Through-wall gait recognition system building method based on transmission RIS and through-wall gait recognition method

Abstract

The invention belongs to the technical field of through-wall gait recognition, and particularly relates to a through-wall gait recognition system building method based on transmission RIS and a through-wall gait recognition method, and the method comprises the steps: respectively arranging an electromagnetic wave transmitter and a receiver in the spatial positions of the two sides of a target wall; the transmission RISs are sequentially arranged at different positions of the wall surface of one side where the receiver is located, and after each time of setting, the optimal codebook of the transmission RISs is obtained by taking the received channel state information with the strongest strength as a target; setting a transmission RIS according to the RIS setting position and the optimal codebook corresponding to the strongest channel state information in multiple settings; wherein the transmitter is used for transmitting an electromagnetic wave signal to a space, and the receiver is used for receiving channel state information modulated by the transmission RIS and used for gait recognition; a through-wall gait recognition system is formed by a transmitter, a receiver, a transmission RIS and a controller of the transmission RIS. The method is low in cost and high in through-wall gait recognition accuracy in a difference signal scene.

Description

Technical Field

[0001] The present invention belongs to the technical field of through-wall gait recognition, and more specifically, relates to a through-wall gait recognition system construction method based on transmission RIS and a through-wall gait recognition method. Background Art

[0002] Through-the-wall gait recognition can monitor indoor people in real time without infringing personal privacy, and promptly detect and warn of potential security threats, such as illegal intrusions and violent acts. This is of great significance for protecting personal and social security. For example, compared with traditional video surveillance, through-the-wall gait recognition technology can penetrate walls for detection, avoiding the camera from directly shooting indoor scenes, thus protecting personal privacy to a certain extent; in the medical field, through-the-wall gait recognition technology can be used to monitor the walking status of the elderly, promptly detect gait abnormalities, and provide important basis for medical diagnosis and treatment; when disasters such as earthquakes and fires occur, through-the-wall gait recognition technology can help rescuers quickly locate trapped people and improve rescue efficiency.

[0003] At present, the technology of through-wall gait recognition mainly relies on through-wall radar and advanced signal processing algorithms. Through-wall radar uses low-frequency ultra-wideband electromagnetic waves to penetrate the walls of buildings and detect people indoors. By extracting the micro-Doppler characteristics of human motion and using implicit information such as human motion speed and acceleration, human gait recognition can be achieved. However, the existing through-wall gait recognition methods are obviously very expensive due to the use of radar and advanced signal processing algorithms. In addition, there are the following problems: (1) Limited recognition accuracy: Due to the attenuation and scattering of electromagnetic waves by walls, the signals received by through-wall radars are often weak and fuzzy, resulting in limited gait feature extraction and recognition accuracy; (2) High algorithm complexity: In order to extract effective gait features from through-wall radar echoes, it is necessary to adopt complex signal processing algorithms, such as multi-layer mixed dynamic probability maps, fast multi-scale intelligent identification methods, etc. These algorithms have high computational complexity and high performance requirements for hardware equipment; (3) Large environmental interference: Through-wall gait recognition technology is easily affected by indoor environmental factors, such as wall material, thickness, indoor layout, etc. These factors will cause the propagation path and attenuation degree of electromagnetic waves to change, thereby affecting the accuracy of gait recognition.

[0004] Therefore, there is an urgent need for a high-precision alternative method with low economic and energy costs to improve the accuracy of gait recognition in closed scenes such as long corridors at low cost. Summary of the invention

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a method for building a through-wall gait recognition system based on transmission RIS and a through-wall gait recognition method, the purpose of which is to propose a method with low cost and high accuracy in through-wall gait recognition in a difference signal scenario.

[0006] To achieve the above object, according to one aspect of the present invention, a method for building a through-wall gait recognition system based on transmission RIS is provided, comprising:

[0007] An electromagnetic wave transmitter and a receiver are respectively arranged in the spatial positions on both sides of the target wall;

[0008] The transmission RIS is sequentially set at different positions on the wall on the side where the receiver is located, and after each setting, the optimal codebook of the transmission RIS is optimized with the strongest intensity of the received channel state information as the goal; the transmission RIS is set according to the RIS setting position corresponding to the strongest channel state information in multiple settings, and a controller is configured for the transmission RIS so that it can control the phase state of the transmission RIS according to the optimal codebook corresponding to the RIS setting position;

[0009] Among them, the transmitter is used to transmit electromagnetic wave signals into space, and the receiver is used to receive channel state information for gait recognition after modulation from the transmitted RIS; the set transmitter, receiver, transmitted RIS and its controller constitute the through-wall gait recognition system, and the construction is completed.

[0010] Furthermore, the transmission RIS is a 1-bit transmission RIS.

[0011] Furthermore, after each setting, the method for obtaining the optimal codebook of the transmission RIS is:

[0012] Initialize variables, including: codebook Φ, maximum received signal strength s max , column number col, row number row, current codebook Φ current ;

[0013] Traverse multiple rounds, and the number of traversals in each round i ranges from 1 to n+m, where n represents the number of rows of the transmitted RIS and m represents the number of columns of the transmitted RIS. When i≤16, col=col+1, otherwise, row=row+1. Use the greedy algorithm to perform flip operations row by row and column by column to obtain the next generation optimized codebook Φ next ; Among them, each time traversal, Φ current =Φ next , and obtain the current received channel state information strength s current , if s current >s max , then s max =s current ,Φ=Φ current , the codebook Φcurrent Assigned to the transmissive RIS.

[0014] Furthermore, the wall-walking gait recognition system further includes a gait recognition model, which is constructed in the following manner:

[0015] The receiver collects channel state information corresponding to different volunteer gaits, constructs a training sample set, and trains to obtain a gait recognition model, wherein each training sample includes a volunteer label.

[0016] Furthermore, the construction method of each training sample is:

[0017] Performing preprocessing operations on the channel state information including sliding average filtering denoising and data format conversion;

[0018] Perform feature extraction on the preprocessed channel state information to obtain a key information vector;

[0019] Feature selection and dimensionality reduction operations are performed on the key information vector to obtain a low-dimensional feature vector. The low-dimensional feature vector and the corresponding volunteer label constitute a training sample.

[0020] According to another aspect of the present invention, a method for wall-penetrating gait recognition based on transmission RIS is provided, comprising:

[0021] A through-the-wall gait recognition system based on the target wall collects channel state information, wherein the through-the-wall gait recognition system of the target space is constructed by the through-the-wall gait recognition system construction method based on the transmission RIS as described above;

[0022] Gait recognition is achieved based on channel state information.

[0023] Furthermore, gait recognition is realized based on a through-wall gait recognition system of a target wall, wherein the through-wall gait recognition system of a target space is constructed by a through-wall gait recognition system construction method based on a transmission RIS as described above.

[0024] In general, compared with the prior art, the above technical solution conceived by the present invention has the following beneficial effects:

[0025] 1. The present invention proposes a method for building a through-wall gait recognition system based on a transmissive intelligent metasurface (RIS) for poor signal scenarios (i.e., low signal-to-noise ratio scenarios). The active regulation characteristics of RIS on electromagnetic waves are used to improve the strength of the received signal, thereby improving the signal-to-noise ratio. During the construction process, the setting position of the transmissive RIS on the wall is optimized to maximize the received signal strength. The method of the present invention can achieve exponential enhancement of the received signal power and enhancement of the gait recognition accuracy in such scenarios without changing the existing perception network hardware structure. It can be mainly used for gait recognition in closed and low signal-to-noise ratio scenarios such as through-walls and laboratories, and accurate gait recognition in target scenarios can be achieved.

[0026] 2. Based on the system constructed based on electromagnetic waves and transmission RIS, the present invention further proposes to use a neural network that is lighter than the existing signal processing algorithm for signal processing, which has low cost and low computational complexity. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a schematic diagram of the structure of a wall-walking gait recognition system provided by an embodiment of the present invention;

[0028] Figure 2 is a schematic diagram of a wall-walking gait recognition system provided by an embodiment of the present invention;

[0029] Figure 3 It is a schematic diagram of a transmissive RIS and its controller provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0031] Embodiment 1

[0032] A method for building a through-wall gait recognition system based on transmission RIS, comprising:

[0033] An electromagnetic wave transmitter and a receiver are respectively set in the spatial positions on both sides of the target wall; the transmissive RIS is sequentially set at different positions on the wall on the side where the receiver is located, and after each setting, the optimal codebook of the transmissive RIS is optimized with the strongest intensity of the received channel state information as the goal; the transmissive RIS is set according to the RIS setting position corresponding to the strongest channel state information in multiple settings, and a controller is configured for the transmissive RIS so that it can control the phase state of the transmissive RIS according to the optimal codebook corresponding to the RIS setting position; wherein the transmitter is used to transmit electromagnetic wave signals to space, and the receiver is used to receive the channel state information modulated from the transmissive RIS for gait recognition; the set transmitter, receiver, transmissive RIS and its controller constitute a through-wall gait recognition system, such as Figure 1 As shown, the construction is completed.

[0034] With the advent of the information age, electromagnetic wave transmission technology has greatly improved the speed and quality of communication. However, in closed spaces such as through walls and laboratories with low signal-to-noise ratio, wireless signals suffer severe attenuation when passing through solid reinforced concrete structures, resulting in extremely poor quality of received signals, which seriously affects the accuracy of gait recognition.

[0035] Reconfigurable Intelligent Surface (RIS) is a cutting-edge 6G technology that represents an innovative electromagnetic surface solution. This artificially constructed electromagnetic surface is composed of many carefully designed electromagnetic units and has programmable electromagnetic properties. By finely controlling the phase state of each unit, the reconfigurable RIS can actively regulate the amplitude, phase, polarization, and frequency of electromagnetic waves in space, thereby achieving active manipulation of electromagnetic waves in space.

[0036] Current technology is insufficient in dealing with the challenges of gait recognition in low signal-to-noise ratio scenarios such as through walls and laboratories, and the application of RIS technology makes it possible to achieve this goal. This embodiment proposes a method for building a through-wall gait recognition system based on a transmissive reconfigurable intelligent surface (RIS). This method utilizes the active control characteristics of electromagnetic waves of RIS to enhance the transmission effect of through-wall signals while reducing the interference of environmental noise, significantly improving the signal strength and gait recognition accuracy in these traditional signal attenuation environments. In addition, this method can be seamlessly integrated into the existing perception network without making any changes to the existing hardware equipment, and has a low construction cost. This technology not only has broad application potential in current low signal-to-noise ratio scenarios, but also provides new solutions for future perception scenarios.

[0037] From the perspective of technical principles, the transmissive RIS can achieve precise control of the wall-penetrating signal by adjusting the electromagnetic characteristics of its surface unit. This control capability not only improves the transmission efficiency of the signal, but also enables the signal to better maintain its original characteristic information during the wall-penetrating process, thus ensuring the recognition accuracy. Subsequently, by combining advanced signal processing and deep learning algorithms, effective gait features can be extracted from the wall-penetrating signal.

[0038] The method of this embodiment can also optimize wireless communication performance: in a wireless communication system, the transmission RIS can be used to enhance the signal transmission effect, improve the communication quality and coverage. Especially in complex environments (such as inside buildings, tunnels, etc.), the transmission RIS can significantly improve the performance of the wireless communication system. Therefore, the method of this embodiment can also optimize the propagation path and energy distribution of electromagnetic waves by adjusting the surface unit configuration of RIS, thereby improving signal transmission efficiency and coverage. The transmission RIS can flexibly regulate the propagation path and energy distribution of electromagnetic waves, so that the signal can be better propagated and received in a complex environment, thereby improving communication quality and coverage.

[0039] For specific implementation, please refer to Figure 2 , use computer to control USRP, and use USRP to control the transmission and reception of signals by the transmitter and receiver.

[0040] As a preferred implementation, the transmission RIS is a 1-bit transmission RIS, where 1 bit indicates that the phase of each unit has two states. Figure 3 shown.

[0041] Regarding specific parameters, the transmissive RIS used in this embodiment is 28.8×28.8×0.3 cm and includes a two-dimensional electrically controllable RIS element array. The structure of the array contains 16 RIS elements in each row and column, for a total of 256 elements. Each RIS element is 1.8×1.8×0.3 cm and includes four copper layers supported by three substrate layers. It includes two PIN diodes for state modulation: in the 0 state, PIN diode #1 is off and PIN diode #2 is on; for the 1 state, this configuration is reversed, PIN diode #1 is on, and PIN diode #2 is off. This binary setting can dynamically control the electromagnetic behavior of the RIS and achieve precise wave control. It should be noted that this is only an example, and the method of this embodiment is not limited to this type of RIS.

[0042] As a preferred implementation, after each setting, the method for obtaining the optimal codebook of the transmission RIS is:

[0043] Initialize variables, including: codebook Φ, maximum received signal strength s max, column number col, row number row, current codebook Φ current ;

[0044] Traverse multiple rounds, and the number of traversals in each round i ranges from 1 to n+m, where n represents the number of rows of the transmitted RIS and m represents the number of columns of the transmitted RIS. When i≤16, col=col+1, otherwise, row=row+1. Use the greedy algorithm to perform flip operations row by row and column by column to obtain the next generation optimized codebook Φ next ; Among them, each time traversal, Φ current =Φ next , and obtain the current received channel state information strength s current , if s current >s max , then s max =s current , Φ=Φ current , the codebook Φ current Assigned to the transmissive RIS.

[0045] In order to illustrate the optimization process of RIS configuration (i.e., codebook), the model of the received signal can be described in detail as follows: y = hΦHx + w, where x represents the transmission signal (transmitted signal), Φ represents the phase shift matrix (i.e., codebook) implemented on the transmission RIS, and w represents zero-mean additive white Gaussian noise with variance σ 2 The matrices H and h represent the channel matrices from the transmitter to the transmitted RIS and from the transmitted RIS to the receiver, respectively.

[0046] The signal-to-noise ratio is Definition,The optimization problem can be expressed as:

[0047]

[0048] In the formula, |φ n | represents the phase shift modulus value of RIS unit n, and N represents the total number of RIS units in the transmission RIS.

[0049] Using the greedy algorithm, the local (i.e. current) optimal codebook configuration is iteratively obtained to gradually enhance the received signal strength. This process is called the configuration alternation optimization algorithm.

[0050] When the method of this embodiment is specifically applied, firstly, simulation optimization is performed according to the application scenario type and the site size to determine the position of the RIS board; the transmission RIS is connected to the computer, the code book of the transmission RIS is controlled by matlab, and the optimal code book of the RIS is obtained by the traversal algorithm, so as to complete the control of the beam direction of the transmission RIS board to enhance the perception ability; after the system is built, the transmission RIS will enhance the signal-to-noise ratio, and the system obtains the channel state information (received signal) to achieve accurate gait recognition.

[0051] As a preferred implementation, the wall-walking gait recognition system further includes a gait recognition model, which is constructed in the following manner:

[0052] The channel state information corresponding to the gaits of different volunteers is collected through the receiver, a training sample set is constructed, and a gait recognition model is obtained through training, wherein each training sample includes a volunteer label.

[0053] The construction method of each training sample is:

[0054] Performing preprocessing operations on the channel state information including sliding average filtering denoising and data format conversion;

[0055] Perform feature extraction on the preprocessed channel state information to obtain a key information vector;

[0056] Feature selection and dimensionality reduction operations are performed on the key information vector to obtain a low-dimensional feature vector. The low-dimensional feature vector and the corresponding volunteer label constitute a training sample.

[0057] The channel state information can be the amplitude information or phase information of the electromagnetic signal, which exists in the form of a numerical matrix with a dimension of 250 (time) * 8192 (space). First, feature extraction is performed on the preprocessed CSI data to obtain a data vector to capture the key information corresponding to the corresponding gait pattern. Then, the data vector is subjected to feature selection and dimensionality reduction operations to reduce the data dimension and retain the most relevant features.

[0058] In general, this embodiment uses an algorithm to calculate the codebook configuration of the transmission RIS to optimize the signal-to-noise ratio. In particular, in low signal-to-noise ratio environments, such as closed laboratories, an efficient network architecture is designed and deployed to ensure accurate recognition. Regarding data collection and preprocessing, the CSI data of the gait patterns of different volunteers are collected using the transmitter and receiver in the CSI monitoring environment, and preprocessed, including denoising and data format conversion, to prepare high-quality data sets for subsequent processing. Regarding non-invasive gait recognition, non-invasive gait recognition is achieved using CSI data to avoid interference with the identified individual and improve the naturalness and accuracy of recognition. Regarding recognition capabilities in complex scenarios, by extracting gait features from CSI data, the recognition capabilities in complex scenarios are enhanced, such as closed spaces, low signal-to-noise ratio environments, etc. Regarding gait recognition model training and optimization, by training and optimizing the neural network model, the accuracy and generalization of gait recognition are improved to ensure recognition performance in different individuals and environments. Regarding parameter adjustment and structure optimization, the model performance is evaluated based on the recognition results, and parameter adjustment and neural network structure optimization are performed to achieve accurate recognition of complex gait patterns.

[0059] Embodiment 2

[0060] A through-the-wall gait recognition method based on transmission RIS, comprising:

[0061] A through-the-wall gait recognition system based on the target wall collects channel state information, wherein the through-the-wall gait recognition system of the target space is constructed by the through-the-wall gait recognition system construction method based on the transmission RIS as described above;

[0062] Gait recognition is achieved based on channel state information.

[0063] As a preferred implementation, a through-wall gait recognition system based on a target wall can be used to realize gait recognition, wherein the through-wall gait recognition system of the target space is constructed by a through-wall gait recognition system construction method based on transmission RIS as described above.

[0064] The relevant technical solutions are the same as above and will not be described again here.

[0065] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for building a through-the-wall gait recognition system based on transmissive RIS, comprising: An electromagnetic wave transmitter and a receiver are respectively arranged in the spatial positions on both sides of the target wall; The transmission RIS is sequentially set at different positions on the wall on the side where the receiver is located, and after each setting, the optimal codebook of the transmission RIS is optimized with the strongest intensity of the received channel state information as the goal; the transmission RIS is set according to the RIS setting position corresponding to the strongest channel state information in multiple settings, and a controller is configured for the transmission RIS so that it can control the phase state of the transmission RIS according to the optimal codebook corresponding to the RIS setting position; Among them, the transmitter is used to transmit electromagnetic wave signals into space, and the receiver is used to receive channel state information for gait recognition after modulation from the transmitted RIS; the set transmitter, receiver, transmitted RIS and its controller constitute the through-wall gait recognition system, and the construction is completed.

2. The method for building a wall-crossing gait recognition system according to claim 1, characterized in that: The transmission RIS is a 1-bit transmission RIS.

3. The method for building a wall-crossing gait recognition system according to claim 2, characterized in that: After each setting, the optimal codebook of the transmission RIS is obtained as follows: Initialize variables, including: codebook Φ, maximum received signal strength s max , column number col, row number row, current codebook Φ current ; Traverse multiple rounds, and the number of traversals in each round i ranges from 1 to n+m, where n represents the number of rows of the transmitted RIS and m represents the number of columns of the transmitted RIS. When i≤16, col=col+1, otherwise, row=row+1. Use the greedy algorithm to perform flip operations row by row and column by column to obtain the next generation optimized codebook Φ next ; Among them, each time traversal, Φ current =Φ next , and obtain the current received channel state information strength s current , if s current >s max , then s max =s current ,Φ=Φ current , the codebook Φ current Assigned to the transmissive RIS.

4. The method for building a wall-walking gait recognition system according to claim 1, characterized in that: The wall-walking gait recognition system further includes a gait recognition model, which is constructed in the following manner: The receiver collects channel state information corresponding to different volunteer gaits, constructs a training sample set, and trains to obtain a gait recognition model, wherein each training sample includes a volunteer label.

5. The method for building a wall-crossing gait recognition system according to claim 4, characterized in that: The construction method of each training sample is: Performing preprocessing operations on the channel state information including sliding average filtering denoising and data format conversion; Perform feature extraction on the preprocessed channel state information to obtain a key information vector; Feature selection and dimensionality reduction operations are performed on the key information vector to obtain a low-dimensional feature vector. The low-dimensional feature vector and the corresponding volunteer label constitute a training sample.

6. A method for wall-penetrating gait recognition based on transmission RIS, characterized in that: include: A through-the-wall gait recognition system based on a target wall collects channel state information, wherein the through-the-wall gait recognition system of the target space is constructed by a through-the-wall gait recognition system construction method based on a transmission RIS as claimed in any one of claims 1 to 3; Gait recognition is achieved based on channel state information.

7. The wall-walking gait recognition method according to claim 6, characterized in that: A through-the-wall gait recognition system based on a target wall realizes gait recognition, wherein the through-the-wall gait recognition system of the target space is constructed by a through-the-wall gait recognition system construction method based on a transmission RIS as described in claim 4 or 5.

Images