UWB-based seating posture detection method, apparatus, device, and storage medium

Abstract

To avoid infringing on user privacy, the system achieves high-precision position tracking of target objects and monitors individual seating postures in real time. [Solution] A pulse signal is received at the UWB signal receiving end, and the pulse signal is amplified to obtain a first pulse signal. Based on the difference between the average phase of the reference pulse signal and the phase of the reference pulse signal of any one frame, the phase of the first pulse signal of the corresponding frame is adjusted. A cascade filter is used to remove noise from the first pulse signal and improve the SNR of the received baseband signal to obtain a second pulse signal. If the amplitude and / or Doppler information of the second pulse signal changes abruptly, it is assumed that the seating posture has changed. Based on the second pulse signals before and after the change in seating posture, target distance information and target angle information arising from the different seating postures in the change process are determined. The target distance information and target angle information are concatenated and input as a combined feature to an SVM classifier to obtain the seating posture detection result.

Description

[Technical Field]

[0001] This disclosure relates to the field of smart analytics technology, and more particularly to the cross-fields of the Internet of Things (IoT) and healthcare, and more specifically to a seated posture detection method, apparatus, device, and storage medium based on UWB. [Background technology]

[0002] With the increasing pace of modern life, prolonged sitting has become a daily habit for many people. For the elderly in particular, prolonged, improper sitting postures often lead to various health risks, including spinal problems and muscle fatigue. Therefore, seating posture detection is attracting attention as a field of health monitoring.

[0003] Existing seating posture detection methods typically rely on equipment such as cameras, making them susceptible to interference from factors like light and occlusion. This can lead to delays and inaccuracies in seating posture detection results, and may also raise user privacy concerns. [Overview of the Initiative] [Problems that the invention aims to solve]

[0004] This disclosure provides a seating posture detection method, apparatus, device, and storage medium based on UWB, which address the delays and inaccuracies in seating posture detection results obtained by existing seating posture detection methods, as well as technical issues related to user privacy. [Means for solving the problem]

[0005] According to a first aspect of this disclosure, a seating posture detection method based on UWB is provided. The method is After the UWB signal receiving terminal receives the pulse signal, it amplifies the pulse signal to obtain a first pulse signal, adjusts the phase of the first pulse signal for the corresponding frame based on the difference between the average phase of the reference pulse signal and the phase of the reference pulse signal for any one frame, removes noise from the first pulse signal using a cascade filter and improves the SNR (Signal-to-Noise Ratio) of the received baseband signal to obtain a second pulse signal. The steps include: using the abrupt change in the amplitude and / or Doppler information of the second pulse signal as the dividing point of the seating posture change, and determining the target distance information and target angle information from different coordinates in the change process based on the second pulse signal before and after the change in seating posture; This includes concatenating the target distance information and the target angle information and inputting them as a combined feature into an SVM classifier to obtain a seated posture detection result, The combined feature is a one-dimensional matrix formed by concatenating the target distance information and the target angle information.

[0006] In the embodiments described above and any possible embodiments, a further embodiment is provided in which the pulse signal includes a pulse signal that has been transmitted by the UWB signal transmitting end and has been reflected back at the target point.

[0007] In the embodiments described above and any possible embodiments, and further in one embodiment, a step is provided to adjust the phase of the first pulse signal of a corresponding frame based on the difference between the average phase of the reference pulse signal and the phase of the reference pulse signal of any one of those frames, Steps include selecting one of the reflected pulse signals from a static object as a reference pulse signal, and The steps involve calculating the difference between the average phase of a reference pulse signal in any sequence and the phase of any one frame within that sequence. This includes adjusting the phase of the first pulse signal of the corresponding frame based on the difference value.

[0008] In the above-described embodiment and any possible implementation, yet another implementation is provided. The step of using the cascade filter to remove the noise of the first pulse signal and improve the SNR of the received baseband signal to obtain a second pulse signal is as follows: Input the first pulse signal after phase adjustment into a low-pass filter in the cascade filter to remove high-frequency noise, and then input it into a smoothing filter in the cascade filter to further smooth the signal, improve the SNR of the received baseband signal, and obtain a second pulse signal. This includes the above steps.

[0009] In the above-described embodiment and any possible implementation, yet another implementation is provided. The step of determining the target distance information is as follows: Based on the resolution and detection range, determine the possible range of the target distance information r. Within the possible range, traverse the value of r at a predetermined step size, and determine the actual value of r based on the measured flight time. The flight time is the time elapsed when the pulse signal propagates from the UWB signal transmitter to the target point and then reflects back from the target point to the UWB signal receiver. Traverse all the values of r and calculate P(r) according to the following formula: The formula is:

Equation

[0010] In the above-described embodiment and any possible implementation, yet another implementation is provided. The step of determining the target angle information is as follows: Based on the decomposition energy and the detection range, determining the range within which the target angle information θ value and Φ value can be taken, where the θ value and Φ value respectively represent the angles obtained by projecting the signal received by the two-dimensional antenna array in the horizontal and vertical directions, steps; Combining each θ value and Φ value within the possible range, and calculating the power value P(r,θ,Φ) corresponding to each combination of θ value and φ value according to the following formula:

Number

[0011] According to a second aspect of the present disclosure, a sitting posture detection device based on UWB is provided. The device includes: After the UWB signal receiving end receives a pulse signal, the pulse signal is amplified to obtain a first pulse signal, and the phase of the first pulse signal of the corresponding frame is adjusted based on the difference between the average phase of the reference pulse signal and the phase of any one frame of the reference pulse signal, and a cascade filter is used to remove the noise of the first pulse signal and improve the SNR of the received baseband signal to obtain a second pulse signal. Using the sudden change in the amplitude and / or Doppler information of the second pulse signal as the segmentation point of the sitting posture change, and based on the second pulse signal before and after the change of different sitting postures, determining the target distance information and target angle information from different coordinates in the change process. Connecting the target distance information and the target angle information and inputting them into an SVM classifier as a combined feature amount to obtain a sitting posture detection result. Here, the combined feature is a one-dimensional matrix formed by concatenating the target distance information and the target angle information.

[0012] A third aspect of this disclosure provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor executing the program, thereby realizing the method according to the first and / or second aspects.

[0013] A fourth aspect of the present disclosure provides a computer-readable storage medium, the computer-readable storage medium storing a computer program, and when the program is executed by a processor, the method of the first and / or second aspects of the present disclosure is realized. [Effects of the Invention]

[0014] In this disclosure, a pulse signal is received at the UWB signal receiving end, the pulse signal is amplified to obtain a first pulse signal, the phase of the first pulse signal of the corresponding frame is adjusted based on the difference between the average phase of the reference pulse signal and the phase of the reference pulse signal of any one frame, noise in the first pulse signal is removed using a cascade filter and the SNR of the received baseband signal is improved to obtain a second pulse signal, a change in seating posture is assumed when the amplitude and / or Doppler information of the second pulse signal changes abruptly, target distance information and target angle information arising from different seating postures in the change process are determined based on the second pulse signals before and after the change in seating posture, the target distance information and target angle information are concatenated and input to an SVM classifier as a combined feature to obtain a seating posture detection result. With the above method, high-precision position tracking of the target object is achieved, the individual's seating posture state is monitored in real time, a response to changes in seating posture is made immediately, and the user can be immediately notified of poor seating posture, and UWB technology has high-speed data transmission capability, enabling real-time data collection and processing.

[0015] It should be understood that the contents described in the summary section of the invention are not intended to limit the main or essential features of the embodiments of this disclosure, nor are they intended to limit the scope of this disclosure. Other features of this disclosure will be readily apparent from the following description. [Brief explanation of the drawing]

[0016] The above and other features, advantages, and aspects of various embodiments of this disclosure will become more apparent by referring to the following detailed description in conjunction with the accompanying drawings. The drawings are provided for a better understanding of the solutions of this disclosure, and in the drawings, the same or similar reference numerals indicate the same or similar elements. [Figure 1] This figure shows a flowchart of a seating posture detection method based on UWB according to an embodiment of the disclosure; [Figure 2] This is a block diagram of a seated posture detection device based on UWB according to an embodiment of the present disclosure; [Figure 3] This is a block diagram of an exemplary electronic device for which embodiments of the present disclosure can be implemented. [Modes for carrying out the invention]

[0017] To further clarify the purpose, aspects, and advantages of the embodiments of this disclosure, the technical solutions in the embodiments of this disclosure will be described clearly and completely below, together with the drawings of the embodiments of this disclosure. Of course, the embodiments described are only some, not all, embodiments of this disclosure. All other embodiments that can be obtained by those skilled in the art without inventive effort based on the embodiments of this disclosure are within the scope of this disclosure.

[0018] Furthermore, the terms "and / or" in the text simply describe related objects, meaning there can be three possible relationships, such as A and / or B, which means A alone, both A and B, and B alone. Also, the " / " in the text generally indicates that the related objects before and after it are in an "or" relationship.

[0019] In this disclosure, we present a UWB-based seating posture detection method to address the problems of existing seating posture detection methods, which typically rely on equipment such as cameras, are susceptible to interference from factors such as light rays and shielding, resulting in delays and inaccuracies in seating posture detection results, and potentially raising user privacy concerns. This method receives a pulse signal at the UWB signal receiving end, amplifies the pulse signal to obtain a first pulse signal, adjusts the phase of the first pulse signal for the corresponding frame based on the difference between the average phase of the reference pulse signal and the phase of the reference pulse signal for any one frame, removes noise from the first pulse signal using a cascade filter, and improves the SNR of the received baseband signal to obtain a second pulse signal, considers a change in seating posture when the amplitude and / or Doppler information of the second pulse signal changes abruptly, determines target distance information and target angle information arising from different seating postures in the change process based on the second pulse signals before and after the change in seating posture, concatenates the target distance information and target angle information as a combined feature and inputs it to an SVM classifier to obtain a seating posture detection result. This method enables highly accurate position tracking of target objects, real-time monitoring of an individual's seated posture, and does not infringe on user privacy.

[0020] Figure 1 is a flowchart showing a UWB-based seated posture detection method 100 according to an embodiment of the present disclosure. As shown in Figure 1, the UWB-based seated posture detection method includes the following: In S110, after the UWB signal receiving terminal receives the pulse signal, the pulse signal is amplified to obtain the first pulse signal. Based on the difference between the average phase of the reference pulse signal and the phase of the reference pulse signal of any one frame, the phase of the first pulse signal of the corresponding frame is adjusted. A cascade filter is used to remove noise from the first pulse signal and improve the SNR of the received baseband signal to obtain the second pulse signal.

[0021] In some embodiments, the pulse signal includes a pulse signal that has been transmitted by the UWB signal transmitting end and then reflected back.

[0022] In some embodiments, one reflected pulse signal of a static object is selected as a reference pulse signal; the difference between the average phase of the reference pulse signal of any sequence and the phase of any frame therein is calculated; and the phase of the first pulse signal of the corresponding frame is adjusted based on the difference.

[0023] In some embodiments, the phase-adjusted first pulse signal is input to a low-pass filter in a cascade filter to remove high-frequency noise, and then input to a smoothing filter in the cascade filter to further smooth the signal, thereby improving the SNR of the received baseband signal and obtaining a second pulse signal.

[0024] In one possible implementation, the cascade filter includes one low-pass filter and one smoothing filter. First, a finite impulse response (FIR) low-pass filter is employed, having 26 taps and a Hamming window. Next, a five-point window smoothing filter is used to smooth the output of the FIR low-pass filter.

[0025] In some embodiments, UWB signal generators produce extremely narrow pulses on the order of nanoseconds or microseconds, which are transmitted through radio space as information carriers. Because the time width of these pulses is extremely short, the frequency spectral range they occupy is very wide, thereby enabling ultra-wideband communication.

[0026] In some embodiments, the correlator is a core component of the UWB signal acquisition system. A first pulse signal is transmitted to the correlator, which compares and matches the received first pulse signal with a locally generated reference pulse signal through a correlation algorithm to obtain the pulse signal transmission delay time, determine the distance between the transmitting and receiving ends, and process and analyze the collected data to extract useful information such as position and velocity.

[0027] In one possible implementation, UWB is installed somewhere indoors, and the antenna is directed towards the detection area for signal transmission and reception. Specifically, the transmitter transmits the signal s k (t), which can be expressed as

Number

Number

Number

number

[0028] In one possible implementation, the ADC of a UWB signal introduces a sampling timing offset (STO) due to the imperfection of the sampling clock. Signal phase perturbations affect the Doppler and micro-Doppler information of the signal. Doppler and micro-Doppler are observed at slow time kT. s This is obtained by: If the reflection is from a static object, the phase introduced by both the Doppler and micro-Doppler is zero. The original RF signal frame (slow time) y(t) with phase noise caused by STO is reflected from the same static object. The amplitude of the second frame with phase noise has jitter, but ideally the amplitudes of both frames should be the same. In this invention, because of the presence of phase noise, the static object can be considered to be moving.

[0029] The phase of an object with jitter is Ω p +Δω(t-kT s ) The phase jitter caused by STO in a wireless receiver is Δω(t-kT s ) and the phase of the object reflection signal is Ω p Therefore, the inventors' goal is to reduce the phase jitter Δω(t-kT s The goal is to reduce )

[0030] In one possible implementation, since the UWB is mounted on the ceiling, the maximum reflection peak is always at the floor, where the radar cross-section (RCS) is largest. Therefore, for phase correction, a person can easily distinguish this reflection from reflections from other static objects. Because the phase change is very small, large motions due to human activity have little effect on the neural network's inference results. However, this change can destabilize the learning phase, potentially resulting in longer convergence times. The original received baseband signal is corrupted by noise, and this noise introduces errors into the neural network model. If not handled properly, random noise tends to be learned by the neural network model, leading to overfitting. Therefore, cascaded filters are used to remove noise and improve the SNR of the received baseband signal.

[0031] S120, the sudden change in the amplitude and / or Doppler information of the second pulse signal is used as the dividing point of the seating posture change, and target distance information and target angle information from different coordinates in the change process are determined based on the second pulse signals before and after the change in seating posture.

[0032] In some embodiments, the step of determining target distance information includes: determining the range of possible target distance information r based on resolution and detection range; traversing the values ​​of r within the possible range in predetermined step sizes and determining the actual value of r based on the measured flight time; where the flight time is the time elapsed as the pulse signal propagates from the UWB signal transmitting end to the target point and is reflected back from the target point to the UWB signal receiving end; traversing all values ​​of r, P(r) is calculated by the following formula, which is:

number

[0033] In some embodiments, the step of determining target angle information includes: determining the possible range of target angle information θ and Φ values ​​based on the resolution and detection range; where θ and Φ represent the angles projected horizontally and vertically, respectively, of the signals received by the two-dimensional antenna array; combining each θ and Φ value within the possible range, and calculating the power value P(r,θ,Φ) corresponding to each combination of θ and Φ values ​​using the following formula:

number

[0034] In S130, the target distance information and the target angle information are concatenated and input to the SVM classifier as a combined feature to obtain the seated posture detection result. The combined feature is a one-dimensional matrix formed by concatenating the target distance information and the target angle information.

[0035] In some embodiments, five seating postures—normal seating posture, left tilt, right tilt, forward tilt, and backward tilt—can be distinguished based on distance-angle features.

[0036] While the embodiments of each of the methods described above are presented as a combination of operations for the sake of simplicity, those skilled in the art should understand that this disclosure is not limited to the described sequence of operations, because, based on this disclosure, certain steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should understand that all embodiments described in the specification are preferred embodiments, and the relevant operations and modules are not necessarily essential to this disclosure.

[0037] The above is a description of embodiments of the method, and the present invention will be further described below through embodiments of the apparatus.

[0038] Figure 2 is a block diagram of a seated posture detection device 200 based on UWB according to an embodiment of the present disclosure. As shown in Figure 2, the device 200 includes: The signal processing module 210 is used to obtain a second pulse signal by amplifying the pulse signal after the UWB signal receiving terminal receives the pulse signal, adjusting the phase of the first pulse signal for the corresponding frame based on the difference between the average phase of the reference pulse signal and the phase of the reference pulse signal for any one frame, and removing noise from the first pulse signal and improving the SNR of the received baseband signal using a cascade filter; The echo detection module 220 uses the abrupt change in the amplitude and / or Doppler information of the second pulse signal as a dividing point of the seating posture change, and is used to determine target distance information and target angle information from different coordinates during the change process based on the second pulse signal before and after the change in seating posture; The seated posture detection module 230 is used to obtain seated posture detection results by concatenating the target distance information and the target angle information and inputting the concatenated feature into the SVM classifier; the concatenated feature is a one-dimensional matrix formed by concatenating the target distance information and the target angle information.

[0039] For the convenience and brevity of explanation, engineers in the relevant technical field may refer to the corresponding processes in the embodiments of the aforementioned methods for the specific operating processes of the described modules, which will not be repeated here.

[0040] In the technical solutions disclosed herein, the acquisition, storage, and application of relevant user personal information shall comply with applicable laws and regulations and shall not violate public order and morals.

[0041] In accordance with embodiments of the present disclosure, the present disclosure further provides electronic devices, readable storage media, and computer program products.

[0042] Figure 3 is a block diagram of an exemplary electronic device 300 that can implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing devices, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are shown as examples only and are not intended to limit the implementation of the present disclosure described herein and / or requested herein.

[0043] The electronic device 300 includes a computing unit 301, which performs various appropriate operations and processes according to a computer program stored in ROM 302 or a computer program loaded from storage unit 308 into RAM 303. RAM 303 further stores various programs and data necessary for the operation of the electronic device 300. The computing unit 301, ROM 302, and RAM 303 are connected to each other via bus 304. The I / O interface 305 is also connected to bus 304.

[0044] Multiple components of the electronic device 300 are connected to the I / O interface 305, which includes an input unit 306 (keyboard, mouse, etc.), an output unit 307 (various displays, speakers, etc.), a storage unit 308 (disk, optical disc, etc.), and a communication unit 309 (network card, modem, wireless communication transceiver, etc.). The communication unit 309 enables the electronic device 300 to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunication networks.

[0045] The computing unit 301 can be a variety of general-purpose and / or dedicated processing components having processing and computing capabilities. Examples of the computing unit 301 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, computing units that execute various machine learning model algorithms, digital signal processors (DSPs), and any suitable processors, controllers, microcontrollers, etc. The computing unit 301 performs each of the methods and processes described above, for example, method 100. For example, in some embodiments, method 100 is embodied as a computer software program and formally contained in a machine-readable medium, for example, a storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed into the electronic device 300 via ROM 302 and / or a communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of method 100 described above can be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform method 100 in any other suitable way (e.g., by firmware).

[0046] Various embodiments of the systems and technologies described herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs, ASICs, ASSPs, SOCs, CPLDs, computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include being implemented in one or more computer programs that run and / or interpret on a programmable system. This programmable system includes at least one programmable processor, including a dedicated or general-purpose programmable processor, which receives data and instructions from a storage system, at least one input device, and at least one output device, and transfers data and instructions to the storage system, at least one input device, and at least one output device.

[0047] Program code for carrying out the methods of this disclosure can be written in any combination of one or more programming languages. These program codes are provided to a processor or controller of a general-purpose computer, a dedicated computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations defined in the flowcharts and / or block diagrams are performed. The program code may run entirely on a machine, partially on a machine, partially on a machine as a standalone software package and partially on a remote machine, or fully on a remote machine or server.

[0048] In the context of this disclosure, a machine-readable medium may be a tangible medium that contains or stores a program for use by, or in combination with, a command execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium includes, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0049] To provide user interaction, the systems and technologies described herein may be implemented on a computer equipped with a display device (such as an LCD) for displaying information to the user and a keyboard and pointing device (such as a mouse or trackball). The user can provide input to the computer through the keyboard and pointing device. Other types of devices may also be used to provide user interaction. Feedback to the user may be any form of sensory feedback (visual feedback, auditory feedback, or tactile feedback). Input from the user may be received in any form, including voice input, speech input, or tactile input.

[0050] The systems and technologies described herein may be implemented in computer systems including backend components (as data servers), computer systems including middleware components (as application servers), or computer systems including frontend components (as user computers having a graphical user interface or a web browser; users can interact with embodiments of the systems and technologies described herein through this graphical user interface or web browser), or in computer systems including any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by digital data communications (such as communication networks) of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0051] A computer system can include clients and servers. Clients and servers are generally located remotely from each other and typically interact via a communication network. The client-server relationship arises from computer programs running on each computer that have a client-server relationship with each other. A server can be a cloud server, a server in a distributed system, or a server combined with blockchain technology.

[0052] It should be understood that the steps can be rearranged, added, or deleted using the various forms of processes described above. For example, each step described herein can be performed in parallel, sequentially, or in a different order, and this disclosure does not limit this, as long as it achieves the results expected by the technical solutions disclosed herein.

[0053] The specific embodiments described above do not limit the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions are possible based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection.

Claims

1. A seating posture detection method based on UWB, After the UWB signal receiving terminal receives the pulse signal, the pulse signal is amplified to obtain a first pulse signal, the phase of the first pulse signal of the corresponding frame is adjusted based on the difference between the average phase of the reference pulse signal and the phase of the reference pulse signal of any one frame, noise in the first pulse signal is removed using a cascade filter and the SNR of the received baseband signal is improved to obtain a second pulse signal. The steps include: using the abrupt change in the amplitude and / or Doppler information of the second pulse signal as the dividing point of the seating posture change, and determining the target distance information and target angle information from different coordinates in the change process based on the second pulse signal before and after the change in seating posture; This includes concatenating the target distance information and the target angle information and inputting them as a combined feature into an SVM classifier to obtain a seated posture detection result, The seated posture detection method is characterized in that the combined feature is a one-dimensional matrix formed by concatenating the target distance information and the target angle information.

2. The seated posture detection method according to claim 1, wherein the pulse signal includes a pulse signal that is transmitted by the UWB signal transmitting end and then reflected back at the target point.

3. The step of adjusting the phase of the first pulse signal of a corresponding frame based on the difference between the average phase of the reference pulse signals and the phase of the reference pulse signals of any one frame thereof is: The steps include selecting one of the reflected pulse signals from a static object as a reference pulse signal, and The steps involve calculating the difference between the average phase of a reference pulse signal in any sequence and the phase of any one frame within that sequence. The steps include adjusting the phase of the first pulse signal of the corresponding frame based on the difference value, The method for detecting seated posture according to claim 1 includes the following:

4. The step of using the cascade filter to remove noise from the first pulse signal and improve the SNR of the received baseband signal to obtain the second pulse signal is: The first pulse signal, after phase adjustment, is input to a low-pass filter in a cascade filter to remove high-frequency noise, and then input to a smoothing filter in the cascade filter to further smooth the signal and improve the SNR of the received baseband signal to obtain a second pulse signal. The method for detecting seated posture according to claim 1 includes the following:

5. The step of determining the target distance information is: The steps include determining the possible range of target distance information r based on resolution and detection range, The steps include: traversing the value of r in a predetermined step size within the range of possible values ​​and determining the actual value of r based on the measured flight time; and determining that the flight time is the time elapsed as the pulse signal propagates from the UWB signal transmitting end to the target point and is reflected back from the target point to the UWB signal receiving end. Traversing all values ​​of r, P(r) is calculated using the following formula: [Math 1] In the formula, s ｎ，ｍ This shows the actual measured baseband signal data, in steps, The step of determining the value of r at the position where P(r) is maximum as target distance information, This method includes the seating posture detection method described in claim 1.

6. The step of determining the target angle information is: The steps include determining the possible ranges of target angle information θ and Φ values ​​based on resolution and detection range, where θ and Φ represent the angles projected horizontally and vertically, respectively, of the signals received by the two-dimensional antenna array, and By combining each possible θ and Φ value within the range described above, the power value P(r, θ, Φ) corresponding to each combination of θ and Φ values ​​is calculated using the following formula: [Math 2] In the formula, N is the number of receiving end antennas, M is the number of transmitting end antennas, and s ｎ，ｍ，ｔ Step 1 indicates the signal transmitted from the m-th transmitting antenna and received by the n-th receiving antenna at time t, The steps include determining the θ and Φ values ​​corresponding to the maximum value among all power values ​​P(r, θ, Φ) as target angle information, and This method includes the seating posture detection method described in claim 1.

7. A seating posture detection device based on UWB, A signal processing module is used to obtain a second pulse signal by amplifying a pulse signal after the UWB signal receiving terminal receives the pulse signal, adjusting the phase of the first pulse signal of the corresponding frame based on the difference between the average phase of the reference pulse signal and the phase of the reference pulse signal of any one frame, removing noise from the first pulse signal using a cascade filter, and improving the SNR of the received baseband signal. An echo detection module is used to determine target distance information and target angle information from different coordinates in the change process, based on the second pulse signals before and after different changes in seating posture, using the abrupt change in the amplitude and / or Doppler information of the second pulse signal as a dividing point of the seating posture change. A seated posture detection module is used to obtain seated posture detection results by concatenating the target distance information and the target angle information and inputting them as combined features into an SVM classifier. Here, the combined feature is a one-dimensional matrix formed by concatenating the target distance information and the target angle information. This is a seating posture detection device characterized by having the following features:

8. At least one processor, The system comprises at least one processor and a memory that is communicably connected to it, The memory stores instructions that can be executed by the at least one processor, and the execution of these instructions by the at least one processor enables the at least one processor to perform the seated posture detection method described in any one of claims 1 to 6.

9. A non-temporary computer-readable storage medium in which computer instructions are stored, The computer instruction is a non-temporary computer-readable storage medium characterized by being used to cause a computer to execute the seating posture detection method described in any one of claims 1 to 6.

Images