Access control linkage anti-following control system of unmanned gymnasium
By combining depth cameras and millimeter-wave radar with dual facial recognition verification, the problem of traditional access control systems in unmanned gyms being unable to distinguish between users and tailgating personnel has been solved, achieving accurate identification and proactive defense, thus improving security.
Patent Information
- Application Number
- CN202511599430.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-04
- Publication Date
- 2026-02-06
AI Technical Summary
Traditional access control systems in unmanned gyms cannot effectively distinguish between legitimate users and those who tailgate, posing security risks. Existing detection methods are easily cracked or produce false alarms, leading to property loss and threats to personal safety.
By combining depth cameras and millimeter-wave radar, and through the analysis of skeletal key points and motion trajectories, combined with dual facial recognition verification, it can accurately distinguish between users and tailgators, and execute differentiated access control strategies.
It significantly reduced the false alarm and false alarm rates, achieved proactive security, enhanced the safety of unmanned gyms, prevented external tailgating and internal violations, and built a three-dimensional security system.
Smart Images

Figure CN121482909A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent security technology, specifically to an access control and anti-tailgating control system for an unmanned gym. Background Technology
[0002] With the rapid development of the unmanned economy, unmanned gyms are becoming increasingly popular due to their savings in labor costs and flexible operating hours. However, the unmanned model also brings significant security risks, the most prominent of which is the problem of unauthorized entry. This means that unauthorized personnel follow authorized users through the access control system to enter the premises, which may not only lead to property loss and equipment theft, but also pose a threat to personal safety.
[0003] Currently, unmanned gyms generally use traditional access control systems, such as card swiping, passwords, or facial recognition. These systems have significant drawbacks: they can only verify the identity of the initial user; once the first door is opened, the system cannot detect and prevent other people from following suit. Although some solutions employ a double-door interlocking "buffer zone" (or "turnstile") design, existing detection methods are mostly limited to a single sensor, such as: Infrared beam beams: They are easily deceived by multiple people passing through at the same time, making it impossible to distinguish between a fat person and two people standing close together.
[0004] Ordinary cameras: can only perform two-dimensional image analysis. Their recognition accuracy drops sharply when the light changes, there is obstruction, or people are close by, and they are prone to false alarms or missed alarms.
[0005] Weight sensors: It is difficult to set accurate thresholds and cannot distinguish between a person carrying heavy objects and multiple people following behind.
[0006] These solutions are based on simple logic and have a single criterion, making them easy for malicious followers to crack or for false alarms to affect the experience of normal users. Summary of the Invention
[0007] The purpose of this invention is to provide an access control and anti-tailgating control system for unmanned gyms. This system uses intelligent sensors and algorithms to accurately distinguish between normal users, unintentional followers, and malicious tailgators, and executes differentiated linkage control strategies, thereby greatly improving the security level of unmanned gyms.
[0008] To achieve the above objectives, the present invention provides the following technical solution: an access control and anti-tailgating control system for an unmanned gym, comprising: The main access control device is located at the gym entrance and is used to verify user identity and control the opening of the first door. The buffer zone is the physical space formed by the first gate and the second gate. A tail-following detection module is set within the buffer area to collect monitoring data of targets entering the buffer area; the tail-following detection module includes a depth camera and a millimeter-wave radar to acquire skeletal key point information, movement trajectory, and number of targets; The central processing unit, which is communicatively connected to the main access control device and the tailgating detection module, is configured as follows: a) Receive the authentication success signal from the main access control device; b) Trigger the tail-following detection module to operate and receive the monitoring data it sends; c) Based on the monitoring data, determine whether tailing behavior exists using a predefined anti-tailing logic algorithm; The door linkage control unit is communicatively connected to the central processing unit and is configured to control the opening and closing states of the first and second doors based on the judgment result of the central processing unit. The second gate is equipped with facial recognition screens on both its inner and outer sides to verify the user's identity. Once the verification is successful, a signal is sent to the gate linkage control unit to control the opening of the second gate and to record the card purchase information and identity information of the verified member.
[0009] Preferably, the central processing unit is further configured as follows: Based on the data from the depth camera, the number of targets entering the buffer area is identified and counted. If the number of targets is greater than one, it is determined that there is potential tailing behavior; Analyze the target's trajectory and speed; If two or more targets are detected to be moving in the same direction at close range, it is determined to be a coordinated tailing behavior.
[0010] Preferably, the anti-tailgating logic algorithm includes: If, after successful identity verification, only one target is detected entering the buffer area and its behavior trajectory is normal, it is determined that there is no tailgating, and the second gate is authorized to be opened. If multiple targets are detected, but there is a significant time delay or spatial gap between the subsequent target and the verified user, it is determined to be unintentional following. The second gate is controlled to delay closing after the verified user passes through, and an alarm sound is emitted to remind subsequent personnel to verify themselves. If multiple targets are detected and they meet the characteristics of the potential tailing behavior or coordinated tailing behavior, they are determined to be malicious tailing and the tailing disposal strategy is triggered.
[0011] Preferably, the tailing handling strategy includes at least one of the following: Keep the second door locked to prevent anyone from entering the gym. Control the audible and visual alarm to issue a local alarm; Send alarm information to the terminal device of the remote monitoring center or gym administrator; If the tailing is determined to be malicious, the first gate is controlled to close or lock in a delayed manner to temporarily trap the tailing person in the buffer area.
[0012] Preferably, the system further includes: An internal monitoring module, installed inside the gym, is used to continuously monitor the status of internal activities; The central processing unit is further linked with the internal monitoring module and is configured as follows: After the second gate is opened, the area near the gate is continuously monitored for a period of time. If an unverified person is detected approaching from the inside and attempting to open the second door, the second door will be immediately locked and an alarm will be triggered.
[0013] Preferably, the main access control device is a two-way verification device and is located at the exit; the system further includes: Exit detection logic: When a user verifies and leaves through the main access control device at the exit, the tailgating detection module is triggered to confirm that there are no multiple people leaving at the same time, in order to prevent equipment theft.
[0014] Preferably, the second door is controlled by a magnetic lock. After the face recognition screen verifies the information, it sends a signal to the door linkage control unit to control the magnetic lock to unlock and open the door.
[0015] Compared with the prior art, the beneficial effects of the present invention are: 1. Accurate identification: Using depth cameras and millimeter-wave radar, combined with skeletal key points and motion trajectory analysis, it can effectively distinguish between close following, unconscious following and normal passage, greatly reducing false alarm and false negative rates; 2. Proactive defense: The system can proactively analyze, judge, and execute corresponding access control linkage control and alarm strategies, realizing the transformation from "passive monitoring" to "proactive security"; 3. Dual verification: Facial recognition screens are installed both inside and outside the second gate to perform secondary identity verification and record member information, thereby enhancing security; 4. Multiple layers of protection: It not only prevents external tailgating, but also prevents internal violations and asset loss through internal monitoring and exit logic, forming a three-dimensional security system. Attached Figure Description
[0016] Figure 1 This is a schematic diagram of the overall structural layout of the access control and anti-tailgating control system for the unmanned gym of this invention; Figure 2This is a flowchart of the access control and anti-tailgating control system for an unmanned gym according to the present invention.
[0017] In the attached diagram, the following are the reference numerals: 1. Main access control device; 2. First door; 3. Buffer area; 4. Second door; 5. Depth camera; 7. Central processing unit; 8. Door linkage control unit; 9. Audible and visual alarm; 10. Network module; 11. Internal monitoring module; 12. Face recognition screen. Detailed Implementation
[0018] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Identical components are denoted by the same reference numerals. It should be noted that the terms "front," "rear," "left," "right," "up," and "down" used in the following description refer to directions in the accompanying drawings, while the terms "bottom" and "top," "inner" and "outer" refer to directions toward or away from the geometric center of a specific component, respectively.
[0019] Example: Figure 1 As shown, the present invention provides a technical solution: an access control and anti-tailgating control system for an unmanned gym, comprising: Main access control device 1: This device is installed on the outside of the gym entrance. It integrates a card reader (supporting membership cards, ID cards, IC cards, etc.), a QR code scanner, and a camera for the first layer of user authentication. After successful authentication, the device sends a signal to the central processing unit 7 and controls the opening of the first door 2 (e.g., an electric sliding door or a speed gate).
[0020] First door 2 and second door 4: These two doors together form a physical buffer zone 3. First door 2 is outside the entrance, and second door 4 is inside the entrance. The two doors are linked and will not open at the same time under normal circumstances to prevent outsiders from directly entering. Second door 4 is preferably a normally closed door controlled by a magnetic lock, which has high security and stability.
[0021] Tail-following detection module: This module is the core sensor for the anti-tail-following function. It is deployed on the top or side of the buffer area 3 to ensure that its field of view can cover the entire buffer area 3. In this embodiment, the module uses a depth camera 5 (such as a camera based on structured light or TOF technology) and a millimeter-wave radar 6. It can not only collect traditional two-dimensional image information, but also obtain the depth information of the scene, thereby accurately extracting the skeletal key points, real-time three-dimensional position, and movement trajectory of the target in the area, and can reliably distinguish and count different individuals through algorithms.
[0022] Face recognition screen 12: Two high-resolution face recognition screens 12 are installed on the inner and outer sides of the second door 4, respectively. After entering the buffer area 3, the user needs to perform face recognition on the outer screen to complete the second layer of identity verification. When the user leaves the gym, he / she needs to verify on the inner screen. After the verification is successful, the screen will send a door opening and closing signal to the door linkage control unit 8.
[0023] Central Processing Unit 7 (CPU): Typically deployed in the gym's server room or low-voltage electrical shaft, it can be an industrial computer or a high-performance embedded controller. It communicates with all components, such as the main access control device 1, the tailgating detection module, and the door linkage control unit 8, via wired or wireless networks. It is the brain of the entire system, responsible for running the anti-tailgating logic algorithm and making the final decision.
[0024] Door linkage control unit 8: Receives instructions from central processing unit 7 and face recognition screen 12, directly drives the motors and magnetic locks of the first door 2 and the second door 4, and performs specific door opening and closing operations.
[0025] Sound and light alarm 9: Installed in a prominent location in buffer area 3 and inside the gym, it will emit a strong sound and light alarm when the system determines that the person is being followed maliciously or in other abnormal situations, in order to deter criminals and alert those in the vicinity.
[0026] like Figure 2 As shown, the workflow of this system is as follows: S1: Authentication and access to buffer zone 3: When users arrive at the gym entrance, they swipe their cards or scan QR codes on the main access control device 1. The main access control device 1 verifies the validity of the credential; if the verification fails, the door remains closed. If the verification is successful, the main access control device 1 sends a "successful identity verification" signal to the central processing unit 7 and opens the first door 2; The user enters buffer area 3, and the first door 2 then closes.
[0027] S2: Monitoring and analysis within buffer zone 3: The moment a user enters buffer area 3, the tail detection module is triggered and activated by the central processing unit 7. Depth camera 5 starts working, capturing video streams in real time and using built-in algorithms: Counting: Accurately identify and count the number of targets within buffer zone 3.
[0028] Behavior analysis: Track the skeletal keypoints of each target, generate its motion trajectory, calculate movement speed and direction, and analyze the relative distance and positional relationship between multiple targets; These monitoring data are sent to the central processing unit 7 in real time.
[0029] S3 and S4: Central Processing Unit 7 Decision (Anti-Tail-Following Logic Algorithm): Central processing unit 7 analyzes the monitoring data according to a predefined algorithm and makes a judgment: Scenario 1: No tails following (normal passage) Judgment criteria: There is one and only one target detected in the buffer zone, and its movement trajectory is from the first gate 2 directly to the face recognition screen 12 of the second gate 4, and the speed is normal.
[0030] Action executed: The central processing unit 7 sends a "normal passage" command to the door linkage control unit 8. After the user completes the verification on the face recognition screen 12 on the outside of the second door 4, the second door 4 opens and the user enters the gym.
[0031] Scenario 2: Unconscious following (non-malicious tailing) Judgment criteria: Multiple targets (e.g., 2 people) are detected in the buffer zone, but the latter is far away from the former, with obvious time delay or spatial interval (e.g., >1.5 meters), and the latter's behavior is hesitant and does not follow closely.
[0032] Action Execution: The system determines this is not malicious following (e.g., not keeping up with a friend's chat). The central processing unit 7 controls the second door 4 to close with a delay (e.g., 5 seconds) after the first verified user passes through. Simultaneously, the audible and visual alarm 9 emits a brief warning sound (e.g., a "beep beep") and flashes a light, reminding subsequent personnel: "Please verify your identity yourself." Subsequent personnel must return to the main access control point to verify their identity themselves.
[0033] Scenario 3: Potential / Cooperative Tailing (Malicious Tailing) Judgment condition a (potential tailing): The number of targets detected is greater than 1.
[0034] Judgment condition b (cooperative tailing): Two or more targets are detected to maintain an extremely close distance (e.g., <0.5 meters), move in the same direction and at the same speed, and attempt to be identified as a single individual.
[0035] Action Execution: Once any of the above characteristics are met, the system immediately determines it as malicious tailing and triggers the tailing handling strategy: it sends an instruction to the door linkage control unit 8 to keep the second door 4 locked and prevent it from opening; at the same time, it can control the first door 2 to delay closing or lock, temporarily trapping the tailing person in the buffer area 3, activating the audible and visual alarm 9 to issue a strong alarm; and sends alarm information to the remote monitoring center or the gym administrator's terminal device through the network module 10.
[0036] Internal monitoring and exit theft prevention: The gym is equipped with an internal monitoring module 11 (surveillance camera) that is linked to the system. When the second door 4 is opened, the system will continuously monitor the area near the door for a period of time. If it finds that an unverified person is trying to follow or assist someone out when the door is open, it will immediately lock the door and sound an alarm. The exit is also equipped with a main access control device 1 (two-way verification). When a user leaves, they need to verify their identity and the exit access control will open. At the same time, the tailgating detection module will work to confirm whether it is a single person leaving. If multiple people are detected leaving at the same time (such as carrying unpaid gym equipment), the system will lock the exit door and sound an alarm to prevent equipment theft.
[0037] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.
[0038] In the description of this invention, unless otherwise stated, "a plurality of" means two or more; the terms "upper," "lower," "left," "right," "inner," "outer," "front end," "rear end," "head," "tail," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance.
[0039] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to fixed connections or detachable connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.
Claims
1. A door access control and anti-tailgating control system for an unmanned gym, characterized in that, include: The main access control device (1) is installed at the entrance of the gym to verify the user's identity and control the opening of the first door (2); The buffer area (3) is the physical space formed by the first gate (2) and the second gate (4); The tailing detection module is set in the buffer area (3) and is used to collect monitoring data of targets entering the buffer area (3); the tailing detection module includes a depth camera (5) and a millimeter-wave radar (6) for acquiring the target's skeletal key point information, movement trajectory and number; The central processing unit (7), which is communicatively connected to the main access control device (1) and the tailgating detection module, is configured as follows: a) Receive the authentication success signal from the main access control device (1); b) Trigger the tail-following detection module to operate and receive the monitoring data it sends; c) Based on the monitoring data, determine whether tailing behavior exists using a predefined anti-tailing logic algorithm; The door linkage control unit (8) is communicatively connected to the central processing unit (7) and is configured to control the opening and closing states of the first door (2) and the second door (4) according to the judgment result of the central processing unit (7); The second door (4) is equipped with a face recognition screen (12) on both the inner and outer sides to verify the user's identity. After the verification is successful, a signal is sent to the door linkage control unit (8) to control the opening of the second door (4).
2. The access control and anti-tailgating control system for an unmanned gym according to claim 1, characterized in that, The central processing unit (7) is further configured as follows: Based on the data from the depth camera (5), the number of targets entering the buffer area (3) is identified and counted; If the number of targets is greater than one, it is determined that there is potential tailing behavior; Analyze the target's trajectory and speed; If two or more targets are detected to be moving in the same direction at close range, it is determined to be a coordinated tailing behavior.
3. The access control and anti-tailgating control system for an unmanned gym according to claim 1, characterized in that, The anti-tailing logic algorithm includes: If, after successful identity verification, it is detected that only one target enters the buffer area (3) and its behavior trajectory is normal, it is determined that there is no tailing and the second gate is authorized to be opened (4). If multiple targets are detected, but there is a significant time delay or spatial gap between the subsequent target and the verified user, it is determined to be unconscious following. The second gate (4) is controlled to close after the verified user passes through, and a warning sound is issued to remind subsequent personnel to verify themselves. If multiple targets are detected and they meet the characteristics of the potential tailing behavior or coordinated tailing behavior, they are determined to be malicious tailing and the tailing disposal strategy is triggered.
4. The access control and anti-tailgating control system for an unmanned gym according to claim 1, characterized in that, The tailing disposal strategy includes at least one of the following: Control the second door (4) to remain locked, preventing all personnel from entering the gym; Control the audible and visual alarm (9) to issue a local alarm; And send alarm information to the terminal device of the remote monitoring center or gym administrator through the network module (10); After determining that the tailing is malicious, the first gate (2) is controlled to close or lock in a delayed manner to temporarily trap the tailing person in the buffer area (3).
5. The access control and anti-tailgating control system for an unmanned gym according to claim 1, characterized in that, The system also includes: An internal monitoring module (11) is installed inside the gym to continuously monitor the status of internal activities; The central processing unit (7) is further linked with the internal monitoring module (11) and is configured as follows: After the second gate (4) is opened, the area near the gate is continuously monitored for a period of time; If an unverified person is detected approaching from the inside and attempting to open the second door (4), the second door (4) will be locked immediately and an alarm will be triggered.
6. The access control and anti-tailgating control system for an unmanned gym according to claim 1, characterized in that, The main access control device (1) is a two-way verification device and is also located at the exit; the system also includes: Exit detection logic: When a user passes through the main access control device (1) at the exit and leaves, the tailgating detection module is triggered to confirm that there are no multiple people leaving at the same time, so as to prevent theft of equipment.
7. The access control and anti-tailgating control system for an unmanned gym according to claim 1, characterized in that, The second door (4) uses a magnetic lock control switch. After the face recognition screen is verified, it sends a signal to the door linkage control unit (8) to control the magnetic lock to unlock and open the door.
8. A method for preventing tailgating in an unmanned gym based on the system described in any one of claims 1-7, characterized in that, Includes the following steps: S1: Verify the user's identity through the main access control device (1), and open the first door (2) after the verification is successful. S2: When a user enters the buffer area (3), the tailing detection module is triggered to start working and collect monitoring data; S3: The central processing unit (7) receives the monitoring data and performs analysis and judgment based on the anti-tailgating logic algorithm; S4: Based on the judgment result, the door linkage control unit (8) performs the corresponding operation: If it is determined that there is no tailing, the second door (4) is opened to allow the user to enter; If the tailing is determined to be potential or malicious, the corresponding handling strategy will be implemented.
9. The method according to claim 8, characterized in that, The analysis and judgment in step S3 specifically includes: Counting steps: Count the targets that enter the buffer area (3); Behavioral analysis steps: Analyze the target's trajectory, speed, and the relative positions of multiple targets; Intent determination steps: Combining the counting results and behavior analysis results, comprehensively determine whether the target is malicious tailing, unconscious following, or normal solo passage.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 8-9.