CN219738185U - Face recognition system - Google Patents

Abstract

The utility model provides a face recognition system, comprising: the device comprises a controller, an image acquisition device, a power supply module, a controlled switch, a human body detection module, a storage module and a level detection circuit; the power module is electrically connected with the power end of the image acquisition device through the controlled switch, the control end of the controlled switch is electrically connected with the output end of the controller, the image acquisition device and the human body detection module are electrically connected with the input end of the controller, the storage module is electrically connected with the output end of the controller, the input end of the level detection circuit is electrically connected with the signal end of the energy storage module, and the output end of the level detection circuit is electrically connected with the input end of the controller, so that the problem that video data cannot be normally output under the influence of external environment or after long-time working of the camera is solved.

Description

Face recognition system

Technical Field

The utility model relates to the field of face recognition, in particular to a face recognition system.

Background

Along with the high-speed development of the intelligent age, the application of the face recognition intelligent terminal display screen in the life of people is more and more extensive. The camera is the most basic hardware configuration of a display screen of the face recognition intelligent terminal and is used for realizing data acquisition of face images. The camera generally realizes the data interaction between the camera and the CPU end through an MIPI CSI or USB communication interface mode. Sometimes, in order to shorten the software development period and adapt to cameras of different manufacturers, an interface mode of USB communication is often adopted. In practical application, the problem that the USB camera cannot normally output video data may occur due to the influence of external environmental factors (such as static electricity) or long-time working, if the camera is not reset in time, the problem of incapability of normal face recognition is finally caused.

In view of this, the present utility model has been proposed.

Disclosure of Invention

The utility model discloses a face recognition system, and aims to solve the problem that in the prior art, a camera cannot normally output video data under the influence of external environment or after long-time working.

The embodiment of the utility model provides a face recognition system, which comprises: the device comprises a controller, an image acquisition device, a power supply module, a controlled switch, a human body detection module, a storage module and a level detection circuit;

the power supply module is electrically connected with the power supply end of the image acquisition device through the controlled switch, the control end of the controlled switch is electrically connected with the output end of the controller, the image acquisition device and the human body detection module are electrically connected with the input end of the controller, the storage module is electrically connected with the output end of the controller, the input end of the level detection circuit is electrically connected with the signal end of the energy storage module, and the output end of the level detection circuit is electrically connected with the input end of the controller;

wherein the controller is configured to implement the following steps by executing a computer program stored therein:

acquiring human body signals acquired by the human body detection module in real time;

when the human body signal judges that a human body passes through a position close to the image acquisition device, acquiring waveforms of a signal end of the storage module in a preset period through the level detection circuit;

and resetting the image acquisition device through the controlled switch according to the waveform.

Preferably, the resetting of the image acquisition device by the controlled switch according to the waveform specifically includes:

judging whether the waveform is a preset waveform or not;

if not, generating a low-level signal to the controlled switch, and generating a high-level signal to the controlled switch after preset time delay, so that the image acquisition device is reset.

Preferably, the controlled switch comprises: the single-pole double-throw electronic switch, the first resistor and the first capacitor;

the control end of the single-pole double-throw electronic switch is electrically connected with the output end of the controller, the control end of the single-pole double-throw electronic switch is grounded through the first resistor, a fixed contact of the single-pole double-throw electronic switch is electrically connected with the power end of the image acquisition device, a first movable contact of the single-pole double-throw electronic switch is electrically connected with the output end of the power module, and a second movable contact of the single-pole double-throw electronic switch is grounded through the first capacitor;

one end of the blade of the single-pole double-throw electronic switch is connected with the fixed contact, and the other end of the blade of the single-pole double-throw electronic switch can be switched between the first movable contact and the second movable contact.

Preferably, the storage module comprises a card reader controller and a TF card receiving groove;

the output end of the card reader controller is electrically connected with the TF card receiving groove, the input end of the card reader controller is electrically connected with the input end of the controller, and the signal end of the card reader controller is electrically connected with the input end of the level detection circuit.

Preferably, the level detection circuit includes: the first triode, the second resistor and the third resistor;

the signal end of the card reader controller is electrically connected with the b pole of the first triode through the second resistor, the c pole of the first triode is electrically connected with the input end of the controller, the e pole of the first triode is grounded, and the c pole of the first triode is connected with a power supply through the third resistor.

Preferably, the human body detection module includes: the infrared sensor, the second triode, the fourth resistor and the fifth resistor;

the output end of the infrared sensor is electrically connected with the b pole of the second triode through the fifth resistor, the second triode e is grounded, the c pole of the second triode is electrically connected with the input end of the controller, and the c pole of the second triode is connected with a power supply through the fourth resistor.

Preferably, the method further comprises: a display screen;

wherein, the display screen with the controller electrical connection.

Preferably, the method further comprises: a high-speed switch disposed between the image pickup device and the controller;

the control end of the high-speed switch is electrically connected with the output end of the controller.

Preferably, the image acquisition device is a binocular camera.

Preferably, the model of the controller is: RK3399.

Based on the human face recognition system provided by the utility model, the controller detects whether a human body passes through the image acquisition device through the human body detection module, when detecting that the human body passes through, the controller acquires the waveform of the signal end of the storage module in a preset period through the level detection circuit, and when detecting that the waveform does not accord with the preset waveform, the controller disconnects the image acquisition device from the power module through controlling the controlled switch and electrifies again after delaying for a preset period of time, so that the reset of the image acquisition device is realized, and the problem that the camera cannot normally output video data under the influence of external environment or after working for a long time is solved.

Drawings

Fig. 1 is a schematic circuit diagram of a face recognition system according to the present utility model;

fig. 2 is a schematic flow chart of the steps executed by the controller according to the present utility model.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present utility model more apparent, the technical solutions of the embodiments of the present utility model will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present utility model, and it is apparent that the described embodiments are some embodiments of the present utility model, but not all embodiments. All other embodiments, based on the embodiments of the utility model, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the utility model. Thus, the following detailed description of the embodiments of the utility model, as presented in the figures, is not intended to limit the scope of the utility model, as claimed, but is merely representative of selected embodiments of the utility model. All other embodiments, based on the embodiments of the utility model, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the utility model.

Specific embodiments of the present utility model will be described in detail below with reference to the accompanying drawings.

The utility model discloses a face recognition system, and aims to solve the problem that in the prior art, a camera cannot normally output video data under the influence of external environment or after long-time working.

Referring to fig. 1, an embodiment of the present utility model provides a face recognition system, including: the device comprises a controller U1, an image acquisition device U6, a power supply module U7, a controlled switch, a human body detection module, a storage module and a level detection circuit;

the power module U7 is electrically connected with a power end of the image acquisition device U6 through the controlled switch, a control end of the controlled switch is electrically connected with an output end of the controller U1, the image acquisition device U6 and the human body detection module are electrically connected with an input end of the controller U1, the storage module is electrically connected with an output end of the controller U1, an input end of the level detection circuit is electrically connected with a signal end of the energy storage module, and an output end of the level detection circuit is electrically connected with an input end of the controller U1;

it should be noted that, the controller U1 is a combination of core system modules, and includes PMIC, CPU, LPDDR, EMMC, usb_hub, etc. inside, having audio/video encoding/decoding functions, including mipi_csi interface, mipi_dsi interface, USB interface, and a combination circuit including WIFI, bluetooth, ethernet, etc., actually running under the android platform, where IO1, IO2, IO3 are GPIO ports of U1, IO1 is an output port, IO2, IO3 are input ports, and IO1 outputs a high level by default;

in this embodiment, the image capturing device U6 may be a binocular camera, which is not limited to this, and two USB interfaces are respectively connected to the controller U1.

It should be noted that, the inventor finds that after the camera works for a long time, or is influenced by environmental factors, such as static electricity, the video data cannot be output normally, so that the face recognition function is invalid, and the attendance of a company, the entrance guard of a community gate and the like may be influenced.

In this embodiment, referring to fig. 2, the controller U1 is configured to implement the following steps by executing a computer program stored therein:

acquiring human body signals acquired by the human body detection module in real time;

when the human body signal judges that a human body passes through a position close to the image acquisition device U6, acquiring waveforms of a signal end of the storage module in a preset period through the level detection circuit;

and resetting the image acquisition device U6 through the controlled switch according to the waveform.

In this embodiment, the controller U1 detects whether a human body passes through the position of the image acquisition device U6 through the human body detection module, and when detecting that a human body passes through the position, the controller U1 collects waveforms of a signal end of the storage module (wherein, the signal end of the storage module outputs a certain regular high-low level, which can be represented by a waveform F) within a preset period through the level detection circuit, and when detecting that the waveforms do not conform to the preset waveforms, the controller U1 disconnects the connection between the image acquisition device U6 and the power module U7 by controlling the controlled switch, and re-electrifies the image acquisition device U6 after delaying for a preset period, thereby solving the problem that the camera cannot normally output video data under the influence of external environment or after working for a long time.

In a possible embodiment of the present utility model, the resetting of the image capturing device U6 by the controlled switch according to the waveform is specifically:

judging whether the waveform is a preset waveform or not;

if not, generating a low-level signal to the controlled switch, and after a preset delay, generating a high-level signal to the controlled switch, so that the image acquisition device U6 is reset.

It should be noted that, in this embodiment, the controller U1 does not detect the generated waveform F of the storage module (that is, the signal end of the storage module does not output a certain rule of high-low level) within a preset period of time, which indicates that the controller U1 does not collect the face data, and the image collecting device U6 is in an abnormal working state, so that the image collecting device U6 needs to be reset in time.

In one possible embodiment of the utility model, the controlled switchable comprises: the single-pole double-throw electronic switch K1, the first resistor R1 and the first capacitor C1;

the control end of the single-pole double-throw electronic switch K1 is electrically connected with the output end of the controller U1, the control end of the single-pole double-throw electronic switch K1 is grounded through the first resistor R1, a fixed contact of the single-pole double-throw electronic switch K1 is electrically connected with the power end of the image acquisition device U6, a first movable contact of the single-pole double-throw electronic switch K1 is electrically connected with the output end of the power module U7, and a second movable contact of the single-pole double-throw electronic switch K1 is grounded through the first capacitor C1;

one end of the blade of the single-pole double-throw electronic switch K1 is connected with the fixed contact, and the other end of the blade of the single-pole double-throw electronic switch K1 can be switched between the first movable contact and the second movable contact.

It should be noted that, the first resistor R1 is a pull-down resistor, the first capacitor C1 is a filter capacitor, where the single-pole double-throw electronic switch K1 is controlled by the controller U1, in a default state, the fixed contact is electrically connected with the first movable contact, and when a signal end generates a level that receives a change, the fixed contact is electrically connected with the second movable contact.

The fixed contact and the second movable contact are electrically connected when the initialization power-on is received, the image acquisition device U6 is powered on, the fixed contact and the first movable contact are electrically connected when the reset signal is received, and the image acquisition device U6 is disconnected from the power supply.

In one possible embodiment of the present utility model, the storage module includes a card reader controller U3, a TF card receiving slot U9, wherein the TF card receiving slot U9 is configured to receive TF cards;

the output end of the card reader controller U3 is electrically connected with the TF card receiving groove U9, the input end of the card reader controller U3 is electrically connected with the input end of the controller U1, and the signal end of the card reader controller U3 is electrically connected with the input end of the level detection circuit.

It should be noted that, for the card reader circuit module of the TF card, USB communication is performed with the controller U1, so as to realize the function of converting USB to TF interface, the LED pin on the card reader controller U3 is the LED output pin of the indicator light of the card reader chip, when data is written into the TF card, the LED pin of the indicator light outputs a certain regular high-low level, which is denoted by waveform F for convenience of description later; the chips of different manufacturers have differences, and in actual application, corresponding chips are selected according to the needs.

In one possible embodiment of the present utility model, the level detection circuit includes: the first triode Q1, the second resistor R2 and the third resistor R3;

the signal end of the card reader controller U3 is electrically connected with the b pole of the first triode Q1 through the second resistor R2, the first triode Q1 c pole is electrically connected with the input end of the controller U1, the first triode Q1 e is grounded, and the first triode Q1 c pole is connected with a power supply through the third resistor R3.

It should be noted that, the second resistor R2 is a current limiting resistor, the third resistor R3 is a pull-up resistor, the first triode Q1 is configured to connect the output end of the controller U1 and the LED pin of the card reader controller U3, and the controller U1 can collect the level signal of the LED pin based on the current limiting resistor.

In one possible embodiment of the present utility model, the human body detection module includes: an infrared sensor U2, a second triode Q2, a fourth resistor R4 and a fifth resistor R5;

the output end of the infrared sensor U2 is electrically connected with the b pole of the second triode Q2 through the fifth resistor R5, the second triode Q2e is grounded, the second triode Q2c pole is electrically connected with the input end of the controller U1, and the second triode Q2c pole is connected with the power supply through the fourth resistor R4.

The fourth resistor R4 is a pull-up resistor, and the fifth resistor R5 is a current limiting resistor.

The principle in the above embodiment is explained below, when the infrared sensor U2 does not detect the infrared signal generated by the movement of the human body, the infrared sensor U2 outputs a low level, the second triode Q2 is cut off, at this time, the IO3 of the controller U1 detects a high level, the controller U1 considers that no face recognition request is generated, the controller U1 does not call the IO2 input interface, does not read the status data of the IO2, does not perform the judgment of the communication abnormality of the USB interface, and the controller U1 maintains the current working state.

When the infrared sensor U2 detects an infrared signal generated by movement of a human body, the infrared sensor U2 outputs a high level, the second triode Q2 is conducted, the IO3 of the controller U1 detects a low level, the controller U1 considers that a face recognition request exists, an IO2 input interface is called, IO2 state data is read in unit time (T0 +N), and the controller U1 judges whether the camera works normally or not through the state data.

If the image acquisition device U6 is in a normal working state, the controller U1 and the controller U1 can perform normal communication, the controller U1 will acquire the face DATA of the camera, after the face algorithm processing of the controller U1, the face access recording DATA are finally stored in the TF card, in the process that the face access recording DATA are written in the TF card, the LED pins of the card reader controller U3 will output a certain regular high-low level (waveform F), the IO2 will detect the change of the high-low level (waveform F) in the time (t0+n), and the controller U1 considers that the image acquisition device U6 is in a normal working state and keeps the current state. If the image acquisition device U6 is in an abnormal working state, the controller U1 and the image acquisition device U6 cannot normally communicate, the controller U1 cannot acquire the face DATA of the camera, no face access record DATA DATA is written into the TF, the LED pins of the card reader controller U3 are kept in a high-level state, the IO2 cannot detect the change of the high-low level (waveform F) in time (T0+N), the controller U1 considers that the image acquisition device U6 is in the abnormal working state, the controller U1 controls the IO1 to be low, after the time delay T1, the controller U1 is pulled up again, the reset of the image acquisition device U6 is completed, and finally the controller U1 recalls relevant driving and application to realize the normal work of the camera and ensure the normal face recognition.

In one possible embodiment of the present utility model, it may further include: a display screen U8;

wherein, display screen U8 with controller U1 electrical connection.

It should be noted that the display screen U8 may be a touch screen, which is not limited to this.

In one possible embodiment of the present utility model, further comprising: a high-speed switch arranged between the image pickup device U6 and the controller U1;

the control end of the high-speed switch is electrically connected with the output end of the controller U1.

It should be noted that, the number of the high-speed switches may be two U4/U5, which are USB high-speed switches, and the bandwidth thereof satisfies the USB high-speed communication requirement.

In one possible embodiment of the present utility model, the model number of the controller may be: RK3399.

Of course, in other embodiments, other types of controllers are also possible, and the present utility model is not limited to these embodiments.

Based on the face recognition system provided by the utility model, the controller U1 detects whether a human body passes through the position of the image acquisition device U6 through the human body detection module, when detecting that the human body passes through, the controller U1 acquires the waveform of the signal end of the storage module in a preset period through the level detection circuit, and when detecting that the waveform does not accord with the preset waveform, the controller U1 disconnects the image acquisition device U6 from the power module U7 through controlling the controlled switch, and the controller is electrified again after delaying for a preset period of time, so that the reset of the image acquisition device U6 is realized, and the problem that the camera cannot normally output video data under the influence of external environment or after working for a long time is solved.

The above is only a preferred embodiment of the present utility model, and the protection scope of the present utility model is not limited to the above examples, and all technical solutions belonging to the concept of the present utility model belong to the protection scope of the present utility model.

Claims (9)

1. A face recognition system, comprising: the device comprises a controller, an image acquisition device, a power supply module, a controlled switch, a human body detection module, a storage module and a level detection circuit;

the power module is electrically connected with the power end of the image acquisition device through the controlled switch, the control end of the controlled switch is electrically connected with the output end of the controller, the image acquisition device and the human body detection module are electrically connected with the input end of the controller, the storage module is electrically connected with the output end of the controller, the input end of the level detection circuit is electrically connected with the signal end of the storage module, and the output end of the level detection circuit is electrically connected with the input end of the controller.

2. A face recognition system according to claim 1, wherein the controlled switch comprises: the single-pole double-throw electronic switch, the first resistor and the first capacitor;

the control end of the single-pole double-throw electronic switch is electrically connected with the output end of the controller, the control end of the single-pole double-throw electronic switch is grounded through the first resistor, a fixed contact of the single-pole double-throw electronic switch is electrically connected with the power end of the image acquisition device, a first movable contact of the single-pole double-throw electronic switch is electrically connected with the output end of the power module, and a second movable contact of the single-pole double-throw electronic switch is grounded through the first capacitor;

one end of the blade of the single-pole double-throw electronic switch is connected with the fixed contact, and the other end of the blade of the single-pole double-throw electronic switch can be switched between the first movable contact and the second movable contact.

3. The face recognition system of claim 1, wherein the memory module comprises a card reader controller, a TF card receiving slot;

the output end of the card reader controller is electrically connected with the TF card receiving groove, the input end of the card reader controller is electrically connected with the input end of the controller, the signal end of the card reader controller is electrically connected with the input end of the level detection circuit, and the TF card receiving groove is used for configuring the TF card.

4. A face recognition system according to claim 3, wherein the level detection circuit comprises: the first triode, the second resistor and the third resistor;

the signal end of the card reader controller is electrically connected with the b pole of the first triode through the second resistor, the c pole of the first triode is electrically connected with the input end of the controller, the e pole of the first triode is grounded, and the c pole of the first triode is connected with a power supply through the third resistor.

5. The face recognition system of claim 1, wherein the human detection module comprises: the infrared sensor, the second triode, the fourth resistor and the fifth resistor;

the output end of the infrared sensor is electrically connected with the b pole of the second triode through the fifth resistor, the second triode e is grounded, the c pole of the second triode is electrically connected with the input end of the controller, and the c pole of the second triode is connected with a power supply through the fourth resistor.

6. A face recognition system according to claim 1, further comprising: a display screen;

wherein, the display screen with the controller electrical connection.

7. A face recognition system according to claim 1, further comprising: a high-speed switch disposed between the image pickup device and the controller;

the control end of the high-speed switch is electrically connected with the output end of the controller.

8. A face recognition system according to claim 1, wherein the image acquisition means is a binocular camera.

9. The face recognition system of claim 1, wherein the controller is of the type: RK3399.