A method for matching identity and vital signs information based on radar and SARFID

Abstract

This invention provides a method for matching identity and vital sign information based on radar and SARFID, comprising the following steps: acquiring radar signals and SARFID signals; preprocessing the SARFID signals: using tag data readings collected from different moving positions on the reader antenna to locate the tag and obtain the tag position representing the human target's location; data fusion between radar and SARFID, comprising the following steps: Step 1: acquiring radar signals of multiple human targets at different positions using radar to obtain a radar-based multi-target point cloud cluster; Step 2: determining the position of each radar point cloud in the radar-based target point cloud cluster; Step 3: for human targets, calculating the distance between the radar point cloud and the tag position; Step 4: using the DBSCAN algorithm to obtain the radar center point of the human target; obtaining the human target's location fused from radar and RFID data.

Description

Technical Field

[0001] This invention relates to the fields of millimeter-wave radar and RFID technology, and specifically to a method for matching identity and vital signs information based on radar and SARFID. Background Technology

[0002] Radio frequency identification (RFID) and millimeter-wave radar are important components of integrated sensing and communication. Due to their advantages such as portability, comfort, and all-weather operation, RFID and millimeter-wave radar are widely used in fields such as smart homes and smart elderly care to detect the physiological information (breathing and heartbeat) and locate targets.

[0003] Millimeter-wave radar technology can be used to detect important information such as breathing, heartbeat, gestures, and the identities of multiple people. Reference [1] uses millimeter-wave radar to monitor breathing and heartbeat, and proposes a two-dimensional synthetic aperture radar imaging recognition system based on mobile radar for monitoring the vital signs of multiple targets and detecting the target location, which can be used in complex outdoor environments. In Reference [2], a single-input multi-output continuous wave radar system and adaptive digital beamforming technology are used to simultaneously detect the breathing rate of multiple human targets at unknown locations. Generally speaking, in millimeter-wave radar signal processing, mathematical modeling is usually performed on the detected echo data to obtain the target's location and physiological information. If you want to further confirm the identity of the physiological information, you must use a neural network and build a dataset. This is because it is a multi-classification problem. However, most of the references [3] show that as the number of people increases or when facing unknown identities, the performance (accuracy) of the neural network training decreases.

[0004] RFID technology is also used for physiological information detection. Reference [4] proposes an algorithm for sensing human heart rate, which achieves accurate estimation of heart rate variability by constructing an array of tags attached to the chest and a heart rate signal mapping model. However, when using RFID to detect physiological information (breathing and heartbeat), it is necessary to attach the tags to a fixed position on the clothing (chest) because the skin will greatly affect the sensing accuracy of the RFID tags. In other words, when estimating the accuracy of vital signs, in addition to considering the influence of breathing and heartbeat signals on the channel, it is also necessary to consider the type and placement of the tags, which increases uncertainty. Because RFID tags are directional and carry unique identity information, this makes RFID technology easy to classify multiple targets and operate over longer distances, so RFID is more suitable for multi-target positioning. Reference [5] proposes a holographic synthetic aperture (SAR) RFID positioning system with aperture position error compensation, without needing to know the exact trajectory of the synthetic aperture. This makes it possible to detect the location of a target and provide unique identification information, but compared with millimeter-wave radar, the accuracy of using RFID to detect physiological information is affected by the performance of the RFID tag and its placement.

[0005] In summary, to address the above problems, this invention proposes a method for matching identity and vital sign information based on radar and SARFID (Synthetic Aperture Radio Frequency Identification), termed M-VIMS. It combines millimeter-wave radar and RFID, using location information as a link, to achieve matching of the target's physiological and identity information, while maintaining a constant 100% accuracy rate in identity recognition.

[0006] Related literature

[0007] [1]Yan J, Zhang G, Hong H, et al. Phase-Based Human Target 2-DIdentification With a Mobile FMCW Radar Platform [J]. IEEE Transactions onMicrowave Theory and Techniques, 2019, 67(12): 5348–5359.

[0008] [2] Xiong J, Hong H, Zhang H, et al. Multitarget Respiration Detection With Adaptive Digital Beamforming Technique Based on SIMO Radar[J]. IEEE Transactions on Microwave Theory and Techniques, 2020, 68(11): 4814–4824.

[0009] [3] Zhao H, Ma Y, Wang X. MN-UIV: Multimodal Neural Network Enabling User Identity Verification Based on Millimeter Wave Radar[J]. IEEE Internet of Things Journal, 2024, 11(15): 26304–26313.

[0010] [4] Wang C, Xie L, Wang W, et al. Rf-ecg: Heart rate variability assessment based on cots rfid tag array[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2018, 2(2): 1–26.

[0011] [5] Zhao R, Wang D, Zhang Q, et al. PEC: Synthetic Aperture RFID Localization with Aperture Position Error Compensation[C]. In 2019 16th Annual IEEE International Conference on Sensing, Communication, and Networking(SECON), 2019: 1–9.

[0012] [6] Ren W, Hou K Y, Wang G, et al. Multi-person respiration detection method using FMCW millimeter wave radar[J]. Signal Processing, 2021, 37

[0013] (09): 1581-1588.

[0014] [7]

[181] Motroni A,Nepa P,Tripicchio P,et al.A Multi-Antenna SAR-basedmethod for UHF RFID Tag Localization via UGV[C].In 2018IEEE InternationalConference on RFID Technology&Application(RFID-TA),2018:1–6. Summary of the Invention

[0015] The purpose of this invention is to provide a method for matching identity and vital sign information based on radar and SARFID. This method combines radar and RFID, using location information as a link, to match the physiological and identity information of human targets, while maintaining a constant 100% accuracy rate in identity recognition. The technical solution is as follows:

[0016] A method for matching identity and vital sign information based on radar and SARFID includes the following steps:

[0017] Collect radar signals and SARFID signals;

[0018] SARFID signal preprocessing: Using tag data readings collected from different moving positions on the reader antenna to locate the tag and obtain the tag position representing the human target's location;

[0019] Data fusion between radar and SARFID includes the following steps:

[0020] Step 1: Use radar to collect radar signals from multiple human targets at different locations to obtain radar-based multi-target point cloud clusters;

[0021] Step 2: Determine the location of each radar point cloud in the target point cloud cluster based on radar;

[0022] Step 3: For human targets, calculate the distance between the radar point cloud and the tag location;

[0023] Step 4: Use the DBSCAN algorithm to obtain the radar center point of the human target, as follows:

[0024] For the k-th human target, a distance threshold is set, and the distance between each point cloud in the multi-target point cloud cluster measured by radar and the tag position is calculated. The radar point cloud is selected according to the distance threshold. By setting a density reachable radius threshold and a point cloud number threshold, the selected radar point cloud is clustered to obtain the final radar point cloud measured for the k-th target. Based on the obtained final radar point cloud, the radar center point of the k-th human target is calculated.

[0025] Step 5: Based on the radar center point of the kth human target and the tag position of the kth human target obtained by SARFID, obtain the radar and RFID fused human target position of the kth human target.

[0026] Furthermore, the methods for acquiring radar signals and SARFID signals are as follows: the radar and reader antennas start from the same point, the reader moves in a straight line to continuously acquire tag data readings, and obtains SARFID signals; the radar acquires radar signals at different locations; for two consecutive tag data readings, the distance the reader antenna moves is less than one-quarter of the wavelength distance.

[0027] Furthermore, the radar signals are preprocessed to determine the location of the human target obtained from the radar signals and to obtain vital sign information. The method is as follows:

[0028] Step 1: Use Time Division Multiplexing Multiple Input Multiple Target Output (TDM-MIMO) technology to generate intermediate frequency signals for multiple targets, and perform three-dimensional discrete-time Fourier transform on the received intermediate frequency signals;

[0029] Step 2: Remove clutter and determine the location of human targets obtained from radar signals;

[0030] Step 3: Extract the phase waveform of the target human physiological signal;

[0031] Step 4: Decompose the phase waveform of the target human physiological signal into respiratory waveform and heartbeat waveform by variational mode decomposition (VMD); set appropriate frequency ranges according to respiratory frequency and heartbeat frequency, select the modal components of respiratory signal and heartbeat signal, and select the maximum value from the corresponding modal components as the frequency of respiratory and heartbeat.

[0032] Furthermore, clutter is removed using static clutter cancellation methods and two-dimensional constant false alarm rate (2D-CFAR) methods.

[0033] Furthermore, modal components between 0.1-0.5 Hz and 0.9-2 Hz were selected for respiratory and heartbeat signals, respectively.

[0034] Furthermore, the method in step 2 is as follows: For a point cloud cluster consisting of K targets, the total number of radar point clouds is i, and the point cloud cluster of the k-th target is represented as...

[0035] A k ={(x1,y1),(x2,y2),…,(x i ,y i )}

[0036] Let the radar's position relative to the origin be at the s-th data acquisition time.

[0037] B (s) =(x,y)

[0038] Through coordinate system transformation, the point cloud position relative to the origin is...

[0039] Furthermore, the method for step 3 is as follows:

[0040] Let the tag location of the k-th human target measured using SARFID technology be denoted as .

[0041] C=(x k ,y k )

[0042] The distance between the radar point cloud of the k-th human target, as measured by radar, and the tag location is:

[0043] d k =||AC||2.

[0044] Furthermore, in step 4, the distance threshold is half the width of the human body; the threshold for the density radius is the width of the human body; and the threshold for the number of point clouds is in the range of 25-50.

[0045] Furthermore, in step 4, the radar center point of this target is obtained using the following formula, where l is the final total number of radar point clouds:

[0046]

[0047] The beneficial effects of this invention are as follows: The identity and vital sign information matching method based on radar and SARFID proposed in this invention, called M-VIMS, uses location information as a link to match personal identity information with breathing and heartbeat information. It is applicable to multi-target scenarios, ensuring a fixed identity recognition accuracy of 100%. This method avoids the hassle of building datasets and constructing neural networks, and also avoids the impact of tag location and performance. This method filters human targets (removing environmental noise, such as wall reflections), reduces positioning deviation in multi-target scenarios, and reduces physiological signal detection errors. Attached Figure Description

[0048] Figure 1 Overall Flowchart

[0049] Figure 2 Radar signal processing flowchart

[0050] Figure 3 SARFID diagram

[0051] Figure 4 Experimental diagram

[0052] Figure 5 Comparison chart of experimental results for identity recognition accuracy

[0053] Figure 6 Schematic diagram for filtering human targets

[0054] Figure 7 Comparison chart of experimental results for positioning error

[0055] Figure 8 Measurement results of respiration and heart rate Detailed Implementation

[0056] The present invention will now be further described in conjunction with the accompanying drawings and embodiments.

[0057] This invention uses location information as a link to match personal identification information with respiratory and heart rate information. First, multiple-input multiple-output (MIMO) and digital beamforming (DBF) technologies are used to process multi-target radar echo signals, and static clutter cancellation and two-dimensional constant false alarm detection (2D-CFAR) are employed to acquire location information. Based on threshold filtering using 2D-CFAR, point cloud clusters of multiple targets are formed. After obtaining the location information corresponding to multiple targets, variational mode decomposition (VMD) technology is used to obtain physiological signal information (respiration and heart rate). Second, SARFID technology is used to acquire the tag location, i.e., the target's location. Since the RFID tag carries its own identification (ID) information, the ID and the target's location are bound together. Then, to fuse the locations detected by millimeter-wave radar and RFID, the distance between the two locations is calculated, and the radar point cloud is filtered. Density-based noise applied spatial clustering (DBSCAN) is used to distinguish the remaining point cloud corresponding to each target, clustering them, calculating their average value, and obtaining the final location. Finally, using location information as a link, the identification information and physiological signal information are matched one-to-one.

[0058] The identity and vital sign information matching method based on radar and SARFID of the present invention mainly consists of three parts. For example... Figure 1 As shown, (1) radar signal preprocessing. (2) SARFID signal preprocessing. (3) data fusion between radar and SARFID.

[0059] (1) The preprocessing procedure for radar signals is as follows: Figure 2 As shown, it includes the following steps:

[0060] Step 1: To improve the radar's angular resolution and multi-target localization capability, this invention employs Time Division Multiplexing Multiple Input Multiple Target Output (TDM-MIMO) technology to generate intermediate frequency (IF) signals for multiple targets. The received IF signals are then subjected to a three-dimensional discrete-time Fourier transform.

[0061] Step 2: After Fourier transform, clutter is removed using static clutter cancellation and two-dimensional constant false alarm rate (2D-CFAR) detection to determine the location of human targets. Multiple target point clouds, representing the target locations, are formed by determining the detection threshold of 2D-CFAR.

[0062] Step 3: After determining the target location, the phase waveforms of multiple target physiological signals are separated using digital beamforming (DBF), phase unwrapping, and variance determination techniques. Existing technologies already exist in this area; for example, references 1 and 2 both relate to this technology. This embodiment of the invention adopts the scheme provided in reference [6].

[0063] Step 4: Decompose the phase waveform using Variational Mode Decomposition (VMD) to obtain the respiratory and heartbeat waveforms. By setting appropriate parameters, the modal components between 0.1-0.5 Hz and 0.9-2 Hz are used as the respiratory and heartbeat signals, respectively, and the maximum values ​​are selected as the frequencies of respiratory and heartbeat.

[0064] (2) The preprocessing flow of SARFID signals is as follows: Figure 3 As shown, it includes the following steps:

[0065] Step 1: In a line-of-sight path, the distance between the reader antenna and the tag changes as the reader antenna moves along a straight line. Due to phase ambiguity, for two consecutive tag data readings, the distance the reader antenna moves should be less than one-quarter of the wavelength distance.

[0066] Step 2: The tag is located and the target position is obtained by using tag data readings collected from different positions on the reader antenna. The embodiment of the present invention adopts the scheme provided in reference [7].

[0067] (3) Data fusion between radar and SARFID, such as Figure 4 The experiment scenario shown consists of millimeter-wave radar and RFID. It includes the following steps:

[0068] Step 1: Through the above technical steps, a point cloud cluster of multiple targets based on millimeter-wave radar is obtained. Assuming a point cloud cluster consisting of K targets and a point cloud cluster with i points, the point cloud cluster of the k-th target can be represented as...

[0069] A k ={(x1,y1),(x2,y2),…,(x i ,y i )}

[0070] Step 2: The radar and reader antennas start from the same point, and the RFID continuously collects data while moving at a constant speed in a straight line. The millimeter-wave radar collects data three times at three different locations. During the data collection process, duplicate target point clouds will appear. Therefore, the radar position relative to the origin during the s-th data collection is...

[0071] B (s) =(x,y)

[0072] Through coordinate system transformation, relative to the origin, the positions of all point clouds are:

[0073]

[0074] Step 3: Assume the k-th target location measured using SARFID technology is...

[0075] C=(x k ,y k )

[0076] The distance between the target point cloud cluster and the tag location was measured by radar.

[0077] d k =|AC|2

[0078] Step 4: Use the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to obtain the radar center point of each target. The method is as follows: For the k-th target, set a distance threshold, where the distance threshold is half the width of a human body. Calculate the distance between the target point cloud cluster measured by the radar and the tag position, and filter the radar point clouds according to the distance threshold. By setting a density reachable radius threshold and a point cloud number threshold, cluster the filtered radar point clouds to obtain the final radar point cloud. The density reachable radius threshold is the width of a human body, and the point cloud number threshold is within the range of 25-50. Then, based on the obtained final radar point cloud, obtain the radar center point of this target using the following formula, where l is the final total number of radar point clouds:

[0079]

[0080] Step 5: Average the center point of the final radar target point cloud and the position obtained by SARFID to obtain the final target position fused by radar and RFID.

[0081] Experimental results

[0082] To verify the feasibility of the algorithm, an experimental scenario was constructed using millimeter-wave radar and SARFID, such as... Figure 4 As shown. To verify the accuracy of the algorithm, millimeter-wave radar and a contact sensing device (SCG) were used, one for measurement and the other for reference. The millimeter-wave radar and reader antennas started at the same point. The RFID tag was placed in the middle below the human heart and lungs. The millimeter-wave radar acquired the target's position and physiological signals at positions (0, 0), (0.75, 0), and (1.75, 0). The reader antenna collected data from the three tags at equal intervals of 0.02 m and a speed of 0.05 m / s.

[0083] Experimental results

[0084] (1) The accuracy rate of identity recognition is constantly 100%. For example... Figure 5 As shown, this invention compares several commonly used deep learning architectures and verifies the performance of the algorithm. First, the frequencies of physiological signals (respiration and heartbeat) are obtained by preprocessing millimeter-wave radar signals. A dataset consists of data from three targets. Subsequently, Conv1d, BiLSTM, and Encoder networks are trained respectively, using a cross-loss function and 5x cross-validation. Experimental results are shown below. Figure 5 As shown. From Figure 5 As can be seen, the average recognition accuracy of Conv1d, BiLSTM, and Encoder networks for identity information is 84%, 64%, and 98%, respectively. In contrast, because tag location information and tag ID information are bound in RFID technology, the identity recognition rate remains constant at 100%. Compared with the M-VIMS algorithm proposed in this invention, the identity information recognition accuracy of different architectures trained by neural networks is lower and less than ideal. These three factors can be explained as follows: First, as long as identity information recognition is achieved by building a dataset and using a neural network, its recognition accuracy will not remain at 100%. Second, if the identity information of the tested personnel changes, such as in a meeting scenario where the identity information of the test personnel changes daily, the practicality of the neural network and the dataset will be significantly reduced. Third, as the number of people increases, the accuracy of personnel identity information recognition decreases. Conversely, RFID technology itself has an identification number, so it does not face problems such as decreased recognition rate, dataset construction, and neural networks.

[0085] (2) Screening human targets. For example... Figure 6 As shown in (a), noise (such as wall reflections) needs to be filtered out before the positions of the three targets are determined. Figure 6 (b) shows the positioning results from millimeter-wave radar, RFID, and the actual target location. The algorithm proposed in this invention filters out non-human targets.

[0086] (3) Reduce positioning deviation. Since the algorithm in this invention confirms identity information by confirming location, the key to this algorithm lies in whether the locations are consistent, that is, whether the locations measured by millimeter-wave radar and SARFID are the same. The actual locations of the three targets are (0.25, 1.25), (1.25, 1.25) and (2.25, 1.25). The locations of the three targets detected by radar are (0.239, 1.298), (1.21, 1.37) and (2.1, 1.29). The locations of the three targets detected using SARFID are (0.29, 1.2), (1.2, 1.28) and (2.28, 1.21). Compared with the actual locations of the three targets, such as Figure 7 As shown, the deviations between the radar-detected position and the actual position are 0.049m, 0.126m, and 0.155m, respectively, with an average deviation of 0.11m. The deviations between the SARFID-detected position and the actual position are 0.064m, 0.058m, and 0.05m, respectively, with an average deviation of 0.05733m. The center point offset after radar point cloud clustering is greater than that of SARFID technology because the width of a human body is approximately 0.5m. The tags in SARFID technology have uniqueness and directionality, therefore their deviation is relatively smaller compared to radar technology. After averaging the positions obtained from radar and SARFID, three positions are obtained with coordinates (0.2645, 1.249), (1.205, 1.325), and (2.19, 1.25), respectively. The deviation from the actual position is 0.015m, with deviations of 0.087m and 0.06m, respectively, and an average deviation of 0.054m. Compared with radar and SARFID technologies, the algorithm proposed in this invention significantly reduces position deviation.

[0087] (4) Reducing physiological information errors. After determining identity and location information, the next step is to assess the accuracy of extracting physiological signals to achieve a one-to-one correspondence between identity, location, and physiological data. When the target is stationary, the point cloud coverage of each target is approximately 50 cm, indicating that the point cloud is generated not only by breathing and heartbeat but also by other limb movements. The width of the human body is approximately 50 cm, with the heart and lungs located at the center. The diameter of the human chest cavity (which houses the heart and lungs) is typically approximately 25.3 cm. The tag is also placed at the center of the body. Utilizing the directionality of the tag, the location range measured by RFID can limit the radar's detection area and filter out noise from limb movements. In previous experiments, due to positional deviation, only the phase with the highest energy value within the positional deviation range of each frame in the distance-angle map was used for phase unwrapping to determine breathing and heart rate. This method calculates the distance between each point cloud and the RFID tag measurement location, removing any point cloud exceeding this distance. Contact sensors measure actual breathing and heart rate, while the M-VIMS algorithm estimates these rates using heart rate per minute (bpm) as the evaluation metric. The error is calculated as the difference between the actual and estimated values. Figure 8 The results show that the average errors in respiration and heart rate generated by the traditional algorithm are 0.86 bpm and 1.17 bpm, respectively. Here, the traditional algorithm refers to the algorithm that uses only radar detection. In contrast, after applying the M-VIMS algorithm for matching, the average errors in respiration and heart rate decreased to 0.71 bpm and 0.97 bpm, respectively, representing reductions of 0.15 bpm and 0.2 bpm compared to the radar-only method. These findings indicate that the M-VIMS algorithm provides accurate physiological signal detection for multiple targets.

[0088] according to Figure 5 , Figure 7 and Figure 8 The results clearly show that identity, location, and physiological information can be effectively matched. For example, 100% of target 1 has a respiratory rate of 0.275 Hz and a heart rate of 1.1 Hz at locations (0.2645, 1.249). The static information matching for the other two targets is similar.

Claims

1. A method for matching identity and vital sign information based on radar and SARFID, comprising the following steps: Collect radar signals and SARFID signals; SARFID signal preprocessing: Tag data readings collected from different moving positions on the reader antenna are used to locate the tag and obtain the tag position representing the human target's location. The method is as follows: The intermediate frequency signal of multiple targets is generated by using time division multiple multiple input multiple target output (TDM-MIMO) technology, and the received intermediate frequency signal is subjected to three-dimensional discrete-time Fourier transform. Remove clutter to determine the location of human targets obtained from radar signals; Extracting the phase waveform of target physiological signals in humans; The phase waveform of the target human physiological signal is decomposed by variational mode decomposition (VMD) to obtain the respiratory waveform and heartbeat waveform; according to the respiratory frequency and heartbeat frequency, appropriate frequency ranges are set respectively, the modal components of the respiratory signal and heartbeat signal are selected, and the maximum value of the corresponding modal components is selected as the respiratory and heartbeat frequencies; Data fusion between radar and SARFID includes the following steps: Step 1: Use radar to collect radar signals from multiple human targets at different locations to obtain radar-based multi-target point cloud clusters; Step 2: Determine the location of each radar point cloud in the target point cloud cluster based on radar; Step 3: For human targets, calculate the distance between the radar point cloud and the tag location; Step 4: Use the DBSCAN algorithm to obtain the radar center point of the human target, as follows: For the kth human target, a distance threshold is set, and the distance between each point cloud in the multi-target point cloud cluster measured by radar and the tag location is calculated. The radar point cloud is then selected based on the distance threshold. By setting a density reachable radius threshold and a point cloud quantity threshold, the selected radar point clouds are clustered to obtain the final radar point cloud measured for the k-th target; based on the obtained final radar point cloud, the radar center point of the k-th human target is calculated. Step 5: Based on the radar center point of the kth human target and the tag position of the kth human target obtained by SARFID, obtain the radar and RFID fused human target position of the kth human target.

2. The identity and vital sign information matching method according to claim 1, characterized in that, The methods for acquiring radar and SARFID signals are as follows: the radar and reader antennas start from the same point, the reader moves in a straight line to continuously acquire tag data readings, and obtains SARFID signals; the radar acquires radar signals at different locations; for two consecutive tag data readings, the distance the reader antenna moves is less than one-quarter of the wavelength distance.

3. The identity and vital sign information matching method according to claim 1, characterized in that, Clutter was removed using a static clutter cancellation method and a two-dimensional constant false alarm rate (CFAR) detection method.

4. The identity and vital sign information matching method according to claim 3, characterized in that, For respiratory and heartbeat signals, modal components between 0.1-0.5 Hz and 0.9-2 Hz were selected, respectively.

5. The identity and vital sign information matching method according to claim 1, characterized in that, The method in step 2 is as follows: For a point cloud cluster consisting of K targets, the total number of radar point clouds is i, and the point cloud cluster of the k-th target is represented as: ； Let the radar's position relative to the origin be at the s-th data acquisition time. ； Through coordinate system transformation, the point cloud position relative to the origin is... 。 6. The identity and vital sign information matching method according to claim 5, characterized in that, The method for step 3 is as follows: Let the tag location of the k-th human target measured using SARFID technology be denoted as . ； The distance between the radar point cloud of the k-th human target, as measured by radar, and the tag location is: 。 7. The identity and vital sign information matching method according to claim 1, characterized in that, In step 4, the distance threshold is half the width of the human body; the threshold for the density radius is the width of the human body; and the threshold for the number of point clouds is in the range of 25-50.

8. The identity and vital sign information matching method according to claim 7, characterized in that, In step 4, the radar center point of the human target is obtained using the following formula, where l is the final total number of radar point clouds: ； Where l represents the final total number of radar point clouds.

Images