A hidden face capture device and method for residential use

Abstract

The present invention relates to a hidden face capture device and method for residential use. The device includes a shell and a central processing unit, a face capture sensor, a time-of-flight (TOF) sensor, a power conversion unit, and a WiFi communication unit installed in the shell. The shell is a square box, one of the side surfaces of the shell is a mounting surface, and the face capture sensor is arranged on the mounting surface and is mounted in a direction away from the mounting surface. On the side surface opposite to the mounting surface, a one-way light-transmitting glass panel is provided at a position corresponding to the face capture sensor. After the device is powered on, the face capture sensor detects and captures faces in real time. When the TOF sensor is triggered, the captured face information is uploaded. The present invention is based on a face detection algorithm and TOF (Time‑of-Flight) measurement technology to achieve accurate and automatic face capture of people entering and exiting doors of hotels, apartments, public rental housing, etc., with the characteristics of no missed captures and no mistaken captures, thereby improving user experience.

Description

Technical Field

[0001] The present invention relates to the field of security technology, and in particular to a hidden face capturing device and method for residential use. Background Art

[0002] Currently, most facial capture devices on the market are traditional surveillance cameras, used for security monitoring and facial capture. Public security departments require strict management of personnel entering and exiting places such as hotels, apartments, and public rental housing. Traditional facial capture devices have the following shortcomings:

[0003] 1. Traditional face capture devices are usually installed in public places such as passages and lobbies to monitor places with large traffic flow, but cannot monitor and manage people entering and leaving the room.

[0004] 2. Traditional face capture devices are bulky, lack concealment, and provide a poor user experience.

[0005] 3. Traditional face capture devices are powered by POE or DC power adapters. Construction and deployment require re-laying of network cables and power cables, and cannot achieve 220V AC power supply and 86 box installation. Summary of the Invention

[0006] In response to the technical problems existing in the prior art, the present invention provides a hidden face capture device and method for residential use. Based on a face detection algorithm and TOF (Time-of-Flight) measurement technology, the device and method can accurately and automatically capture the faces of people entering and leaving doors of hotels, apartments, public rental housing, etc., with the characteristics of no missed or mistaken capture, thereby improving the user experience.

[0007] The technical solution of the present invention to solve the above technical problems is as follows:

[0008] On the one hand, the present invention provides a hidden face capture device for residential use, comprising a housing and a central processing unit, a face capture sensor, a TOF sensor, a power conversion unit, and a WiFi communication unit installed in the housing;

[0009] The housing is a square box, one side of the housing is a mounting surface, and the face capture sensor is arranged on the mounting surface and is mounted in a direction away from the mounting surface;

[0010] On the side surface opposite to the mounting surface, a one-way light-transmitting glass panel is provided at a position corresponding to the face capture sensor;

[0011] The TOF sensor is mounted on a side surface adjacent to the mounting surface, and a scanning axis of the TOF sensor is perpendicular to a shooting axis of the face capture sensor;

[0012] The face capture sensor, TOF sensor, and WiFi communication unit are all electrically connected to the central processing unit;

[0013] The power conversion unit is externally connected to a 220V mains power supply and supplies power to the central processing unit, the face capture sensor, the TOF sensor, and the WiFi communication unit respectively.

[0014] Furthermore, a fill light device is provided in the housing.

[0015] Furthermore, the fill light device includes a photosensor and an infrared fill light. The photosensor is used to detect the brightness of the ambient light and automatically turns on the infrared fill light mode when there is insufficient light, ensuring that a clear face is captured in a dark environment.

[0016] Furthermore, the central processing unit is built with the image processing chip Hi3516CV500 as the core.

[0017] Furthermore, the face capture sensor uses a 2-megapixel high-definition wide dynamic CMOS sensor, which can meet the lighting scenes of different intensities such as dark light and strong light in the corridor, ensuring the clarity of the captured face.

[0018] Furthermore, the TOF chip uses the TOF10120 chip and the image processing chip Hi3516CV500 with a computing power of 0.5T (Tera Operations Per Second). It has an embedded intelligent face algorithm, supports face capture, face tracking, and face exposure compensation in complex environments, supports detection, tracking, capture, scoring, and screening of moving faces, and outputs the optimal face photos.

[0019] On the other hand, the present invention also provides a residential hidden face capture method based on the above device, comprising:

[0020] When the device is powered on, the face capture sensor enters real-time scanning mode. If there is no moving object within the preset time period, the device automatically enters power saving mode. When a moving object is detected, it enters face detection mode.

[0021] In face detection mode, the face capture sensor automatically recognizes facial images. If there is a face image within the field of view, it enters face capture mode and caches the captured face information. If there is no face, it returns to face camera scanning mode.

[0022] After the face capture sensor captures the face information, if the TOF sensor is triggered within the preset time period, the cached face information will be uploaded to the cloud server; if the TOF sensor is not triggered within the preset time period, the cached data will be deleted.

[0023] Furthermore, the preset time period is 60 seconds.

[0024] The beneficial effects of this invention are as follows: A TOF (Time-of-Flight) sensor, utilizing the principle that light takes different distances to travel, detects whether someone is passing a residential door. When someone passes, the sensor detects a change in distance and triggers a command to upload the facial recognition data. This allows for accurate recording of the person entering the door. The TOF sensor avoids the drawbacks of infrared sensors, which require the transmitter and receiver to be mounted on opposite sides of the aisle, and also avoids the drawbacks of radar sensors that can cause false triggering due to their large detection radius. A Wi-Fi wireless communication module is used to upload detected facial data to a cloud server, resolving the wiring difficulties associated with construction deployment. The invention utilizes 220V AC power supply and a built-in 220V AC to 12V DC power conversion circuit, eliminating the need for an additional power adapter at the construction site. The device features a one-way light-transmitting glass panel that can be screen-printed with environmentally friendly patterns to conceal both the camera and infrared fill light. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A diagram showing the structure of a device provided in an embodiment of the present invention;

[0026] Figure 2 A schematic diagram of the installation of the device provided in an embodiment of the present invention;

[0027] Figure 3 A flow chart of a method provided by an embodiment of the present invention;

[0028] Figure 4 This is a schematic diagram of a power conversion unit circuit provided by an embodiment of the present invention.

[0029] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0030] 1. Housing, 2. Central processing unit, 3. Face capture sensor, 4. TOF sensor, 5. Power conversion unit, 6. WiFi communication unit, 7. Fill light device. DETAILED DESCRIPTION

[0031] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0032] The present invention provides a hidden face capturing device for residential use, such as Figure 1 As shown, it includes a housing 1 and a central processing unit 2, a face capture sensor 3, a TOF sensor 4, a power conversion unit 5, and a WiFi communication unit 6 installed in the housing 1;

[0033] The housing 1 is a square box, one side of which is a mounting surface, and the face capture sensor 3 is arranged on the mounting surface and is mounted in a direction away from the mounting surface;

[0034] On the side surface opposite to the mounting surface, a one-way light-transmitting glass panel (not shown in the figure) is provided at a position corresponding to the face capture sensor 3;

[0035] The TOF sensor 4 is mounted on a side surface adjacent to the mounting surface, and a scanning axis of the TOF sensor 4 is perpendicular to a shooting axis of the face capture sensor 3;

[0036] The face capture sensor 3, TOF sensor 4, and WiFi communication unit 6 are all electrically connected to the central processing unit 2;

[0037] The power conversion unit 5 is externally connected to a 220V mains power supply and supplies power to the central processing unit 2 , the face capture sensor 3 , the TOF sensor 4 , and the WiFi communication unit 6 respectively.

[0038] Furthermore, a fill light device 7 is provided in the housing 1 .

[0039] Furthermore, the fill light device 7 includes a photosensor and an infrared fill light. The photosensor is used to detect the brightness of the ambient light and automatically turns on the infrared fill light mode when the light is insufficient to ensure that a clear face is captured in a dark environment.

[0040] Furthermore, the central processing unit 2 is built around the Hi3516CV500 image processing chip, which boasts a computing power of 0.5T (Tera Operations Per Second). It also features an embedded intelligent facial recognition algorithm, supporting face capture, face tracking, and face exposure compensation in complex environments. It also supports detection, tracking, capture, scoring, and screening of moving faces, ultimately outputting the optimal face photo.

[0041] Furthermore, the face capture sensor 3 uses a 2-megapixel high-definition wide dynamic CMOS sensor, which can meet the lighting scenes of different intensities such as dark light and strong light in the corridor, ensuring the clarity of the captured face.

[0042] Furthermore, the TOF sensor 4 uses a TOF10120 chip. It can be installed on the left and right sides of the device, and the installation position can be adjusted according to the door opening direction. As an example, the TOF is installed on the right side of the device. Figure 2As shown in the figure, the TOF sensor detects whether someone enters the room and triggers the facial recognition camera to upload facial information. For example, if the door opens to the right, the device is installed on the left side of the entrance. The facial recognition camera captures the face in front of the door. When the person opens the door and enters the room, the TOF sensor detects the change in detection distance, triggering the device to upload facial information, thereby accurately counting the number of people entering the room.

[0043] On the other hand, an embodiment of the present invention further provides a residential hidden face capture method based on the above device, comprising:

[0044] When the device is powered on, the face capture sensor enters real-time scanning mode. Its intelligent detection function can determine moving objects within the field of view. If there is no moving object within the preset time period, the device automatically enters power saving mode. When a moving object is detected, it enters face detection mode.

[0045] In face detection mode, the face capture sensor automatically recognizes facial images. If there is a face image within the field of view, it enters face capture mode and caches the captured face information. If there is no face, it returns to face capture sensor scanning mode.

[0046] After the face capture sensor captures a person's face, if the TOF sensor triggers within a preset time period, indicating that the person whose face was captured has entered the room, the cached facial information will be uploaded to the cloud server. If the TOF sensor does not trigger within the preset time period, indicating that the person whose face was captured has not entered the room and is someone else passing through the hallway, the cached data will be deleted. In this embodiment, the preset time period is 60 seconds.

[0047] The TOF ranging method is as follows:

[0048] The TOF sensor measures the distance in real time at a preset frequency and returns the result to the central processing unit. As an example, the present invention measures the distance once every 100 milliseconds.

[0049] When someone passes by the door, the distance detected by the TOF sensor changes, generating a trigger event and linking the face capture sensor to upload a face image. For example, if the measured distance data decreases by more than 20 cm and continues to decrease for more than 500 milliseconds, it is determined that someone has passed by.

[0050] It should be noted that this invention uses TOF (Time-of-Flight) measurement technology for personnel access detection. Similar technical solutions include radar detection, pyroelectric infrared sensor detection, through-beam infrared sensor detection, and door magnetic detection. However, these sensors are not as large, costly, and easy to install as TOF measurement technology.

[0051] In this embodiment of the present invention, a Time-of-Flight (TOF) sensor uses the principle that light takes different distances to detect whether someone is passing a residential door. When someone passes, the sensor detects a change in distance and triggers a facial recognition command. This accurately records the person entering the door. The TOF sensor avoids the drawbacks of infrared sensors, which require the transmitter and receiver to be installed on both sides of the aisle, and also avoids the false triggering issues of radar sensors due to their large detection radius. A Wi-Fi wireless communication module is used to upload detected facial data to a cloud server, solving the wiring difficulties during construction deployment. The invention utilizes 220V mains power supply and a built-in 220V AC to 12V DC power conversion circuit, eliminating the need for an additional power adapter on the construction site. The device features a one-way light-transmitting glass panel that can be screen-printed with environmentally friendly patterns to conceal cameras and infrared fill lights.

[0052] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A hidden face capture device for residential use, characterized in that: It comprises a housing (1) and a central processing unit (2), a face capture sensor (3), a TOF sensor (4), a power conversion unit (5), and a WiFi communication unit (6) installed in the housing (1); The housing (1) is a square box body, one side surface of the housing (1) is a mounting surface, and the face capture sensor (3) is arranged on the mounting surface and is mounted in a direction away from the mounting surface; On the side surface opposite to the mounting surface, a one-way light-transmitting glass panel is provided at a position corresponding to the face capture sensor (3); The TOF sensor (4) is mounted on a side surface adjacent to the mounting surface, and the scanning axis of the TOF sensor (4) is perpendicular to the shooting axis of the face capture sensor (3); The face capture sensor (3), the TOF sensor (4), and the WiFi communication unit (6) are all electrically connected to the central processing unit (2); The power conversion unit (5) is externally connected to a 220V mains electricity supply and supplies power to the central processing unit (2), the face capture sensor (3), the TOF sensor (4), and the WiFi communication unit (6); The face capture sensor (3) is used to enter a real-time scanning mode after the device is powered on to detect moving objects, and is used to automatically identify a face image, capture face information and cache it when a moving object is detected; The TOF sensor (4) is used to detect a change in distance within a preset time period and trigger a face upload instruction.

2. The device according to claim 1, characterized in that A light-filling device (7) is also provided in the housing (1).

3. The device according to claim 2, characterized in that The fill light device includes a photosensor and an infrared fill light.

4. The device according to any one of claims 1 to 3, characterized in that The central processing unit (2) is built with the image processing chip Hi3516CV500 as the core.

5. The device according to any one of claims 1 to 3, characterized in that: The face capture sensor adopts a 2 million high-definition wide dynamic CMOS sensor.

6. The device according to any one of claims 1 to 3, characterized in that The TOF sensor uses the TOF10120 chip.

7. A residential hidden face capture method based on the device according to any one of claims 1 to 6, characterized in that: include: When the device is powered on, the face capture sensor enters real-time scanning mode. If there is no moving object within the preset time period, the device automatically enters power saving mode. When a moving object is detected, it enters face detection mode. In face detection mode, the face capture sensor automatically recognizes face images. If there is a face image within the viewing range, it enters face capture mode and caches the captured face information. If there is no face, it returns to the face camera scanning mode; After the face capture sensor captures the face information, if the TOF sensor is triggered within the preset time period, the cached face information will be uploaded to the cloud server; if the TOF sensor is not triggered within the preset time period, the cached data will be deleted.

8. The method according to claim 7, characterized in that The preset time period is 60 seconds.

Images