平均值，得到第二距离维信号阵列。
在一些实施例中，对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列，包括：
计算各个距离维采样点的时间维信号值的平均值；
将第一距离维信号阵列中每个距离维采样点的时间维信号值减去平均值，得到过渡距离维信号阵列；
根据波达方向定位技术对过渡距离维信号阵列进行波达方向估计，得到第二距离维信号阵列。
在一些实施例中，对第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到第x个雷达帧信号的预设探测点的滤波结果，包括：
获取第x-1个雷达帧信号的预设探测点的相位和第一相位滤波系数的第一乘值、第x个雷达帧信号的预设探测点的相位和第二相位滤波系数的第二乘值、第x-1个雷达帧信号的预设探测点的置信度和第一置信度滤波系数的第三乘值、第x个雷达帧信号的预设探测点的置信度和第二置信度滤波系数的第四乘值；
将第一乘值和第二乘值的和值，以及第三乘值和第四乘值的和值，确定为第x个雷达帧信号的预设探测点的滤波结果；
其中，第一相位滤波系数小于第二相位滤波系数，第一置信度滤波系数小于第二置信度滤波系数。
在一些实施例中，在滤波结果大于预设阈值的情况下，确定预设探测点存在生命，包括：
当第一乘值和第二乘值的和值大于第一预设阈值，且第三乘值和第四乘值的和值大于第二预设阈值时，确定预设探测点存在生命。
在一些实施例中，在确定预设探测点存在生命之后，方法还包括：
在检测到车辆锁闭信号后，生成报警信息；报警信息包括声音信息、光信息和即时信息中的至少一种。
在一些实施例中，预设毫米波雷达的频率范围为60GHz-64GHz。
需要说明的是，本申请提供的车内生命探测装置能够实现与上述车内生命探测方法相同的步骤功能，具有相同的技术效果，车内生命探测方法中未重复在车内生命探测装置中记载的内容，应当被认为已经明确记载在说明书中。
在本申请实施例中，可以获取由车内的预设毫米波雷达采集的第x个雷达帧信号，然后对第x个雷达帧信号进行解调采样和时频变换，得到第一距离维信号阵列。之后，可以对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列，然后可以在第二距离维信号阵列中提取预设探测点的相位和置信度，接着可以根据预先提取的第x-1个雷达帧信号的预设探测点的相位和置信度，对第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到第x个雷达帧信号的预设探测点的滤波结果。如果滤波结果大于预设阈值，则可以确定预设探测点存在生命。由于毫米波雷达可以应用于多种场景，因此，基于毫米波雷达的探测信号，再结合上述探测算法，可以准确地识别出车内的呼吸微动目标，即车内生命，如此，可以广泛地应用于各个场景下的车内生命探测，且具有较好的探测效果。
此外，由于毫米波雷达具备穿透雾烟灰尘强、不受气候温度光线影响、能够全天候全天时工作、比光波的衰减小、能够穿透衣物准确探测车内复杂空间中的活体目标等特点，可以将毫米波雷达采用隐藏式安装在车内，从而可以无需破坏车内造型，保持车辆造型的完整性和美观化。
图5是本申请一实施例提供的电子设备的示意图。如图5所示，该实施例的电子设备5包括：处理器50、存储器51以及存储在存储器51中并可在处理器50上运行的计算机程序52。处理器50执行计算机程序52时实现上述各个车内生命探测方法实施例中的步骤。或者，处理器50执行计算机程序52时实现上述各装置实施例中各模块/单元的功能。
示例性地，计算机程序52可以被分割成一个或多个模块/单元，一个或者多个模块/单元被存储在存储器51中，并由处理器50执行，以完成本申请。一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述计算机程序52在电子设备5中的执行过程。例如，计算机程序52可以被分割成获取模块、采样变换模块、滤波模块、提取模块、迭代模块、探测模块，各模块具体功能如下：
获取模块，用于获取由车内的预设毫米波雷达采集的第x个雷达帧信号，x为大于或者等于2的自然数；
采样变换模块，用于对第x个雷达帧信号进行解调采样和时频变换，得到第一距离维信号阵列，第一距离维信号阵列包括多个距离维采样点的时间维信号值；
滤波模块，用于对第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列；
提取模块，用于在第二距离维信号阵列中提取预设探测点的相位和置信度；
迭代模块，用于根据预先提取的第x-1个雷达帧信号的预设探测点的相位和置信度，对第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到第x个雷达帧信号的预设探测点的滤波结果；
探测模块，用于在滤波结果大于预设阈值的情况下，确定预设探测点存在生命。
电子设备5可以是桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。电子设备可包括，但不仅限于，处理器50、存储器51。本领域技术人员可以理解，图5仅仅是电子设备5的示例，并不构成对电子设备5的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如，电子设备还可以包括输入输出设备、网络接入设备、总线等。
处理器50可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器 (Digital Signal Processor，DSP)、专用集成电路 (Application Specific Integrated Circuit，ASIC)、现场可编程门阵列 (Field-Programmable Gate Array，FPGA) 或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者也可以是任何常规的处理器等。
存储器51可以是电子设备5的内部存储单元，例如，电子设备5的硬盘或内存。存储器51也可以是电子设备5的外部存储设备，例如，电子设备5上配备的插接式硬盘，智能存储卡（Smart Media Card, SMC），安全数字（Secure Digital, SD）卡，闪存卡（Flash Card）等。进一步地，存储器51还可以既包括电子设备5的内部存储单元，也包括外部存储设备。存储器51用于存储计算机程序以及电子设备所需的其他程序和数据。存储器51还可以用于暂时地存储已经输出或者将要输出的数据。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将上述装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元、模块的具体名称也只是为了便于相互区分，并不用于限制本申请的保护范围。上述系统中单元、模块的具体工作过程，可以参考上述方法实施例中的对应过程，在此不再赘述。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参见其它实施例的相关描述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
在本申请所提供的实施例中，应该理解到，所揭露的装置/终端设备和方法，可以通过其它的方式实现。例如，以上所描述的装置/终端设备实施例仅仅是示意性的，例如，所述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通讯连接可以是通过一些接口，装置或单元的间接耦合或通讯连接，可以是电性，机械或其它的形式。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实现上述实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，计算机程序包括计算机程序代码，计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。计算机可读存储介质可以包括：能够携带计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器（ROM，Read-Only Memory）、随机存取存储器（RAM，Random Access Memory）、电载波信号、电信信号以及软件分发介质等。需要说明的是，计算机可读存储介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，计算机可读存储介质不包括电载波信号和电信信号。
以上所述实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照上述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对上述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (10)

  1. 一种车内生命探测方法，其特征在于，包括：
    获取步骤：获取由车内的预设毫米波雷达采集的第x个雷达帧信号，x为大于或者等于2的自然数；
    采样变换步骤：对所述第x个雷达帧信号进行解调采样和时频变换，得到第一距离维信号阵列，所述第一距离维信号阵列包括多个距离维采样点的时间维信号值；
    滤波步骤：对所述第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列；
    提取步骤：在所述第二距离维信号阵列中提取预设探测点的相位和置信度；
    迭代步骤：根据预先提取的第x-1个雷达帧信号的预设探测点的相位和置信度，对所述第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到所述第x个雷达帧信号的预设探测点的滤波结果；
    探测步骤：在所述滤波结果大于预设阈值的情况下，确定所述预设探测点存在生命。
  2. 如权利要求1所述的车内生命探测方法，其特征在于，所述滤波步骤，包括：
    计算各个所述距离维采样点的时间维信号值的平均值；
    将所述第一距离维信号阵列中每个距离维采样点的时间维信号值减去所述平均值，得到所述第二距离维信号阵列。
  3. 如权利要求1所述的车内生命探测方法，其特征在于，所述滤波步骤，包括：
    计算各个所述距离维采样点的时间维信号值的平均值；
    将所述第一距离维信号阵列中每个距离维采样点的时间维信号值减去所述平均值，得到过渡距离维信号阵列；
    根据波达方向定位技术对所述过渡距离维信号阵列进行波达方向估计，得到所述第二距离维信号阵列。
  4. 如权利要求1至3任一项所述的车内生命探测方法，其特征在于，所述迭代步骤，包括：
    获取所述第x-1个雷达帧信号的预设探测点的相位和第一相位滤波系数的第一乘值、所述第x个雷达帧信号的预设探测点的相位和第二相位滤波系数的第二乘值、所述第x-1个雷达帧信号的预设探测点的置信度和第一置信度滤波系数的第三乘值、所述第x个雷达帧信号的预设探测点的置信度和第二置信度滤波系数的第四乘值；
    将所述第一乘值和所述第二乘值的和值，以及所述第三乘值和所述第四乘值的和值，确定为所述第x个雷达帧信号的预设探测点的滤波结果；
    其中，所述第一相位滤波系数小于所述第二相位滤波系数，所述第一置信度滤波系数小于所述第二置信度滤波系数。
  5. 如权利要求4所述的车内生命探测方法，其特征在于，所述探测步骤，包括：
    当所述第一乘值和所述第二乘值的和值大于第一预设阈值，且所述第三乘值和所述第四乘值的和值大于第二预设阈值时，确定所述预设探测点存在生命。
  6. 如权利要求1所述的车内生命探测方法，其特征在于，在所述探测步骤之后，所述方法还包括：
    在检测到车辆锁闭信号后，生成报警信息；所述报警信息包括声音信息、光信息和即时信息中的至少一种。
  7. 如权利要求1所述的车内生命探测方法，其特征在于，所述预设毫米波雷达的频率范围为60GHz-64GHz。
  8. 一种车内生命探测装置，其特征在于，包括：
    获取模块，用于获取由车内的预设毫米波雷达采集的第x个雷达帧信号，x为大于或者等于2的自然数；
    采样变换模块，用于对所述第x个雷达帧信号进行解调采样和时频变换，得到第一距离维信号阵列，所述第一距离维信号阵列包括多个距离维采样点的时间维信号值；
    滤波模块，用于对所述第一距离维信号阵列进行滤波处理，得到第二距离维信号阵列；
    提取模块，用于在所述第二距离维信号阵列中提取预设探测点的相位和置信度；
    迭代模块，用于根据预先提取的第x-1个雷达帧信号的预设探测点的相位和置信度，对所述第x个雷达帧信号的预设探测点的相位和置信度进行迭代滤波，得到所述第x个雷达帧信号的预设探测点的滤波结果；
    探测模块，用于在所述滤波结果大于预设阈值的情况下，确定所述预设探测点存在生命。
  9. 一种电子设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1至7任一项所述方法的步骤。
  10. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至7任一项所述方法的步骤。
PCT/CN2022/073491 2021-02-03 2022-01-24 车内生命探测方法、装置、设备和存储介质 WO2022166649A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110149511.X 2021-02-03
CN202110149511.XA CN112816960B (zh) 2021-02-03 2021-02-03 车内生命探测方法、装置、设备和存储介质

Publications (1)

Publication Number Publication Date
WO2022166649A1 true WO2022166649A1 (zh) 2022-08-11

Family

ID=75860944

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/073491 WO2022166649A1 (zh) 2021-02-03 2022-01-24 车内生命探测方法、装置、设备和存储介质

Country Status (2)

Country Link
CN (1) CN112816960B (zh)
WO (1) WO2022166649A1 (zh)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112816960B (zh) * 2021-02-03 2023-03-17 森思泰克河北科技有限公司 车内生命探测方法、装置、设备和存储介质
CN113589277B (zh) * 2021-07-14 2023-10-10 森思泰克河北科技有限公司 车内生命体的雷达探测方法、装置及终端设备
CN113740855B (zh) * 2021-08-12 2023-10-13 森思泰克河北科技有限公司 占位识别方法、装置、毫米波雷达及存储介质
CN113561911B (zh) * 2021-08-12 2023-03-17 森思泰克河北科技有限公司 车辆控制方法、装置、毫米波雷达及存储介质
CN113715766B (zh) * 2021-08-17 2022-05-24 厦门星图安达科技有限公司 一种车内人员检测方法
CN113734046B (zh) * 2021-08-17 2023-09-19 江苏星图智能科技有限公司 基于雷达的车内位置分区人员检测方法、装置以及设备
CN116338608B (zh) * 2023-05-22 2023-07-28 亿慧云智能科技（深圳）股份有限公司 微波雷达探测角度调整方法、装置、设备及存储介质
CN117250609A (zh) * 2023-08-22 2023-12-19 南京航空航天大学 一种舱内活体检测结果平滑方法、存储介质及电子设备

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170039835A1 (en) * 2014-04-14 2017-02-09 Novelic D.O.O. Millimetre-wave seat occupation radar sensor
CN109375215A (zh) * 2018-10-09 2019-02-22 深圳卓影科技有限公司 车内生命体探测方法、装置、计算机设备及存储介质
CN109521422A (zh) * 2018-10-15 2019-03-26 中国人民解放军第四军医大学 一种基于雷达信号的多目标生命探测方法及探测雷达
CN109774641A (zh) * 2019-03-25 2019-05-21 森思泰克河北科技有限公司 车内人员检测方法、雷达和车
CN110346790A (zh) * 2019-07-09 2019-10-18 长沙莫之比智能科技有限公司 一种基于毫米波雷达的非接触式生命体征监测方法、装置及系统
CN111812629A (zh) * 2020-07-21 2020-10-23 成都阶跃时进科技有限公司 一种活体存在检测方法、装置、设备及可读存储介质
CN112272779A (zh) * 2018-06-11 2021-01-26 Iee国际电子工程股份公司 通过生命体征监测进行稳健的车辆占用检测的方法
CN112816960A (zh) * 2021-02-03 2021-05-18 森思泰克河北科技有限公司 车内生命探测方法、装置、设备和存储介质

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102313884B (zh) * 2010-06-29 2013-02-13 电子科技大学 一种基于多帧相参积累的目标检测前跟踪方法
CN102008291B (zh) * 2010-10-11 2012-11-14 中国人民解放军第四军医大学 一种可用于多目标探测的单通道基于uwb的雷达式生命探测仪
CN106199549B (zh) * 2016-06-30 2019-01-22 南京理工大学 一种采用谱减法提升lfmcw雷达信噪比的方法
CN106842194A (zh) * 2017-03-07 2017-06-13 北京海兰信数据科技股份有限公司 一种自适应目标检测方法及装置
CN107132512B (zh) * 2017-03-22 2019-05-17 中国人民解放军第四军医大学 基于多通道hht的uwb雷达人体运动微多普勒特征提取方法
CN107688178A (zh) * 2017-08-25 2018-02-13 上海通趣科技有限公司 一种基于77GHz毫米波雷达的锯齿波测距测速方法
IL259190A (en) * 2018-05-07 2018-06-28 Arbe Robotics Ltd System and method for frequency hopping MIMO FMCW imaging radar
CN109633633B (zh) * 2018-12-27 2021-01-19 西安交通大学 一种基于分段分类增强处理的生命信号增强方法
CN109613508A (zh) * 2018-12-29 2019-04-12 森思泰克河北科技有限公司 前向目标检测雷达和方法
CN110687530A (zh) * 2019-09-18 2020-01-14 上海广电通信技术有限公司 微型安防雷达监控系统
CN111366919B (zh) * 2020-03-24 2022-05-13 南京矽典微系统有限公司 基于毫米波雷达的目标检测方法和装置、电子设备、存储介质
CN111882579A (zh) * 2020-07-03 2020-11-03 湖南爱米家智能科技有限公司 基于深度学习和目标跟踪的大输液异物检测方法、系统、介质及设备
CN112244794B (zh) * 2020-11-02 2023-11-21 深圳大学 基于周期性特征的生命体征检测方法、装置和存储介质

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170039835A1 (en) * 2014-04-14 2017-02-09 Novelic D.O.O. Millimetre-wave seat occupation radar sensor
CN112272779A (zh) * 2018-06-11 2021-01-26 Iee国际电子工程股份公司 通过生命体征监测进行稳健的车辆占用检测的方法
CN109375215A (zh) * 2018-10-09 2019-02-22 深圳卓影科技有限公司 车内生命体探测方法、装置、计算机设备及存储介质
CN109521422A (zh) * 2018-10-15 2019-03-26 中国人民解放军第四军医大学 一种基于雷达信号的多目标生命探测方法及探测雷达
CN109774641A (zh) * 2019-03-25 2019-05-21 森思泰克河北科技有限公司 车内人员检测方法、雷达和车
CN110346790A (zh) * 2019-07-09 2019-10-18 长沙莫之比智能科技有限公司 一种基于毫米波雷达的非接触式生命体征监测方法、装置及系统
CN111812629A (zh) * 2020-07-21 2020-10-23 成都阶跃时进科技有限公司 一种活体存在检测方法、装置、设备及可读存储介质
CN112816960A (zh) * 2021-02-03 2021-05-18 森思泰克河北科技有限公司 车内生命探测方法、装置、设备和存储介质

Also Published As

Publication number Publication date
CN112816960A (zh) 2021-05-18
CN112816960B (zh) 2023-03-17

Similar Documents

Publication Publication Date Title
WO2022166649A1 (zh) 车内生命探测方法、装置、设备和存储介质
US11885872B2 (en) System and method for camera radar fusion
CN111650582B (zh) 一种基于mimo毫米波雷达的手势识别方法
CN111373282A (zh) 用于fmcw雷达系统的雷达处理链
CN204203457U (zh) 基于空间谱估计算法的短波测向系统
CN109738861A (zh) 一种基于Wi-Fi信道状态信息的三维联合估计方法
CN113589277B (zh) 车内生命体的雷达探测方法、装置及终端设备
CN111693978A (zh) 基于mimo毫米波雷达的散点检测方法
WO2023071992A1 (zh) 多传感器信号融合的方法、装置、电子设备及存储介质
CN112859033A (zh) 目标探测的方法、装置及相关设备
WO2022199431A1 (zh) 干扰检测方法及装置
CN114390463B (zh) 一种室内多目标被动式定位方法、系统及电子设备
Weiß et al. Improved people counting algorithm for indoor environments using 60 GHz FMCW radar
CN113109781B (zh) 波达方向估计方法、雷达和可移动设备
CN112946618B (zh) 室内人员的定位方法及装置、系统、家电设备
Swami et al. High performance automotive radar signal processing on TI's TDA3X platform
CN111983595A (zh) 一种室内定位的方法及装置
CN116125458A (zh) 一种基于毫米波雷达的人员定位方法
KR102490396B1 (ko) 레이더 센서 및 이의 물체 검출 방법
CN108008347A (zh) 用于acas的测向方法
CN113740855B (zh) 占位识别方法、装置、毫米波雷达及存储介质
CN115575905A (zh) 噪声背景下抑制多秩干扰的智能融合检测方法
CN116027288A (zh) 生成数据的方法、装置、电子设备及存储介质
Erhel et al. A method of direction finding operating on an array of collocated antennas
CN111337886B (zh) 基于通道比函数的雷达干扰抑制方法、装置及电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22748928

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22748928

Country of ref document: EP

Kind code of ref document: A1