Wall contour recognition method and device

Abstract

The present application provides a wall contour recognition method and device, relating to the field of radar detection technology, for improving the accuracy of wall contour recognition. The method comprises: transmitting electromagnetic waves into a target space and receiving M frames of echo signals, where M is an integer greater than 1; processing the M frames of echo signals to obtain M positions of a real target person and M positions of a false target person within the target space; processing the M positions of the real target person to obtain a motion trajectory of the real target person; processing the M positions of the false target person to obtain a motion trajectory of the false target person; and determining the contour of the wall within the target space based on the motion trajectory of the real target person and the motion trajectory of the false target person.

Description

Technical Field

[0001] The present application relates to the field of radar detection technology, and in particular to a method and device for recognizing the outline of a wall. Background Art

[0002] Radar is a device that detects and identifies targets by emitting electromagnetic waves and receiving echoes, that is, it uses radio methods to detect targets and determine their positions in space.

[0003] Typically, when using radar to identify the contours of walls within a space, electromagnetic waves are incident perpendicularly on the wall, and the distance is directly measured using the echo signal received from the wall. Because walls reflect electromagnetic waves, if the electromagnetic waves do not enter the wall perpendicularly, most of the electromagnetic waves will be reflected away from the wall, resulting in a weak echo signal received by the radar. This results in low accuracy in measuring the wall's position, and consequently, the radar cannot accurately identify the contours of the wall within the space. Summary of the Invention

[0004] The embodiments of the present application provide a wall contour recognition method and device for improving the accuracy of wall contour recognition.

[0005] In a first aspect, a method for recognizing the outline of a wall is provided. The method includes: transmitting electromagnetic waves into a target space and receiving M frames of echo signals, where M is an integer greater than 1. The M frames of echo signals are processed to obtain M positions of a real target person and M positions of a false target person within the target space. The M positions of the real target person are then processed to obtain a motion trajectory of the real target person, and the M positions of the false target person are then processed to obtain a motion trajectory of the false target person. The outline of the wall within the target space is then determined based on the motion trajectories of the real target person and the false target person.

[0006] In this way, by combining the wall's reflection characteristics for electromagnetic waves, a real target person is introduced as a reference object in the target space. When the real target person moves near the wall, a false target person is generated, and the false target person typically has similar motion patterns to the real target person. Because the false target person's echo signal undergoes multiple reflections, the false target person's position may appear outside the area where the real target person moves, such as outside the wall. The ray tracing model shows that the positions of the real target person and the false target person are mirror-symmetric about the wall. Therefore, based on the motion trajectories of the real target person and the false target person, as well as the geometric relationship between the real target person and the false target person, the contour of the wall in the space is identified. Compared to identifying the position and contour of the wall by transmitting electromagnetic waves from a radar to the wall, this method improves the accuracy of wall contour identification in the space and avoids the problem of low wall contour identification accuracy caused by the electromagnetic waves not being incident perpendicularly on the wall, which makes it impossible to accurately measure the wall's position.

[0007] In some embodiments, M frames of echo signals are processed to obtain M positions of a real target body and M positions of a false target body in the target space, including: for each frame of the M frames of echo signals, performing pulse compression and moving target display processing on the echo signal to obtain a range image; extracting the distance unit of the real target body and the distance unit of the false target body from the range image based on a constant false alarm rate algorithm of sorting statistics; extracting the azimuth angle of the real target body and the pitch angle of the real target body from the echo signal according to the distance unit of the real target body; determining the position of the real target body according to the distance unit of the real target body, the azimuth angle of the real target body and the pitch angle of the real target body; extracting the azimuth angle of the false target body and the pitch angle of the false target body from the echo signal according to the distance unit of the false target body; determining the position of the false target body according to the distance unit of the false target body.

[0008] In some embodiments, M positions of the real target body are processed to obtain the motion trajectory of the real target body, including: clustering the M positions of the real target body to obtain N first cluster sets, each cluster set in the N first cluster sets includes multiple positions of the real target body, and N is an integer greater than 1 and less than M; according to the multiple positions of the real target body included in each first cluster set, the position of the trajectory point corresponding to each first cluster set is determined; according to the position of the trajectory point corresponding to each first cluster set in the N first cluster sets, the motion trajectory of the real target body is determined.

[0009] In some embodiments, clustering is performed on the M positions of the real target body to obtain N first cluster sets, including: clustering is performed on the M positions of the real target body according to a density-based spatial clustering of applications with noise (DBSCAN) algorithm to obtain P second cluster sets, each second cluster set includes at least one position of the real target body, and P is an integer greater than 1 and less than or equal to M; from the P second cluster sets, a second cluster set whose number of positions of the real target body is greater than or equal to a preset value is selected as the first cluster set, and N is less than or equal to P.

[0010] In some embodiments, the motion trajectory of the real target human body is determined based on the position of the trajectory point corresponding to each first cluster set in the N first cluster sets, including: performing Kalman filtering on the position of the trajectory point corresponding to each first cluster set in the N first cluster sets to obtain the motion trajectory of the real target human body.

[0011] In some embodiments, M positions of the false target body are processed to obtain a motion trajectory of the false target body, including: clustering the M positions of the false target body to obtain S cluster sets, each of the S cluster sets including multiple positions of the false target body, and S being an integer less than M; determining the position of the trajectory point corresponding to each cluster set based on the multiple positions of the false target body included in each cluster set; and determining the motion trajectory of the false target body based on the position of the trajectory point corresponding to each cluster set in the S cluster sets.

[0012] In some embodiments, the outline of a wall in a target space is determined based on the motion trajectory of a real target body and the motion trajectory of a fake target body, including: determining the position coordinates of each contour boundary point of the wall based on the position coordinates of each trajectory point in the motion trajectory of the real target body and the position coordinates of each trajectory point in the motion trajectory of the fake target body; determining the outline of the wall based on the position coordinates of each contour boundary point of the wall.

[0013] In some embodiments, the position coordinates of the boundary points of the wall outline satisfy the following relationship:

[0014]

[0015] Among them, X t Y is the horizontal coordinate of the real target human body position at time t, t is the vertical coordinate of the real target body position at time t, X′ t Y′ is the horizontal coordinate of the position of the false target human body at time t,t is the vertical coordinate of the false target human body at time t, is the horizontal coordinate of the boundary point of the wall contour at time t, is the vertical coordinate of the boundary point of the wall contour at time t.

[0016] In a second aspect, a wall contour recognition device is provided, comprising: a communication unit for emitting electromagnetic waves into a target space and receiving M frames of echo signals, where M is an integer greater than 1; a processing unit for processing the M frames of echo signals to obtain M positions of a real target human body and M positions of a false target human body in the target space; the processing unit is further configured to: process the M positions of the real target human body to obtain a motion trajectory of the real target human body; process the M positions of the false target human body to obtain a motion trajectory of the false target human body; and determine the contour of the wall in the target space based on the motion trajectory of the real target human body and the motion trajectory of the false target human body.

[0017] In some embodiments, the processing unit is specifically used to: for each frame of the M frames of echo signals, perform pulse compression and moving target display processing on the echo signal to obtain a range image; based on a constant false alarm rate (CFAR) algorithm of ordered statistics (OS), extract the distance unit of the real target body and the distance unit of the false target body from the range image; according to the distance unit of the real target body, extract the azimuth angle of the real target body and the pitch angle of the real target body from the echo signal; determine the position of the real target body according to the distance unit of the real target body, the azimuth angle of the real target body and the pitch angle of the real target body; according to the distance unit of the false target body, extract the azimuth angle of the false target body and the pitch angle of the false target body from the echo signal; determine the position of the false target body according to the distance unit of the false target body, the azimuth angle of the false target body and the pitch angle of the false target body.

[0018] In some embodiments, the processing unit is specifically used to: perform clustering processing on the M positions of the real target human body to obtain N first cluster sets, each cluster set in the N first cluster sets includes multiple positions of the real target human body, and N is an integer greater than 1 and less than M; determine the position of the trajectory point corresponding to each first cluster set according to the multiple positions of the real target human body included in each first cluster set; determine the movement trajectory of the real target human body according to the position of the trajectory point corresponding to each first cluster set in the N first cluster sets.

[0019] In some embodiments, the processing unit is specifically used to: cluster the M positions of the real target human body according to a density-based clustering method algorithm to obtain P second cluster sets, each second cluster set includes at least one position of the real target human body, and P is an integer greater than 1 and less than or equal to M; from the P second cluster sets, select the second cluster set whose number of positions of the real target human body is greater than or equal to a preset value as the first cluster set, and N is less than or equal to P.

[0020] In some embodiments, the processing unit is specifically configured to perform Kalman filtering on the position of the trajectory point corresponding to each of the N first cluster sets to obtain the motion trajectory of the real target human body.

[0021] In some embodiments, the processing unit is specifically used to: cluster the M positions of the false target human body to obtain S cluster sets, each of the S cluster sets including multiple positions of the false target human body; determine the position of the trajectory point corresponding to each cluster set based on the multiple positions of the false target human body included in each cluster set; determine the movement trajectory of the false target human body based on the position of the trajectory point corresponding to each cluster set in the S cluster sets.

[0022] In some embodiments, the processing unit is specifically used to: determine the position coordinates of each contour boundary point of the wall based on the position coordinates of each trajectory point in the motion trajectory of the real target human body and the position coordinates of each trajectory point in the motion trajectory of the false target human body; determine the contour of the wall based on the position coordinates of each contour boundary point of the wall.

[0023] In some embodiments, the position coordinates of the boundary points of the wall outline satisfy the following relationship:

[0024]

[0025] Among them, X t Y is the horizontal coordinate of the real target human body position at time t, t is the vertical coordinate of the real target body position at time t, X′ t Y′ is the horizontal coordinate of the position of the false target human body at time t, t is the vertical coordinate of the false target human body at time t, is the horizontal coordinate of the boundary point of the wall contour at time t, is the vertical coordinate of the boundary point of the wall contour at time t.

[0026] In a third aspect, a wall contour recognition device is provided, comprising: one or more processors; and one or more memories; wherein the one or more memories are used to store computer program codes, the computer program codes comprising computer instructions, and when the one or more processors execute the computer instructions, the wall contour recognition device executes any one of the wall contour recognition methods provided in the first aspect.

[0027] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes computer instructions, which, when executed on a computer, enable the computer to execute any one of the wall contour recognition methods provided in the first aspect.

[0028] In a fifth aspect, an embodiment of the present invention provides a computer program product, which can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program product can implement any wall contour recognition method provided in the first aspect.

[0029] The beneficial effects of the second to fifth aspects of this application can be analyzed with reference to the beneficial effects of the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0031] Figure 1 A schematic diagram of the composition of a radar device provided in an embodiment of the present application;

[0032] Figure 2 A schematic diagram of a wall contour recognition scenario provided in an embodiment of the present application;

[0033] Figure 3 A schematic diagram of an antenna array provided in an embodiment of the present application;

[0034] Figure 4 A schematic diagram of a wall contour recognition system provided in an embodiment of the present application;

[0035] Figure 5 A schematic diagram of a flow chart of a wall contour recognition method provided in an embodiment of the present application;

[0036] Figure 6 A schematic flow chart of another wall contour recognition method provided in an embodiment of the present application;

[0037] Figure 7A schematic diagram of a DBSCAN clustering algorithm provided in an embodiment of the present application;

[0038] Figure 8 A schematic flow chart of another wall contour recognition method provided in an embodiment of the present application;

[0039] Figure 9 A schematic flow chart of another wall contour recognition method provided in an embodiment of the present application;

[0040] Figure 10 A schematic diagram of the outline of a wall provided in an embodiment of the present application;

[0041] Figure 11 A schematic diagram of the composition of a wall contour recognition device provided in an embodiment of the present application;

[0042] Figure 12 A schematic diagram of the hardware structure of a wall contour recognition device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0044] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0045] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "connected" and "connect" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances. Furthermore, when describing pipelines, the terms "connected" and "connected" used in this application have the meaning of conducting electricity. The specific meanings need to be understood in the context.

[0046] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0047] As described in the background technology, due to the wall's rebound characteristics to electromagnetic waves, the radar equipment will generate a large number of echo signals when detecting the wall, which makes the radar equipment subject to more interference factors during the detection process. The radar equipment needs to screen numerous echo signals to identify the outline of the wall, resulting in low efficiency and low recognition accuracy of the radar equipment in recognizing the wall outline.

[0048] To address this issue, an embodiment of the present application provides a wall contour recognition method. This method incorporates a real target person into the radar device's wall recognition process. Combined with the wall's ability to bounce electromagnetic waves, the real target person creates a strong false target person when moving close to the wall. The false target person typically has similar motion patterns to the real target person. The wall's contour is then determined by combining the real target person's and the false target person's motion trajectories, improving the radar device's accuracy and efficiency in wall contour recognition.

[0049] In the embodiments of the present application, a radar device is an electronic device that uses electromagnetic waves to detect targets, such as a millimeter-wave radar, a microwave radar, an ultra-wideband radar, etc. In some embodiments of the present application, a millimeter-wave radar with strong anti-interference capability, strong resolution capability, and high measurement accuracy is used.

[0050] Among them, millimeter waves refer to electromagnetic waves in the frequency domain of 30 to 300 GHz (wavelength of 1 to 10 mm). The wavelength of millimeter waves is between centimeter waves and light waves, so millimeter waves have the advantages of both microwave guidance and photoelectric guidance. Millimeter waves have extremely wide bandwidth, which can alleviate the problem of tight frequency domain resources; millimeter waves have narrow beams, which can observe the details of target objects more clearly. In this way, some embodiments of the present application use millimeter waves to identify the contours of walls, effectively improving the anti-interference ability, resolution ability and measurement accuracy of radar equipment.

[0051] For example, Figure 1 As shown, the radar device 10 may be composed of a radar transmitter 11 , a radar receiver 12 , an antenna 13 and a transceiver switch 14 .

[0052] Radar transmitter 11 is a radio device that provides high-power RF signals to radar equipment 10. It generates high-power RF signals with a modulated carrier wave, i.e., electromagnetic waves. Based on the modulation method, transmitters can be categorized as continuous wave transmitters or pulse transmitters. The transmitter consists of a first-stage RF oscillator and a pulse modulator.

[0053] Radar receiver 12 is the device within radar equipment 10 that performs frequency conversion, filtering, amplification, and demodulation. It uses appropriate filtering to separate the weak high-frequency signal received by the antenna from accompanying noise and interference. After amplification and detection, it is used for target detection, display, or other radar signal processing.

[0054] Antenna 13 is the device in radar equipment 10 that transmits or receives electromagnetic waves and determines their detection direction. During transmission, it radiates energy in the desired direction. During reception, it receives echoes in the detection direction and determines the target's azimuth and / or elevation.

[0055] When radar device 10 transmits a signal, transceiver switch 14 connects antenna 13 to radar transmitter 11 and disconnects it from radar receiver 12 to prevent the high-power transmit signal from entering radar receiver 12 and damaging the high-power amplifier or mixer. When radar device 10 receives a signal, transceiver switch 14 connects antenna 13 to radar receiver 12 and disconnects it from radar transmitter 11 to prevent the weak received signal from being lost due to bypassing radar transmitter 11.

[0056] The principle of radar equipment in measuring distance is that the radar equipment can obtain the distance of the target object by measuring the time difference between the emission of electromagnetic waves and the reception of electromagnetic waves.

[0057] The principle of azimuth measurement by radar equipment is that the radar equipment measures the distance and elevation angle based on the azimuth beam and elevation beam of the antenna, and then obtains the azimuth of the target object.

[0058] The above radar equipment can be used in wall contour recognition scenarios. Figure 2 As shown, after the air conditioner is installed, the radar device can activate the wall contour recognition function. When a real target person moves along the wall, the radar device recognizes the wall contour. The radar device transmits electromagnetic waves into the target space through the transmitting antenna and receives the echo signal through the receiving antenna. The echo signal is sent to the receiver for signal processing. After frequency conversion, filtering, amplification, or demodulation, the receiver extracts relevant information about the dynamic target (including real target people and fake target people) (such as the distance between the dynamic target and the radar, the dynamic target's direction, and the dynamic target's speed). By analyzing the relevant information of the dynamic target, the dynamic target's motion trajectory is obtained, and the wall contour is then recognized based on the dynamic target's motion trajectory.

[0059] In some embodiments, the radar device may be deployed on a home device, such as Figure 2 The smart air conditioner shown in the figure can also be deployed on other furniture devices such as smart TVs or smart door locks.

[0060] In some embodiments, the radar device may be a millimeter wave radar device of the TI IWR1443 or TI IWR6843 model. Figure 3 As shown in FIG, a schematic diagram of an antenna array provided in an embodiment of the present application is provided. Figure 3 As shown in (a) of FIG, the radar device has four receiving antennas (such as R1, R2, R3 and R4) that can receive echo signals. Figure 3 As shown in (b) of Figure 1, the radar device has three transmitting antennas (e.g., T1, T2, and T3) that can emit electromagnetic waves. Assuming the distance between any two receiving antennas is d, the distance between any two transmitting antennas is 2d.

[0061] like Figure 4 FIG2 is a schematic diagram of a wall contour recognition system provided in an embodiment of the present application. The system may include a radar device and an electronic device. The radar device and the electronic device may be connected via a wired or wireless connection. For example, the radar device and the electronic device may be connected via a wireless local area network.

[0062] The electronic device is used to issue control instructions to the radar device and receive detection results from the radar device. For example, the electronic device in the embodiments of the present application can be a mobile phone, tablet computer, desktop computer, laptop computer, handheld computer, notebook computer, ultra-mobile personal computer (UMPC), netbook, as well as cellular phone, personal digital assistant (PDA), augmented reality (AR) and virtual reality (VR) devices. The present disclosure does not impose any special restrictions on the specific form of the electronic device. It can interact with the user through one or more methods such as a keyboard, touchpad, touch screen, remote control, voice interaction or handwriting device.

[0063] The following describes in detail a wall contour recognition method provided by the present application in conjunction with the accompanying drawings.

[0064] An embodiment of the present application provides a method for recognizing the outline of a wall, which is performed by a wall outline recognition device. The wall outline recognition device can be a radar device or other device equipped with a radar component (e.g., a household appliance), without limitation. The following description uses a radar device as an example.

[0065] like Figure 5 As shown, the wall contour recognition method includes the following steps.

[0066] S101. A radar device transmits electromagnetic waves to a target space and receives M frames of echo signals.

[0067] In the embodiment of the present application, the target space may be a space where wall contour recognition is required, such as a living room, a bedroom, and a study, etc., without limitation thereto.

[0068] In some embodiments, the electromagnetic waves emitted by the radar device and the echo signals received by the radar device are collectively referred to as radar signals. Radar signals can be detected using linear frequency modulated continuous wave (LFMCW), which can effectively reduce the probability of being intercepted and interfered with.

[0069] In one possible implementation, upon receiving a recognition instruction, the radar device activates its radar function, transmits electromagnetic waves toward the target space, and receives M frames of echo signals. The recognition instruction is used to instruct the recognition of the outline of a wall within the target space.

[0070] It should be understood that since the radar device can emit electromagnetic waves for a long time, the above echo signal can have M frames, where M is an integer greater than 1.

[0071] In some embodiments, the recognition instruction received by the radar device may be sent by the user to the radar device through an electronic device. Specifically, the radar device may be connected to the electronic device via a wired connection (e.g., a signal line) or a wireless connection (e.g., Bluetooth, Wi-Fi). When the user needs to recognize the outline of a wall, the user turns on the recognition function through the electronic device. In response to the user turning on the recognition function, the electronic device sends a recognition instruction to the radar device.

[0072] S102: The radar device processes M frames of echo signals to obtain M positions of real target bodies and M positions of false target bodies in the target space.

[0073] As can be seen from the above background technology, walls have the property of reflecting electromagnetic waves. A false target human body is formed by interference signals caused by walls during the process of electromagnetic wave detection of a real target human body.

[0074] Optional, such as Figure 6 As shown, step S102 can be specifically implemented as the following steps:

[0075] S1021. The radar device performs pulse compression and moving target display processing on each frame of the M frames of echo signals to obtain a range image.

[0076] It should be noted that since LFMCW signals are ultra-wide signals, pulse compression processing cannot be performed in the time domain. Before the radar equipment performs pulse compression and moving target display processing on each frame of the M-frame echo signal to obtain the range image, the radar equipment can perform Fourier transform on the M-frame echo signal and transform the M-frame echo signal into the frequency domain for processing.

[0077] The purpose of the Fourier transform is to convert the time domain signal into the frequency domain signal so as to perform signal processing more intuitively.

[0078] In some embodiments, the above-mentioned Fourier transform can be replaced by fast Fourier transform (FFT). FFT is obtained by improving the discrete Fourier transform algorithm based on the odd, even, imaginary, and real characteristics of discrete Fourier transform.

[0079] As a possible implementation method, the radar device performs pulse compression and moving target display processing on each frame of the M frames of echo signals to obtain a range image, which can be specifically implemented as follows:

[0080] Pulse compression involves compressing the echo of a linear frequency modulated (LFM) or phase-coded signal and suppressing its sidelobe. This compresses wide pulses into narrow pulses, causing the output signal to peak at the target's range gate while improving the signal-to-noise ratio. Radar equipment transmits signals with a large time-width and bandwidth to improve velocity measurement accuracy and resolution. At the receiver, pulse compression compresses wide pulses into narrow pulses, improving the radar's range resolution and accuracy.

[0081] In some embodiments, the pulse compression process may satisfy the following formula (1):

[0082]

[0083] Among them, TR (m,k) represents the amplitude value of the mth linear frequency modulation signal (chirp signal) at frequency k. Frequency k can refer to the distance unit. Frequency k is proportional to the distance. Frequency k can satisfy the following formula (2):

[0084]

[0085] Where s is the slope of the FM signal of the radar device, d is the distance between the radar device and the target human body, and c is the speed of light.

[0086] Moving target indication (MTI) technology eliminates interference from static targets within a radar's monitoring area. Because the clutter components in the echo signals received by radar equipment are uniform, only the phase of moving targets changes due to changes in distance. Therefore, MTI primarily uses pulse cancellation, canceling the preceding and following pulses to completely eliminate static targets.

[0087] The above moving target display processing can satisfy the following formula (3):

[0088] RI MTI (tT r )=RI(tT r )-RI(t) Formula (3)

[0089] Among them, RI(t) represents the target range image without moving target display, RI MTI (tT r ) represents the target range image displayed by the moving target, RI(tT r ) indicates the time T before the current moment r Target distance image at the moment.

[0090] Through the above-mentioned pulse compression and moving target display processing, a distance image of a dynamic target (including a real target human body and a false target human body) can be obtained without interference from static targets, which can improve the accuracy of identifying the position of the real target human body and the false target human body.

[0091] S1022: The radar device performs OS-based CFAR processing on the range image, and extracts the range unit of the real target human body and the range unit of the false target human body from the range image.

[0092] It should be noted that at the same moment, there will be two distance units for a dynamic target. Among the two distance units, the distance unit farther away from the radar device can be used as the distance unit of the false target human body, and the distance unit closer to the radar device can be used as the distance unit of the real target human body.

[0093] Understandably, because the echo signal of a false human target undergoes multiple reflections, the reflected path is longer than the direct path. Therefore, the false human target often appears outside the area where the real human target is likely to appear, such as outside a wall. Therefore, the distance unit of the false human target is larger than the distance unit of the real human target.

[0094] As a possible implementation method, the radar device performs OS-based CFAR processing on the range image to extract the distance units of the real target human body and the distance units of the false target human body from the range image. The specific implementation can be as follows:

[0095] Collect reference unit sample data x i (i=1,2,……,R), the probability density function (PDF) of the reference unit sample data can satisfy the following formula (4), and the cumulative distribution function (CDF) can satisfy the following formula (5):

[0096]

[0097] F(x)=1-e -x / λ' ,x≥0 formula (5)

[0098] Among them, λ' can satisfy the following formula (6):

[0099]

[0100] Where μ represents the total power level of the clutter signal and the noise signal, λ is the ratio of the echo signal to the average power of the clutter signal and the noise signal, H0 is the assumption that there is no target, and H1 is the assumption that there is a target. i (i=1,2,……,R) are statistically independent and identically distributed.

[0101] In the CFAR detection of OS, the reference unit samples are sorted from small to large. In a uniform clutter background, the PDF of the kth ordered sample from the R total samples can satisfy the following formula (7):

[0102]

[0103] The CDF of the kth ordered sample from R total samples can satisfy the following formula (8):

[0104]

[0105] Among them, f(x) and F(x) represent the reference unit sample x in the uniform clutter background, respectively. i PDF and CDF of (i=1,2,…,R).

[0106] In the CFAR detection of OS, the cell under test (CUT) is the reference cell sample to be detected. First, the reference cell samples are sorted by size. The sorting process can satisfy the following formula (9):

[0107] x(1)≤x(2)≤…≤x( R ) Formula (9)

[0108] After the above sorting process, take the kth sorted sample x (k) As an estimate of the clutter signal power level Z, that is, Z = x (k) Then, from formula (7), we can see that the PDF of Z in a uniform clutter background can satisfy the following formula (10):

[0109]

[0110] In a uniform clutter background, the moment-generating function (MGF) of Z can satisfy the following formula (11):

[0111]

[0112] Where u is the variable of the moment generating function. When , the detection probability of the target can be calculated by the moment generating function. Where T is defined as the normalization factor.

[0113] Therefore, the detection probability of OS CFAR detection in a uniform clutter background can satisfy the following formula (12), and the false alarm probability can satisfy the following formula (13):

[0114]

[0115]

[0116] From formula (10), we can see that the statistical average of Z can satisfy the following formula (14):

[0117]

[0118] Therefore, the average decision threshold (ADT) of CFAR detection of OS can satisfy the following formula (15):

[0119]

[0120] When the radar device detects a dynamic target through the OS-based CFAR, it begins data acquisition and accumulates the data at a designated address on the radar device. The radar device detects one or more dynamic target range cells through CFAR and stores each range cell separately for signal processing to achieve target separation.

[0121] S1023. The radar device extracts the azimuth angle and the elevation angle of the real target human body from the echo signal according to the distance unit of the real target human body.

[0122] In some embodiments, the radar device provided by the embodiments of the present application includes an antenna array. The radar device can extract the azimuth angle and elevation angle of the dynamic target from the echo signal using an angle estimation method based on adaptive beamforming (minimum variance distortionless response, MVDR) according to the range unit of the dynamic target.

[0123] MVDR is an adaptive beamforming algorithm based on the maximum signal-to-interference-and-noise ratio (SINR) criterion. The weights derived from the MVDR algorithm minimize the array output power in the desired direction while maximizing the SINR. Applying MVDR to spatial spectrum estimation can improve resolution and noise suppression performance.

[0124] In some embodiments, the radar device may extract the azimuth angle and pitch angle of the real target human body from the echo signal using an MVDR-based angle estimation method according to the distance unit of the real target human body.

[0125] Among them, MVDR is a super-resolution method, and the expression when applied to the angle estimation of the real target human body is:

[0126]

[0127] Where α is the azimuth angle of the real target body, θ is the pitch angle of the real target body (based on the principle of radar equipment measuring azimuth, the pitch angle of the real target body can be known), R is the spatial correlation matrix of the input signal, and a is the steering vector when the azimuth angle of the real target body is α and the pitch angle is θ. R can be determined according to the following formula (17):

[0128] R=E[x(n)x H (n)] Formula (17)

[0129] Wherein, E is the data expectation calculation symbol, and x(n) is the vector consisting of the signals received by each receiving antenna of the radar device.

[0130] Traverse all azimuth angles and pitch angles to obtain a matrix P about azimuth angles and pitch angles MVDR When the traversal reaches the azimuth angle and pitch angle of the real target human body, P MVDR There will be a spike, so by calculating P MVDR The position of the peak can be used to obtain the azimuth and pitch angle of the real target human body.

[0131] S1024. The radar device determines the position of the real target human body according to the distance unit of the real target human body, the azimuth angle of the real target human body, and the pitch angle of the real target human body.

[0132] Combining the above formulas (16) and (17), the position of the real target human body can be determined according to the following formula (18):

[0133]

[0134] Where W is the distance unit of the real target human body.

[0135] According to the above formulas (16), (17) and (18), M positions of the real target human body can be obtained.

[0136] S1025. The radar device extracts the azimuth angle and the elevation angle of the false target human body from the echo signal according to the distance unit of the false target human body.

[0137] In some embodiments, the radar device may extract the azimuth angle and pitch angle of the false target human body from the echo signal using an MVDR-based angle estimation method according to the distance unit of the false target human body.

[0138] The expression of MVDR applied to the angle estimation of false target human body is:

[0139]

[0140] Wherein, α′ is the azimuth angle of the false target body, θ′ is the pitch angle of the false target body (according to the principle of azimuth measurement of radar equipment, the pitch angle of the false target body can be known), R is the spatial correlation matrix of the input signal, and a′ is the steering vector when the azimuth angle of the false target body is α′ and the pitch angle is θ′.

[0141] R can be determined according to the above formula (17).

[0142] Traverse all azimuth angles and pitch angles to obtain a matrix P′ about azimuth angles and pitch angles MVDR When traversing to the azimuth angle and pitch angle of the false target human body, P′MVDR There will be a peak, so by calculating P' MVDR The position of the peak can be used to obtain the azimuth and elevation angles of the false target human body.

[0143] S1026. The radar device determines the position of the false target human body according to the distance unit of the false target human body, the azimuth angle of the false target human body, and the pitch angle of the false target human body.

[0144] Combining the above formulas (17) and (19), the position of the false target human body can be determined according to the following formula (20):

[0145]

[0146] Where W′ is the distance unit of the false target human body.

[0147] According to the above formulas (17), (19) and (20), M positions of the false target human body can be obtained.

[0148] The present embodiment does not limit the execution order of steps S1023-S1024 and steps S1025-S1026. For example, steps S1023-S1024 may be executed first, followed by steps S1025-S1026; or steps S1025-S1026 may be executed first, followed by steps S1023-S1024; or steps S1023-S1024 and steps S1025-S1026 may be executed simultaneously.

[0149] S103: The radar device processes the M positions of the real target human body to obtain a motion trajectory of the real target human body.

[0150] In some embodiments, in order to solve the problem of false alarms and missed detections that are difficult to avoid during the detection process, the embodiments of the present application adopt a density-based DBSCAN method with noise, and regard the position coordinates within a certain range as a class of dynamic targets to obtain the final position of the dynamic target.

[0151] For example, Figure 7 As shown in the figure, A represents the core object, B and C represent boundary points, and N represents a noise point. After obtaining the positions of multiple consecutive frames, we first randomly select one of the positions as the core object. Then, we find a set of samples that can reach the density of this core object. This set is a clustering result. The average value of the samples in the clustering result is calculated to obtain the final position of the dynamic target.

[0152] Optional, such as Figure 8 As shown, step S103 can be specifically implemented as the following steps:

[0153] S1031. The radar device performs clustering processing on the M positions of the real target human body to obtain N first cluster sets.

[0154] Each of the N first cluster sets includes multiple positions of the real target human body, and N is an integer greater than 1 and less than M.

[0155] It should be understood that false alarms and missed detections are inevitable in radar equipment during detection. Therefore, the embodiment of the present application clusters the M positions obtained by detection to make the position information of the actual target human body more accurate.

[0156] In some embodiments, clustering is performed on M positions of the real target human body to obtain N first cluster sets, which can be specifically implemented as follows:

[0157] Step 1: Cluster the M positions of the real target body according to the DBSCAN clustering algorithm to obtain P second cluster sets, where the second cluster sets include at least one position of the target body, and P is an integer greater than 1 and less than or equal to M.

[0158] For example, after obtaining M locations of the real target body, the DBSCAN clustering algorithm randomly selects one location as the core object, and then finds all sample sets that are densely accessible to this core object. This set is a cluster set. Then, another core object without a category is selected, and the sample sets that are densely accessible to this core object are found to obtain another cluster set. In this way, P second cluster sets can be obtained.

[0159] Step 2: From the P second cluster sets, select a second cluster set whose number of locations containing real target human bodies is greater than or equal to a preset value as the first cluster set.

[0160] In this way, the embodiment of the present application regards the cluster set whose number of positions of real target human bodies is less than a preset value as a noise set, and selects the cluster set whose number of positions of real target human bodies is greater than or equal to the preset value as the first cluster set, which can filter out the interference of noise and make the obtained position information more accurate.

[0161] S1032: The radar device determines the position of the trajectory point corresponding to each first cluster set according to the multiple positions of the real target human body included in each first cluster set.

[0162] In some embodiments, for each first clustering set, the average value of the vertical coordinates of multiple positions in the first clustering set is taken, and the average value of the vertical coordinates is used as the vertical coordinate of the trajectory point corresponding to the first clustering set; the average value of the horizontal coordinates of multiple positions in the first clustering set is taken, and the average value of the horizontal coordinates is used as the horizontal coordinate of the trajectory point corresponding to the first clustering set. Thus, by determining the vertical and horizontal coordinates of the trajectory point, the position of the trajectory point is determined.

[0163] Exemplarily, assume that the positions of the target human body included in the i-th (1 < i ≤ N) first clustering set are: (3, 2), (4, 4), (4, 3), (5, 3), then the position of the trajectory point corresponding to the i-th clustering set is

[0164] S1033. The radar device determines the movement trajectory of the real target human body according to the positions of the trajectory points corresponding to each first clustering set in the N first clustering sets.

[0165] In some embodiments, Kalman filtering is performed on the positions of the trajectory points corresponding to each first clustering set in the multiple first clustering sets to obtain the trajectory of the real target human body moving along the wall in the target space.

[0166] Among them, Kalman filtering is an algorithm that uses a linear system state equation to optimally estimate the system state through system input and output observation data. Since the observation data includes the influence of noise and interference in the system, the optimal estimate can also be regarded as a filtering process.

[0167] Specifically, the radar device continuously detects the positions of multiple trajectory points. Assume that the positions of a total of K trajectory points are obtained: Further construct the target state vector of the position of the (k - 1)-th trajectory point. The target state vector of the position of the (k - 1)-th trajectory point can satisfy the following formula (21):

[0168]

[0169] Among them, Y(k - 1) represents the target state vector of the position of the (k - 1)-th trajectory point.

[0170] According to Kalman filtering, the further prediction equation of the target state can satisfy the following formula (22):

[0171]

[0172] Among them, is the state prediction value at time k of the k - 1 period, and F is the state transition matrix. Further derivation of Kalman filtering shows that the predicted mean square error matrix can satisfy the following formula (23):

[0173] P(k|k-1)=FP(k-1)F T +Q w Formula (23)

[0174] Among them, P(k) is the error correlation matrix of state estimation, Q w is the system noise correlation matrix.

[0175] The filter gain matrix can satisfy the following formula (24):

[0176] K(k)=P(k|k-1)H T [HP(k|k-1)H T +Q w ] -1 Formula (24)

[0177] Among them, H is the observation matrix, Q w is the system noise correlation matrix.

[0178] The state estimation can satisfy the following formula (25):

[0179]

[0180] The mean square error matrix can satisfy the following formula (26):

[0181] P(k)=[IK(k)H]P(k|k-1) Formula (26)

[0182] The position result Y of the smoothed trajectory point of the real target human body within K cycles is obtained through the above filtering process K (k=1,2,3…k). Y K That is the motion trajectory of the real target human body.

[0183] S104: The radar device processes the M positions of the false target human body to obtain a motion trajectory of the false target human body.

[0184] Optionally, step S104 may be specifically implemented as the following steps:

[0185] S1041. The radar device clusters the M positions of the false target human body to obtain S cluster sets.

[0186] Each of the S cluster sets includes multiple positions of the false target human body, and S is an integer greater than 1 and less than M.

[0187] S1042: The radar device determines the position of the trajectory point corresponding to each first cluster set according to the multiple positions of the false target human bodies included in each first cluster set.

[0188] S1043: The radar device determines the motion trajectory of the false target human body according to the position of the trajectory point corresponding to each first cluster set in the N first cluster sets.

[0189] For the specific description of steps S1041 to S1043 regarding the radar equipment determining the motion trajectory of the false target human body, you can also refer to the above description of steps S1031 to S1033 regarding the radar equipment determining the motion trajectory of the real target human body, which will not be repeated here.

[0190] It should be noted that in the embodiment of the present application, step S103 may be performed first, and then step S104. Step S104 may also be performed first, and then step S103. Step S103 and step S104 may also be performed simultaneously, which is not limited.

[0191] S105. The radar device determines the outline of the wall in the target space according to the motion trajectory of the real target human body and the motion trajectory of the false target human body.

[0192] Optional, such as Figure 9 As shown, step S105 can be specifically implemented as the following steps:

[0193] S1051. The radar device determines the position coordinates of each contour boundary point of the wall according to the position coordinates of each trajectory point in the motion trajectory of the real target human body and the position coordinates of each trajectory point in the motion trajectory of the false target human body.

[0194] Assume that the position coordinates of the trajectory point in the motion trajectory of the real target human body at time t are (X t , Y t ), the position coordinates of the trajectory point in the motion trajectory of the false target human body are (X′ t , Y′ t ), then the position coordinates of the boundary points of the wall contour at time t satisfy the following formula (27).

[0195]

[0196] That is, at time t, the position coordinates of the boundary points of the wall contour are

[0197] It should be noted that the ray tracing model shows that the real target person and the fake target person are mirror-symmetric about the wall. The ray tracing model treats the reflecting surface (i.e., the wall) as a mirror of the source, accurately finding the corresponding path through geometric relationships. After a single reflection from the transmitting antenna, the mirror point can be determined by the receiving antenna and the reflection point. For multiple reflections, the mirror point can be obtained by simply mirroring it again.

[0198] S1052: The radar device determines the outline of the wall according to the position coordinates of each outline boundary point of the wall.

[0199] The position coordinates of the boundary points of the wall contour at each moment can be connected to determine the contour of the wall.

[0200] For example, according to the motion trajectory of the real target body and the motion trajectory of the false target body, the contour of the wall can be determined as follows: Figure 10 shown. Figure 10 In this example, the path between the real target person and the radar device is called the direct path, and the path between the fake target person and the wall is called the reflected path. The distance between the radar device and the fake target person is greater than the distance between the radar device and the real target person, and the movement trajectory of the real target person and the fake target person are mirror-symmetrical with respect to the wall.

[0201] In one possible implementation, combining Figure 2 The wall outline shown in the scene is recognized by Figure 2 The example shown in the figure uses a radar device deployed in a smart air conditioner. After the smart air conditioner is installed, the radar device activates its wall contour recognition function. As the installer moves along the room's walls, the radar device detects the movement trajectories of both the real and fake human subjects, thereby identifying the wall contours. After the radar device identifies the wall contours, the smart air conditioner adjusts its state based on the detected wall contours, such as adjusting the air outlet direction and cooling or heating power, to achieve precise temperature and humidity control.

[0202] In another possible implementation, after the radar device identifies the outline of a wall in a room, the radar device may send the identified outline of the wall to the electronic device. In this way, the user can view the outline of the wall in the room through the electronic device to understand the structure of the room.

[0203] based on Figure 5In the embodiment shown, a wall contour recognition method proposed in the embodiment of the present application, combined with the characteristics of the wall's reflection of electromagnetic waves, introduces a real target human body as a reference object in the target space. It can be seen from the ray tracing model that the position of the real target human body and the position of the false target human body are mirror-symmetrical about the wall, so the contour of the wall in the space can be identified based on the motion trajectory of the real target human body and the motion trajectory of the false target human body. Compared with identifying the position and contour of the wall in the space by transmitting electromagnetic waves to the wall by the radar equipment, the wall contour recognition method proposed in the present application does not need to consider whether the electromagnetic waves emitted by the radar equipment to the wall are vertically incident. It only needs to identify the motion trajectory of the real target human body and the motion trajectory of the false target human body in the space to identify the contour of the wall in the space, thereby improving the accuracy and efficiency of wall contour recognition.

[0204] It can be seen that the above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the embodiment of the present application provides hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily appreciate that, in combination with the modules and algorithm steps of each example described in the embodiment disclosed herein, the embodiment of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0205] In the embodiments of the present application, the radar device can be divided into functional modules according to the above-mentioned method examples. For example, each functional module can be divided according to each function, or two or more functions can be integrated into a single processing module. The above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. Optionally, the module division in the embodiments of the present application is illustrative and is only a logical functional division. In actual implementation, other division methods may be used.

[0206] like Figure 11 As shown, the embodiment of the present application provides a wall contour recognition device for performing the following Figure 5 The wall contour recognition method shown in FIG. The wall contour recognition device 300 includes: a communication unit 301 and a processing unit 302. In some embodiments, the recognition device 300 may further include a storage unit 303.

[0207] The communication unit 301 is configured to transmit electromagnetic waves to a target space and receive M frames of echo signals, where M is an integer greater than 1.

[0208] The processing unit 302 is configured to process the M frames of echo signals to obtain M positions of real target bodies and M positions of false target bodies in the target space.

[0209] The processing unit 302 is further configured to process the M positions of the real target human body to obtain a motion trajectory of the real target human body.

[0210] The processing unit 302 is further configured to process the M positions of the false target human body to obtain a motion trajectory of the false target human body.

[0211] The processing unit 302 is further configured to determine the contour of the wall in the target space according to the motion trajectory of the real target human body and the motion trajectory of the false target human body.

[0212] In some embodiments, the processing unit 302 is specifically used to: for each frame of the M frame echo signal, perform pulse compression and moving target display processing on the echo signal to obtain a range image; based on a constant false alarm rate algorithm of sorting statistics, extract the distance unit of the real target human body and the distance unit of the false target human body from the range image; according to the distance unit of the real target human body, extract the azimuth angle of the real target human body and the pitch angle of the real target human body from the echo signal; determine the position of the real target human body according to the distance unit of the real target human body, the azimuth angle of the real target human body and the pitch angle of the real target human body; according to the distance unit of the false target human body, extract the azimuth angle of the false target human body and the pitch angle of the false target human body from the echo signal; determine the position of the false target human body according to the distance unit of the false target human body, the azimuth angle of the false target human body and the pitch angle of the false target human body.

[0213] In some embodiments, the processing unit 302 is specifically used to: cluster the M positions of the real target human body to obtain N first cluster sets, each cluster set in the N first cluster sets includes multiple positions of the real target human body, and N is an integer greater than 1 and less than M; determine the positions of the trajectory points corresponding to each first cluster set according to the multiple positions of the real target human body included in each first cluster set; determine the movement trajectory of the real target human body according to the positions of the trajectory points corresponding to each first cluster set in the N first cluster sets.

[0214] In some embodiments, the processing unit 302 is specifically used to: cluster the M positions of the real target human body according to the density-based clustering method DBSCAN algorithm to obtain P second cluster sets, each second cluster set includes at least one position of the real target human body, and P is an integer greater than 1 and less than or equal to M; from the P second cluster sets, select the second cluster set whose number of positions of the real target human body is greater than or equal to a preset value as the first cluster set, and N is less than or equal to P.

[0215] In some embodiments, the processing unit 302 is specifically configured to perform Kalman filtering on the position of the trajectory point corresponding to each of the N first cluster sets to obtain the motion trajectory of the real target human body.

[0216] In some embodiments, the processing unit 302 is specifically used to: cluster the M positions of the false target human body to obtain S cluster sets, each of the S cluster sets including multiple positions of the false target human body; determine the position of the trajectory point corresponding to each cluster set based on the multiple positions of the false target human body included in each cluster set; determine the movement trajectory of the false target human body based on the position of the trajectory point corresponding to each cluster set in the S cluster sets.

[0217] In some embodiments, the processing unit 302 is specifically used to: determine the position coordinates of each contour boundary point of the wall based on the position coordinates of each trajectory point in the motion trajectory of the real target human body and the position coordinates of each trajectory point in the motion trajectory of the false target human body; determine the contour of the wall based on the position coordinates of each contour boundary point of the wall.

[0218] In some embodiments, the storage unit 303 is configured to store M frames of echo signals.

[0219] In some embodiments, the storage unit 303 is further configured to store the outline of the wall.

[0220] Figure 11 A unit in a can also be called a module, for example, a processing unit can be called a processing module.

[0221] Figure 11 If the various units in the embodiment are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The storage medium for storing computer software products includes: various media that can store program codes, such as USB flash drives, mobile hard drives, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0222] The embodiment of the present application also provides a hardware structure diagram of a wall contour recognition device, such as Figure 12 As shown, the wall outline recognition device 2000 includes a processor 2001 and, optionally, a memory 2002 and a communication interface 2003 connected to the processor 2001. The processor 2001, the memory 2002 and the communication interface 2003 are connected via a bus 2004.

[0223] The processor 2001 may be a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 2001 may also be any other device having a processing function, such as a circuit, a device, or a software module. The processor 2001 may also include multiple CPUs, and the processor 2001 may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor here may refer to one or more devices, circuits, or processing cores for processing data (such as computer program instructions).

[0224] The memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and can be accessed by a computer, and the present embodiment of the application does not impose any restrictions on this. The memory 2002 may exist independently or be integrated with the processor 2001. Among them, the memory 2002 may contain computer program code. The processor 2001 is used to execute the computer program code stored in the memory 2002, thereby implementing the method provided in the embodiment of the present application.

[0225] The communication interface 2003 can be used to communicate with other devices or communication networks (such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.) The communication interface 2003 can be a module, circuit, transceiver or any device capable of achieving communication.

[0226] The bus 2004 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus 2004 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 12 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0227] An embodiment of the present application further provides a computer-readable storage medium, comprising computer-executable instructions, which, when executed on a computer, enables the computer to execute any one of the methods provided in the above embodiments.

[0228] An embodiment of the present application further provides a computer program product comprising computer-executable instructions, which, when executed on a computer, enables the computer to execute any one of the methods provided in the above embodiments.

[0229] An embodiment of the present application also provides a chip, including: a processor and an interface, the processor is coupled to a memory through the interface, and when the processor executes a computer program or computer execution instruction in the memory, any one of the methods provided in the above embodiments is executed.

[0230] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented using a software program, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer-executable instructions. When the computer-executable instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer-executable instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer-executable instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0231] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other variations of the disclosed embodiments by reviewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0232] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely illustrative of the present application as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, the present application is intended to include such modifications and variations as fall within the scope of the claims of the present application and their equivalents.

[0233] The above is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A wall contour recognition method, characterized in that: The method comprises: Transmit electromagnetic waves into the target space and receive M frames of echo signals, where M is an integer greater than 1; Processing the M frames of echo signals to obtain M positions of real target bodies and M positions of false target bodies in the target space; Processing the M positions of the real target human body to obtain a motion trajectory of the real target human body; Processing the M positions of the false target human body to obtain a motion trajectory of the false target human body; The contour of the wall in the target space is determined according to the motion trajectory of the real target human body and the motion trajectory of the false target human body.

2. The method according to claim 1, characterized in that The processing of the M frames of echo signals to obtain M positions of the real target human body and M positions of the false target human body in the target space includes: For each frame of the M frames of echo signals, pulse compression and moving target display processing are performed on the echo signal to obtain a range image; Extracting the distance unit of the real target human body and the distance unit of the false target human body from the range image based on a constant false alarm rate algorithm of sorting statistics; extracting the azimuth angle and the pitch angle of the real target human body from the echo signal according to the distance unit of the real target human body; Determining the position of the real target human body according to the distance unit of the real target human body, the azimuth angle of the real target human body, and the pitch angle of the real target human body; extracting the azimuth angle and the elevation angle of the false target body from the echo signal according to the distance unit of the false target body; The position of the false target body is determined according to the distance unit of the false target body, the azimuth angle of the false target body, and the pitch angle of the false target body.

3. The method according to claim 1, characterized in that The processing of the M positions of the real target human body to obtain the motion trajectory of the real target human body includes: Performing clustering processing on the M positions of the real target human body to obtain N first cluster sets, each cluster set in the N first cluster sets includes multiple positions of the real target human body, where N is an integer greater than 1 and less than M; Determining the position of the trajectory point corresponding to each first cluster set according to the multiple positions of the real target human body included in each first cluster set; The motion trajectory of the real target human body is determined according to the position of the trajectory point corresponding to each first cluster set in the N first cluster sets.

4. The method according to claim 3, characterized in that The clustering process is performed on the M positions of the real target human body to obtain N first cluster sets, including: Clustering the M positions of the real target body according to the density-based clustering method DBSCAN algorithm to obtain P second cluster sets, each second cluster set including at least one position of the real target body, where P is an integer greater than 1 and less than or equal to M; From the P second cluster sets, a second cluster set whose number of locations containing the real target human body is greater than or equal to a preset value is selected as the first cluster set, and N is less than or equal to P.

5. The method according to claim 3, characterized in that The determining the motion trajectory of the real target human body according to the position of the trajectory point corresponding to each first cluster set in the N first cluster sets includes: Kalman filtering is performed on the position of the trajectory point corresponding to each first cluster set in the N first cluster sets to obtain the motion trajectory of the real target human body.

6. The method according to claim 1, characterized in that The processing of the M positions of the false target human body to obtain the motion trajectory of the false target human body includes: Clustering the M positions of the false target body to obtain S cluster sets, each of the S cluster sets including multiple positions of the false target body, where S is an integer greater than 1 and less than M; Determine the position of the trajectory point corresponding to each cluster set according to the multiple positions of the false target human body included in each cluster set; The motion trajectory of the false target human body is determined according to the position of the trajectory point corresponding to each cluster set in the S cluster sets.

7. The method according to any one of claims 1 to 6, characterized in that The step of determining the contour of the wall in the target space according to the motion trajectory of the real target person and the motion trajectory of the false target person includes: Determine the position coordinates of each contour boundary point of the wall according to the position coordinates of each trajectory point in the motion trajectory of the real target human body and the position coordinates of each trajectory point in the motion trajectory of the false target human body; The outline of the wall is determined according to the position coordinates of each outline boundary point of the wall.

8. The method according to claim 7, characterized in that The position coordinates of the boundary points of the wall outline satisfy the following relationship: Among them, X t Y is the horizontal coordinate of the real target human body position at time t, t is the vertical coordinate of the real target body position at time t, X′ t Y′ is the horizontal coordinate of the position of the false target human body at time t, t is the vertical coordinate of the position of the false target human body at time t, is the horizontal coordinate of the boundary point of the wall contour at time t, is the vertical coordinate of the boundary point of the wall contour at time t.

9. A wall contour recognition device, characterized in that: include: a communication unit, configured to transmit electromagnetic waves to a target space and receive M frames of echo signals, where M is an integer greater than 1; a processing unit, configured to process the M frames of echo signals to obtain M positions of real target bodies and M positions of false target bodies in the target space; The processing unit is further used to: process the M positions of the real target body to obtain the motion trajectory of the real target body; process the M positions of the false target body to obtain the motion trajectory of the false target body; and determine the outline of the wall in the target space based on the motion trajectory of the real target body and the motion trajectory of the false target body.

10. A wall contour recognition device, characterized in that: include: one or more processors; one or more memories; The one or more memories are used to store computer program codes, and the computer program codes include computer instructions. When the one or more processors execute the computer instructions, the wall contour recognition device performs the method according to any one of claims 1 to 8.

Images