Intelligent channel gate based on face recognition
By introducing self-cleaning face recognition device and neural network algorithm into the gate, automatically cleaning the camera and adjusting the shooting position, the problem of easy damage and pollution of the face recognition device of the gate is solved, and the quality and traffic efficiency of face recognition are improved .
Patent Information
- Application Number
- CN202420158962.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-23
- Publication Date
- 2024-12-17
- Estimated Expiration
- 2034-01-23
AI Technical Summary
The face recognition device of the existing gate machine is easily damaged and the camera is easily contaminated, resulting in unclear face photos taken and affecting passage.
A self-cleaning face recognition device is designed, including a camera module and a telescopic rod. The camera is automatically cleaned by a self-cleaning device, and combined with a neural network algorithm module, the camera is automatically adjusted according to the height of the human body to ensure that the captured photos are clear.
Effectively filter dust and handprints, keep the camera clean, improve the quality and recognition rate of face recognition, and improve the traffic efficiency of the gate.
Smart Images
Figure CN222189924U_ABST
Abstract
Description
Technical Field
[0001] The utility model belongs to the technical field of gate machines, and in particular relates to an intelligent channel gate machine based on face recognition. Background Art
[0002] The turnstile is a channel blocking device, that is, a channel management device, which is used to manage the flow of people and regulate the entry and exit of pedestrians. It is mainly used in airport, high-speed rail and subway turnstile systems and toll ticket gate systems. Its most basic core function is to ensure that only one person passes at a time. It can be used at the entrance of various toll and access control occasions.
[0003] The existing facial recognition device of the gate is fixed on the top of the gate, which is easy to cause damage to the facial recognition device. At the same time, too many passengers pass through the gate every day, and the camera of the gate may be contaminated by dust, human fingerprints, etc. The camera is blurred, and the face taken will be unclear, resulting in the failure of face detection, affecting the passage of passengers. Utility Model Content
[0004] In order to solve the above technical problems, the utility model proposes an intelligent channel gate based on face recognition, comprising: a first single-door gate, a second single-door gate, a self-cleaning face recognition device, and a sensing device;
[0005] The first single-door gate machine and the second single-door gate machine constitute the intelligent channel gate machine;
[0006] The sensing device is provided at the entrance of the gate door side of the first single-door gate machine;
[0007] A cavity is provided at the top of the entrance of the second single-door gate machine, and the self-cleaning face recognition device is arranged in the cavity;
[0008] The self-cleaning face recognition device includes a self-cleaning device, a camera module and a telescopic rod; the bottom of the camera module is connected to the telescopic rod, and the top of the camera module is connected to the self-cleaning device, and the camera on the camera module is cleaned by the self-cleaning device.
[0009] Preferably, a hinge is also provided above the cavity. When the intelligent channel gate is working, the hinge opens and the telescopic rod controls the lifting and lowering of the self-cleaning face recognition device. When the intelligent channel gate stops working, the telescopic rod controls the self-cleaning face recognition device to descend into the cavity and the hinge closes at the same time.
[0010] Preferably, the algorithm module is also provided inside the second single-door gate machine, and the algorithm module is pre-equipped with a neural network algorithm model, and the neural network algorithm model automatically calculates the height of the human body according to the ratio of the height of the human body to the photograph of the human body in the photograph.
[0011] Furthermore, the algorithm module is connected to a self-cleaning face recognition device. When a person passes through the second gate opening machine, the self-cleaning face recognition device will receive the human body height sent by the algorithm module, and control the telescopic rod to automatically extend and lower according to the human body height, so that the camera module can take clear facial photos.
[0012] Beneficial effects of the utility model:
[0013] The utility model is provided with an automatic cleaning device, which can effectively filter out dust, marks and other interferences to the camera imaging in the unattended gate passage, so that the camera always maintains a clear state, thereby improving the quality of capturing human faces and the recognition rate, and finally achieving the result of improving the gate communication efficiency;
[0014] The camera module of the utility model is provided with a telescopic rod, through which the same module can be raised and lowered. When working, the camera module is raised, and when not working, the camera module is lowered into the gate body, so that the camera module can be protected. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 This is a schematic diagram of the overall structure of an intelligent channel gate based on face recognition in the utility model;
[0016] Figure 2 This is a schematic diagram of the structure of the self-cleaning face recognition device of the utility model; Description of the drawings:
[0018] 1. First single-door gate machine; 2. Second single-door gate machine; 3. Self-cleaning face recognition device; 4. Sensing device; 5. Cavity; 6. Hinge; 7. Self-cleaning device; 8. Camera module; 9. Telescopic rod. DETAILED DESCRIPTION
[0019] The following will be combined with the drawings in the embodiments of the utility model to clearly and completely describe the technical solutions in the embodiments of the utility model. Obviously, the described embodiments are only part of the embodiments of the utility model, not all of the embodiments. Based on the embodiments in the utility model, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the utility model.
[0020] An intelligent channel gate based on face recognition, such as Figure 1 As shown, it includes: a first single-door gate machine 1, a second single-door gate machine 2, a self-cleaning face recognition device 3, and a sensing device 4;
[0021] The first single-door gate machine 1 and the second single-door gate machine 2 constitute the intelligent channel gate machine;
[0022] The sensing device 4 is provided at the entrance of the gate door side of the first single-door gate machine 1;
[0023] A cavity 5 is provided at the top of the entrance of the second single-door gate machine 2, and the self-cleaning face recognition device 3 is arranged in the cavity 5;
[0024] like Figure 2 As shown, the self-cleaning face recognition device 3 includes a self-cleaning device 7, a camera module 8 and a telescopic rod 9; the bottom of the camera module 8 is connected to the telescopic rod 9, and the top of the camera module 8 is connected to the self-cleaning device 7, and the camera on the camera module 8 is cleaned by the self-cleaning device 7.
[0025] In this embodiment, a hinge 6 is further provided above the cavity 5. When the intelligent channel gate is working, the hinge 6 is opened, and the telescopic rod 9 controls the lifting and lowering of the self-cleaning face recognition device 3. When the intelligent channel gate stops working, the telescopic rod 9 controls the self-cleaning face recognition device 3 to descend into the cavity 5, and the hinge 6 is closed at the same time.
[0026] In this embodiment, the algorithm module is also provided inside the second single-door gate machine 2. The algorithm module is pre-equipped with a neural network algorithm model. The neural network algorithm model automatically calculates the height of the human body according to the ratio of the height of the human body to the height of the photographed human body.
[0027] In this embodiment, the algorithm module is connected to the self-cleaning face recognition device 3. When a person passes through the second gate opening machine 2, the self-cleaning face recognition device 3 will receive the human height sent by the algorithm module, and control the telescopic rod 9 to automatically extend and lower according to the human height, so that the camera module 8 can take clear facial photos. The adaptive lifting function can effectively improve the traffic efficiency, and will not cause irregular facial features of the captured person due to the problem of the passenger's angle, resulting in multiple recognitions, and the passenger needs to constantly adjust the angle and height.
[0028] In this embodiment, the sensing device 4 can use an infrared sensor to detect the thermal radiation of the human body. When someone arrives at the gate, the infrared sensor detects the change in the thermal radiation of the human body, thereby obtaining the perception information of the arrival of the person, so that the entire gate group enters the working state.
[0029] In this embodiment, the self-cleaning device 7 includes a motor and a brush rod. The motor is arranged inside the camera module 8. The transmission shaft of the motor is connected to the brush rod. The brush rod is fixed with bristles on a side wall close to the camera. In actual use, when dust or fingerprints are attached to the surface of the camera lens, causing blur, the motor is started to rotate, thereby driving the brush rod to rotate back and forth, so that the dust can be brushed off, thereby ensuring the clarity of the image acquisition;
[0030] The use process of this utility model is as follows:
[0031] When a passenger approaches the gate channel, the sensing device of the gate channel is triggered, and the sensing device triggers the automatic face recognition device, which will start the automatic cleaning device above to clean the camera of the face;
[0032] When the camera captures a person, the algorithm module uses an algorithm to roughly calculate the height of the person based on the proportion of the person's height in the entire photo;
[0033] When the height of the face is found to be high, the lifting device at the bottom of the face recognition device will rise to a certain height. For example, the original optimal height of the gate machine test is about 1.6-1.7cm, and the current passenger is found to be about 1.8cm high, so the lifting device will rise by about 1-2cm. The specific height can be set according to the actual lifting height.
[0034] When the passenger has his / her face captured and authenticated at the best position, the gate door opens and prompts the passenger to pass through. After the passenger passes through the gate, the lifting device returns to the initial set height and the cleaning device is turned on to clean the lens to prevent the passenger from contaminating the camera with his / her hands or other objects.
[0035] The automatic cleaning device can also be actively triggered multiple times during the face capture process. For example, when a blur assessment is performed on the captured face, if it is found that the face is blurry when captured multiple times, the cleaning device can be actively started to clean the dust and marks on the camera.
[0036] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. An intelligent channel gate based on face recognition, characterized in that: include: The first single-door gate machine, the second single-door gate machine, the self-cleaning face recognition device, and the sensing device; The first single-door gate machine and the second single-door gate machine constitute the intelligent channel gate machine; The sensing device is provided at the entrance of the gate door side of the first single-door gate machine; A cavity is provided at the top of the entrance of the second single-door gate machine, and the self-cleaning face recognition device is arranged in the cavity; The self-cleaning face recognition device includes a self-cleaning device, a camera module and a telescopic rod; the bottom of the camera module is connected to the telescopic rod, and the top of the camera module is connected to the self-cleaning device, and the camera on the camera module is cleaned by the self-cleaning device.
2. According to claim 1, the intelligent channel gate based on face recognition is characterized in that: A hinge is also provided above the cavity. When the intelligent channel gate is working, the hinge is opened, and the telescopic rod controls the lifting and lowering of the self-cleaning face recognition device. When the intelligent channel gate stops working, the telescopic rod controls the self-cleaning face recognition device to descend into the cavity, and the hinge is closed at the same time.
3. The intelligent channel gate based on face recognition according to claim 1 is characterized in that: An algorithm module is also provided inside the second single-door gate machine. The algorithm module is pre-equipped with a neural network algorithm model. The neural network algorithm model automatically calculates the height of the human body according to the ratio of the height of the human body to the height of the human body in the photograph.
4. The intelligent channel gate based on face recognition according to claim 3 is characterized in that: The algorithm module is connected to the self-cleaning face recognition device. When a person passes through the second single-door gate, the self-cleaning face recognition device will receive the human body height sent by the algorithm module, and control the telescopic rod to automatically extend and lower according to the human body height, so that the camera module can take clear facial photos.