WO2023138253A1 - 检测方法及通信设备 - Google Patents

检测方法及通信设备 Download PDF

Info

Publication number
WO2023138253A1
WO2023138253A1 PCT/CN2022/137626 CN2022137626W WO2023138253A1 WO 2023138253 A1 WO2023138253 A1 WO 2023138253A1 CN 2022137626 W CN2022137626 W CN 2022137626W WO 2023138253 A1 WO2023138253 A1 WO 2023138253A1
Authority
WO
WIPO (PCT)
Prior art keywords
detection
echo signal
signal
measured space
arrival
Prior art date
Application number
PCT/CN2022/137626
Other languages
English (en)
French (fr)
Inventor
索士强
苏昕
龚秋莎
粟欣
高晖
唐勐
Original Assignee
大唐移动通信设备有限公司
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 大唐移动通信设备有限公司 filed Critical 大唐移动通信设备有限公司
Publication of WO2023138253A1 publication Critical patent/WO2023138253A1/zh

Links

Images

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
    • G01S3/00—Direction-finders for determining the direction from which infrasonic, sonic, ultrasonic, or electromagnetic waves, or particle emission, not having a directional significance, are being received
    • G01S3/02—Direction-finders for determining the direction from which infrasonic, sonic, ultrasonic, or electromagnetic waves, or particle emission, not having a directional significance, are being received using radio waves
    • G01S3/14—Systems for determining direction or deviation from predetermined direction
    • 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
    • G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
    • G01S13/04—Systems determining presence of a target
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/22—Electrical actuation
    • G08B13/24—Electrical actuation by interference with electromagnetic field distribution
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/22—Electrical actuation
    • G08B13/24—Electrical actuation by interference with electromagnetic field distribution
    • G08B13/2491—Intrusion detection systems, i.e. where the body of an intruder causes the interference with the electromagnetic field

Definitions

  • the present disclosure relates to the technical field of wireless communication, and in particular, to a detection method, communication equipment, a device, and a storage medium.
  • Intrusion detection refers to the monitoring of a designated area to determine whether an object has entered the designated area and to issue an alarm if necessary. Intrusion detection has broad application prospects in indoor services such as security prevention and control, building security, and smart home.
  • intrusion detection based on computer vision needs to take pictures of the scene through image sensors.
  • this method has good intrusion detection accuracy, it requires relatively high installation costs and high deployment difficulties. It has high computational complexity and is difficult to use in dark scenes, and there may be a risk of violating personal privacy.
  • the disclosure provides a detection method, communication equipment, device and storage medium.
  • a detection method including: acquiring a plurality of detection echo signals in a measured space; determining a direction of arrival DOA corresponding to the plurality of detection echo signals; and detecting whether there is an intrusion object in the measured space according to the difference in the angle of arrival between the multiple DOAs.
  • a communication device including: a memory, a transceiver, and a processor: the memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: acquire multiple detection echo signals in the measured space; determine the DOA corresponding to the multiple detection echo signals;
  • a detection device including: an acquisition unit, configured to acquire a plurality of detection echo signals in a measured space; a determination unit, configured to determine a direction of arrival DOA corresponding to the plurality of detection echo signals; a detection unit, configured to detect whether there is an intrusion object in the measured space according to the difference in the angle of arrival between the plurality of DOAs.
  • a processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the method described in the embodiment of the first aspect of the present disclosure.
  • a computer program product including a computer program, wherein when the computer program is executed by a processor, the method described in the embodiment of the first aspect of the present disclosure is implemented.
  • FIG. 1 is a schematic flow diagram of the detection method provided by Embodiment 1 of the present disclosure
  • FIG. 2 is a schematic diagram of a detection scene of a smart home device in an embodiment of the present disclosure
  • FIG. 3 is a schematic flow chart of the detection method provided in Embodiment 2 of the present disclosure.
  • FIG. 4 is a schematic flow chart of the detection method provided by Embodiment 3 of the present disclosure.
  • FIG. 5 is a schematic flow diagram of the detection method provided in Embodiment 4 of the present disclosure.
  • FIG. 6 is a schematic diagram of detection echoes received by an array antenna in an embodiment of the present disclosure
  • FIG. 7 is a schematic structural diagram of a communication device provided by Embodiment 5 of the present disclosure.
  • FIG. 8 is a schematic structural diagram of a detection device provided by Embodiment 6 of the present disclosure.
  • intrusion detection can also be performed based on wireless technology, which detects whether there is an intruder based on the channel state information in the device or the degree of change in received signal strength.
  • wireless technology which detects whether there is an intruder based on the channel state information in the device or the degree of change in received signal strength.
  • the received signal strength will fluctuate greatly.
  • the present disclosure proposes a detection method, a communication device, an apparatus, and a storage medium.
  • the method and the device are conceived based on the same application. Since the principle of solving problems of the method and the device is similar, the implementation of the device and the method can be referred to each other, and the repetition will not be repeated.
  • FIG. 1 is a schematic flow chart of the detection method provided by Embodiment 1 of the present disclosure.
  • the detection method in the embodiment of the present disclosure can be executed by a detection device, and the detection device can be configured on a communication device, wherein the communication device can be a smart terminal device, a base station device, a smart home device, or a smart security device.
  • the communication device is illustrated as a smart home device as shown in FIG. 2 .
  • the smart home device may include multiple smart devices, such as TX (transmitter) and RX (receiver) in FIG. 2 . It can be understood that when there is an intrusion object, the intrusion object will affect the indoor propagation path, and the multipath state of the indoor channel will change.
  • this detection method can detect that infants and young children enter the dangerous area of the window balcony, and send an alarm message to the guardian through the smart device in the smart home device, or trigger the automatic switch to automatically close the window to prevent the infant from falling.
  • the communication device may also be a smart terminal device, a related device on the network device side, etc.
  • the communication device may include multiple access points (AccessPoint, AP for short) in the base station or other related devices, and those skilled in the art can select according to actual needs.
  • AccessPoint AccessPoint
  • one of the relevant devices in the base station is a sending device, and the other is a receiving device.
  • the sending device transmits detection waves, and the receiving device receives corresponding detection echoes.
  • the intrusion object will affect the propagation path of the detection echo in the measured space, and the multipath state of the channel of the detection echo in the measured space will change. Therefore, it can be determined whether there is an intrusion object in the measured space based on the multipath state of the detection echo in the measured space.
  • the smart terminal device may be a device that provides voice and/or data connectivity to the user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem, and the like.
  • the name of the terminal equipment may be different.
  • the terminal equipment may be called User Equipment (User Equipment, UE).
  • Wireless terminal equipment can communicate with one or more core networks (Core Network, CN) via a radio access network (Radio Access Network, RAN).
  • the wireless terminal equipment can be mobile terminal equipment, such as mobile phones (or called "cellular" phones) and computers with mobile terminal equipment.
  • a wireless terminal device may also be called a system, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal, an access terminal, a user terminal, a user agent, A user device (user device), etc., can be selected according to actual needs in the present disclosure.
  • the base station may include multiple cells providing services for the terminal.
  • the base station can also be called an access point, or it can be a device in the access network that communicates with wireless terminals through one or more sectors on the air interface, or other names.
  • the base station is operable to interchange received over-the-air frames with Internet Protocol (IP) packets and acts as a router between the wireless terminal and the rest of the access network, which may include an Internet Protocol (IP) communications network.
  • IP Internet Protocol
  • the base station may also coordinate attribute management for the air interface.
  • the base station involved in the embodiments of the present disclosure may be a base station (Base Transceiver Station, BTS for short) in Global System for Mobile communications (GSM for short) or Code Division Multiple Access (CDMA for short), or a base station (NodeB) in Wide-band Code Division Multiple Access (WCDMA for short).
  • BTS Base Transceiver Station
  • NodeB base station
  • WCDMA Wide-band Code Division Multiple Access
  • eNB or e-NodeB for short in a long term evolution (LTE for short) system
  • gNB 5G base station
  • gNB 5G network architecture
  • HeNB Home evolved Node B
  • the base station may include a Centralized Unit (CU for short) node and a Distributed Unit (DU for short) node, and the Centralized Unit and the distributed unit may also be arranged geographically separately.
  • CU Centralized Unit
  • DU Distributed Unit
  • the detection method may include steps 101 to 103 as follows.
  • Step 101 acquiring a plurality of detection echo signals in a measured space.
  • a detection wave may be transmitted into the measured space, and a plurality of detection echo signals in the measurement space may be received, so as to obtain a plurality of detection echo signals in the measurement space.
  • the detection device includes a bistatic radar, node A of the bistatic radar sends multiple detection echoes in the measured space, and the detection device receives corresponding detection echoes through node B of the bistatic radar to obtain multiple detection echo signals.
  • multiple detection waves are sent in the measured space; corresponding detection echoes are received to obtain multiple detection echo signals.
  • the detection device includes a full-duplex radar, and the full-duplex radar sends multiple detection waves in the measured space and receives corresponding detection echoes, thereby obtaining multiple detection echoes.
  • Step 102 determining the directions of arrival DOAs corresponding to the multiple detection echo signals.
  • the Direction of Arrival (DOA) corresponding to multiple sounding echo signals may be the direction angle at which each sounding echo signal arrives at an array element in the array antenna, wherein the array antenna refers to arranging the antennas in an array to form an antenna array, and the antenna array can receive the sounding echo signals in the measured space to obtain the DOA corresponding to the multiple sounding echo signals.
  • DOA Direction of Arrival
  • Step 103 according to the differences in the angles of arrival among multiple DOAs, it is detected whether there is an intrusion object in the measured space.
  • multiple DOAs determine the difference in angle of arrival between multiple DOAs, and determine whether there is an intrusion object in the detected space according to the difference in angle of arrival between multiple DOAs and the set angle threshold.
  • the present disclosure also proposes a detection method.
  • FIG. 3 is a schematic flow chart of the detection method provided by Embodiment 2 of the present disclosure.
  • the detection method includes the following steps 301 to 304 .
  • Step 301 acquiring a plurality of detection echo signals in a measured space.
  • Step 302 determining the directions of arrival DOAs corresponding to the multiple detection echo signals.
  • Step 303 determining the variance of the angle of arrival among multiple DOAs.
  • Step 304 according to the variance of the angle of arrival, detect whether there is an intrusion object in the measured space.
  • the variance of the angle of arrival among multiple DOAs may be calculated, and it is determined whether there is an intrusion object in the measured space according to the variance of the angle of arrival.
  • the variance of the angle of arrival is greater than the angle threshold, it is determined that there is an intrusion object in the measured space; if the variance of the angle of arrival is less than or equal to the angle threshold, it is determined that there is no intrusion object in the measured space.
  • the variance of the angle of arrival can be compared with the angle threshold. If the variance of the angle of arrival is greater than the angle threshold, it can be determined that there is an intrusion object in the measured space;
  • the present disclosure also proposes a detection method.
  • FIG. 4 is a schematic flow chart of the detection method provided by Embodiment 3 of the present disclosure.
  • the detection method includes the following steps 401 to 405 .
  • Step 401 monitor the signal strength and/or channel state information of the communication signal in the measured space.
  • the detection device monitors the signal strength and/or channel state information of the communication signal in the measured space, so as to obtain the signal strength and/or channel state information of the communication signal in the measured space.
  • Step 402 Based on the signal strength and/or channel state information, when it is determined that there is an intruder object, the array antenna is used to receive detection echoes multiple times to obtain detection echo signals output by the array antenna for each reception.
  • the signal strength of the communication signal and/or the change degree of the channel state information in the measured space is greater than or equal to the change threshold, it can be determined that there is an intrusion object in the measured space, and multiple detection echo signals in the measured space can be acquired.
  • the array antenna is used to receive the detection echo multiple times, so as to obtain the detection echo signal output by the array antenna for each reception. For example, the array antenna receives detection echoes continuously for m minutes with a period of n seconds, so that the detection echo signals output by the array antenna for each reception within m minutes can be obtained.
  • Step 403 acquiring any target echo signal among the plurality of detection echo signals.
  • the target echo signal may include sub-signals output by each array element in the array antenna.
  • Step 404 According to the covariance information among the sub-signals in the target echo signal, the DOA corresponding to the target echo signal is determined by using the trained classification model.
  • the covariance matrix among the sub-signals in the target echo signal can be determined, and the DOA corresponding to the target echo signal can be determined according to each element in the covariance matrix and a trained classification model.
  • Step 405 according to the differences in the angles of arrival among multiple DOAs, it is detected whether there is an intrusion object in the measured space.
  • the passive sensing method is adopted to monitor the signal strength of the communication signal and/or the channel state information in the measured space, and according to the signal strength of the communication signal in the measured space and/or the channel state information, the rough discrimination of the intrusion object is performed, and the fine discrimination of the intrusion object is performed according to the DOA corresponding to the detection echo signal received multiple times, which improves the detection accuracy of the intrusion object and personal privacy security, and reduces the computational complexity.
  • FIG. 5 is a schematic flow chart of the detection method provided by Embodiment 4 of the present disclosure.
  • the detection method includes the following steps 501 to 507 .
  • Step 501 monitor the signal strength and/or channel state information of communication signals in the measured space.
  • Step 502 Based on the signal strength and/or channel state information, when it is determined that there is an intruder object, the array antenna is used to receive detection echoes multiple times to obtain detection echo signals output by the array antenna for each reception.
  • Step 503 acquiring any target echo signal among the plurality of detection echo signals.
  • Step 504 Determine a covariance matrix according to each sub-signal in the target echo signal.
  • each row and each column in the covariance matrix has a corresponding array element, and the elements in the covariance matrix are used to indicate the covariance between the sub-signal output by the array element corresponding to the row and the sub-signal output by the array element corresponding to the column.
  • the uniform linear array is a uniform linear array composed of M array elements, and the distance between each array element is d.
  • d is less than 1/2 of the wavelength corresponding to the highest frequency of the detection echo signal.
  • the signal (sub-signal) received by the mth array element can be expressed as:
  • a m ( ⁇ k ) is the response vector of the k-th signal on the m-th array element
  • s k (t) is the k-th source, that is, the amplitude and phase of the target echo signal at point k, expressed in complex numbers
  • n m (t) is the noise value of the m-th array element.
  • the vector form of the target echo signal received by the array antenna (uniform linear array) can be expressed as:
  • A is the direction matrix of the array antenna, the matrix A is in complex form, and N(t) is the noise matrix.
  • the a i, j elements in the matrix A depend on the i-th array element, its position relative to the coordinate origin and the incident direction of the j-th signal it receives.
  • the j-th column a( ⁇ j ) of A is the response vector to the j-th signal with angle of arrival ⁇ j .
  • the covariance matrix between the sub-signals in the target echo signal can be expressed as:
  • ⁇ is the variance of Gaussian white noise
  • R s is the correlation matrix of the input signal
  • X(t) is the response matrix of the array.
  • Step 505 generate an input sequence according to the elements in the covariance matrix.
  • multiple target elements at set positions in the covariance matrix are extracted; a first subsequence is generated according to the real parts contained in the multiple target elements; a second subsequence is generated according to the imaginary parts contained in the multiple target elements; the first subsequence and the second subsequence are spliced to obtain an input sequence.
  • the covariance matrix is a complex matrix
  • the real part and the imaginary part contained in the multiple target elements at the set positions in the covariance matrix can be sequentially extracted, and the first subsequence is generated according to the real part of each target element extracted in sequence, and the second subsequence is generated according to the imaginary part of each target element extracted in sequence, the first subsequence and the second subsequence are spliced, and the splicing result is used as the input sequence.
  • Step 506 Input the input sequence into the trained classification model to obtain the DOA corresponding to the target echo signal.
  • the input sequence is input into the trained classification model, and the trained classification model can output the DOA corresponding to the target echo signal.
  • the trained classification model is obtained by performing the first training on the set classification model based on the adapted training samples.
  • the adaptive training samples include: the first sample sequence, corresponding to the test echo signal obtained by receiving the test signal by the array antenna, the first sample covariance matrix is determined according to each sub-signal in the test echo signal, and the first sample covariance matrix is generated according to the elements in the first sample covariance matrix; the calibration DOA is determined based on the test echo signal using the angle of arrival algorithm.
  • the classification model is set to be obtained by performing second training based on pre-training samples; wherein, the pre-training samples include: a second sample sequence corresponding to a simulated echo signal with a known DOA, which is based on each sub-signal in the simulated echo signal to determine a second sample covariance matrix, which is generated according to elements in the second sample covariance matrix; DOA of the simulated echo signal.
  • the classification model is set to be obtained by pre-training the classification model using pre-training samples, wherein the pre-training samples include a second sample sequence and a DOA of a simulated echo signal, and the second sample sequence corresponds to a simulated echo signal with a known DOA; wherein, the simulated echo signal with a known DOA is determined according to each sub-signal in the simulated echo signal.
  • the coefficients of the classification model are adjusted to obtain the set classification model. Since the simulated echo signal and the DOA of the simulated echo signal are generated by the simulation software, the generation environment is relatively ideal, and the influence of the complex physical environment on the detection echo signal is lacking.
  • the adaptive training samples can be used to train the set classification model (coefficient adjustment).
  • the adaptive training sample may include the first sample sequence and the calibration DOA, the first sample sequence corresponds to the test echo signal obtained by receiving the test signal by the array antenna, the test echo signal is based on each sub-signal in the test echo signal, and according to the covariance matrix between the sub-signals in the test echo signal, and the test echo signal generated according to the elements in the covariance matrix; the calibration DOA is determined based on the test echo signal using the angle-of-arrival algorithm, wherein the angle-of-arrival algorithm can be multiple signal classification based on noise subspace classification, MUSIC) method or the signal subspace-based rotation invariant subspace algorithm (Estimation of signal parameters via rotational invariance techniques, ESPRIT).
  • the angle-of-arrival algorithm can be multiple signal classification based on noise subspace classification, MUSIC) method or the signal subspace-based rotation invariant subspace algorithm (Estimation of signal parameters via rotational invariance techniques, ESPRIT).
  • the trained classification model does not require a large amount of training data for training, and it is not affected by outliers according to changes in the environment in the actual scene, which improves the robustness and perception accuracy of deployment in different environments.
  • Step 507 according to the differences in the angles of arrival among the multiple DOAs, it is detected whether there is an intrusion object in the measured space.
  • the covariance matrix is determined, wherein each row and column in the covariance matrix has a corresponding array element, and the elements in the covariance matrix are used to indicate the covariance between the sub-signal output by the corresponding array element in the row and the sub-signal output by the corresponding array element in the column; an input sequence is generated according to the elements in the covariance matrix; the input sequence is input into the trained classification model to obtain the DOA corresponding to the target echo signal.
  • the DOAs corresponding to the multiple detection echo signals in the measured space can be accurately obtained.
  • the detection method in the embodiment of the present disclosure obtains multiple detection echo signals in the measured space; determines the DOA corresponding to the multiple detection echo signals; and detects whether there is an intrusion object in the measured space according to the difference in the angle of arrival between the multiple DOAs. Therefore, according to the difference in the angle of arrival between the directions of arrival corresponding to multiple detection echo signals in the measured space, it is detected whether there is an intrusion object in the measured space, and the real-time perception of the target and the environment of the non-active terminal is realized.
  • the applicable system can be Global System of Mobile communication (GSM for short) system, Code Division Multiple Access (CDMA for short) system, Wideband Code Division Multiple Access (WCDMA for short), General Packet Radio Service (GPRS for short) system, long term evolution (long term evolu LTE) system, LTE Frequency Division Duplex (FDD) system, LTE time division duplex (TDD) system, Long Term Evolution Advanced (LTE-A) system, Universal Mobile Telecommunications System (UMTS), Worldwide Interoperability for Microwave Access, referred to as WiMAX) system, 5G new air interface (New Radio, referred to as NR) system, etc.
  • GSM Global System of Mobile communication
  • CDMA Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • GPRS General Packet Radio Service
  • TDD Long Term Evolution Advanced
  • LTE-A Long Term Evolution Advanced
  • UMTS Universal Mobile Telecommunications System
  • WiMAX 5G new air interface
  • NR New Radio
  • the present disclosure also proposes a communication device.
  • FIG. 7 is a schematic structural diagram of a communication device provided by Embodiment 5 of the present disclosure.
  • the communication device includes: a memory 710 , a transceiver 720 and a processor 730 .
  • the memory 710 is used to store computer programs; the transceiver 720 is used to send and receive data under the control of the processor; the processor 730 is used to read the computer program in the memory and perform the following operations: acquire multiple detection echo signals in the measured space; determine the DOA corresponding to the multiple detection echo signals; detect whether there is an intrusion object in the measured space according to the difference in the angle of arrival between the multiple DOAs.
  • the transceiver 720 is used for receiving and sending data under the control of the processor 730 .
  • the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by the processor 730 and various circuits of the memory represented by the memory 710 are linked together.
  • the bus architecture can also link together various other circuits such as peripherals, voltage regulators and power management circuits, etc., which are not further described in this article.
  • the bus interface provides the interface.
  • Transceiver 720 may be a plurality of elements, including a transmitter and a receiver, providing a unit for communicating with various other devices over transmission media, including wireless channels, wired channels, optical cables, and other transmission media.
  • the processor 730 is responsible for managing the bus architecture and general processing, and the memory 710 may store data used by the processor 730 when performing operations.
  • the processor 730 may be a CPU, ASIC, FPGA or CPLD, and the processor 730 may also adopt a multi-core architecture.
  • detecting whether there is an intrusion object in the measured space where the array antenna is located according to the difference in the angle of arrival between the multiple DOAs includes: determining the variance of the angle of arrival among the multiple DOAs; and detecting whether there is an intruder object in the measured space where the array antenna is located according to the variance of the angle of arrival.
  • detecting whether there is an intrusion object in the measured space where the array antenna is located according to the variance of the angle of arrival includes: determining that there is an intrusion object in the measured space where the array antenna is located when the variance of the angle of arrival is greater than an angle threshold; and determining that there is no intrusion object in the measured space where the array antenna is located when the variance of the angle of arrival is less than or equal to the angle threshold.
  • acquiring multiple detection echo signals in the measured space includes: monitoring signal strength and/or channel state information of communication signals in the measured space; and acquiring multiple detection echo signals in the measured space when it is determined that an intruder exists based on the signal strength and/or channel state information.
  • obtaining a plurality of detection echo signals in the measured space includes: using an array antenna to receive detection echoes multiple times to obtain detection echo signals output by the array antenna for each reception; correspondingly, determining the direction of arrival DOA corresponding to the multiple detection echo signals includes: obtaining any target echo signal in the multiple detection echo signals; wherein the target echo signal includes sub-signals output by each array element in the array antenna; according to the covariance information between the sub-signals in the target echo signal, using a trained classification model The DOA corresponding to the wave signal.
  • using a trained classification model to determine the DOA corresponding to the target echo signal includes: determining the covariance matrix according to each sub-signal in the target echo signal, wherein each row and column in the covariance matrix has a corresponding element, and the elements in the covariance matrix are used to indicate the covariance between the sub-signal output by the corresponding array element in the row and the sub-signal output by the corresponding array element in the column; generate an input sequence according to the elements in the covariance matrix ; Input the input sequence into the trained classification model to obtain the DOA corresponding to the target echo signal.
  • generating an input sequence according to the elements in the covariance matrix includes: extracting a plurality of target elements at set positions in the covariance matrix; generating a first subsequence according to real parts contained in the multiple target elements; generating a second subsequence according to imaginary parts contained in the multiple target elements; splicing the first subsequence and the second subsequence to obtain the input sequence.
  • the trained classification model is obtained by performing first training on the set classification model based on the adapted training samples; wherein, the adapted training samples include: a first sample sequence corresponding to the test echo signal obtained by receiving the test signal by the array antenna, determining a first sample covariance matrix according to each sub-signal in the test echo signal, and generating it according to elements in the first sample covariance matrix; calibration DOA is determined based on the test echo signal using an angle of arrival algorithm.
  • the classification model is set to be obtained by performing second training based on pre-training samples; wherein, the pre-training samples include: a second sample sequence corresponding to a simulated echo signal with a known DOA, which is determined according to each sub-signal in the simulated echo signal, and is generated according to elements in the second sample covariance matrix; DOA of the simulated echo signal.
  • obtaining multiple detection echo signals in the measured space includes: receiving corresponding detection echoes for multiple detection waves sent by the sending device in the measured space, so as to obtain the multiple detection echo signals; or, sending multiple detection waves in the measured space; receiving corresponding detection echoes, so as to obtain the multiple detection echo signals.
  • the communication device provided by the embodiment of the present disclosure can realize all the method steps realized by the method embodiments in Fig. 1 to Fig. 6 above, and can achieve the same technical effect, so it will not be repeated here.
  • the present disclosure also provides a detection device. Since the detection device provided by the embodiments of the present disclosure corresponds to the detection method provided by the embodiments of FIGS. 1 to 6 above, the implementation of the detection method is also applicable to the detection device provided by the embodiments of the present disclosure, and will not be described in detail in the embodiments of the present disclosure.
  • FIG. 8 is a schematic structural diagram of a detection device provided by Embodiment 6 of the present disclosure.
  • the detection device 800 includes: an acquisition unit 810 , a determination unit 820 and a detection unit 830 .
  • the acquiring unit 810 is configured to acquire a plurality of detection echo signals in the measured space; the determination unit 820 is configured to determine the direction of arrival DOA corresponding to the plurality of detection echo signals; the detection unit 830 is configured to detect whether there is an intrusion object in the measured space according to the difference in the angle of arrival between the multiple DOAs.
  • the detection unit 830 is further configured to: determine the variance of the angle of arrival among multiple DOAs; and detect whether there is an intrusion object in the measured space according to the variance of the angle of arrival.
  • the detection unit 830 is further configured to: determine that there is an intrusion object in the measured space if the variance of the angle of arrival is greater than the angle threshold; and determine that there is no intrusion object in the measured space if the variance of the angle of arrival is less than or equal to the angle threshold.
  • the obtaining unit 810 is further configured to: monitor the signal strength and/or channel state information of the communication signal in the measured space; and acquire multiple detection echo signals in the measured space when it is determined that there is an intruder object based on the signal strength and/or channel state information.
  • the obtaining unit 810 is further configured to: use the array antenna to receive the detection echo multiple times, so as to obtain the detection echo signal output by the array antenna for each reception; correspondingly, the determination unit 820 is also configured to: obtain any target echo signal in the plurality of detection echo signals; wherein the target echo signal includes sub-signals output by each array element in the array antenna; according to the covariance information between the sub-signals in the target echo signal, use a trained classification model to determine the DOA corresponding to the target echo signal.
  • the determining unit 820 is further configured to: determine a covariance matrix according to each sub-signal in the target echo signal, wherein each row and column in the covariance matrix has a corresponding array element, and the elements in the covariance matrix are used to indicate the covariance between the sub-signal output by the corresponding array element in the row and the sub-signal output by the array element corresponding to the column; generate an input sequence according to the elements in the covariance matrix; input the input sequence into a trained classification model to obtain the DOA corresponding to the target echo signal.
  • the determining unit 820 is further configured to: extract multiple target elements at set positions in the covariance matrix; generate a first subsequence according to the real parts contained in the multiple target elements; generate a second subsequence according to the imaginary parts contained in the multiple target elements; splice the first subsequence and the second subsequence to obtain the input sequence.
  • the trained classification model is obtained by performing first training on the set classification model based on the adaptation training samples; wherein the adaptation training samples include: a first sample sequence, corresponding to the test echo signal obtained by receiving the test signal from the array antenna, determining the first sample covariance matrix according to each sub-signal in the test echo signal, and generating it according to the elements in the first sample covariance matrix; the calibration DOA is determined based on the test echo signal using the angle of arrival algorithm.
  • the classification model is set to be obtained by performing second training based on pre-training samples; wherein, the pre-training samples include: a second sample sequence corresponding to a simulated echo signal with a known DOA, which is determined according to each sub-signal in the simulated echo signal, and is generated according to elements in the second sample covariance matrix; DOA of the simulated echo signal.
  • the obtaining unit 810 is further configured to: receive corresponding detection echoes for multiple detection waves sent by the sending device in the measured space, so as to obtain multiple detection echo signals; or, send multiple detection waves in the measured space; receive corresponding detection echoes, so as to obtain multiple detection echo signals.
  • the above-mentioned communication device provided by the embodiments of the present disclosure can implement all the method steps implemented by the above-mentioned method embodiments in FIG. 1 to FIG. 6 , and can achieve the same technical effect, which will not be repeated here.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.
  • the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a processor-readable storage medium.
  • the technical solution of the present disclosure is essentially or part of the contribution to the prior art, or all or part of the technical solution can be embodied in the form of a software product
  • the computer software product is stored in a storage medium, and includes several instructions to make a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) execute all or part of the steps of the method described in each embodiment of the present disclosure.
  • the aforementioned storage medium includes: various media that can store program codes such as U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk.
  • the present disclosure further proposes a processor-readable storage medium.
  • the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the detection method of any one of the embodiments shown in FIG. 1 to FIG. 6 of the present disclosure.
  • the processor-readable storage medium may be any available medium or data storage device that the processor can access, including but not limited to magnetic storage (such as floppy disk, hard disk, magnetic tape, magneto-optical disk (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state hard disk (SSD)) and the like.
  • magnetic storage such as floppy disk, hard disk, magnetic tape, magneto-optical disk (MO), etc.
  • optical storage such as CD, DVD, BD, HVD, etc.
  • semiconductor storage such as ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state hard disk (SSD)
  • the present disclosure further proposes a computer program product, including a computer program, wherein, when the computer program is executed by a processor, the detection method of any one of the embodiments in FIGS. 1 to 6 of the present disclosure is implemented.
  • the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Accordingly, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) having computer-usable program code embodied therein.
  • processor-executable instructions may also be stored in a processor-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, such that the instructions stored in the processor-readable memory produce an article of manufacture comprising instruction means that implement the functions specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.
  • processor-executable instructions can also be loaded on a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate computer-implemented processing, so that the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in one or more processes of the flow chart and/or one or more blocks of the block diagram.

Landscapes

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

Abstract

一种检测方法及通信设备，涉及无线通信技术领域。具体实现方案为：获取被测空间内的多个探测回波信号（101）；确定多个探测回波信号对应的波达方向DOA（102）；根据多个DOA之间的波达角差异，检测被测空间是否存在入侵对象（103）。

Description

检测方法及通信设备
相关申请的交叉引用
本公开基于申请号为202210067070.3、申请日为2022年01月20日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本公开作为参考。
技术领域
本公开涉及无线通信技术领域，尤其涉及一种检测方法、通信设备、装置及存储介质。
背景技术
入侵检测是指对指定区域进行监视，以确定是否有对象进入该指定区域，并在必要时发出警报。入侵检测在实现安全防控、楼宇保障、智能家居等室内服务中有着广泛的应用前景。
一般地，基于计算机视觉进行入侵检测，需要通过图像传感器拍摄场景中的照片，虽然该方法具有良好的入侵检测精度，但其需要较为高昂的安装费用和较高的部署难度，存在较高的计算复杂度以及在暗光场景下难以使用的问题，且可能存在侵犯个人隐私的风险。
发明内容
本公开提供了一种用于检测方法、通信设备、装置及存储介质。
根据本公开的一方面，提供了一种检测方法，包括：获取被测空间内的多个探测回波信号；确定所述多个探测回波信号对应的波达方向DOA；根据多个所述DOA之间的波达角差异，检测所述被测空间是否存在入侵对象。
根据本公开的另一方面，提供了一种通信设备，包括：存储器，收发机，处理器：存储器，用于存储计算机程序；收发机，用于在所述处理器的控制下收发数据；处理器，用于读取所述存储器中的计算机程序并执行以下操作：获取被测空间内的多个探测回波信号；确定所述多个探测回波信号对应的波达方向DOA；根据多个所述DOA之间的波达角差异，检测所述被测空间是否存在入侵对象。
根据本公开的另一方面，提供了一种检测装置，包括：获取单元，用于获取被测空间内的多个探测回波信号；确定单元，用于确定所述多个探测回波信号对应的波达方向DOA；检测单元，用于根据多个所述DOA之间的波达角差异，检测所述被测空间是否存在入侵对象。
根据本公开的另一方面，提供了一种处理器可读存储介质，所述处理器可读存储介质存储有计算机程序，所述计算机程序用于使所述处理器执行本公开第一方面实施例所述的方法。
根据本公开的另一方面，提供了一种计算机程序产品，包括计算机程序，其中，所述计算机程序被处理器执行时实现本公开第一方面实施例所述的方法。
本公开应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。
附图说明
附图用于更好地理解本方案，不构成对本公开的限定。其中：
图1为本公开实施例一所提供的检测方法的流程示意图；
图2为本公开实施例中智能家居设备的检测场景示意图；
图3为本公开实施例二所提供的检测方法的流程示意图；
图4为本公开实施例三所提供的检测方法的流程示意图；
图5为本公开实施例四所提供的检测方法的流程示意图；
图6为本公开实施例中阵列天线接收探测回波示意图；
图7为本公开实施例五所提供的通信设备的结构示意图；
图8为本公开实施例六所提供的检测装置的结构示意图。
具体实施方式
本公开实施例中术语“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。
本公开实施例中术语“多个”是指两个或两个以上，其它量词与之类似。
下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本公开一部分实施例，并不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本公开保护的范围。
一般地，入侵检测还可以基于无线技术进行，基于无线技术是基于设备中的信道状态信息或者接收信号强度等的变化程度来检测是否有入侵者，但是在复杂的室内环境下，即使在固定的链路上接收信号强度也会产生较大的波动。
因此，为了解决上述问题，本公开提出了一种检测方法、通信设备、装置及存储介质。其中，方法和装置是基于同一申请构思的，由于方法和装置解决问题的原理相似，因此装置和方法的实施可以相互参见，重复之处不再赘述。
下面参考附图对本公开提供的检测方法、通信设备、装置及存储介质进行详细描述。
图1为本公开实施例一所提供的检测方法的流程示意图。本公开实施例的检测方法可由检测装置执行，该检测装置可被配置于通信设备上，其中，通信设备可为智能终端设备、基站设备、智能家居设备或智能安防设备等。
随着无线通信系统的不断发展与演进，超5代移动通信系统(Beyond 5th-Generation，B5G)或第六代移动通信系统(6th-Generation，6G)将提供更高的通信技术指标，伴随着无线通信频谱向更高频段、更大带宽发展，这将与传统感知频段使用产生更多的重叠，同时两者在信号处理等方面具有很大的相似性，以及通信系统中超大规模天线、人工智能等技术为通信设备实现感知功能提供了可能。
作为一种示例，以通信设备为如图2所示的智能家居设备进行示例性说明，智能家居设备可包括多个智能设备，比如，图2中的TX(发送端)和RX(接收端)。可以理解的是，在存在入侵对象时，入侵对象会影响室内的传播路径，室内信道的多径状态会发生改变。
比如，该检测方法可检测婴幼儿进入窗口阳台危险区域，通过智能家居设备中的智能设备向监护人发出报警信息，或触发自动开关自动关好窗户，以避免婴幼儿坠落，或者，该检测方法可检测老人摔倒等危险情况，通过智能家居设备中的智能设备发出报警信息；又比如，在住户离家或者是熟睡时，该检测方法可检测检测到有人入侵，通过智能家居设备中的智能设备自动发出报警信息，以阻止入侵者的动作；再比如，该检测方法对禁入的危险工作区域进行监测，对异常情况预警或报警，形成相应控制指令给智能机器人或智能设备。
需要说明的是，上述仅以通信设备为智能家居设备为例进行说明示例，实际应用时，通信设备也可以为智能终端设备、网络设备侧的相关设备等，比如，通信设备可以包括基站中的多个接入点(AccessPoint，简称AP)或者其他相关设备，本领域技术人员可以根据实际需要进行选择。
比如，基站中的相关设备中的一个为发送设备，另一个为接收设备，发送设备发射探测波，接收设备接收对应的探测回波，在存在入侵对象时，入侵对象会影响被测空间内探测回波的传播路径，被测空间内的探测回波的信道的多径状态会发生改变。因此，可基于被测空间内探测回波的多径状态，确定被测空间是否存在入侵对象。
其中，智能终端设备可以是指向用户提供语音和/或数据连通性的设备，具有无线连接功能的手持式设备、或连接到无线调制解调器的其他处理设备等。在不同的系统中，终端设备的名称可能也不相同，例如在5G系统中，终端设备可以称为用户设备(User Equipment，UE)。无线终端设备可以经无线接入网(Radio Access Network,RAN)与一个或多个核心网(Core Network,CN)进行通信，无线终端设备可以是移动终端设备，如移动电话(或称为“蜂窝”电话)和具有移动终端设备的计算机，例如，可以是便携式、袖珍式、手持式、计算机内置的或者车载的移动装置，它们与无线接入网交换语言和/或数据。例如，个人通信业务(Personal Communication Service，PCS)电话、无绳电话、会话发起协议(Session Initiated Protocol，SIP)话机、无线本地环路(Wireless Local Loop，WLL)站、个人数字助理(Personal Digital Assistant，PDA)等设备。无线终端设备也可以称为系统、订户单元(subscriber unit)、订户站(subscriber station)、移动站(mobile station)、移动台(mobile)、远程站(remote station)、接入点(access point)、远程 终端设备(remote terminal)、接入终端设备(access terminal)、用户终端设备(user terminal)、用户代理(user agent)、用户装置(user device)等，本公开可以根据实际需要选择。
其中，基站可以包括多个为终端提供服务的小区。根据具体应用场合不同，基站又可以称为接入点，或者可以是接入网中在空中接口上通过一个或多个扇区与无线终端通信的设备，或者其它名称。基站可用于将收到的空中帧与网际协议(Internet Protocol，简称IP)分组进行相互更换，作为无线终端与接入网的其余部分之间的路由器，其中接入网的其余部分可包括网际协议(IP)通信网络。基站还可协调对空中接口的属性管理。例如，本公开实施例涉及的基站可以是全球移动通信系统(Global System for Mobile communications，简称GSM)或码分多址接入(Code Division Multiple Access，简称CDMA)中的基站(Base Transceiver Station，简称BTS)，也可以是带宽码分多址接入(Wide-band Code Division Multiple Access，简称WCDMA)中的基站(NodeB)，还可以是长期演进(long term evolution，简称LTE)系统中的演进型基站(evolutional Node B，简称eNB或e-NodeB)、5G网络架构(next generation system)中的5G基站(简称gNB)，也可以是家庭演进基站(Home evolved Node B，简称HeNB)、中继节点(relay node)、家庭基站(femto)、微微基站(pico)等。在一些网络结构中，基站可以包括集中单元(Centralized Unit，简称CU)节点和分布单元(Distributed Unit，简称DU)节点，集中单元和分布单元也可以地理上分开布置。
如图1所示，该检测方法可包括如下步骤101至步骤103。
步骤101，获取被测空间内的多个探测回波信号。
在本公开实施例中，可向被测空间内发射探测波，并接收该被测空间内的多个探测回波信号，以获取被测空间内的多个探测回波信号。
作为一种示例，对发送设备在被测空间发送的多个探测波，接收对应的探测回波，以得到多个探测回波信号。比如，检测装置中包括双基雷达，双基雷达的节点A在被测空间发送多个探测回波，检测装置通过双基雷达的节点B接收对应的探测回波，以得到多个探测回波信号。
作为另一种示例，在被测空间发送多个探测波；接收对应的探测回波，以得到多个探测回波信号。比如，检测装置中包括全双工雷达，该全双工雷达在被测空间发送多个探测波，并接收对应的探测回波，从而得到多个探测回波。
步骤102，确定多个探测回波信号对应的波达方向DOA。
在本公开实施例中，多个探测回波信号对应的波达方向(Direction of arrival，简称DOA)可为各个探测回波信号到达阵列天线中阵元的方向角，其中，阵列天线是指将天线以阵列形式排布，以形成天线阵列，天线阵列可接收被测空间中的探测回波信号，以得到多个探测回波信号对应的DOA。
步骤103，根据多个DOA之间的波达角差异，检测被测空间是否存在入侵对象。
根据多个DOA，确定多个DOA之间的波达角差异，并根据多个DOA之间的波达 角差异与设定的角度阈值，确定被检测空间是否存在入侵对象。
综上，通过获取被测空间内的多个探测回波信号；确定多个探测回波信号对应的波达方向DOA；根据多个DOA之间的波达角差异，检测被测空间是否存在入侵对象。由此，根据被测空间内的多个探测回波信号对应的波达方向之间的波达角差异，检测被测空间是否存在入侵对象，实现了非有源终端的目标及环境的实时感知，可适用于暗光场景，提高了入侵检测精度和个人隐私安全，且降低了计算复杂度。
为了更加清楚地说明本公开实施例如何根据多个DOA之间的波达角差异，检测被测空间是否存在入侵对象，本公开还提出一种检测方法。
图3为本公开实施例二所提供的检测方法的流程示意图。
如图3所示，该检测方法包括以下步骤301至步骤304。
步骤301，获取被测空间内的多个探测回波信号。
步骤302，确定多个探测回波信号对应的波达方向DOA。
步骤303，确定多个DOA之间的波达角方差。
步骤304，根据波达角方差，检测被测空间是否存在入侵对象。
在本公开实施例中，可计算多个DOA之间的波达角方差，根据波达角方差确定被测空间是否存在入侵对象。
在一些实施例中，在波达角方差大于角度阈值的情况下，确定被测空间内存在入侵对象；在波达角方差小于或等于角度阈值的情况下，确定被测空间内未存在入侵对象。
也就是说，由于在被测空间中存在入侵对象时，探测回波信号对象对应的DOA变化较大，因此，可将波达角方差与角度阈值进行比对，在波达角方差大于角度阈值的情况下，可确定被测空间内存在入侵对象；在波达角方差小于或等于角度阈值的情况下，可确定被测空间内未存在入侵对象。
综上，通过多个DOA之间的波达角方差，可准确地确定被测空间内是否存在入侵对象，并提高了个人隐私安全和检测精度，降低了计算复杂度。
为了准确地说明本公开实施例是如何获取被测空间内的多个探测回波信号，本公开还提出一种检测方法。
图4为本公开实施例三所提供的检测方法的流程示意图。
如图4所示，该检测方法包括以下步骤401至步骤405。
步骤401，监测被测空间内通信信号的信号强度和/或信道状态信息。
在本公开实施例中，检测装置对被测空间内通信信号的信号强度和/或信道状态信息进行监测，以获取被测空间内通信信号的信号强度和/或信道状态信息。
步骤402，基于信号强度和/或信道状态信息，确定存在入侵对象的情况下，采用阵列天线多次接收探测回波，以得到阵列天线各次接收所输出的探测回波信号。
进一步地，在被测空间内通信信号的信号强度和/或信道状态信息的变化程度大于或等于变化阈值时，可确定被测空间内存在入侵对象，并可获取被测空间内的多个探测回波信号。
在一些实施例中，采用阵列天线多次接收探测回波，以得到阵列天线各次接收所输出的探测回波信号。比如，阵列天线以n秒为周期连续m分钟接收探测回波，从而，可得到阵列天线m分钟内的各次接收所输出的探测回波信号。
步骤403，获取多个探测回波信号中任一目标回波信号。
获取多个探测回波信号中的任一目标回波信号；其中，目标回波信号中可包括阵列天线中各阵元输出的子信号。
步骤404，根据目标回波信号中的各子信号之间的协方差信息，采用经过训练的分类模型确定目标回波信号对应的DOA。
在本公开实施例中，可确定目标回波信号中的各子信号之间的协方差矩阵，并根据协方差矩阵中的各元素，并采用经过训练的分类模型确定目标回波信号对应的DOA。
步骤405，根据多个DOA之间的波达角差异，检测被测空间是否存在入侵对象。
综上，通过监测被测空间内通信信号的信号强度和/或信道状态信息；基于信号强度和/或信道状态信息，确定存在入侵对象的情况下，采用阵列天线多次接收探测回波，以得到阵列天线各次接收所输出的探测回波信号；获取多个探测回波信号中任一目标回波信号；根据目标回波信号中的各子信号之间的协方差信息，采用经过训练的分类模型确定目标回波信号对应的DOA，根据多个DOA之间的波达角差异，检测被测空间是否存在入侵对象，由此，采用被动感知的方式，监测被测空间内通信信号的信号强度和/或信道状态信息，并根据被测空间内通信信号的信号强度和/或信道状态信息，进行入侵对象的粗判别，并根据多次接收的探测回波信号对应的DOA进行入侵对象的精细判别，提高了入侵对象的检测精度和个人隐私安全，降低了计算复杂度。
为了清楚地说明本公开实施例是如何根据协方差矩阵中的元素生成输入序列，本公开还提出一种检测方法。图5为本公开实施例四所提供的检测方法的流程示意图。
如图5所示，该检测方法包括以下步骤501至步骤507。
步骤501，监测被测空间内通信信号的信号强度和/或信道状态信息。
步骤502，基于信号强度和/或信道状态信息，确定存在入侵对象的情况下，采用阵列天线多次接收探测回波，以得到阵列天线各次接收所输出的探测回波信号。
步骤503，获取多个探测回波信号中任一目标回波信号。
步骤504，根据目标回波信号中各子信号，确定协方差矩阵。
在本公开实施例中，协方差矩阵中各行和各列具有对应的阵元，协方差矩阵中的元素用于指示所在行对应阵元输出的子信号与所在列对应阵元输出的子信号之间的协方差。
比如，如图6所示，以阵列天线为均匀直线阵为例，该均匀直线阵是由M个阵元组成的均匀线阵，各阵元之间的间距为d，为避免相位模糊，d小于探测回波信号最高频率所对应波长的1/2，空间中有k个远场平面波，占有相同的带宽，其入射方向分别为θ 1、θ 2，…θ k，第m个阵元接收到的信号(子信号)可表示为：
Figure PCTCN2022137626-appb-000001
其中，m＝1,2,...,M,k＝1,2,...,K；a m(θ k)为第m个阵元上第k个信号的响应矢量；s k(t)为第k个信源，即目标回波信号在k点上的振幅与相位，以复数形式表示，n m(t)为第m个阵元的噪声值。
进而，阵列天线(均匀线阵)所接收的目标回波信号的向量形式可表示为：
Figure PCTCN2022137626-appb-000002
其中，A是阵列天线的方向矩阵，矩阵A是复数形式，N(t)为噪声矩阵。
矩阵A中的a i,j元素取决于第i个阵元，它相对于坐标原点的位置和它接收到的第j个信号的入射方向。A的第j列a(θ j)是对第j个信号到达角为θ j的响应向量。
目标回波信号中的各子信号之间的协方差矩阵可表示为：
R＝E[X(t)X H(t)]
＝E[(AS(t)+N(t))(AS(t)+N(t)) H]
＝E[(AS(t)+N)(S H(t)A H)+N H]
＝E[AS(t)S H(t)A H+ASN H+NS H(t)A H+NN H]；
在本公开实施例中，假设信源信号(S(t))与噪声之间不相关，且噪声为加性高斯白噪声，则可得到AE[S(t)N H]和E[NS H(t)]A H为0，且
Figure PCTCN2022137626-appb-000003
因此，各子信号之间的协方差矩阵为：
Figure PCTCN2022137626-appb-000004
其中，σ为高斯白噪声的方差，R s为输入信号的相关矩阵，X(t)为阵列的响应矩阵。
步骤505，根据协方差矩阵中的元素，生成输入序列。
在一些实施例中，提取协方差矩阵中处于设定位置的多个目标元素；根据多个目标元素中包含的实部，生成第一子序列；根据多个目标元素中包含的虚部，生成第二子序列；拼接第一子序列和第二子序列，以得到输入序列。
在本公开实施例中，协方差矩阵为复矩阵，可依次提取协方差矩阵中处于设定位置的多个目标元素中包含的实部和虚部，并根据依次提取的各目标元素中的实部，生成第一子序列，并根据依次提取的各目标元素中的虚部，生成第二子序列，将第一子序列和 第二子序列进行拼接，将拼接结果作为输入序列。
步骤506，将输入序列输入经过训练的分类模型，以得到目标回波信号对应的DOA。
进而，将输入序列输入经过训练的分类模型中，经过训练的分类模型可输出目标回波信号对应的DOA。
其中，需要说明的是，经过训练的分类模型是对设定分类模型，基于适配训练样本进行第一训练得到的。其中，适配训练样本包括：第一样本序列，对应阵列天线接收测试信号得到的测试回波信号，是根据测试回波信号中各子信号，确定第一样本协方差矩阵，根据第一样本协方差矩阵中的元素生成；校准DOA，是基于测试回波信号采用波达角算法确定。设定分类模型是基于预训练样本进行第二训练得到；其中，预训练样本包括：第二样本序列，对应已知DOA的仿真回波信号，是根据仿真回波信号中各子信号，确定第二样本协方差矩阵，根据第二样本协方差矩阵中的元素生成；仿真回波信号的DOA。
也就是说，设定分类模型为采用预训练样本对分类模型进行预训练得到的，其中，预训练样本中包括第二样本序列和仿真回波信号的DOA，第二样本序列对应已知DOA的仿真回波信号；其中，已知DOA的仿真回波信号是根据仿真回波信号中各子信号，确定仿真回波信号中各子信号之间的第二样本协方差矩阵，接着，根据第二样本协方差矩阵中的元素生成仿真回波信号。根据已知DOA的仿真回波信号与仿真回波信号的DOA，对分类模型的系数进行调整，得到设定分类模型。由于，仿真回波信号与仿真回波信号的DOA通过由仿真软件生成，生成环境较为理想，缺少复杂的物理环境对探测回波信号的影响，进而，可采用适配训练样本对设定分类模型进行训练(系数调整)。
其中，适配训练样本可包括第一样本序列和校准DOA，第一样本序列对应阵列天线接收测试信号得到的测试回波信号，测试回波信号是根据测试回波信号中各子信号，并根据测试回波信号中各子信号之间的协方差矩阵，根据该协方差矩阵中的元素生成的测试回波信号；校准DOA，是基于测试回波信号采用波达角算法确定，其中，波达角算法可为基于噪声子空间的多重信号分类(multiple signal classification，MUSIC)方法或基于信号子空间的旋转不变子空间算法(Estimation of signal parameters via rotational invariance techniques，ESPRIT)。
由此，经过训练的分类模型不需要大量的训练数据进行训练，并且可根据实际场景中环境的变化，不受异常值的影响，提高了对不同环境部署的鲁棒性和感知精度。
步骤507，根据多个DOA之间的波达角差异，检测被测空间是否存在入侵对象。
综上，根据目标回波信号中各子信号，确定协方差矩阵，其中，协方差矩阵中各行和各列具有对应的阵元，协方差矩阵中的元素用于指示所在行对应阵元输出的子信号与所在列对应阵元输出的子信号之间的协方差；根据协方差矩阵中的元素，生成输入序列；将输入序列输入经过训练的分类模型，以得到目标回波信号对应的DOA。由此，根据目标回波信号中各子信号的协方差矩阵中的元素以以及经过训练的分类模型，可准确地获取被测空间内的多个探测回波信号对应的DOA。
本公开实施例的检测方法，通过获取被测空间内的多个探测回波信号；确定多个探测回波信号对应的波达方向DOA；根据多个DOA之间的波达角差异，检测被测空间是否存在入侵对象。由此，根据被测空间内的多个探测回波信号对应的波达方向之间的波达角差异，检测被测空间是否存在入侵对象，实现了非有源终端的目标及环境的实时感知，可适用于暗光场景，提高了入侵检测精度和个人隐私安全，降低了计算复杂度。
本公开实施例提供的技术方案可以适用于多种系统，尤其是5G系统。例如适用的系统可以是全球移动通讯(Global System of Mobile communication，简称GSM)系统、码分多址(Code Division Multiple Access，简称CDMA)系统、宽带码分多址(Wideband Code Division Multiple Access，简称WCDMA)通用分组无线业务(General Packet Radio Service，简称GPRS)系统、长期演进(long term evolution，简称LTE)系统、LTE频分双工(Frequency Division Duplex，简称FDD)系统、LTE时分双工(time division duplex，简称TDD)系统、高级长期演进(Long Term Evolution Advanced，简称LTE-A)系统、通用移动系统(Universal Mobile Telecommunication System，简称UMTS)、全球互联微波接入(Worldwide interoperability for Microwave Access，简称WiMAX)系统、5G新空口(New Radio，简称NR)系统等。这多种系统中均包括终端设备和网络设备。系统中还可以包括核心网部分，例如演进的分组系统(Evloved Packet System，简称EPS)、5G系统(5GS)等。
为了实现上述实施例，本公开还提出一种通信设备。
图7为本公开实施例五所提供的通信设备的结构示意图。
如图7所示，该通信设备包括：存储器710，收发机720和处理器730。
其中，存储器710，用于存储计算机程序；收发机720，用于在处理器的控制下收发数据；处理器730，用于读取存储器中的计算机程序并执行以下操作：获取被测空间内的多个探测回波信号；确定多个探测回波信号对应的波达方向DOA；根据多个DOA之间的波达角差异，检测被测空间是否存在入侵对象。
收发机720，用于在处理器730的控制下接收和发送数据。
其中，在图7中，总线架构可以包括任意数量的互联的总线和桥，具体由处理器730代表的一个或多个处理器和存储器710代表的存储器的各种电路链接在一起。总线架构还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其他电路链接在一起，在本文中不对其进行进一步描述。总线接口提供接口。收发机720可以是多个元件，即包括发送机和接收机，提供用于在传输介质上与各种其他装置通信的单元，这些传输介质包括无线信道、有线信道、光缆等传输介质。处理器730负责管理总线架构和通常的处理，存储器710可以存储处理器730在执行操作时所使用的数据。
处理器730可以是CPU、ASIC、FPGA或CPLD，处理器730也可以采用多核架构。
在一些实施例中，根据所述多个DOA之间的波达角差异，检测所述阵列天线所在的被测空间是否存在入侵对象，包括：确定所述多个DOA之间的波达角方差；根据所述波达角方差，检测所述阵列天线所在的被测空间是否存在入侵对象。
在一些实施例中，根据所述波达角方差，检测阵列天线所在的被测空间是否存在入侵对象，包括：在波达角方差大于角度阈值的情况下，确定阵列天线所在的被测空间内存在入侵对象；在波达角方差小于或等于角度阈值的情况下，确定阵列天线所在的被测空间内未存在入侵对象。
在一些实施例中，获取被测空间内的多个探测回波信号，包括：监测被测空间内通信信号的信号强度和/或信道状态信息；基于信号强度和/或信道状态信息，确定存在入侵对象的情况下，获取被测空间内的多个探测回波信号。
在一些实施例中，获取被测空间内的多个探测回波信号，包括：采用阵列天线多次接收探测回波，以得到阵列天线各次接收所输出的探测回波信号；相对应地，确定多个探测回波信号对应的波达方向DOA，包括：获取多个探测回波信号中任一目标回波信号；其中，目标回波信号中包括阵列天线中各阵元输出的子信号；根据目标回波信号中的各子信号之间的协方差信息，采用经过训练的分类模型确定目标回波信号对应的DOA。
在一些实施例中，根据所述目标回波信号中的各子信号之间的协方差信息，采用经过训练的分类模型确定目标回波信号对应的DOA，包括：根据目标回波信号中各子信号，确定协方差矩阵，其中，协方差矩阵中各行和各列具有对应的阵元，协方差矩阵中的元素用于指示所在行对应阵元输出的子信号与所在列对应阵元输出的子信号之间的协方差；根据协方差矩阵中的元素，生成输入序列；将所述输入序列输入经过训练的分类模型，以得到目标回波信号对应的DOA。
在一些实施例中，根据所述协方差矩阵中的元素，生成输入序列，包括：提取协方差矩阵中处于设定位置的多个目标元素；根据多个目标元素中包含的实部，生成第一子序列；根据多个目标元素中包含的虚部，生成第二子序列；拼接第一子序列和所述第二子序列，以得到输入序列。
在一些实施例中，经过训练的分类模型，是对设定分类模型，基于适配训练样本进行第一训练得到；其中，适配训练样本包括：第一样本序列，对应所述阵列天线接收测试信号得到的测试回波信号，是根据所述测试回波信号中各子信号，确定第一样本协方差矩阵，根据所述第一样本协方差矩阵中的元素生成；校准DOA，是基于所述测试回波信号采用波达角算法确定。
在一些实施例中，设定分类模型是基于预训练样本进行第二训练得到；其中，所述预训练样本包括：第二样本序列，对应已知DOA的仿真回波信号，是根据所述仿真回波信号中各子信号，确定第二样本协方差矩阵，根据所述第二样本协方差矩阵中的元素生成；仿真回波信号的DOA。
在一些实施例中，获取被测空间内的多个探测回波信号，包括：对发送设备在所述被测空间发送的多个探测波，接收对应的探测回波，以得到所述多个探测回波信号；或者，在所述被测空间发送多个探测波；接收对应的探测回波，以得到所述多个探测回波信号。
在此需要说明的是，本公开实施例提供的通信设备，能够实现上述图1至图6方法 实施例所实现的所有方法步骤，且能够达到相同的技术效果，在此不再赘述。
与上述图1至图6实施例提供的检测方法相对应，本公开还提供一种检测装置，由于本公开实施例提供的检测装置与上述图1至图6实施例提供的检测方法相对应，因此在检测方法的实施方式也适用于本公开实施例提供的检测装置，在本公开实施例中不再详细描述。
图8为本公开实施例六所提供的检测装置的结构示意图。
如图8所示，检测装置800包括：获取单元810、确定单元820和检测单元830。
其中，获取单元810，用于获取被测空间内的多个探测回波信号；确定单元820，用于确定多个探测回波信号对应的波达方向DOA；检测单元830，用于根据多个DOA之间的波达角差异，检测被测空间是否存在入侵对象。
在一些实施例中，检测单元830还用于：确定多个DOA之间的波达角方差；根据所述波达角方差，检测被测空间是否存在入侵对象。
在一些实施例中，检测单元830，还用于：在波达角方差大于角度阈值的情况下，确定被测空间内存在入侵对象；在波达角方差小于或等于角度阈值的情况下，确定被测空间内未存在入侵对象。
在一些实施例中，获取单元810，还用于：监测被测空间内通信信号的信号强度和/或信道状态信息；基于信号强度和/或信道状态信息，确定存在入侵对象的情况下，获取被测空间内的多个探测回波信号。
在一些实施例中，获取单元810，还用于：采用阵列天线多次接收探测回波，以得到阵列天线各次接收所输出的探测回波信号；相对应地，确定单元820，还用于：获取多个探测回波信号中任一目标回波信号；其中，目标回波信号中包括阵列天线中各阵元输出的子信号；根据目标回波信号中的各子信号之间的协方差信息，采用经过训练的分类模型确定目标回波信号对应的DOA。
在一些实施例中，确定单元820，还用于：根据目标回波信号中各子信号，确定协方差矩阵，其中，协方差矩阵中各行和各列具有对应的阵元，协方差矩阵中的元素用于指示所在行对应阵元输出的子信号与所在列对应阵元输出的子信号之间的协方差；根据协方差矩阵中的元素，生成输入序列；将所述输入序列输入经过训练的分类模型，以得到目标回波信号对应的DOA。
在一些实施例中，确定单元820，还用于：提取协方差矩阵中处于设定位置的多个目标元素；根据多个目标元素中包含的实部，生成第一子序列；根据多个目标元素中包含的虚部，生成第二子序列；拼接第一子序列和第二子序列，以得到输入序列。
在一些实施例中，经过训练的分类模型，是对设定分类模型，基于适配训练样本进行第一训练得到；其中，适配训练样本包括：第一样本序列，对应阵列天线接收测试信号得到的测试回波信号，是根据测试回波信号中各子信号，确定第一样本协方差矩阵，根据第一样本协方差矩阵中的元素生成；校准DOA，是基于测试回波信号采用波达角算法确定。
在一些实施例中，设定分类模型是基于预训练样本进行第二训练得到；其中，预训练样本包括：第二样本序列，对应已知DOA的仿真回波信号，是根据所述仿真回波信号中各子信号，确定第二样本协方差矩阵，根据所述第二样本协方差矩阵中的元素生成；仿真回波信号的DOA。
在一些实施例中，获取单元810，还用于：对发送设备在被测空间发送的多个探测波，接收对应的探测回波，以得到多个探测回波信号；或者，在被测空间发送多个探测波；接收对应的探测回波，以得到多个探测回波信号。
在此需要说明的是，本公开实施例提供的上述通信装置，能够实现上述图1至图6方法实施例所实现的所有方法步骤，且能够达到相同的技术效果，在此不再赘述。
需要说明的是，本公开实施例中对单元的划分是示意性的，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。另外，在本公开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。
所述集成的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，可以存储在一个处理器可读取存储介质中。基于这样的理解，本公开的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本公开各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
为了实现上述实施例，本公开还提出一种处理器可读存储介质。
其中，该处理器可读存储介质存储有计算机程序，该计算机程序用于使该处理器执行本公开图1至图6任一实施例的检测方法。
其中，处理器可读存储介质可以是处理器能够存取的任何可用介质或数据存储设备，包括但不限于磁性存储器(例如软盘、硬盘、磁带、磁光盘(MO)等)、光学存储器(例如CD、DVD、BD、HVD等)、以及半导体存储器(例如ROM、EPROM、EEPROM、非易失性存储器(NAND FLASH)、固态硬盘(SSD))等。
为了实现上述实施例，本公开还提出一种计算机程序产品，包括计算机程序，其中，所述计算机程序被处理器执行时实现本公开图1至图6任一实施例的检测方法。
本领域内的技术人员应明白，本公开的实施例可提供为方法、系统、或计算机程序产品。因此，本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器和光学存储器等)上实施的计算机程序产品的形式。
本公开是参照根据本公开实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机可执行指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机可执行指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些处理器可执行指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的处理器可读存储器中，使得存储在该处理器可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些处理器可执行指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
显然，本领域的技术人员可以对本公开进行各种改动和变型而不脱离本公开的精神和范围。这样，倘若本公开的这些修改和变型属于本公开权利要求及其等同技术的范围之内，则本公开也意图包含这些改动和变型在内。

Claims (32)

  1. 一种检测方法，包括：
    获取被测空间内的多个探测回波信号；
    确定所述多个探测回波信号对应的波达方向Direction of arrival(DOA)；
    根据多个所述DOA之间的波达角差异，检测所述被测空间是否存在入侵对象。
  2. 根据权利要求1所述的方法，其中，所述根据所述多个DOA之间的波达角差异，检测所述被测空间是否存在入侵对象，包括：
    确定所述多个DOA之间的波达角方差；
    根据所述波达角方差，检测所述被测空间是否存在入侵对象。
  3. 根据权利要求2所述的方法，其中，所述根据所述波达角方差，检测所述被测空间是否存在入侵对象，包括：
    在所述波达角方差大于角度阈值的情况下，确定所述被测空间内存在入侵对象；
    在所述波达角方差小于或等于所述角度阈值的情况下，确定所述被测空间内未存在入侵对象。
  4. 根据权利要求1所述的方法，其中，所述获取被测空间内的多个探测回波信号，包括：
    监测所述被测空间内通信信号的信号强度和/或信道状态信息；
    基于所述信号强度和/或信道状态信息，当确定存在入侵对象的情况下，获取被测空间内的多个探测回波信号。
  5. 根据权利要求1至4中任一项所述的方法，其中，所述获取被测空间内的多个探测回波信号，包括：
    采用阵列天线多次接收探测回波，以得到所述阵列天线各次接收所输出的探测回波信号；
    所述确定所述多个探测回波信号对应的波达方向DOA，包括：
    获取所述多个探测回波信号中任一目标回波信号；其中，所述目标回波信号中包括所述阵列天线中各阵元输出的子信号；
    根据所述目标回波信号中的各子信号之间的协方差信息，采用经过训练的分类模型确定所述目标回波信号对应的DOA。
  6. 根据权利要求5所述的方法，其中，所述根据所述目标回波信号中的各子信号之间的协方差信息，采用经过训练的分类模型确定所述目标回波信号对应的DOA，包括：
    根据所述目标回波信号中各子信号，确定协方差矩阵，其中，所述协方差矩阵中各行和各列具有对应的阵元，所述协方差矩阵中的元素用于指示所在行对应阵元输出的子信号与所在列对应阵元输出的子信号之间的协方差；
    根据所述协方差矩阵中的元素，生成输入序列；
    将所述输入序列输入所述经过训练的分类模型，以得到所述目标回波信号对应的 DOA。
  7. 根据权利要求6所述的方法，其中，所述根据所述协方差矩阵中的元素，生成输入序列，包括：
    提取所述协方差矩阵中处于设定位置的多个目标元素；
    根据所述多个目标元素中包含的实部，生成第一子序列；
    根据所述多个目标元素中包含的虚部，生成第二子序列；
    拼接所述第一子序列和所述第二子序列，以得到所述输入序列。
  8. 根据权利要求6所述的方法，其中，所述经过训练的分类模型，是对设定分类模型，基于适配训练样本进行第一训练得到；
    其中，所述适配训练样本包括：
    第一样本序列，其中，获得所述第一样本序列包括：基于所述阵列天线接收测试信号，得到测试回波信号；根据所述测试回波信号中各子信号，确定第一样本协方差矩阵；根据所述第一样本协方差矩阵中的元素生成所述第一样本序列；
    校准DOA，是基于所述测试回波信号采用波达角算法确定。
  9. 根据权利要求8所述的方法，其中，所述设定分类模型是基于预训练样本进行第二训练得到；
    其中，所述预训练样本包括：
    第二样本序列，对应已知DOA的仿真回波信号；其中，获得所述第二样本序列包括：获得所述DOA的仿真回波信号；根据所述仿真回波信号中各子信号，确定第二样本协方差矩阵；根据所述第二样本协方差矩阵中的元素生成所述第二样本序列；
    所述仿真回波信号的DOA。
  10. 根据权利要求1至4中任一项所述的方法，其中，所述获取被测空间内的多个探测回波信号，包括：
    在使用双基雷达进行检测的情况下，对发送设备在所述被测空间发送的多个探测波，接收对应的探测回波，以得到所述多个探测回波信号；
    或者，
    在使用全双工雷达进行检测的情况下，在所述被测空间发送多个探测波；接收对应的探测回波，以得到所述多个探测回波信号。
  11. 一种通信设备，包括存储器，收发机，处理器：
    存储器，用于存储计算机程序；收发机，用于在所述处理器的控制下收发数据；处理器，用于读取所述存储器中的计算机程序并执行以下操作：
    获取被测空间内的多个探测回波信号；
    确定所述多个探测回波信号对应的波达方向DOA；
    根据多个所述DOA之间的波达角差异，检测所述被测空间是否存在入侵对象。
  12. 根据权利要求11所述的通信设备，其中，所述根据所述多个DOA之间的波达角差异，检测所述阵列天线所在的被测空间是否存在入侵对象，包括：
    确定所述多个DOA之间的波达角方差；
    根据所述波达角方差，检测所述阵列天线所在的被测空间是否存在入侵对象。
  13. 根据权利要求12所述的通信设备，其中，所述根据所述波达角方差，检测所述阵列天线所在的被测空间是否存在入侵对象，包括：
    在所述波达角方差大于角度阈值的情况下，确定所述阵列天线所在的被测空间内存在入侵对象；
    在所述波达角方差小于或等于所述角度阈值的情况下，确定所述阵列天线所在的被测空间内未存在入侵对象。
  14. 根据权利要求11所述的通信设备，其中，所述获取被测空间内的多个探测回波信号，包括：
    监测所述被测空间内通信信号的信号强度和/或信道状态信息；
    基于所述信号强度和/或信道状态信息，确定存在入侵对象的情况下，获取被测空间内的多个探测回波信号。
  15. 根据权利要求11至14中任一项所述的通信设备，其中，所述获取被测空间内的多个探测回波信号，包括：
    采用阵列天线多次接收探测回波，以得到所述阵列天线各次接收所输出的探测回波信号；
    所述确定所述多个探测回波信号对应的波达方向DOA，包括：
    获取所述多个探测回波信号中任一目标回波信号；其中，所述目标回波信号中包括所述阵列天线中各阵元输出的子信号；
    根据所述目标回波信号中的各子信号之间的协方差信息，采用经过训练的分类模型确定所述目标回波信号对应的DOA。
  16. 根据权利要求15所述的通信设备，其中，所述根据所述目标回波信号中的各子信号之间的协方差信息，采用经过训练的分类模型确定所述目标回波信号对应的DOA，包括：
    根据所述目标回波信号中各子信号，确定协方差矩阵，其中，所述协方差矩阵中各行和各列具有对应的阵元，所述协方差矩阵中的元素用于指示所在行对应阵元输出的子信号与所在列对应阵元输出的子信号之间的协方差；
    根据所述协方差矩阵中的元素，生成输入序列；
    将所述输入序列输入所述经过训练的分类模型，以得到所述目标回波信号对应的DOA。
  17. 根据权利要求16所述的通信设备，其中，所述根据所述协方差矩阵中的元素，生成输入序列，包括：
    提取所述协方差矩阵中处于设定位置的多个目标元素；
    根据所述多个目标元素中包含的实部，生成第一子序列；
    根据所述多个目标元素中包含的虚部，生成第二子序列；
    拼接所述第一子序列和所述第二子序列，以得到所述输入序列。
  18. 根据权利要求16所述的通信设备，其中，所述经过训练的分类模型，是对设定分类模型，基于适配训练样本进行第一训练得到；
    其中，所述适配训练样本包括：
    第一样本序列，其中，获得所述第一样本序列包括：基于所述阵列天线接收测试信号，得到测试回波信号；根据所述测试回波信号中各子信号，确定第一样本协方差矩阵；根据所述第一样本协方差矩阵中的元素生成所述第一样本序列；
    校准DOA，是基于所述测试回波信号采用波达角算法确定。
  19. 根据权利要求18所述的通信设备，其中，所述设定分类模型是基于预训练样本进行第二训练得到；
    其中，所述预训练样本包括：
    第二样本序列，对应已知DOA的仿真回波信号；其中，获得所述第二样本序列包括：获得所述DOA的仿真回波信号；根据所述仿真回波信号中各子信号，确定第二样本协方差矩阵；根据所述第二样本协方差矩阵中的元素生成所述第二样本序列；
    所述仿真回波信号的DOA。
  20. 根据权利要求11至14中任一项所述的通信设备，其中，所述获取被测空间内的多个探测回波信号，包括：
    在使用双基雷达进行检测的情况下，对发送设备在所述被测空间发送的多个探测波，接收对应的探测回波，以得到所述多个探测回波信号；
    或者，
    在使用全双工雷达进行检测的情况下，在所述被测空间发送多个探测波；接收对应的探测回波，以得到所述多个探测回波信号。
  21. 一种检测装置，包括：
    获取单元，用于获取被测空间内的多个探测回波信号；
    确定单元，用于确定所述多个探测回波信号对应的波达方向DOA；
    检测单元，用于根据多个所述DOA之间的波达角差异，检测所述被测空间是否存在入侵对象。
  22. 根据权利要求21所述的检测装置，其中，所述检测单元还用于：
    确定所述多个DOA之间的波达角方差；
    根据所述波达角方差，检测所述阵列天线所在的被测空间是否存在入侵对象。
  23. 根据权利要求22所述的检测装置，其中，所述检测单元还用于：
    在所述波达角方差大于角度阈值的情况下，确定所述阵列天线所在的被测空间内存在入侵对象；
    在所述波达角方差小于或等于所述角度阈值的情况下，确定所述阵列天线所在的被测空间内未存在入侵对象。
  24. 根据权利要求21所述的检测装置，其中，所述获取单元还用于：
    监测所述被测空间内通信信号的信号强度和/或信道状态信息；
    基于所述信号强度和/或信道状态信息，确定存在入侵对象的情况下，获取被测空间内的多个探测回波信号。
  25. 根据权利要求21至24中任一项所述的检测装置，其中，所述获取单元还用于：
    采用阵列天线多次接收探测回波，以得到所述阵列天线各次接收所输出的探测回波信号；
    所述确定单元还用于：
    获取所述多个探测回波信号中任一目标回波信号；其中，所述目标回波信号中包括所述阵列天线中各阵元输出的子信号；
    根据所述目标回波信号中的各子信号之间的协方差信息，采用经过训练的分类模型确定所述目标回波信号对应的DOA。
  26. 根据权利要求25所述的检测装置，其中，所述确定单元还用于：
    根据所述目标回波信号中各子信号，确定协方差矩阵，其中，所述协方差矩阵中各行和各列具有对应的阵元，所述协方差矩阵中的元素用于指示所在行对应阵元输出的子信号与所在列对应阵元输出的子信号之间的协方差；
    根据所述协方差矩阵中的元素，生成输入序列；
    将所述输入序列输入所述经过训练的分类模型，以得到所述目标回波信号对应的DOA。
  27. 根据权利要求26所述的检测装置，其中，所述确定单元还用于：
    提取所述协方差矩阵中处于设定位置的多个目标元素；
    根据所述多个目标元素中包含的实部，生成第一子序列；
    根据所述多个目标元素中包含的虚部，生成第二子序列；
    拼接所述第一子序列和所述第二子序列，以得到所述输入序列。
  28. 根据权利要求26所述的检测装置，其中，所述经过训练的分类模型，是对设定分类模型，基于适配训练样本进行第一训练得到；
    其中，所述适配训练样本包括：
    第一样本序列，其中，获得所述第一样本序列包括：基于所述阵列天线接收测试信号，得到测试回波信号；根据所述测试回波信号中各子信号，确定第一样本协方差矩阵；根据所述第一样本协方差矩阵中的元素生成所述第一样本序列；
    校准DOA，是基于所述测试回波信号采用波达角算法确定。
  29. 根据权利要求28所述的检测装置，其中，所述设定分类模型是基于预训练样本进行第二训练得到；
    其中，所述预训练样本包括：
    第二样本序列，对应已知DOA的仿真回波信号；其中，获得所述第二样本序列包括：获得所述DOA的仿真回波信号；根据所述仿真回波信号中各子信号，确定第二样本协方差矩阵；根据所述第二样本协方差矩阵中的元素生成所述第二样本序列；
    所述仿真回波信号的DOA。
  30. 根据权利要求21至24中任一项所述的通信设备，其中，所述获取单元还用于：
    在使用双基雷达进行检测的情况下，对发送设备在所述被测空间发送的多个探测波，接收对应的探测回波，以得到所述多个探测回波信号；
    或者，
    在使用全双工雷达进行检测的情况下，在所述被测空间发送多个探测波；接收对应的探测回波，以得到所述多个探测回波信号。
  31. 一种处理器可读存储介质，所述处理器可读存储介质存储有计算机程序，所述计算机程序用于使所述处理器执行权利要求1至10任一项所述的方法。
  32. 一种计算机程序产品，包括计算机程序，其中，所述计算机程序被处理器执行时实现权利要求1至10任一项所述的方法。
PCT/CN2022/137626 2022-01-20 2022-12-08 检测方法及通信设备 WO2023138253A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210067070.3A CN116520237A (zh) 2022-01-20 2022-01-20 检测方法、通信设备、装置及存储介质
CN202210067070.3 2022-01-20

Publications (1)

Publication Number Publication Date
WO2023138253A1 true WO2023138253A1 (zh) 2023-07-27

Family

ID=87347774

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/137626 WO2023138253A1 (zh) 2022-01-20 2022-12-08 检测方法及通信设备

Country Status (2)

Country Link
CN (1) CN116520237A (zh)
WO (1) WO2023138253A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117220725A (zh) * 2023-10-30 2023-12-12 威海天拓合创电子工程有限公司 一种多相控阵天线的探测误差修正方法及装置

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117687013B (zh) * 2024-02-04 2024-05-17 中亿(深圳)信息科技有限公司 基于5g的安防高精度定位方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN202995036U (zh) * 2012-12-24 2013-06-12 西安电子工程研究所 一种基于雷达回波特征的铁路路障探测与告警方法的系统
KR20160105178A (ko) * 2015-02-27 2016-09-06 주식회사 유컴테크놀러지 침입자 탐지 장치 및 방법
CN109142507A (zh) * 2018-08-07 2019-01-04 四川钜莘信合科技有限公司 管道缺陷检测方法及装置
CN111693932A (zh) * 2020-06-08 2020-09-22 西安电子科技大学 基于微波光子的多微波信号波达方向角估计方法
CN111736131A (zh) * 2020-07-13 2020-10-02 深圳大学 一种剔除一比特信号谐波虚假目标的方法及相关组件
CN111915830A (zh) * 2020-07-24 2020-11-10 辽宁工程技术大学 一种基于csi信号稀疏表示的室内入侵检测方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN202995036U (zh) * 2012-12-24 2013-06-12 西安电子工程研究所 一种基于雷达回波特征的铁路路障探测与告警方法的系统
KR20160105178A (ko) * 2015-02-27 2016-09-06 주식회사 유컴테크놀러지 침입자 탐지 장치 및 방법
CN109142507A (zh) * 2018-08-07 2019-01-04 四川钜莘信合科技有限公司 管道缺陷检测方法及装置
CN111693932A (zh) * 2020-06-08 2020-09-22 西安电子科技大学 基于微波光子的多微波信号波达方向角估计方法
CN111736131A (zh) * 2020-07-13 2020-10-02 深圳大学 一种剔除一比特信号谐波虚假目标的方法及相关组件
CN111915830A (zh) * 2020-07-24 2020-11-10 辽宁工程技术大学 一种基于csi信号稀疏表示的室内入侵检测方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117220725A (zh) * 2023-10-30 2023-12-12 威海天拓合创电子工程有限公司 一种多相控阵天线的探测误差修正方法及装置
CN117220725B (zh) * 2023-10-30 2024-03-26 威海天拓合创电子工程有限公司 一种多相控阵天线的探测误差修正方法及装置

Also Published As

Publication number Publication date
CN116520237A (zh) 2023-08-01

Similar Documents

Publication Publication Date Title
WO2023138253A1 (zh) 检测方法及通信设备
EP3726896B1 (en) Methods and apparatus for positioning a terminal device
RU2632475C1 (ru) Инициированное точкой доступа позиционирование по времени распространения
US20210329416A1 (en) Method and Apparatus for Location Services
Bandiera et al. A cognitive algorithm for received signal strength based localization
US20160044551A1 (en) Methods and Network Nodes for Enabling Accurate Measurements
US20200396710A1 (en) Methods and devices for configuration of signaling associated with multiple aoa positioning
CN114007183B (zh) 定位方式的触发方法及通信装置
CN114521012B (zh) 定位方法、装置、终端设备、基站及位置管理服务器
CN108828570A (zh) 一种基于路径损耗因子动态估计的测距方法及测距装置
EP3958593A1 (en) Wireless positioning method, positioning apparatus, and network device
Jia et al. Received signal strength difference–based tracking estimation method for arbitrarily moving target in wireless sensor networks
WO2022190122A1 (en) Method of positioning a node in a cellular network
US20210281311A1 (en) Timing measurement method and related device
CN115604728A (zh) 通信感知方法、装置及网络设备
Skiribou et al. LOS identification for high accuracy TOA-based ranging system in tunnel environments
WO2023116756A1 (zh) 感知测量方法、装置、通信设备及可读存储介质
CN110392387B (zh) 无线信号的角度测量方法和设备
WO2020139180A1 (en) Adaptation of a beam sweep in a communications network
WO2018076216A1 (zh) 一种生成测量结果的方法及设备
WO2023231868A1 (zh) 感知方式切换方法、装置、通信设备及存储介质
WO2023185407A1 (zh) 一种通信方法及装置
WO2022135026A1 (zh) 信号发送方法、目标感知方法、设备和存储介质
CN106796277B (zh) 移动通信网络中的位置调整
EP4181537A1 (en) Multi-path single anchor point positioning method and communication apparatus

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: 22921677

Country of ref document: EP

Kind code of ref document: A1