Elevator face recognition control method

Abstract

The invention discloses a face recognition control method for an elevator. The face recognition control method comprises the steps that images and depth information of passengers in an elevator entrance area are collected through an image collecting module; the image processing module processes the image, extracts face features of each passenger and compares the face features with information in a database; the behavior recognition module judges whether each passenger walks towards the elevator and enters the elevator or not according to the depth image and the posture estimation; the system establishes an association binding relationship between the face recognition and the entering behavior; an elevator call and a target floor selection instruction are sent to the passengers which are successfully recognized and have the authority; and the identification and behavior records are stored in a database for background audit analysis. The invention belongs to the technical field of artificial intelligence buildings, and particularly provides an artificial intelligence building system which is used for solving the problems that visitors are inconvenient to pass, recognition of multiple persons is confused, and follow-up potential safety hazards exist in the prior art.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence building technology, and specifically refers to an elevator face recognition control method. Background Art

[0002] Currently, for residents on high floors, elevators are essential for access. To prevent strangers from entering the building, gates are installed at the entrances and exits of the first floor of the building. Only after passing identity recognition can one take the stairs to the designated floor. Existing elevator facial recognition has the following technical problems:

[0003] 1. Visitors need to pre-register or obtain temporary authorization, which may cause delays and security risks;

[0004] 2. When multiple people enter the identification area at the same time, the system cannot accurately distinguish individual behaviors, and the system may misidentify or confuse the identification results, causing unauthorized personnel to board the elevator, reducing system security;

[0005] 3. Traditional systems rely on a single sensor, resulting in a high false alarm rate and inability to detect unauthorized tailgating. Summary of the Invention

[0006] The technical problems to be solved by the present invention are the inconvenience of visitor passage, confusion in identification of multiple people, and the potential safety hazards of tailgating in the existing technology.

[0007] In order to solve the above problems, the technical solutions adopted by the present invention are as follows:

[0008] On the one hand, the present invention proposes an elevator face recognition control method, comprising the following steps:

[0009] Step S1: collecting images and depth information of passengers in the elevator entrance area through an image acquisition module;

[0010] Step S2: The image processing module processes the image, extracts facial features of each passenger and compares them with the information in the database;

[0011] Step S3: The behavior recognition module determines whether each passenger walks towards the elevator and enters the elevator based on the depth image and posture estimation;

[0012] Step S4: The system establishes an association and binding relationship between face recognition and entry behavior;

[0013] Step S5: Sending an elevator call and target floor selection instruction to the passenger who has been successfully identified and has the authority;

[0014] Step S6: Store the identification and behavior records in the database for background audit analysis.

[0015] On the other hand, based on the above control method, the present application also includes an elevator face recognition control system, the system comprising:

[0016] Image acquisition module: including an infrared binocular camera and a depth perception camera, which collects facial data to simultaneously obtain color images and depth information;

[0017] Image processing module: connected to the image acquisition module, used to process the facial data collected by the image acquisition module, extract the facial features of each passenger and compare them with the information in the database;

[0018] Behavior recognition and binding module: Uses OpenPose or MediaPipe to obtain human key points in real time; determines whether the passenger moves toward the elevator and enters the elevator car; and establishes a "Face ID-Behavior-ID" binding based on image and trajectory data;

[0019] Elevator control interface module: realizes communication with the elevator control host through RS485 or CAN bus;

[0020] Data storage and event analysis module: used to store identification records and analyze abnormal events;

[0021] Processor: The processor uses NVIDIA Jetson Xavier NX, which supports simultaneous recognition of no less than 6 people and real-time posture tracking.

[0022] Preferably, the system also includes a rights management platform for providing personnel registration, rights configuration, temporary visitor authorization, and log recording; and supports LAN or cloud deployment.

[0023] By adopting the above scheme, the beneficial effects achieved by the present invention are as follows:

[0024] 1. An elevator control method that combines face recognition, depth perception, posture estimation, and trajectory tracking ensures that the system can still achieve precise control in a multi-person environment.

[0025] 2. Behavior recognition can prevent tailgating, and contactless automatic control can achieve high traffic efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a block diagram of the system provided by the present invention.

[0027] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0029] In the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they cannot be understood as limiting the present invention.

[0030] Example 1

[0031] like Figure 1 As shown, the present invention proposes an elevator face recognition control system, comprising:

[0032] Image acquisition module: This includes an infrared binocular camera and a depth perception camera, which collect facial data to simultaneously obtain color images and depth information. The binocular infrared camera uses a Hikvision DS-K1T671MF-B to capture facial images and infrared images, while the depth camera uses an Intel RealSense D435i to obtain 3D depth information of passengers and the scene.

[0033] Image processing module: This module is connected to the image acquisition module and is used to process the facial data collected by the image acquisition module, extract each passenger's facial features, and compare them with the information in the database. It uses an embedded AI processing platform such as NVIDIA Jetson Xavier NX.

[0034] Behavior recognition and binding module: Uses OpenPose or MediaPipe to obtain human key points in real time to determine human behavior (whether to enter the elevator); determines whether the passenger moves toward the elevator and enters the elevator car; and establishes a "face ID-behavior-ID" binding based on image and trajectory data.

[0035] Elevator control interface module: communicates with the elevator control host via RS485 or CAN bus to control elevator calls and floor buttons;

[0036] Data storage and event analysis module: used to store identification records and analyze abnormal events (such as multiple invalid attempts, tailgating behavior, etc.);

[0037] Processor: NVIDIA Jetson Xavier NX, supports simultaneous recognition of no less than 6 people and real-time posture tracking for AI face recognition, posture analysis, and behavior binding.

[0038] In addition, this system also includes a rights management platform, which is used to provide personnel registration, rights configuration, temporary visitor authorization, and log records; it supports LAN or cloud deployment.

[0039] Example 2

[0040] Based on the system described in Example 1, the present invention proposes an elevator face recognition control method, comprising the following steps:

[0041] Step S1: collecting images and depth information of passengers in the elevator entrance area through an image acquisition module;

[0042] Step S2: The image processing module processes the image, extracts facial features of each passenger and compares them with the information in the database;

[0043] Step S3: The behavior recognition module determines whether each passenger walks towards the elevator and enters the elevator based on the depth image and posture estimation;

[0044] Step S4: The system establishes an association and binding relationship between face recognition and entry behavior;

[0045] Step S5: Sending an elevator call and target floor selection instruction to the passenger who has been successfully identified and has the authority;

[0046] Step S6: Store the identification and behavior records in the database for background audit analysis.

[0047] Example 3

[0048] Application scenarios include the following:

[0049] Scene 1: Single person scene in an office building:

[0050] Employee A approaches the elevator door. The system captures their facial image and, after comparison, successfully identifies them as "Zhang," whose access is granted to the 5th floor. Their face faces the elevator and they move toward the car. The system confirms their entry and associates their facial ID with their behavior ID. The elevator automatically arrives, and the button for the 5th floor lights up, without Zhang having to press anything.

[0051] Scenario 2: Multiple people enter the scene at the same time:

[0052] Employees B and C arrive at the elevator door simultaneously. The system identifies each person separately and tracks their movements. B enters the elevator, while C remains in place and moves backward. The system only authorizes B to call the elevator and illuminates the corresponding floor. C's entry behavior is not associated with the system, so no control command is triggered.

[0053] Scenario 3: Tailing behavior recognition:

[0054] Visitor D approaches the elevator without authorization at the same time as authorized visitor E. The system recognizes that E has permission to enter the elevator, but D has no identification information and is not recognized as a visitor. Based on behavior tracking, the system determines that D is following an abnormal person, issues an alarm, and prohibits the elevator door from closing.

[0055] This technology can be widely used in smart building scenarios such as smart parks, office buildings, residential communities and government buildings, and has great promotion value.

[0056] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. An elevator face recognition control method, characterized in that: The following steps are involved: Step S1: collecting images and depth information of passengers in the elevator entrance area through an image acquisition module; Step S2: The image processing module processes the image, extracts facial features of each passenger and compares them with the information in the database; Step S3: The behavior recognition module determines whether each passenger walks towards the elevator and enters the elevator based on the depth image and posture estimation; Step S4: The system establishes an association and binding relationship between face recognition and entry behavior; Step S5: Sending an elevator call and target floor selection instruction to the passenger who has been successfully identified and has the authority; Step S6: Store the identification and behavior records in the database for background audit analysis.

2. The elevator face recognition control method according to claim 1, characterized in that: The image acquisition module in step S1 includes an infrared binocular camera and a depth perception camera to synchronously acquire color images and depth information.

3. The elevator face recognition control method according to claim 2, characterized in that: In step S3, the posture estimation uses the OpenPose or MediaPipe algorithm to identify the passenger's behavior in real time.

4. The elevator face recognition control method according to claim 3, characterized in that: The behavior binding condition in step S4 includes at least one of the following: Passengers enter the elevator car; The passenger faces the camera and moves towards the elevator; Passengers complete the entry process within 3 seconds.

5. A system based on the elevator face recognition control method according to any one of claims 1 to 4, characterized in that: include: Image acquisition module: including an infrared binocular camera and a depth perception camera, which collects facial data to simultaneously obtain color images and depth information; Image processing module: connected to the image acquisition module, used to process the facial data collected by the image acquisition module, extract the facial features of each passenger and compare them with the information in the database; Behavior recognition and binding module: This module uses OpenPose or MediaPipe to acquire key points of the human body in real time; determines whether a passenger moves toward the elevator and enters the elevator car; and establishes a "Face ID-Behavior-ID" binding based on image and trajectory data. Elevator control interface module: realizes communication with the elevator control host through RS485 or CAN bus; Data storage and event analysis module: used to store identification records and analyze abnormal events.

6. The system according to claim 5, characterized in that Also includes: The permission management platform is used to provide personnel registration, permission configuration, temporary visitor authorization, and log records; Supports LAN or cloud deployment.

7. The system according to claim 6, characterized in that: The system also includes a processor using the NVIDIA Jetson Xavier NX, which supports simultaneous recognition of no less than 6 people and real-time posture tracking.

8. The system according to claim 7, characterized in that: The system can identify situations where multiple people enter at the same time and establish identity control binding for each matching recognition result and behavior result.

9. The system according to claim 5, characterized in that: The abnormal events include multiple invalid attempts and tailgating behavior.

Images