UWB-based sitting posture detection method, device and equipment and storage medium

Abstract

The embodiment of the invention provides a UWB-based sitting posture detection method and device, equipment and a storage medium. The method is applied to the technical field of intelligent analysis and comprises the steps that a UWB signal receiving end receives and amplifies a pulse signal to obtain a first pulse signal, and the phase of the first pulse signal of a corresponding frame is adjusted based on the difference value between the average phase of a reference pulse signal and the phase of any frame of reference pulse signal to obtain a second pulse signal; noise is removed by using a cascade filter, and the signal-to-noise ratio of the received baseband signal is improved, so that a second pulse signal is obtained; suddenly changing the amplitude and / or Doppler information of the second pulse signal as a sign of sitting posture change, and determining target distance and angle information of different sitting postures; and splicing the target distance and angle information as a joint feature, and inputting the joint feature into an SVM classifier to obtain a sitting posture detection result. In this way, accurate position tracking of the target object can be achieved, the sitting posture state of an individual can be monitored in real time, and user privacy is not involved.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent analysis technology, and further to the intersection of the Internet of Things and medical health, and in particular to a sitting posture detection method, device, equipment and storage medium based on UWB. Background Art

[0002] With the accelerated pace of life in modern society, sitting for long periods of time has become a daily habit for many people, especially for the elderly. Long periods of incorrect sitting posture are often accompanied by a variety of health risks, such as spinal problems, muscle fatigue, etc. Therefore, sitting posture detection has become a health monitoring field that has attracted much attention.

[0003] Existing sitting posture detection methods usually rely on devices such as cameras, which are easily interfered by factors such as light and occlusion, causing delays and inaccuracies in sitting posture detection results, and may also involve user privacy issues. Summary of the invention

[0004] The present disclosure provides a UWB-based sitting posture detection method, apparatus, device and storage medium, which solve the technical problems that the sitting posture detection results obtained by the existing sitting posture detection methods are delayed and inaccurate, and also involve user privacy.

[0005] According to the first aspect of the present disclosure, a sitting posture detection method based on UWB is provided. The method comprises: after receiving a pulse signal, a UWB signal receiving end amplifies the pulse signal to obtain a first pulse signal, adjusts 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 any frame reference pulse signal, and uses a cascade filter to remove the noise of the first pulse signal and improve the signal-to-noise ratio of the received baseband signal to obtain a second pulse signal;

[0006] Using the amplitude and / or Doppler information mutation of the second pulse signal as the segmentation point of the sitting posture change, and determining the target distance information and target angle information generated by different sitting postures during the change process according to the second pulse signals before and after the different sitting posture changes;

[0007] The target distance information and the target angle information are spliced ​​together as a joint feature and input into the SVM classifier to obtain a sitting posture detection result; wherein the joint feature is a one-dimensional matrix formed by splicing the target distance information and the target angle information.

[0008] According to the above aspects and any possible implementation manner, there is further provided an implementation manner, wherein the pulse signal comprises a pulse signal reflected back after being sent by a UWB signal transmitter.

[0009] According to the above aspects and any possible implementation, an implementation is further provided, wherein 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 any frame reference pulse signal comprises:

[0010] Select a reflected pulse signal from a static object as a reference pulse signal;

[0011] Calculate the difference between the average phase of any sequence of reference pulse signals and the phase of any frame therein;

[0012] The phase of the first pulse signal of the corresponding frame is adjusted according to the difference.

[0013] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the step of removing the noise of the first pulse signal by using a cascade filter and improving the signal-to-noise ratio of the received baseband signal to obtain the second pulse signal comprises:

[0014] The first pulse signal after phase adjustment is input into the low-pass filter in the cascade filter to remove high-frequency noise, and then input into the smoothing filter in the cascade filter to further smooth the signal to improve the signal-to-noise ratio of the received baseband signal, thereby obtaining a second pulse signal.

[0015] According to the above aspect and any possible implementation manner, an implementation manner is further provided, wherein determining the target distance information includes:

[0016] Determine the value range of the target distance information r according to the resolution and detection range;

[0017] Within the value range, the value of r is traversed with a preset step size, and the actual value of r is determined according to the measured flight time; wherein the flight time is the time taken for the pulse signal to propagate from the UWB signal transmitting end to the target point and then be reflected from the target point back to the UWB signal receiving end;

[0018] Traverse all r values ​​and calculate P(r) using the formula:

[0019] Among them, s n,m is the baseband signal data actually measured;

[0020] The r value at which P(r) is the maximum is determined as the target distance information.

[0021] According to the above aspect and any possible implementation manner, an implementation manner is further provided, wherein determining the target angle information includes:

[0022] Determine the value range of the target angle information θ and φ according to the resolution and detection range; wherein the θ and φ values ​​represent the angles of the signal projected in the horizontal and vertical directions received by the two-dimensional antenna array, respectively;

[0023] Combine each θ value and φ value within the value range, and use the formula to calculate the power value P(r,θ,φ) corresponding to each θ value and φ value combination, and the formula is:

[0024] Where N is the number of antennas at the receiving end, M is the number of antennas at the transmitting end, and s n,m,t is the signal sent by the mth transmitting antenna at time t and received by the nth receiving antenna;

[0025] Determine the θ value and φ value corresponding to the maximum value among all power values ​​P(r,θ,φ) as the target angle information.

[0026] According to a second aspect of the present disclosure, a UWB-based sitting posture detection device is provided. The device includes: a signal processing module, which is used to amplify the pulse signal after the UWB signal receiving end receives the pulse signal to obtain a first pulse signal, adjust 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 any frame reference pulse signal, and use a cascade filter to remove the noise of the first pulse signal and improve the signal-to-noise ratio of the received baseband signal to obtain a second pulse signal;

[0027] The echo detection module is used to use the amplitude of the second pulse signal and / or the sudden change of Doppler information as the segmentation point of the sitting posture change, and determine the target distance information and target angle information generated by different sitting postures during the change process according to the second pulse signals before and after the different sitting posture changes;

[0028] The sitting posture detection module is used to splice the target distance information and the target angle information as a joint feature and input it into the SVM classifier to obtain a sitting posture detection result; wherein the joint feature is a one-dimensional matrix spliced ​​by the target distance information and the target angle information.

[0029] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method of the first aspect and / or the second aspect described above is implemented.

[0030] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method according to the first aspect and / or the second aspect of the present disclosure is implemented.

[0031] In the present disclosure, it is only necessary to receive a pulse signal at the UWB signal receiving end, amplify the pulse signal to obtain a first pulse signal, adjust 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 any frame reference pulse signal, and use a cascade filter to remove the noise of the first pulse signal and improve the signal-to-noise ratio of the received baseband signal to obtain a second pulse signal. When the amplitude and / or Doppler information of the second pulse signal suddenly changes, it is considered that the sitting posture has changed, and the target distance information and target angle information generated by different sitting postures during the change process are determined according to the second pulse signal before and after the different sitting posture changes. The target distance information and target angle information are spliced ​​as joint features and input into the SVM classifier to obtain the sitting posture detection result. The above method can realize accurate position tracking of the target object, real-time monitoring of the individual's sitting posture state, and respond immediately after the sitting posture changes, and promptly remind the user of bad sitting posture. The UWB technology has high-speed data transmission capability and can realize real-time data collection and processing.

[0032] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0034] Figure 1 A flowchart of a sitting posture detection method based on UWB according to an embodiment of the present disclosure is shown;

[0035] Figure 2 A block diagram of a UWB-based sitting posture detection device according to an embodiment of the present disclosure is shown;

[0036] Figure 3 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0038] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0039] In the present disclosure, in order to solve the problem that the existing sitting posture detection method usually relies on equipment such as cameras and is easily interfered by factors such as light and occlusion, resulting in delays and inaccuracies in the sitting posture detection results, and may also involve user privacy issues, a sitting posture detection method based on UWB is proposed, the method comprising: a UWB signal receiving end receives a pulse signal, and amplifies the pulse signal to obtain a first pulse signal, and adjusts 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 any frame reference pulse signal, and uses a cascade filter to remove the noise of the first pulse signal and improve the signal-to-noise ratio of the received baseband signal to obtain a second pulse signal; a sudden change in the amplitude and / or Doppler information of the second pulse signal is used as a segmentation point for sitting posture changes, and the target distance information and target angle information generated by different sitting postures are determined; the target distance information and the target angle information are spliced ​​and input into the SVM classifier as a joint feature to obtain a sitting posture detection result. In this way, accurate position tracking of the target object can be achieved, the individual's sitting posture can be monitored in real time, and an immediate response can be made when the sitting posture changes, reminding the user in time if they have a bad sitting posture without involving user privacy.

[0040] Figure 1 FIG. 1 is a flowchart of a UWB-based sitting posture detection method 100 according to an embodiment of the present disclosure. Figure 1 As shown, the UWB-based sitting posture detection method includes:

[0041] S110, after receiving the pulse signal, the UWB signal receiving end amplifies the pulse signal to obtain a first pulse signal, adjusts 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 any frame reference pulse signal, and uses a cascade filter to remove the noise of the first pulse signal and improve the signal-to-noise ratio of the received baseband signal to obtain a second pulse signal.

[0042] In some embodiments, the pulse signal includes a pulse signal reflected back after being sent by a UWB signal transmitter.

[0043] In some embodiments, a reflected pulse signal of a static object is selected as a reference pulse signal; the difference between the average phase of any sequence of reference pulse signals and the phase of any frame thereof is calculated; and the phase of the first pulse signal of the corresponding frame is adjusted according to the difference.

[0044] In some embodiments, the first pulse signal after phase adjustment is input into a low-pass filter in the cascade filter to remove high-frequency noise, and then input into a smoothing filter in the cascade filter to further smooth the signal to improve the signal-to-noise ratio of the received baseband signal to obtain a second pulse signal.

[0045] In one possible implementation, the cascade filter includes a low-pass filter and a smoothing filter. We first use a finite impulse response (FIR) low-pass filter with 26 taps and a Hamming window. Then use a 5-point window smoothing filter to smooth the output of the FIR low-pass filter.

[0046] In some embodiments, the UWB signal generator generates extremely narrow pulses of nanosecond or microsecond level, which are transmitted in wireless space as information carriers. The time width of these pulses is extremely short, so the spectrum range they occupy is very wide, thus realizing ultra-wideband communication.

[0047] In some embodiments, the correlator is a core component of the UWB signal acquisition system. The first pulse signal is sent to the correlator, and the correlator compares and matches the received first pulse signal with the locally generated reference pulse signal through a correlation algorithm to obtain the delay time of the pulse signal transmission, and determine the distance between the transmitting end and the receiving end, and process and analyze the collected data to extract useful information, such as position, speed, etc.

[0048] In one possible implementation, the UWB is placed somewhere in the room with the antenna facing the detection area for sending and receiving signals. Specifically, the transmitter sends a signal s k (t), can be expressed as: Among them, V tx represents the pulse amplitude, T p Indicates the duration of the signal. represents the standard deviation determined by the -10db bandwidth. After up-conversion, the time domain transmission signal of the kth frame is: x k (t) = s(t-kT s )·cos(2πf c (t-kT s )), where f c is expressed as the carrier frequency, and the operation · is the scalar product, is the duration of the frame, where f p is the pulse repetition frequency, s(t-kT s )=s(t). For simplicity, we record t=t′+kT s ,t′∈[0,T s ], so the transmission signal can be simplified to: x k(t) = s(t)·cos(2πf c t), multipath channel state information (CSI) h k (t) can be expressed as the following formula:

[0049] where α p is the propagation attenuation of the pth reflected path signal, τ p is the time delay caused by the signal propagation process, The time delay caused by large-scale body movements (such as walking, jumping, etc.) The time delay caused by small-scale body movement (such as the ups and downs of a person's chest due to breathing). Therefore, the received signal can be expressed as:

[0050]

[0051] Where n(t) is the variance and operator * is the convolution operation.

[0052] In one possible implementation, the ADC of the UWB signal introduces sampling timing offset (STO) due to an imperfect sampling clock. The disturbance of the signal phase will affect the Doppler and micro-Doppler information of the signal. Doppler and micro-Doppler are obtained by slow-time observation. s Measured. If the reflection is from a static object, the phase introduced by 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 amplitude of the two frames should be the same. For the present invention, static objects can be considered to be moving due to the presence of phase noise.

[0053] The phase of the object with jitter is Ω p +Δω(t-kT s ). The phase jitter caused by STO at the radio receiver is Δω(t-kT s ), the phase of the reflected signal from the object is Ω p Our goal is to reduce the phase jitter Δω(t-kT s ).

[0054] In one possible implementation, since the UWB is mounted on the ceiling, the maximum peak of the reflection is always at the floor where the radar cross section (RCS) is the largest. Therefore, one can easily identify this reflection from the reflections of other static objects to correct the phase. Since the change in phase is very small, it will hardly affect the inference results of our neural network due to the large movements of human activities. However, this change will make the training phase unstable, resulting in a long convergence time. The original received baseband signal is corrupted by noise, which will introduce errors to the neural network model. If not handled properly, the random noise will be learned by the neural network model and tend to overfit. Therefore, we utilize cascade filters to remove noise and improve the signal-to-noise ratio of the received baseband signal.

[0055] S120, using the amplitude of the second pulse signal and / or the sudden change of Doppler information as the segmentation point of the sitting posture change, and determining the target distance information and target angle information generated by different sitting postures during the change process according to the second pulse signals before and after the different sitting posture changes.

[0056] In some embodiments, determining the target distance information includes: determining a value range of the target distance information r according to the resolution and the detection range; traversing the value of r within the value range with a preset step size, and determining the actual r value according to the measured flight time; wherein the flight time is the time taken for the pulse signal to propagate from the UWB signal transmitting end to the target point and then be reflected from the target point back to the UWB signal receiving end; traversing all r values, and calculating P(r) using the formula, the formula is: Among them, s n,m is the baseband signal data actually measured; the r value at the maximum of P(r) is determined as the target distance information.

[0057] In some embodiments, determining the target angle information includes: determining a value range of a θ value and a φ value of the target angle information according to a resolution and a detection range; wherein the θ value and the φ value represent the angles of the projection of the signal received by the two-dimensional antenna array in the horizontal and vertical directions, respectively; combining each θ value and φ value within the value range, and calculating a power value P(r,θ,φ) corresponding to each combination of the θ value and the φ value using a formula, wherein the formula is:

[0058] Where N is the number of antennas at the receiving end, M is the number of antennas at the transmitting end, and s n,m,t It is the signal sent by the mth transmitting antenna at time t and received by the nth receiving antenna; the θ value and φ value corresponding to the maximum value of all power values ​​P(r,θ,φ) are determined as the target angle information.

[0059] S130, splicing the target distance information and the target angle information as a joint feature and inputting it into the SVM classifier to obtain a sitting posture detection result; wherein the joint feature is a one-dimensional matrix spliced ​​by the target distance information and the target angle information.

[0060] In some embodiments, five sitting postures, namely normal sitting posture, left leaning, right leaning, forward leaning, and backward leaning, can be distinguished according to the distance angle characteristics.

[0061] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0062] The above is an introduction to the method embodiment. The following is a further explanation of the scheme disclosed in the present invention through an apparatus embodiment.

[0063] Figure 2 FIG. 2 shows a block diagram of a UWB-based sitting posture detection device 200 according to an embodiment of the present disclosure. Figure 2 As shown, the device 200 includes:

[0064] The signal processing module 210 is used for amplifying the pulse signal after the UWB signal receiving end receives the pulse signal to obtain a first 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 any frame reference pulse signal, and using a cascade filter to remove noise from the first pulse signal and improve the signal-to-noise ratio of the received baseband signal to obtain a second pulse signal;

[0065] The echo detection module 220 is used to use the amplitude of the second pulse signal and / or the sudden change of Doppler information as the segmentation point of the sitting posture change, and determine the target distance information and target angle information generated by different sitting postures during the change process according to the second pulse signals before and after the different sitting posture changes;

[0066] The sitting posture detection module 230 is used to splice the target distance information and the target angle information as a joint feature and input it into the SVM classifier to obtain a sitting posture detection result; wherein the joint feature is a one-dimensional matrix spliced ​​by the target distance information and the target angle information.

[0067] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0068] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0069] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0070] Figure 3 A schematic block diagram of an electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. 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 suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0071] The electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a ROM 302 or a computer program loaded from a storage unit 308 into a RAM 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An I / O interface 305 is also connected to the bus 304.

[0072] A number of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0073] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as method 100. For example, in some embodiments, the method 100 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the method 100 in any other appropriate manner (e.g., by means of firmware).

[0074] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0075] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0076] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0077] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0078] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0079] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0080] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0081] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A sitting posture detection method based on UWB, characterized in that: include: After receiving the pulse signal, the UWB signal receiving end amplifies the pulse signal to obtain a first pulse signal, adjusts 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 any frame reference pulse signal, and uses a cascade filter to remove noise from the first pulse signal and improve the signal-to-noise ratio of the received baseband signal to obtain a second pulse signal; Using the amplitude and / or Doppler information mutation of the second pulse signal as the segmentation point of the sitting posture change, and determining the target distance information and target angle information generated by different sitting postures during the change process according to the second pulse signals before and after the different sitting posture changes; The target distance information and the target angle information are spliced ​​together as a joint feature and input into the SVM classifier to obtain a sitting posture detection result; wherein the joint feature is a one-dimensional matrix formed by splicing the target distance information and the target angle information.

2. The method according to claim 1, characterized in that The pulse signal includes a pulse signal that is sent by the UWB signal transmitter and then reflected by the target point.

3. The method according to claim 1, characterized in that The step of 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 any frame reference pulse signal comprises: Select a reflected pulse signal from a static object as a reference pulse signal; Calculate the difference between the average phase of any sequence of reference pulse signals and the phase of any frame therein; The phase of the first pulse signal of the corresponding frame is adjusted according to the difference.

4. The method according to claim 1, characterized in that: The step of removing noise from the first pulse signal by using a cascade filter and improving the signal-to-noise ratio of the received baseband signal to obtain a second pulse signal comprises: The first pulse signal after phase adjustment is input into the low-pass filter in the cascade filter to remove high-frequency noise, and then input into the smoothing filter in the cascade filter to further smooth the signal to improve the signal-to-noise ratio of the received baseband signal, thereby obtaining a second pulse signal.

5. The method according to claim 1, characterized in that The determining target distance information includes: Determine the value range of the target distance information r according to the resolution and detection range; Within the value range, the value of r is traversed with a preset step size, and the actual value of r is determined according to the measured flight time; wherein the flight time is the time taken for the pulse signal to propagate from the UWB signal transmitting end to the target point and then be reflected from the target point back to the UWB signal receiving end; Traverse all r values ​​and calculate P(r) using the formula: Among them, s n,m is the baseband signal data actually measured; The r value at which P(r) is the maximum is determined as the target distance information.

6. The method according to claim 1, characterized in that Determining the target angle information includes: Determine the value range of the target angle information θ and φ according to the resolution and detection range; wherein the θ and φ values ​​represent the angles of the signal projected in the horizontal and vertical directions received by the two-dimensional antenna array, respectively; Combine each θ value and φ value within the value range, and use the formula to calculate the power value P(r,θ,φ) corresponding to each θ value and φ value combination, and the formula is: Where N is the number of antennas at the receiving end, M is the number of antennas at the transmitting end, and s n,m,t is the signal sent by the mth transmitting antenna at time t and received by the nth receiving antenna; Determine the θ value and φ value corresponding to the maximum value among all power values ​​P(r,θ,φ) as the target angle information.

7. A sitting posture detection device based on UWB, comprising: A signal processing module, which is used for amplifying the pulse signal after the UWB signal receiving end receives the pulse signal to obtain a first 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 any frame reference pulse signal, and using a cascade filter to remove noise from the first pulse signal and improve the signal-to-noise ratio of the received baseband signal to obtain a second pulse signal; an echo detection module, for using the amplitude of the second pulse signal and / or the sudden change of Doppler information as a segmentation point for sitting posture change, and determining target distance information and target angle information generated by different sitting postures during the change process according to the second pulse signals before and after the different sitting posture changes; The sitting posture detection module is used to splice the target distance information and the target angle information as a joint feature and input it into the SVM classifier to obtain a sitting posture detection result; wherein the joint feature is a one-dimensional matrix spliced ​​by the target distance information and the target angle information.

8. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 6.

Images