Subway turnstile non-inductive passing system and method

Abstract

The invention relates to a subway turnstile non-inductive passing system and method, and belongs to the technical field of the Internet of Things, and the system comprises a client which is used for broadcasting an anonymous equipment identifier and reporting a target fingerprint to a turnstile end; the gate end is used for scanning and receiving the anonymous equipment identifier, and awakening a sensing system corresponding to the gate end under the condition that the distance between the client and the Bluetooth beacon is determined to be within a preset distance range based on the signal strength of the client and the Bluetooth beacon, and fusing the physical entity point cloud track generated by the millimeter wave radar and the Bluetooth positioning track of the anonymous device identifier, determining a target physical entity corresponding to the Bluetooth identity, and sending a gate opening instruction to the cloud under the condition of determining that the target physical entity meets a gate opening condition, and the cloud end is used for executing a gate opening operation and a charging operation under the condition that the gate opening instruction is received. According to the system, non-inductive passing is realized, the user does not need any operation, the passing speed is increased, and the problem of queuing congestion is avoided.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of Internet of Things, and particularly relates to a subway gate non-inductive passing system and method. BACKGROUND

[0002] As the backbone system of urban public transportation, the passing efficiency and user experience of subway directly affect the operation efficiency of the city. The traditional ticket passing mode, such as physical ticket card, two-dimensional code scanning, etc., all need passengers to actively complete card swiping, code scanning or face recognition operation, which is easy to form a bottleneck at the entrance and exit in peak period, reduces the passing efficiency, and cannot completely realize the non-inductive convenient experience. Therefore, how to better realize the non-inductive passing of subway gate becomes a problem to be solved. SUMMARY

[0003] In view of the deficiencies of the prior art, the purpose of the application is to provide a subway gate non-inductive passing system and method. The system realizes non-inductive passing, the user does not need any operation, improves the passing speed, and avoids the problem of queuing congestion.

[0004] In the first aspect of the application, a subway gate non-inductive passing system is provided, which comprises: a client, configured to broadcast an anonymous device identifier, simultaneously scan a Bluetooth beacon around the client, determine a target fingerprint according to the signal strength of the client and the Bluetooth beacon, and report the target fingerprint to a gate end; the gate end is configured to scan and receive the anonymous device identifier, determine the distance between the client and the Bluetooth beacon based on the signal strength of the client and the Bluetooth beacon, wake up the corresponding perception system of the gate end in the case that the distance between the client and the Bluetooth beacon is within a preset distance range, fuse the physical entity point cloud track generated by the millimeter wave radar and the Bluetooth positioning track of the anonymous device identifier, determine the target physical entity corresponding to the Bluetooth identity, and in the case that the target physical entity meets the gate opening condition, send a gate opening instruction to a cloud end; the cloud end is configured to execute a gate opening operation and a billing operation in the case that the gate opening instruction is received.

[0005] Further, the client is further configured to bind the anonymous device identifier and the user account corresponding to the client, and send the binding relationship to the cloud end, so that the cloud end stores the binding relationship.

[0006] Further, in the case that the gate machine end receives the anonymous device identifier, the anonymous device identifier is legally verified; wherein, the physical entity point cloud track is generated based on the millimeter wave radar, including: the millimeter wave radar emits high frequency electromagnetic wave signals and receives reflected echo signals; the distance, speed and angle of the physical entity are calculated based on the high frequency electromagnetic wave signals and the reflected echo signals; the physical entity point cloud track is determined based on the distance, speed and angle of the physical entity; wherein, the Bluetooth positioning track of the anonymous device identifier is determined, including: matching the target fingerprint with a preset fingerprint library to obtain an estimated position corresponding to the target fingerprint, wherein the preset fingerprint library includes a plurality of target fingerprints and the estimated positions corresponding to the target fingerprints; obtaining the estimated positions at continuous time points, wherein each time point corresponds to an estimated position; smoothing the estimated positions at continuous time points based on a time sequence filtering algorithm to generate a time sequence based Bluetooth positioning track, and taking the time sequence based Bluetooth positioning track as the Bluetooth positioning track of the anonymous device identifier.

[0007] Further, the physical entity point cloud track generated by the millimeter wave radar and the Bluetooth positioning track of the anonymous device identifier are fused to determine the target physical entity corresponding to the Bluetooth identity, including: obtaining a first track of the physical entity point cloud track and a second track of the Bluetooth positioning track in a plurality of sliding time windows; determining the similarity of the first track and the second track; in the case that the similarities of a plurality of sliding time windows are all greater than a similarity threshold, obtaining the target physical entity matched with the Bluetooth identity; wherein, the similarity of the first track and the second track is determined, including: in the case that the first track and the second track are determined to be aligned in time and space, determining the average value of the position distance of the first track and the second track at the same time stamp; determining the similarity of the speed of the first track and the second track at the same time stamp; determining the similarity of the first track and the second track based on the average value of the position distance at a plurality of the same time stamps and the similarity of the speed at a plurality of the same time stamps; wherein, in the case that the average value of the position distance at the same time stamp is less than a distance threshold and the speed at the same time stamp is consistent, it is determined that the similarity of the first track and the second track is greater than the similarity threshold.

[0008] Further, the gate opening conditions include living body verification, behavior analysis and anti-following judgment, wherein, in the case that the target physical entity is determined to be a living body, the behavior of the target physical entity is normal and the target physical entity does not exist a follower, it is determined that the target physical entity meets the gate opening conditions.

[0009] Further, the target physical entity is analyzed based on the micro-Doppler to determine whether the target physical entity is a living body; in a case that the motion speed of the target physical entity at each moment is within a preset speed range, it is determined that the behavior of the target physical entity is normal; in a case that no other physical entity exists within a preset safety range of the target physical entity, the target physical entity and the other physical entity are not synchronized in speed, and there is no spatial occlusion, it is determined that the target physical entity has no follower; in a case that the target physical entity has the follower, an interception or alarm mechanism is triggered.

[0010] Further, the gate machine end comprises a camera triggering mechanism, which is used to be triggered in a case that the millimeter wave radar cannot identify two or more physical entities close to each other, the millimeter wave radar detects abnormal behavior and / or Bluetooth interruption, and the camera does not extract facial features.

[0011] In a second aspect of the present application, a subway gate machine non-inductive passing method is provided, which is applied to a gate machine end and includes: scanning and receiving an anonymous device identifier of a client, determining, based on the signal strength of a Bluetooth beacon of the client and the gate machine end, whether the distance between the client and the Bluetooth beacon is within a preset distance range, and waking up the corresponding perception system of the gate machine end in the case that the distance is within the preset distance range; fusing a physical entity point cloud track generated by a millimeter wave radar and a Bluetooth positioning track of the anonymous device identifier to determine a target physical entity corresponding to a Bluetooth identity; in a case that the target physical entity meets gate opening conditions, sending a gate opening instruction to a cloud end, so that the cloud end receives the gate opening instruction and performs a gate opening operation and a billing operation.

[0012] In a third aspect of the present application, an electronic device is provided, which includes at least one processor and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable 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 execute the method of the second aspect of the present application.

[0013] In a fourth aspect of the present application, a non-transitory computer readable storage medium storing computer instructions is provided, wherein the computer instructions are used to make the computer execute the method of the second aspect of the present application.

[0014] The present application has the following advantages: The subway gate non-sensing passing system and method, the system comprises: a client, used for broadcasting an anonymous device identifier, simultaneously scanning a Bluetooth beacon around the client, and determining a target fingerprint according to a signal strength of the client and the Bluetooth beacon, and reporting the target fingerprint to a gate end; the gate end is used for scanning and receiving the anonymous device identifier, determining that the distance between the client and the Bluetooth beacon is within a preset distance range based on the signal strength of the client and the Bluetooth beacon, awakening a corresponding perception system of the gate end, and fusing a physical entity point cloud track generated by a millimeter wave radar and a Bluetooth positioning track of the anonymous device identifier to determine a target physical entity corresponding to the Bluetooth identity, and in the case that the target physical entity meets a gate opening condition, sending a gate opening instruction to a cloud end; the cloud end is used for, in the case that the gate opening instruction is received, performing a gate opening operation and a charging operation. The system realizes non-sensing passing, and the user does not need to perform any operation, improves the passing speed, and avoids the problem of queuing congestion. BRIEF DESCRIPTION OF DRAWINGS

[0015] The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings:

[0016] Figure 1 FIG. 1 is a schematic diagram of a subway gate non-sensing passing system according to an embodiment of the application; Figure 2 FIG. 2 is a flowchart of a subway gate non-sensing passing method according to an embodiment of the application; Figure 3 FIG. 3 is a structural block diagram of an electronic device according to an embodiment of the application. DETAILED DESCRIPTION

[0017] In order to enable persons skilled in the art to better understand the technical solutions in the embodiments of the application, the technical solutions of the application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the application, rather than all the embodiments of the application. It should be understood that these descriptions are only exemplary, and are not used to limit the scope of the application. Based on the embodiments of the application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the scope of protection of the application.

[0018] In addition, in the following description, the description of well-known structures and techniques is omitted to avoid unnecessary confusion of the concepts disclosed in the application.

[0019] In the description of the present application, it should be noted that, unless otherwise explicitly specified and limited, the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer" and the like is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", "third" are only for descriptive purposes and cannot be understood as indicating or implying relative importance. The terms "mounting", "connection", "connection" should be broadly understood, for example, it can be fixed connection, or detachable connection, or integral connection; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or the communication between two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0020] The exemplary embodiments will be described in detail hereinbelow with reference to the drawings. In the following description, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of methods and systems consistent with some aspects of the present application as detailed in the appended claims.

[0021] The existing subway access technology mainly has the following problems and challenges: low efficiency of traditional ticketing mode: relying on traffic cards or mobile phone two-dimensional codes, passengers need to perform the cumbersome process of "taking out the card / mobile phone - aligning - waiting", which can easily form a queuing bottleneck during peak hours, and the access efficiency is low. Security risks are prominent: traditional gates mainly rely on a pair of infrared opposite sensors to determine the access logic, which cannot accurately distinguish between two closely following individuals who pass through continuously, resulting in the difficulty of eliminating the "tail evasion" phenomenon.

[0022] Existing non-inductive solutions have defects: pure face recognition solution: although it can achieve "non-induction", it has serious public privacy leakage concerns. At the same time, its recognition rate decreases in weak light, backlight, wearing masks, etc. and there is a risk of being attacked by photos or videos, and live detection is not absolutely reliable. Pure Bluetooth solution: can only solve the problem of identity recognition, but cannot track the exact position and movement trajectory of the access person, and cannot determine whether there is a tail person, and the security and reliability are insufficient. Single system function: the existing system is difficult to accurately perceive and real-time alarm abnormal behaviors (such as reverse, stay, jump) in the channel.

[0023] Therefore, the present invention proposes a contactless access system, method and related equipment for subway turnstiles. Specifically, the contactless access system, method and related equipment for subway turnstiles of the present invention are described below with reference to the accompanying drawings.

[0024] Figure 1 This is a schematic diagram of a contactless access system for subway turnstiles according to an embodiment of the present invention. It should be noted that the contactless access system for subway turnstiles of this embodiment is applicable to the contactless access method for subway turnstiles of this embodiment. This contactless access system can be configured on an electronic device or in a server. This application does not limit the scope of this application.

[0025] like Figure 1 As shown, the subway turnstile contactless access system includes: Client 110 is used to broadcast anonymous device identifiers, scan Bluetooth beacons around the client, determine the target fingerprint based on the signal strength between the client and the Bluetooth beacons, and report the target fingerprint to gate terminal 120.

[0026] The gate terminal 120 is used to scan and receive anonymous device identifiers. Based on the signal strength between the client and the Bluetooth beacon, if the distance between the client 110 and the Bluetooth beacon is within a preset distance range, the gate terminal 120 wakes up the corresponding perception system. It also fuses the physical entity point cloud trajectory generated by the millimeter-wave radar with the Bluetooth positioning trajectory of the anonymous device identifier to determine the target physical entity corresponding to the Bluetooth identity. If the target physical entity meets the gate opening conditions, the gate terminal 120 sends an opening command to the cloud terminal 130.

[0027] Cloud 130 is used to execute gate opening and billing operations when a gate opening command is received.

[0028] In other words, client 110 broadcasts an anonymous device identifier, scans nearby Bluetooth beacons, and reports the target fingerprint to gate terminal 120. Gate terminal 120, by scanning and receiving the anonymous device identifier, determines that the distance between client 110 and the Bluetooth beacon is within a preset range. It then activates the corresponding sensing system at gate terminal 120 and fuses the physical entity point cloud trajectory generated by millimeter-wave radar with the Bluetooth positioning trajectory of the anonymous device identifier to identify the target physical entity corresponding to the Bluetooth identity. If the target physical entity meets the gate opening conditions, it sends an opening command to cloud terminal 130. Upon receiving the opening command, cloud terminal 130 executes the gate opening operation and billing operation. The entire process achieves seamless passage, requiring no user intervention, improving passage speed, and avoiding queuing congestion.

[0029] In the case that the distance between the client 110 and the Bluetooth beacon is within the preset distance range, the corresponding sensing system of the gate terminal 120 is woken up, that is, the high-power sensing system is woken up only when a potential user is close (within the preset distance), so as to reduce the overall standby power consumption of the gate terminal 120.

[0030] In an embodiment of the present application, the anonymous device identifier is an encrypted identifier. For example, the client 110 broadcasts an encrypted anonymous device identifier which can be changed at a preset period. In this case, the client 110 can bind the anonymous device identifier with the user account of the client 110 and send the binding relationship to the cloud 130, so that the cloud 130 stores the binding relationship.

[0031] In an embodiment of the present application, in the case that the gate terminal 120 receives the anonymous device identifier, the anonymous device identifier can be legally verified. For example, it is judged whether the format of the anonymous device identifier is valid and / or whether it is in the recent legal list, so as to realize the legal verification of the anonymous device identifier.

[0032] In an embodiment of the present application, a Bluetooth positioning module can be arranged in the gate terminal 120. The anonymous device identifier can be scanned and received based on the Bluetooth positioning module. By receiving the signal strength between the client 110 and the Bluetooth beacon, the corresponding sensing system of the gate terminal 120 is woken up in the case that the distance between the client 110 and the Bluetooth beacon is within the preset distance range. At the same time, the signal is transmitted at a fixed power.

[0033] In this case, the Bluetooth positioning module corresponds to the Bluetooth beacon, so that the client 110 scans the surrounding Bluetooth beacon.

[0034] In this case, based on the corresponding library of signal strength and distance, the distance corresponding to the signal strength can be determined in the case that the signal strength between the client 110 and the Bluetooth beacon is determined.

[0035] In an embodiment of the present application, the millimeter wave radar transmits a high-frequency electromagnetic wave signal and receives a reflected echo signal. Based on the high-frequency electromagnetic wave signal and the reflected echo signal, the distance, speed and angle of the physical entity are calculated. Based on the distance, speed and angle of the physical entity, the point cloud trajectory of the physical entity is determined. The millimeter wave radar living body detection effectively prevents attacks of non-biological credentials such as photos and videos.

[0036] That is, the millimeter wave radar adopts a frequency-modulated continuous wave (FMCW) modulation method to transmit a signal (i.e., to transmit a high-frequency electromagnetic wave signal) and receive a reflected echo signal (i.e., to receive a reflected echo signal) reflected by a physical entity. By mixing the echo signal, analog-to-digital conversion, and three-level fast Fourier transform processing, the distance, radial velocity, and azimuth angle information of the physical entity are sequentially analyzed to form an original detection point cloud. Subsequently, the original detection point cloud is segmented by a clustering algorithm to distinguish different physical entities, and a multi-target tracking algorithm is used to associate and estimate the state of the segmented point cloud clusters across frames, and finally a continuous and stable point cloud trajectory of each physical entity is generated.

[0037] Among them, the received echo signal reflected by the physical entity (slightly different from the current transmitted signal due to time delay) is mixed (i.e., multiplied) with the transmitted signal. This process produces a key intermediate frequency signal. The frequency of this signal is very low, and its frequency is directly proportional to the target distance, and its phase change is related to the relative radial velocity of the target.

[0038] Among them, the three-level fast Fourier transform includes a first-level FFT (i.e., distance dimension FFT), a second-level FFT (i.e., velocity dimension FFT), and a third-level FFT (i.e., angle dimension FFT).

[0039] Among them, the first-level FFT (i.e., distance dimension FFT) can be understood as performing FFT on the mixed intermediate frequency signal of each transmission period (Chirp). A frequency spectrum is obtained, and the frequency position of the peak value directly corresponds to the distance of the target (the farther the distance, the higher the intermediate frequency frequency). A peak value represents a detected "point", and the distance value is analyzed. At this time, each point only has one distance information.

[0040] The second-level FFT (i.e., velocity dimension FFT) can be understood as: performing FFT again on the signal sampling points of multiple consecutive Chirps (in a frame period) at the same distance unit along the time axis (slow time dimension). The Doppler frequency position of the peak value directly corresponds to the radial velocity of the target. At this time, each detection point has two attributes: distance and velocity.

[0041] The third-level FFT (i.e., angle dimension FFT) can be understood as: using the multi-transmission and multi-reception antenna array of the radar. At the same time, the signals reflected by the same target to different receiving antennas will produce a phase difference due to the path difference. Perform FFT on the signals of all receiving antennas at the same (distance, velocity) unit along the space axis (antenna dimension). The spatial frequency position of the peak value corresponds to the azimuth angle of the target.

[0042] So far, through the three-level FFT of distance-velocity-angle, a three-dimensional data cube is generated, and each resolved unit (a peak) is a point in the original detection point cloud, containing information of three dimensions (distance, radial velocity, and azimuth).

[0043] Wherein, since the original detection point cloud is sparse and noisy, and may contain false points, and one object will generate multiple reflection points, the multiple point clouds belonging to the same physical entity (such as a car or a pedestrian) are clustered together by a clustering algorithm to form a "point cloud cluster", thereby distinguishing different objects to form a series of point cloud clusters, each cluster representing a candidate target.

[0044] Wherein, in order to solve the problem of "which target detected in the current frame is which target in the last frame", and to perform cross-frame state (position, velocity) smoothing estimation, generate stable and continuous trajectories, match the detection cluster of the current frame with the existing target trajectory. Common methods include nearest neighbor, joint probability data association, or matching based on the Hungarian algorithm. For the matched trajectory, a filter (such as a Kalman filter and its variants) is used to predict the position of the target in the next frame, and the measurement value of the current frame is used for updating. This can smooth out measurement noise and provide more accurate speed and position estimates, and even predict the motion state in the near future. Create a new target trajectory (when a new detection that is not matched appears), maintain existing trajectories, and delete disappearing target trajectories. Further, each physical entity (target) has a unique ID, and a trajectory (including position, velocity, acceleration, etc.) that changes over time and has a smoothed state.

[0045] Wherein, the millimeter wave radar is not affected by light intensity (light and dark), common obstructions (such as clothing, bags), and daily makeup, and can work stably in various complex environments (strong light, backlight, darkness) to provide continuous and accurate spatial trajectories.

[0046] In the embodiment of the present application, when the gate machine end 120 receives the target fingerprint, the target fingerprint can be matched with the preset fingerprint library to obtain the estimated position corresponding to the target fingerprint, wherein the preset fingerprint library includes a plurality of target fingerprints and the estimated positions corresponding to the target fingerprints; the estimated positions of the continuous time points are obtained, wherein each time point corresponds to an estimated position; the estimated positions of the continuous time points are smoothed based on a timing filtering algorithm to generate a timing-based Bluetooth positioning trajectory, and the timing-based Bluetooth positioning trajectory is used as the Bluetooth positioning trajectory of the anonymous device identifier.

[0047] That is, since the client 110 is mobile, the client 110 can report the target fingerprints at continuous time points to the gate end 120, and then the gate end 120 matches the plurality of target fingerprints with the preset fingerprint library to obtain the estimated positions at the continuous time points. Then, the estimated positions at the continuous time points are smoothed based on a timing filtering algorithm to generate a Bluetooth positioning trajectory based on timing.

[0048] The timing filtering algorithm includes Kalman filtering, particle filtering, etc.

[0049] For example, first, the original RSSI signal is subjected to outlier rejection and sliding window filtering; then, a state prediction and update are performed through an extended Kalman filter to establish a target motion model; then, a particle filter is used to process the nonlinear and non-Gaussian noise characteristics of the system; finally, a trajectory smoother is used to impose physical motion constraints to ensure the continuity of the generated trajectory speed and spatial reasonableness. That is, the estimated positions at the continuous time points are smoothed based on the timing filtering algorithm. The original RSSI signal can be understood as the signal strength indication value received by Bluetooth without any processing, usually expressed in dBm (decibel milliwatt). It is a direct physical quantity used to measure the strength of the received signal in Bluetooth communication.

[0050] In the embodiments of the present application, in the case of determining the physical entity point cloud trajectory generated based on the millimeter wave radar and the Bluetooth positioning trajectory of the anonymous device identifier, the physical entity point cloud trajectory generated by the millimeter wave radar and the Bluetooth positioning trajectory of the anonymous device identifier can be fused to determine the target physical entity corresponding to the Bluetooth identity.

[0051] The first trajectory of the physical entity point cloud trajectory and the second trajectory of the Bluetooth positioning trajectory in a plurality of sliding time windows are obtained; the similarity of the first trajectory and the second trajectory is determined; and in the case that the similarity of the plurality of sliding time windows is greater than the similarity threshold, the target physical entity matched with the Bluetooth identity is obtained.

[0052] That is, the physical entity point cloud trajectory and the Bluetooth positioning trajectory are generated by two different sensing systems, and their hardware characteristics, working frequencies, triggering conditions and processing procedures are different, which will inevitably cause differences in time, and then the start and end times of the physical entity point cloud trajectory and the Bluetooth positioning trajectory may not be completely consistent. Therefore, the present application can select a plurality of sliding time windows, and the segments of the two trajectories, i.e., the first trajectory and the second trajectory, are intercepted in each window.

[0053] Specifically, given that the first trajectory and the second trajectory are aligned in time and space, the average positional distance between the first trajectory and the second trajectory at the same timestamp is determined; the similarity of the velocities of the first trajectory and the second trajectory at the same timestamp is determined; and the similarity of the first trajectory and the second trajectory is determined based on the average positional distance at multiple timestamps and the similarity of the velocities at multiple timestamps.

[0054] The time and space alignment of the first trajectory and the second trajectory includes: synchronizing the time of the first trajectory and the second trajectory to ensure that the timestamps of the two types of data are aligned; and aligning the coordinate systems of the first trajectory and the second trajectory, that is, transforming the first trajectory and the second trajectory to the same coordinate system.

[0055] Specifically, if the average distance between locations at the same timestamp is less than a distance threshold and the speeds at the same timestamp are consistent, then the similarity between the first trajectory and the second trajectory is determined to be greater than a similarity threshold.

[0056] Specifically, if the speed and direction of the first and second trajectories are the same at the same timestamp, then the speeds of the first and second trajectories at the same timestamp are determined to be consistent.

[0057] In embodiments of the present invention, a sliding time window and a spatiotemporal alignment method (such as Kalman filtering) are used to fuse Bluetooth positioning trajectories and physical entity point cloud trajectories. Even in environments with fluctuating or interfering signals, the device identity can be reliably bound to the correct physical entity, reducing the false association rate.

[0058] In one specific embodiment of the present invention, when the gate terminal 120 scans and receives an anonymous device identifier and receives a target fingerprint, the gate terminal 120 performs a valid verification of the anonymous device identifier. Then, if it determines that the distance between the client 110 and the Bluetooth beacon is within a preset distance range, it wakes up the sensing system corresponding to the gate terminal 120. For example, if it determines that a potentially valid target is approaching (e.g., the signal strength RSSI exceeds -75dBm, meaning the distance is within 3-5 meters), the gate terminal 120 is immediately woken up from the low-power standby mode.

[0059] Then the gate machine end 120 generates a physical entity point cloud trajectory based on the millimeter wave radar and an anonymous device identifier Bluetooth positioning trajectory based on the target fingerprint. Among them, 1) the millimeter wave radar does not care about identity, but objectively detects the physical space. And the generated physical entity point cloud trajectory can clearly distinguish that there are several independent moving "entities" in the channel, as well as the accurate three-dimensional position, speed and motion direction of each entity; 2) match the target fingerprint at consecutive time points with the preset fingerprint library to obtain the estimated position at consecutive time points, and smooth the estimated position at consecutive time points through a time sequence filtering algorithm to generate a time sequence based Bluetooth positioning trajectory (i.e. anonymous device identifier Bluetooth positioning trajectory).

[0060] Then the millimeter wave radar generated physical entity point cloud trajectory and the anonymous device identifier Bluetooth positioning trajectory are fused (i.e. matched) to determine the target physical entity corresponding to the Bluetooth identity. For example, the physical entity point cloud trajectory provides: it is detected that physical entity A is moving accurately at coordinate B. (The information is very accurate, but nameless); the Bluetooth positioning trajectory provides: anonymous device identifier X is moving near the approximate area A. (The information is relatively rough, but with identity). Within a preset time, whether the estimated motion trajectory of the anonymous device identifier X (i.e. the Bluetooth positioning trajectory) is highly consistent with the accurate radar trajectory of the physical entity A (i.e. the physical entity point cloud trajectory) in terms of motion mode (speed change, direction turning) and spatial position? If highly consistent, it is determined that the anonymous device identifier X = physical entity A. That is, the target physical entity corresponding to the Bluetooth identity is determined.

[0061] In an embodiment of the present application, the gate opening conditions include living body verification, behavior analysis and anti-following judgment. Among them, in the case that the target physical entity is determined to be a living body, the behavior of the target physical entity is normal, and there is no follower of the target physical entity, it is determined that the target physical entity meets the gate opening condition.

[0062] Among them, the target physical entity is analyzed based on the micro-Doppler (for example, the heart rate feature and the respiration feature are analyzed) to determine whether the target physical entity is a living body; in the case that the motion speed of the target physical entity at each moment is within the preset speed range, it is determined that the behavior of the target physical entity is normal; in the case that there is no other physical entity within the preset safety range of the target physical entity, the speed of the target physical entity is not synchronized with that of other physical entities, and there is no spatial occlusion, it is determined that the target physical entity has no follower.

[0063] Among them, the theory of micro-Doppler phenomenon and its application in real-time, non-contact and high-precision extraction and identification of weak vital signs such as heart rate and respiration on a consumer-level, low-cost millimeter wave radar hardware platform in a complex dynamic scene (such as a subway gate) and using it as a reliable criterion for passage verification belong to the frontiers of application and technology integration with high creativity.

[0064] The target physical entity is analyzed based on the micro-Doppler, non-contact living body detection is realized, and specifically, first, macro motion compensation is performed on the echo signal to separate the micro motion signal caused by vital signs; then, the phase information of the signal is extracted and analyzed, a high-resolution spectrum estimation method is used to generate the micro motion spectrum of the target in the 0.1-2.0Hz frequency band; finally, whether the heart rate spectrum peak and the respiration rate spectrum peak conforming to the human physiological characteristics exist in the micro motion spectrum is detected, and the harmonic coherence and rhythm rationality are verified, to determine whether the target physical entity is a living body.

[0065] In the case that it is determined that the target physical entity has a follower, an interception or alarm mechanism is triggered. Through the precise spatial perception ability of the millimeter wave radar, active and high-precision anti-following that cannot be achieved by traditional technologies is realized, and the behavior of escaping tickets is significantly reduced.

[0066] In the case that it is determined that the target physical entity has a follower, an interception or alarm mechanism is triggered. Through the precise spatial perception ability of the millimeter wave radar, active and high-precision anti-following that cannot be achieved by traditional technologies is realized, and the behavior of escaping tickets is significantly reduced.

[0067] In the embodiment of the application, the gate machine end 120 includes a camera trigger mechanism, the camera trigger mechanism is used for triggering in the case that the millimeter wave radar cannot identify two and more close physical entities, the millimeter wave radar detects abnormal behavior and / or Bluetooth interruption, wherein the camera does not extract face features.

[0068] In the case that it is determined that the target physical entity has a follower, an interception or alarm mechanism is triggered. Through the precise spatial perception ability of the millimeter wave radar, active and high-precision anti-following that cannot be achieved by traditional technologies is realized, and the behavior of escaping tickets is significantly reduced.

[0069] In an embodiment of the present application, taking the normal non-inductive behavior as an example, passenger A has pre-installed the App on the client and completed the registration. When he walks to the gate end, the anonymous device identifier broadcasted by his mobile phone is captured by the gate end Bluetooth module, and the induction system of the gate end is awakened. The millimeter wave radar immediately detects a motion trajectory A towards the gate. At the same time, the client of passenger A continuously scans the surrounding Bluetooth beacons, converts the signal strength data into a specific fingerprint (target fingerprint), and matches it with the preset fingerprint library, thereby determining the Bluetooth positioning trajectory based on the time sequence; through the data fusion algorithm, the anonymous device identifier of passenger A is successfully associated with the radar trajectory A. Analysis shows that the trajectory A has a smooth speed, and the micro-Doppler feature confirms that it is a living body. When the centroid of trajectory A crosses the virtual "passage authorization line" and the radar confirms that there is no following target behind it, the edge unit sends the anonymous device identifier of passenger A to the cloud. After the cloud verifies that the anonymous device identifier is valid, the gate is authorized to open. Passenger A does not need any pause, and naturally walks through the gate end, and the whole process is completed within milliseconds.

[0070] In an embodiment of the present application, taking the anti-following and abnormal processing as an example, passenger B (a legal passenger) is followed by passenger C who tries to follow and escape. The system first associates the anonymous device identifier of passenger B with the physical entity point cloud trajectory generated by the millimeter wave radar. At the same time, the millimeter wave radar clearly detects an independent trajectory F of passenger C, and finds that the trajectory F is too close to the trajectory of passenger B (<0.4 meters) and has the same speed. The system immediately determines that it is a "following" event. At this time, the system can execute strategy A: delay the gate opening for passenger B, and prompt "please keep a distance" through voice; or strategy B: normally open the gate for passenger B, but trigger the sound and light alarm when passenger C passes through, and simultaneously trigger the camera to record the on-site video (only record the physical appearance and behavior, not the close-up of the face) as evidence, and notify the staff to handle.

[0071] According to an embodiment of the subway turnstile contactless passage system of the present invention, millimeter-wave radar can accurately distinguish multiple targets at a distance of centimeters. Combined with behavioral analysis (speed synchronization, close proximity, spatial occlusion judgment), it can actively identify tailgating attempts. This is difficult to achieve with traditional turnstiles (mechanical anti-blocking, area sensing) or simple facial recognition turnstiles, effectively reducing fare evasion. The micro-Doppler feature analysis of millimeter-wave radar (heartbeat, breathing) can effectively determine whether the target is a real living person, eliminating attacks using non-biological credentials such as photos, videos, and masks, making its security far superior to ordinary vision systems. The gate opening decision is not based on a single signal (such as "swipe card to open"), but integrates "legitimate device identity (Bluetooth anonymous ID)," "precise spatial trajectory (radar)," and "biological behavioral characteristics (living, normal speed)," forming a robust multi-factor security authentication system, improving the accuracy of anti-impersonation and anti-deception. The system allows users to pass through naturally by walking without using a mobile phone to swipe a card, show a code, or undergo facial recognition. This improves passage speed and fundamentally avoids queuing congestion caused by slow operation, with particularly significant effects during peak hours. Furthermore, while pursuing "seamless" speed, it achieves a higher level of security than single authentication methods (such as card swiping) or single biometric identification (such as face recognition) through multimodal sensor fusion.

[0072] To enable those skilled in the art to more readily understand the present invention, Figure 2 This is a method for contactless passage through subway turnstiles according to an embodiment of the present invention. The method is applied to the turnstile end, such as... Figure 2 As shown, the contactless passage method of the subway turnstile includes: S210: Scan and receive the anonymous device identifier of the client. Based on the signal strength of the Bluetooth beacon between the client and the gate, if the distance between the client and the Bluetooth beacon is within a preset distance range, wake up the corresponding sensing system of the gate.

[0073] In an embodiment of the present invention, the client can broadcast an anonymous device identifier, simultaneously scan Bluetooth beacons around the client, determine the target fingerprint based on the signal strength between the client and the Bluetooth beacons, and report the target fingerprint to the gate. The gate can then receive the client's anonymous device identifier and the target fingerprint.

[0074] In an embodiment of the present invention, when an anonymous device identifier is received at the gate, the anonymous device identifier is validated for legitimacy.

[0075] S220 fuses the physical entity point cloud trajectory generated by millimeter-wave radar with the Bluetooth positioning trajectory of anonymous device identifiers to determine the target physical entity corresponding to the Bluetooth identity.

[0076] In the embodiment of the present application, the millimeter wave radar transmits a high-frequency electromagnetic wave signal and receives a reflected echo signal; based on the high-frequency electromagnetic wave signal and the reflected echo signal, the distance, speed and angle of the physical entity are calculated; based on the distance, speed and angle of the physical entity, the physical entity point cloud trajectory is determined.

[0077] In the embodiment of the present application, the target fingerprint is matched with a preset fingerprint library to obtain a predicted position corresponding to the target fingerprint, wherein the preset fingerprint library includes a plurality of target fingerprints and predicted positions corresponding to the target fingerprints; the predicted positions at consecutive time points are obtained, wherein each time point corresponds to a predicted position; the predicted positions at the consecutive time points are smoothed based on a time sequence filtering algorithm to generate a time sequence-based Bluetooth positioning trajectory, and the time sequence-based Bluetooth positioning trajectory is taken as the Bluetooth positioning trajectory of the anonymous device identifier.

[0078] In the embodiment of the present application, the first trajectory of the physical entity point cloud trajectory and the second trajectory of the Bluetooth positioning trajectory in a plurality of sliding time windows are obtained; the similarity of the first trajectory and the second trajectory is determined; in the case that the similarity of the plurality of sliding time windows is greater than a similarity threshold, the target physical entity matched with the Bluetooth identity is obtained. In the case that the first trajectory and the second trajectory are determined to be aligned in time and space, the average value of the position distance of the first trajectory and the second trajectory at the same time stamp is determined; the similarity of the speed of the first trajectory and the second trajectory at the same time stamp is determined; based on the average value of the position distance at a plurality of same time stamps and the similarity of the speed at a plurality of same time stamps, the similarity of the first trajectory and the second trajectory is determined.

[0079] In the case that the average value of the position distance at the same time stamp is less than a distance threshold and the speed at the same time stamp is consistent, the similarity of the first trajectory and the second trajectory is determined to be greater than a similarity threshold.

[0080] S230, in the case that the target physical entity meets the gate opening condition, a gate opening instruction is sent to the cloud end, so that in the case that the cloud end receives the gate opening instruction, a gate opening operation and a charging operation are performed.

[0081] In the embodiment of the present application, the gate opening condition includes living body verification, behavior analysis and anti-following judgment.

[0082] In the embodiment of the present application, in the case that the target physical entity is a living body, the behavior of the target physical entity is normal, and the target physical entity does not have a follower, it is determined that the target physical entity meets the gate opening condition.

[0083] The target physical entity is analyzed based on the micro-Doppler to determine whether the target physical entity is a living body; the motion speed of the target physical entity at each moment is determined to be within a preset speed range, and the behavior of the target physical entity is determined to be normal; in the case that no other physical entity exists within a preset safety range of the target physical entity, the target physical entity and other physical entities are not synchronized in speed, and there is no spatial occlusion, it is determined that the target physical entity has no follower; in the case that the target physical entity has a follower, an interception or alarm mechanism is triggered.

[0084] In an embodiment of the application, the gate machine end comprises a camera trigger mechanism, which is used to trigger in the case that the millimeter wave radar cannot identify two or more closely physical entities, the millimeter wave radar detects abnormal behavior and / or Bluetooth interruption, wherein the camera does not extract facial features.

[0085] According to the subway gate machine non-inductive passing method, the anonymous device identifier of the client is scanned and received, the distance between the client and the Bluetooth beacon is determined based on the signal strength of the Bluetooth beacon of the client and the gate machine end, and the corresponding perception system of the gate machine end is woken up in the case that the distance between the client and the Bluetooth beacon is within a preset distance range; the physical entity point cloud track generated by the millimeter wave radar and the Bluetooth positioning track of the anonymous device identifier are fused to determine the target physical entity corresponding to the Bluetooth identity; in the case that the target physical entity meets the gate opening condition, a gate opening instruction is sent to the cloud end, so that the cloud end performs a gate opening operation and a billing operation in the case that the gate opening instruction is received. The method realizes non-inductive passing, and the user does not need to perform any operation, thereby improving the passing speed and avoiding the problem of queuing congestion.

[0086] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device) to execute the method of each embodiment of the present application.

[0087] Figure 3 is a structural schematic diagram of an electronic device according to an embodiment of the application. As shown in Figure 3 , the electronic device can include one or more Figure 3The electronic device shown in FIG. 1 includes only one processor 102 (the processor 102 can include, but is not limited to, a Microprocessor Unit (MPU) or a Programmable logic device (PLD)) and a memory 104 for storing data. In an exemplary embodiment, the electronic device can further include a transmission device 106 for communication function and an input / output device 108. Those skilled in the art can understand that, Figure 3 The structure shown in FIG. 1 is only schematic and does not limit the structure of the terminal device. For example, the terminal device can include more or fewer components than those shown in FIG. 1, or have different configurations with the same or more functions than those shown in FIG. 1. Figure 3 For example, the terminal device can include more or fewer components than those shown in FIG. 1, or have different configurations with the same or more functions than those shown in FIG. 1. Figure 3 For example, the terminal device can include more or fewer components than those shown in FIG. 1, or have different configurations with the same or more functions than those shown in FIG. 1. Figure 3 For example, the terminal device can include more or fewer components than those shown in FIG. 1, or have different configurations with the same or more functions than those shown in FIG. 1.

[0088] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as the computer program corresponding to the metro gate non-inductive passing method in the embodiments of the present application. The processor 102 can execute various functional applications and data processing by running the computer programs stored in the memory 104, i.e., implement the method described above. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely arranged with respect to the processor 102, and the remote memory can be connected to the terminal device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0089] The transmission device 106 is used to receive or send data via a network. Specific examples of the network can include a wireless network provided by a communication provider of a switching device. In one example, the transmission device 106 includes a network adapter (NIC) which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module which is used to communicate with the Internet in a wireless manner.

[0090] The present application provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to execute a metro gate non-inductive passing method.

[0091] The applicant of the present application has made detailed description and illustration on the embodiments of the present application in combination with the drawings of the present application. However, those skilled in the art should understand that the above embodiments are only preferred embodiments of the present application, and the detailed description is only for helping the readers to better understand the spirit of the present application, and does not limit the protection scope of the present application. On the contrary, any improvement or modification based on the spirit of the present application should fall within the protection scope of the present application.

[0092] In addition, each functional unit in each embodiment of the present application can be integrated in one processing module, or each unit can be physically present separately, or two or more units can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0093] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

[0094] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present application, and not to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. Any changes or replacements that can be easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered within the protection scope of the present application.

Claims

1. A contactless passage system for subway turnstiles, characterized in that, include: The client is used to broadcast an anonymous device identifier, scan Bluetooth beacons around the client, determine the target fingerprint based on the signal strength between the client and the Bluetooth beacons, and report the target fingerprint to the gate. The gate terminal is used to scan and receive the anonymous device identifier. Based on the signal strength between the client and the Bluetooth beacon, if the distance between the client and the Bluetooth beacon is within a preset distance range, the gate terminal's corresponding sensing system is activated. The physical entity point cloud trajectory generated by the millimeter-wave radar and the Bluetooth positioning trajectory of the anonymous device identifier are fused to determine the target physical entity corresponding to the Bluetooth identity. If the target physical entity meets the gate opening conditions, the gate opening command is sent to the cloud. The cloud platform is used to execute the gate opening operation and the billing operation when it receives the gate opening command.

2. The seamless passage system for subway turnstiles according to claim 1, characterized in that, The client is also used to: bind the anonymous device identifier to the user account corresponding to the client, and send the binding relationship to the cloud so that the cloud stores the binding relationship.

3. The seamless passage system for subway turnstiles according to claim 1, characterized in that, Upon receiving the anonymous device identifier at the gate, the anonymous device identifier is validated for legitimacy. The generation of the physical entity point cloud trajectory based on the millimeter-wave radar includes: The millimeter-wave radar transmits high-frequency electromagnetic wave signals and receives reflected echo signals. Based on the high-frequency electromagnetic wave signal and the reflected echo signal, the distance, velocity, and angle of the physical entity are calculated; Based on the distance, velocity, and angle of the physical entity, determine the point cloud trajectory of the physical entity; Determining the Bluetooth location trajectory of the anonymous device identifier includes: The target fingerprint is matched with a preset fingerprint database to obtain the estimated position corresponding to the target fingerprint, wherein the preset fingerprint database includes multiple target fingerprints and the estimated positions corresponding to the target fingerprints; Obtain the estimated positions at consecutive time points, wherein each time point corresponds to one estimated position; The estimated positions at consecutive time points are smoothed using a time-series filtering algorithm to generate a time-series-based Bluetooth positioning trajectory, which is then used as the Bluetooth positioning trajectory of the anonymous device identifier.

4. The contactless passage system for subway turnstiles according to claim 3, characterized in that, The point cloud trajectory of the physical entity generated by millimeter-wave radar and the Bluetooth positioning trajectory of the anonymous device identifier are fused to determine the target physical entity corresponding to the Bluetooth identity, including: Obtain the first trajectory of the physical entity point cloud trajectory and the second trajectory of the Bluetooth positioning trajectory within multiple sliding time windows; Determine the similarity between the first trajectory and the second trajectory; If the similarity of multiple sliding time windows is greater than a similarity threshold, the target physical entity for Bluetooth identity matching is obtained. Determining the similarity between the first trajectory and the second trajectory includes: Given that the first trajectory and the second trajectory are aligned in time and space, determine the average positional distance between the first trajectory and the second trajectory at the same timestamp; Determine the similarity of the velocities of the first trajectory and the second trajectory at the same timestamp; The similarity between the first trajectory and the second trajectory is determined based on the average of the location distances at multiple timestamps and the similarity of the velocities at multiple timestamps. Specifically, if the average distance between the locations at the same timestamp is less than a distance threshold and the speeds at the same timestamp are consistent, then the similarity between the first trajectory and the second trajectory is determined to be greater than a similarity threshold.

5. The contactless passage system for subway turnstiles according to claim 1, characterized in that, The gate opening conditions include liveness verification, behavior analysis, and anti-tailgating judgment. Determining that the target physical entity meets the gate opening conditions includes: If it is determined that the target physical entity is a living entity, the target physical entity is behaving normally, and the target physical entity has no followers, then the target physical entity is determined to meet the gate opening conditions.

6. The seamless passage system for subway turnstiles according to claim 5, characterized in that, Based on micro-Doppler feature analysis, the target physical entity is determined to be a living entity. If the speed of the target physical entity at each moment is within a preset speed range, the behavior of the target physical entity is determined to be normal. If it is determined that there are no other physical entities within the preset safety range of the target physical entity, the target physical entity and the other physical entities have different speeds and there is no spatial obstruction, then it is determined that the target physical entity has no tail. If it is determined that the target physical entity has the tailer, an interception or alarm mechanism is triggered.

7. The contactless passage system for subway turnstiles according to claim 1, characterized in that, The gate terminal includes a camera triggering mechanism, which is used to trigger when the millimeter-wave radar cannot identify two or more closely spaced physical entities, when the millimeter-wave radar detects abnormal behavior, or when Bluetooth is interrupted. The camera does not extract facial features.

8. A method for contactless passage through a subway turnstile, the method being applied to the turnstile end, characterized in that, include: Scan and receive the anonymous device identifier of the client, and based on the signal strength of the Bluetooth beacon between the client and the gate, determine that the distance between the client and the Bluetooth beacon is within a preset distance range, and then wake up the sensing system corresponding to the gate. The physical entity point cloud trajectory generated by the millimeter-wave radar and the Bluetooth positioning trajectory of the anonymous device identifier are fused to determine the target physical entity corresponding to the Bluetooth identity. If the target physical entity meets the gate opening conditions, a gate opening command is sent to the cloud so that the cloud can execute the gate opening operation and the billing operation upon receiving the gate opening command.

9. An electronic device, characterized in that, include: 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 to enable the at least one processor to perform the method of claim 8.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to claim 8.

Images