WO2023097951A1 - 智能安防控制方法、智能安防设备及控制器 - Google Patents

智能安防控制方法、智能安防设备及控制器 Download PDF

Info

Publication number
WO2023097951A1
WO2023097951A1 PCT/CN2022/088325 CN2022088325W WO2023097951A1 WO 2023097951 A1 WO2023097951 A1 WO 2023097951A1 CN 2022088325 W CN2022088325 W CN 2022088325W WO 2023097951 A1 WO2023097951 A1 WO 2023097951A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
detected
intelligent security
person
information
Prior art date
Application number
PCT/CN2022/088325
Other languages
English (en)
French (fr)
Inventor
赵江涛
Original Assignee
歌尔股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 歌尔股份有限公司 filed Critical 歌尔股份有限公司
Publication of WO2023097951A1 publication Critical patent/WO2023097951A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00Burglar, theft or intruder alarms
    • G08B13/18Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
    • G08B13/189Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
    • G08B13/194Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
    • G08B13/196Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B1/00Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
    • H04B1/38Transceivers, i.e. devices in which transmitter and receiver form a structural unit and in which at least one part is used for functions of transmitting and receiving
    • H04B1/40Circuits

Definitions

  • the invention relates to the field of intelligent security technology, in particular to an intelligent security control method, intelligent security equipment and a controller.
  • the main purpose of the present invention is to provide an intelligent security control method, intelligent security equipment and a controller, aiming at reducing the power consumption of the intelligent security equipment.
  • the present invention proposes an intelligent security control method, which is applied to intelligent security equipment.
  • the intelligent security equipment includes a speaker module.
  • the intelligent security control method includes:
  • Step S100 detecting whether a person enters the area to be detected
  • Step S200 when it is determined that a person enters the area to be detected, collect the behavior state of the person in the area to be detected, and generate corresponding behavior state information;
  • Step S300 when it is determined according to the behavior state information that the person in the area to be detected has a call intention, control the speaker module to turn on.
  • the smart security device includes an infrared sensor, and the step S100 is specifically:
  • Step S110 detecting the infrared radiation value in the area to be detected, and generating infrared detection information
  • the step of determining that a person enters the area to be detected is specifically as follows:
  • Step S210 when it is determined according to the infrared detection information that the infrared radiation value in the area to be detected is within a preset range of human body radiation values, it is determined that a person enters the area to be detected.
  • the smart security device includes an image sensing component
  • the step S200 includes:
  • Step S220 when it is determined that a person enters the area to be detected, turn on the image sensing component, and capture the image information of the person in the area to be detected;
  • Step S230 perform motion recognition on the image information, and generate corresponding personnel motion information
  • the step S300 is specifically:
  • Step S310 according to the information of the person's movement, when it is determined that the mouth movement of the person in the area to be detected is a speaking movement, control the speaker module to start working.
  • the smart security device includes a microphone
  • the step S200 includes:
  • Step S240 when it is determined that a person enters the area to be detected, turn on the microphone, acquire the audio in the area to be detected, and output the corresponding audio information of the area to be detected;
  • the step S300 is specifically:
  • Step S320 According to the audio information of the area to be detected, when it is determined that the audio amplitude of the area to be detected reaches a preset audio amplitude, control the speaker module to start working.
  • the smart security device includes a microphone and an image sensing component
  • the step S200 includes:
  • Step S250 when it is determined that a person enters the area to be detected, turn on the image sensing component, and capture the image information of the person in the area to be detected;
  • Step S260 performing motion recognition on the image information, generating corresponding personnel motion information, and controlling the microphone to be turned on when it is determined according to the personnel motion information that the mouth motion of the person in the area to be detected is a speaking motion, To obtain the audio in the area to be detected, and output the corresponding audio information of the area to be detected;
  • the step S300 is specifically:
  • Step S330 according to the audio information of the area to be detected, when it is determined that the audio amplitude of the area to be detected reaches a preset audio amplitude and the mouth movement of the person in the area to be detected is a speaking action, control the The speaker module starts to work.
  • the intelligent security control method also includes:
  • Step S400 when it is determined according to the behavior state information that the person in the area to be detected has no intention of talking, control the speaker module to be in a stop state.
  • the smart security device includes a complete machine and a driving component connected to the drive of the complete machine, the front microphone and the rear microphone in an end-fire array are arranged in the complete machine, after performing the step S300,
  • the intelligent security control method also includes:
  • Step S500 obtaining the position of the person in the area to be detected
  • Step S600 controlling the driving assembly to drive the whole machine to move according to the position of the person in the detection area, so that the front microphone, the rear microphone and the person in the detection area are on the same straight line.
  • the whole machine is provided with an image sensing component, the image sensing component includes an image sensor and a lens, and the step S500 is specifically:
  • Step S510 turn on the image sensing component to photograph the person in the area to be detected, and obtain the distance information between the imaging position on the image sensor and the center point of the image sensor;
  • Step S520 according to the distance information and the distance between the image sensor and the lens, calculate the standing angle between the person in the area to be detected and the whole machine, and generate standing angle information;
  • the step S600 is specifically:
  • Step S610 according to the standing angle information, control the driving assembly to drive the whole machine to move until the standing angle is 0 degrees, so that the front microphone, the rear microphone and the person in the area to be detected are in the same position in a straight line.
  • the present invention also proposes an intelligent security equipment controller, the intelligent security equipment controller comprising:
  • the present invention also proposes an intelligent security device, which includes:
  • the intelligent security equipment controller according to claim 9, the intelligent security equipment controller is arranged in the whole machine;
  • the drive assembly is connected to the complete machine, and the drive assembly is electrically connected to the intelligent security device controller;
  • a speaker module the speaker module is arranged in the whole machine, and the speaker module is electrically connected to the intelligent security device controller;
  • a front microphone and a rear microphone, the front microphone and the rear microphone are arranged in the complete machine in an end-fire array, and both the front microphone and the rear microphone are electrically connected to the intelligent security device controller;
  • the personnel entry detection component is arranged in the complete machine, and the personnel entry detection component is electrically connected to the intelligent security equipment controller;
  • An image sensing component the image sensing component is arranged in the complete machine, the image sensing component includes an image sensor and a lens, and the image sensing component is electrically connected to the intelligent security device controller;
  • the front microphone, the rear microphone and the image sensing component are arranged in the middle of the whole machine.
  • the speaker module is controlled to be turned on.
  • the speaker module when it is determined that someone enters the area to be detected, the speaker module will not be turned on at the first time, but when it is determined that the person in the area to be detected has the intention to speak, then the speaker module will be controlled to turn on, and in the confirmed area to be detected When the person has no intention to speak, the control horn module remains in the stop working state, thereby effectively reducing the power consumption of the intelligent security equipment.
  • Fig. 1 is a flow chart of the method steps of an embodiment of the intelligent security control method of the present invention
  • FIG. 2 is a flow chart of method steps in another embodiment of the intelligent security control method of the present invention.
  • Fig. 3 is a flow chart of method steps in another embodiment of the intelligent security control method of the present invention.
  • Fig. 4 is a flow chart of method steps in yet another embodiment of the intelligent security control method of the present invention.
  • FIG. 5 is a flow chart of method steps in another embodiment of the intelligent security control method of the present invention.
  • FIG. 6 is a flow chart of method steps in another embodiment of the intelligent security control method of the present invention.
  • Fig. 7 is a flow chart of method steps in yet another embodiment of the intelligent security control method of the present invention.
  • FIG. 8 is a flow chart of method steps in another embodiment of the intelligent security control method of the present invention.
  • FIG. 9 is a schematic diagram of the specific implementation of the method of an embodiment of the intelligent security control method of the present invention.
  • Fig. 10 is a schematic diagram of the specific implementation of the method of an embodiment of the intelligent security control method of the present invention.
  • Fig. 11 is a schematic diagram of functional modules of an embodiment of the intelligent security device of the present invention.
  • FIG. 12 is a schematic diagram of front and rear microphones in an endfire array.
  • step codes such as S100 and S200 are used, the purpose of which is to express the corresponding content more clearly and concisely, and does not constitute a substantive limitation on the order.
  • S200 will be executed first, followed by S100, etc., but these should be within the scope of protection of this application.
  • smart security devices are now used in many places, such as smart doorbells, smart surveillance cameras, etc. After detecting that someone has entered the area to be detected, the camera, microphone and speaker modules are turned on, but it is often just unrelated people passing by. Instead of having a voice conversation, if the speaker module is turned on at this time, its internal amplification circuit is generally above the watt level, which will increase the power consumption of the smart security device.
  • the present invention proposes an intelligent security control method, which is applied to intelligent security equipment, and the intelligent security equipment includes a speaker module.
  • the speaker module includes a speaker and an amplifying circuit electrically connected thereto.
  • the present invention proposes an intelligent security control method including:
  • Step S100 detecting whether a person enters the area to be detected
  • Step S200 when it is determined that a person enters the area to be detected, collect the behavior state of the person in the area to be detected, and generate corresponding behavior state information;
  • Step S300 when it is determined according to the behavior state information that the person in the area to be detected has a call intention, the speaker module is controlled to be turned on.
  • the smart security device may include a person-entry detection component and a controller electrically connected thereto.
  • the person-entry detection component is used to detect whether someone has entered the area to be detected, that is, the identifiable area of the smart security device. It can be understood that the specific range of the area to be detected can be set by the research and development personnel, and can also be set by the user according to requirements.
  • the personnel entry detection component can be realized by an infrared sensing device, such as an infrared sensor, which can obtain the infrared radiation value in the area to be detected, that is, within the preset detection range of the infrared sensor, and generate infrared radiation detection information
  • an infrared sensing device such as an infrared sensor
  • the controller can determine that someone has entered when the infrared radiation value in the area to be detected is around the normal human body infrared radiation value according to the infrared radiation detection information.
  • the personnel detection component can also be realized by using a photoelectric sensor, for example, a set of gratings is set in the area to be detected, and when a person enters the area to be detected, the path between the transmitting end and the receiving end of the photoelectric sensor will be blocked , so that the receiving end cannot receive the infrared light emitted by the transmitting end.
  • the photoelectric sensor outputs a signal of someone entering the controller, such as a low-level signal.
  • the receiving end can normally receive the transmitting end. Infrared light is emitted, at this time the photoelectric sensor will output a no-person entry signal to the controller, such as a high-level signal, and the controller can determine whether someone has entered the area to be detected according to the signal from the photoelectric sensor.
  • the controller is electrically connected to the speaker module.
  • the controller When it is determined that a person enters the area to be detected, it can detect and collect the behavior of the person, such as "speaking voice, facial movements, gestures" and other behaviors. status, to generate corresponding behavior status information, and judge whether the personnel in the current area to be detected needs to communicate with the user side of the smart security device according to the behavior status information, that is, to determine whether the personnel in the area to be detected have a call intention.
  • the controller judges that the person in the current area to be detected has the intention to speak, it will control the current speaker module to start working to meet the actual needs of the user to communicate with the person in the area to be detected.
  • the intelligent security control method further includes:
  • Step S400 when it is determined according to the behavior state information that the person in the area to be detected has no intention of talking, control the speaker module to be in a stop state.
  • the controller in the smart security device will not control the opening of the speaker module, and will not start the amplifier circuit inside the speaker module, which effectively reduces the power consumption of the smart security device.
  • the speaker module is controlled to be turned on.
  • the speaker module when it is determined that someone enters the area to be detected, the speaker module will not be turned on at the first time, but when it is determined that the person in the area to be detected has the intention to speak, then the speaker module will be controlled to turn on, and in the confirmed area to be detected When the person has no intention to speak, the control horn module remains in the stop working state, thereby effectively reducing the power consumption of the intelligent security equipment.
  • the intelligent security device includes an image sensing component, and step S200 includes:
  • Step S220 when it is determined that a person enters the area to be detected, the image sensing component is turned on, and the image information of the person in the area to be detected is captured;
  • Step S230 perform motion recognition on the image information, and generate corresponding personnel motion information
  • a human face recognition module can also be integrated in the controller.
  • the controller in the intelligent security device first controls the image sensor component, such as the camera is turned on, and the person in the area to be detected is photographed.
  • the image of the person while determining the location of the person, will also perform action recognition on the image information, such as facial action recognition, and generate corresponding personnel action information.
  • Step S300 is specifically:
  • Step S310 when it is determined that the mouth movement of the person in the area to be detected is a speaking movement according to the movement information of the person, the speaker module is controlled to start working.
  • the speaker module is controlled to start working. For example, within a certain preset time, when the number of mouth opening ratio movements of the people in the area to be detected reaches the preset number of times, it is determined that the mouth movements of the people in the current area to be detected are speaking actions, and the speaker module is controlled to start working .
  • the controller cannot normally recognize the face image in the area to be detected according to the information of the movement of the person, for example, the person in the area to be detected is just a passer-by, it will not recognize When the face image of the person in the waiting area is detected, or when it is recognized that the mouth movement of the person in the waiting area is not a speaking action, it is determined that the current person in the waiting area has no intention of talking. At this time, the controller will control the speaker module to keep in the stop working state. In this way, it is possible to judge whether the person in the current area to be detected has a call intention by means of personnel motion recognition, and when there is no call intention, the speaker module is controlled not to start, thereby reducing the power consumption of the smart security device.
  • the smart security device includes a microphone
  • step S200 includes:
  • Step S240 when it is determined that a person enters the area to be detected, turn on the microphone, acquire the audio in the area to be detected, and output the corresponding audio information of the area to be detected;
  • Step S300 is specifically:
  • Step S320 According to the audio information of the area to be detected, when it is determined that the audio amplitude of the area to be detected reaches a preset audio amplitude, the speaker module is controlled to start working.
  • the controller is electrically connected to the microphone, and the microphone can pick up the audio in the area to be detected, and convert the audio signal picked up as an analog signal to analog-to-digital conversion to generate audio information in the area to be detected as a digital signal.
  • the device will determine the audio amplitude of the current area to be detected according to the audio information of the area to be detected. If the audio amplitude reaches the preset amplitude, for example, the sound intensity represented by the preset amplitude is 30 decibels. If the sound intensity is 40 decibels, it can be determined that the people in the area to be detected have a call demand, and the speaker module will be turned on to meet the call needs of the user and the people in the area to be detected.
  • the controller will not activate the speaker module to reduce the power consumption of the smart security device if the user side is required to make a call.
  • the smart security device includes a microphone and an image sensing component
  • step S200 includes:
  • Step S250 when it is determined that a person enters the area to be detected, the image sensing component is turned on, and the image information of the person in the area to be detected is captured;
  • Step S260 Carry out action recognition on the image information, generate corresponding personnel action information, and according to the personnel action information determine that the mouth movement of the person in the area to be detected is a speaking action, control the microphone to turn on, so as to obtain the audio in the area to be detected , and output the corresponding audio information of the area to be detected;
  • Step S300 is specifically:
  • Step S330 according to the audio information of the area to be detected, when it is determined that the audio amplitude of the area to be detected reaches the preset audio amplitude and the mouth movement of the person in the area to be detected is a speaking action, the speaker module is controlled to start working.
  • the controller when it is determined that a person enters the area to be detected, the controller will control the image sensing component, such as turning on the camera, to capture the current image information of the person in the area to be detected, and After performing motion recognition on the image information, corresponding personnel motion information is generated, and when the mouth motion of the person in the area to be detected is determined to be a speaking motion according to the personnel motion information, the controller will turn on the microphone again, as in the above-mentioned embodiment According to the audio information of the area to be detected, it is determined whether the audio amplitude in the area to be detected has reached a preset amplitude.
  • the speaker module is controlled to start working to meet the needs of the person in the area to be detected and the user for talking ; If it is determined that the audio amplitude of the area to be detected does not reach the preset audio amplitude, then it is judged that the personnel in the area to be detected has no intention of speaking, so the control speaker module remains in a stop working state to reduce the power consumption of the intelligent security device.
  • the front controller determines that the mouth movement of the person in the area to be detected is not a speaking action according to the information of the person's action, that is, when it is determined that the person in the area to be detected does not have any intention to speak, The microphone will not be turned on, thereby further reducing the power consumption of smart security devices.
  • the intelligent security device includes an infrared sensor, and step S100 is specifically:
  • Step S110 detecting the infrared radiation value in the area to be detected, and generating infrared detection information
  • Step S210 when it is determined according to the infrared detection information that the infrared radiation value in the area to be detected is within the preset range of human body radiation values, it is determined that a person enters the area to be detected.
  • the infrared sensor will detect the infrared radiation value in the area to be detected, and generate corresponding infrared detection information to the controller.
  • the human body When a person enters the infrared detection area, the human body will radiate infrared rays to the outside, so when the controller determines that the infrared radiation in the current area to be detected is within the preset human body radiation value range according to the infrared detection information, the controller can determine that there is currently a person Entered the detection zone.
  • the preset range of human body radiation value can be preset by the research and development personnel according to the conventional value of human body infrared radiation value and stored in the controller of the intelligent security device.
  • infrared identification it is possible to detect whether there is a person entering the area to be detected by way of infrared identification.
  • the use of infrared sensors to check whether people have entered the area to be detected can effectively reduce the power consumption of the entire smart security device compared to the use of surveillance cameras.
  • the intelligent security device includes a complete machine and a drive assembly connected to the drive of the complete machine, and a front microphone and a rear microphone in an end-fire array are arranged in the complete machine;
  • the front microphone and the rear microphone form an end-fire array, that is, the front microphone and the rear microphone are arranged on the same straight line in the whole machine, and the front microphone is arranged on the whole machine
  • the front end and the rear microphone are set at the rear end of the machine.
  • the beamforming formed by the dual-microphone end-fire array can be used. If the signal of the front microphone in the array is added to the inverse delay signal of the rear microphone, a " difference". If the sound comes from 0°, the superimposed sound will be doubled, that is, the voice enhancement area.
  • the front microphone may also consist of a plurality of small microphones to form a front microphone array
  • the rear microphone may also consist of a plurality of small microphones to form a rear microphone array.
  • the intelligent security control method further includes:
  • Step S500 obtaining the position of the person in the area to be detected
  • the intelligent security device also includes a personnel position detection component for detecting the personnel position, the personnel position detection component is electrically connected with the controller, after the controller determines that the current personnel has entered the area to be detected, the controller can control The personnel position detection component detects the personnel position in the area to be detected.
  • the personnel position detection component can be realized by a camera, and an image recognition chip can be integrated in the controller.
  • the camera can take pictures of the area to be detected and generate corresponding image information to the controller.
  • the controller not only displays the image information on the user side of the smart security device or uploads it through the internal communication component
  • the controller can also identify the position of the person image in the image in the area to be detected according to the image information, so as to determine the position of the person in the area to be detected.
  • the personnel position detection component can also be realized by using an ultrasonic positioning component or a microwave positioning component.
  • the controller can start after confirming that a person enters the area to be detected Ultrasonic positioning component, the ultrasonic positioning component can locate the position of the area to be detected where the current person is in the way of ultrasonic positioning.
  • Step S600 control the driving assembly to drive the whole machine to move according to the position of the person in the detection area, so that the front microphone, the rear microphone and the person in the detection area are on the same straight line.
  • the front microphone and the rear microphone form an end-fire array, the closer the angle between the line where the front and rear microphones are located and the line between the person and the whole machine is closer to 0°, the final pass The closer the audio amplitude of the audio information of the area to be detected outputted by the speaker module is to twice the amplitude of the sound signal emitted by the person in the area to be detected, the clearer it will be.
  • the controller receives the first audio signal picked up by the front microphone and the second audio signal picked up by the rear microphone.
  • the controller converts the received first audio signal and the second audio signal which are analog signals into digital signals, and then delays the second audio signal of the digital signal according to a preset delay time before returning Phase processing, and superimposed with the first audio signal which is a digital signal to form the audio information of the area to be detected;
  • the front microphone and the rear microphone can also have their own analog-to-digital converters, so that the output of the first audio signal and the second audio signal Both audio signals are digital signals.
  • the preset delay time can be obtained by the research and development personnel through multiple experiments based on the distance between the front microphone and the rear microphone and preset in the controller.
  • the controller will determine whether the person in the current area to be detected has the intention to speak according to the audio information of the area to be detected. It can be understood that in this embodiment, the controller can delay the second audio signal according to the preset After inverting and delaying processing, it is superimposed with the first audio signal to generate audio information of the area to be detected. And according to the audio information of the area to be detected, the audio amplitude in the area to be detected is determined, and then according to the relationship between the audio amplitude in the area to be detected and the preset amplitude, it is determined whether the person in the area to be detected has the intention to speak.
  • the driving component can be a motor, which can drive the whole machine to rotate at 360 degrees
  • the controller can control the motor to drive the whole machine to rotate according to the detected position of the person in the area to be detected until the front of the whole machine is exactly
  • the front microphone will also be facing the person in the detection area at this time, that is, the straight line where the front and rear microphones are located and the distance between the person and the whole machine
  • the included angle of the straight line is 0°, so that the audio amplitude of the audio information of the area to be detected finally output by the speaker module is twice that of the auxiliary sound signal issued by the person in the area to be detected, and it can also reduce the noise in the area to be detected.
  • Noise which plays a role of noise reduction, thereby improving the audio clarity of the output audio information of the area to be detected.
  • the driving component can also be realized by a manipulator, and the controller can perform face recognition on the pictures captured by the camera in the above embodiment, identify the face position of the person in the area to be detected, and control the manipulator to drive the whole machine to always be in the normal position.
  • the face of the person in the detection zone is to be treated.
  • the angle between the straight line where the front and rear microphones are located and the straight line between the person and the whole machine is always 0°, so that the standing position of the speaking person in the area to be detected can be just in front of and behind the end-fire array
  • the voice enhancement area of the microphone can effectively reduce the noise component in the acquired audio information of the area to be detected, that is, the noise component in the sound signal emitted by the person in the area to be detected, and effectively improve the sound signal emitted by the person.
  • the audio amplitude is higher, so that the voice of the person in the area to be detected can be heard more clearly on the user side of the smart security device, which improves the convenience for the user to use the smart security device and improves the call quality of the smart security device.
  • an image sensing component is provided in the whole machine, and the image sensing component includes an image sensor and a lens.
  • Step S500 is specifically:
  • Step S510 turn on the image sensing component to photograph the person in the area to be detected, and obtain the distance information between the imaging position on the image sensor and the center point of the image sensor;
  • Step S520 according to the distance information and the distance between the image sensor and the lens, calculate the standing angle of the person in the area to be detected and the whole machine, and generate standing angle information;
  • the image sensing component may be the image sensing component in the above embodiment, that is, when it is confirmed in the above embodiment that someone enters the area to be detected and the image sensing component is turned on to capture the image information of the person in the area to be detected , the distance information between the imaging position on the image sensor and the center point of the image sensor can also be acquired at the same time.
  • the image sensing component can be a camera, wherein the image sensor in the camera is a photosensitive element array composed of a plurality of photosensitive elements, and the image sensor can calculate the imaging position according to the imaging position on the photosensitive element array.
  • Step S600 is specifically:
  • Step S610 according to the standing angle information, control the driving component to drive the whole machine to move until the standing angle is 0 degrees, so that the front microphone, the rear microphone and the person in the detection area are on the same straight line.
  • the drive assembly can be realized by a motor. It can be seen from the content of the above-mentioned embodiment that when the person in the area to be detected is speaking to the front microphone, the front microphone in the end-fire array will and voice enhancement zone for the rear microphone. Therefore, the controller will control the drive assembly to drive the whole machine to rotate according to the calculated standing angle information until the standing angle is 0 degrees, that is, the current whole machine is facing the person in the area to be detected. There is an end-fire array in the machine, so the front microphone will also be facing the inspector at this time. In this way, the person to be detected can be placed in the speech enhancement area of the front microphone and the rear microphone in the end-fire array.
  • is the standing angle of the whole machine and the personnel in the area to be detected
  • d is the distance between the imaging position on the image sensor and the center point of the image sensor
  • L is the distance between the image sensor and the lens Distance
  • the controller can obtain the standing angle between the person in the current area to be detected and the whole machine, and control the drive assembly according to the standing angle Adjust the orientation angle of the whole machine until the standing angle is 0°, that is, the front microphone in the whole machine is just facing the people in the detection area.
  • an intelligent security equipment controller which includes:
  • a processor 20, the processor 20 is electrically connected to the memory 10;
  • the embodiments of the intelligent security device controller of the present invention include all the technical solutions of all the embodiments of the above-mentioned intelligent security control method, and the achieved The technical effects are also exactly the same, and will not be repeated here.
  • an intelligent security device which includes:
  • the above-mentioned intelligent security equipment controller is set in the whole machine 00;
  • a drive assembly 80 the drive assembly 80 is connected to the complete machine 00, and the drive assembly 80 is electrically connected to the intelligent security device controller;
  • Speaker module 70 the speaker module is set in the whole machine 00, and the speaker module is electrically connected with the intelligent security equipment controller;
  • the front microphone 30 and the rear microphone 40, the front microphone 30 and the rear microphone 40 are arranged in an end-fire array in the whole machine 00, and both the front microphone 30 and the rear microphone 40 are electrically connected to the intelligent security device controller;
  • Personnel entry detection component 50 which is arranged in the complete machine 00, and personnel entry detection component 50 is electrically connected to the intelligent security equipment controller;
  • An image sensing component 60 the image sensing component 60 is arranged in the whole machine 00, the image sensing component 60 includes an image sensor 61 and a lens 62, the image sensing component 60 is electrically connected to the intelligent security device controller;
  • the front microphone 30 , the rear microphone 40 and the image sensing component 60 are arranged in the middle of the whole machine 00 .
  • the intelligent security device controller can be realized by selecting MCU, DSP (Digital Signal Process, digital signal processing chip), FPGA (Field Programmable Gate Array, programmable logic gate array chip).
  • the processor 20 in the intelligent security device controller is electrically connected to the driving component 80 , the speaker module 70 , the front microphone 30 , the rear microphone 40 , the personnel entry detection component 50 and the image sensor 61 .
  • the driving assembly 80 can be realized by a motor, such as a servo motor, a stepping motor, etc.;
  • the speaker module 70 can be realized by a loudspeaker and an amplifying circuit electrically connected thereto;
  • the personnel entering detection assembly 50 can be realized by an infrared sensor, a grating sensor etc.
  • the image sensing component 60 can be implemented as a camera, and the camera is provided with an image sensor 61 and a lens 62 .
  • the front microphone 30, the rear microphone 40 and the image sensor assembly 60 at the middle position of the whole machine 00, that is, the midpoints of these three devices are all located on the center line of the whole machine 00, so, in When the whole machine 00 is rotated according to the standing angle information, the actual angle between the front microphone 30 and the rear microphone 40 of the end-fire array and the personnel in the area to be detected can be closer to 0°, thereby obtaining better sound reception effect and further improving Call quality for smart security devices.
  • the embodiments of the intelligent security equipment of the present invention include all embodiments of the above-mentioned intelligent security equipment controller and intelligent security control method All the technical solutions, and the achieved technical effects are exactly the same, so I won’t repeat them here.

Abstract

本发明提出了一种智能安防控制方法,应用于智能安防设备,智能安防设备包括喇叭模块,智能安防控制方法包括检测是否有人员进入待检测区;在确定有人员进入待检测区时,采集待检测区内人员的行为状态,并生成相应的行为状态信息;在根据行为状态信息,确定待检测区内人员有通话意图时,控制喇叭模块开启。本发明有效地降低了智能安防设备的功耗。

Description

智能安防控制方法、智能安防设备及控制器
本申请要求于2021年11月30日提交中国专利局、申请号为202111445765.2、发明名称为“智能安防控制方法、智能安防设备及控制器”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本发明涉及智能安防技术领域,特别涉及一种智能安防控制方法、智能安防设备及控制器。
背景技术
现在很多场所都使用了智能安防设备,如智能门铃、智能监控摄像头等,在检测到有人进入待检测区后,便开启摄像头、麦克风和喇叭模块,但往往只是无关人路过,而不是要进行语音对话,此时如果喇叭模块开启,其内部的放大电路一般都在瓦级以上,这样会加大智能安防设备的耗电量。
发明内容
本发明的主要目的是提供一种智能安防控制方法、智能安防设备及控制器,旨在降低智能安防设备的功耗。
为实现上述目的,本发明提出一种智能安防控制方法,应用于智能安防设备,所述智能安防设备包括喇叭模块,所述智能安防控制方法包括:
步骤S100、检测是否有人员进入待检测区;
步骤S200、在确定有人员进入所述待检测区时,采集所述待检测区内人员的行为状态,并生成相应的行为状态信息;
步骤S300、在根据所述行为状态信息,确定所述待检测区内人员有通话意图时,控制喇叭模块开启。
可选的,所述智能安防设备包括有红外传感器,所述步骤S100具体为:
步骤S110、检测所述待检测区内的红外辐射值,并生成红外检测信息;
所述在确定有人员进入所述待检测区的步骤具体为:
步骤S210、在根据所述红外检测信息,确定所述待检测区内的红外辐射值在预设人体辐射值区间时,确定有人员进入所述待检测区。
可选的,所述智能安防设备包括图像传感组件,所述步骤S200包括:
步骤S220、在确定有人员进入所述待检测区时,开启图像传感组件,拍摄所述待检测区内人员的图像信息;
步骤S230、对所述图像信息进行动作识别,生成相应的人员动作信息;
所述步骤S300具体为:
步骤S310、根据所述人员动作信息,确定所述待检测区内的人员的嘴部动作为说话动作时,控制所述喇叭模块开始工作。
可选的,所述智能安防设备包括麦克风,所述步骤S200包括:
步骤S240、在确定有人员进入所述待检测区时,开启麦克风,获取待检测区内的音频,并输出相应的待检测区音频信息;
所述步骤S300具体为:
步骤S320、根据所述待检测区音频信息,确定所述待检测区的音频幅值达到预设音频幅值时,控制所述喇叭模块开始工作。
可选的,所述智能安防设备包括麦克风和图像传感组件,所述步骤S200包括:
步骤S250、在确定有人员进入所述待检测区时,开启图像传感组件,拍摄所述待检测区内人员的图像信息;
步骤S260、对所述图像信息进行动作识别,生成相应的人员动作信息,并根据所述人员动作信息确定所述待检测区内的人员的嘴部动作为说话动作时,控制所述麦克风开启,以获取待检测区内的音频,并输出相应的待检测区音频信息;
所述步骤S300具体为:
步骤S330、根据所述待检测区音频信息,在确定所述待检测区的音频幅值达到预设音频幅值且所述待检测区内的人员的嘴部动作为说话动作时,控制所述喇叭模块开始工作。
可选的,所述智能安防控制方法还包括:
步骤S400、在根据所述行为状态信息,确定所述待检测区内人员没有通话意图时,控制所述喇叭模块处于停止状态。
可选的,所述智能安防设备包括整机以及与所述整机驱动连接的驱动组件,所述整机内设置有成端射阵列的前麦克风和后麦克风,在执行所述步骤S300后,所述智能安防控制方法还包括:
步骤S500、获取所述待检测区内人员的位置;
步骤S600、根据所述待检测区内人员的位置控制所述驱动组件驱动所述整机移动,以使所述前麦克风、所述后麦克风与所述待检测区内人员处于同一直线上。
可选的,所述整机内设置有图像传感组件,所述图像传感组件包括图像传感器和透镜,所述步骤S500具体为:
步骤S510、开启图像传感组件拍摄所述待检测区内人员,并获取所述图像传感器上成像位置与所述图像传感器的中心点之间的距离信息;
步骤S520、根据所述距离信息和所述图像传感器与所述透镜之间的距离,计算得到所述待检测区内人员与所述整机的站立角度,并生成站立角度信息;
所述步骤S600具体为:
步骤S610、根据所述站立角度信息,控制所述驱动组件驱动整机移动,直至所述站立角度为0度,以使所述前麦克风、所述后麦克风与所述待检测区内人员处于同一直线上。
本发明还提出了一种智能安防设备控制器,所述智能安防设备控制器包括:
存储器;
处理器;以及
存储在所述存储器上并被所述处理器执行的智能安防控制程序,所述智能安防控制程序在被所述处理器执行时,实现如上述任一项所述的智能安防控制方法。
本发明还提出了一种智能安防设备,所述智能安防设备包括:
整机;
如权利要求9所述的智能安防设备控制器,所述智能安防设备控制器设置于所述整机内;
驱动组件,所述驱动组件与所述整机驱动连接,所述驱动组件与所述智能安防设备控制器电连接;
喇叭模块,所述喇叭模块设置于所述整机内,所述喇叭模块与所述智能安防设备控制器电连接;
前麦克风和后麦克风,所述前麦克风与所述后麦克风成端射阵列设置于所述整机内,所述前麦克风与所述后麦克风均与所述智能安防设备控制器电连接;
人员进入检测组件,所述人员进入检测组件设置于所述整机内,所述人员进入检测组件与所述智能安防设备控制器电连接;
图像传感组件,所述图像传感组件设置于所述整机内,所述图像传感组件包括图像传感器和透镜,所述图像传感组件与所述智能安防设备控制器电连接;
其中,所述前麦克风、所述后麦克风和所述图像传感组件设置于所述整机的中间位置。
本发明技术方案中,先检测是否有人员进入待检测区,并在确定有人员进入所述待检测区时,采集所述待检测区内人员的行为状态,并生成相应的行为状态信息,并在根据所述行为状态信息,确定所述待检测区内人员有通话意图时,控制喇叭模块开启。如此,便能够在确定有人进入待检测区内时,先不第一时间开启喇叭模块,而是在确定待检测区内人员有说话意图时,再控制喇叭模块开启,并在确认待检测区内人员没有说话意图时,控制喇叭模块保持停止工作状态,从而有效地降低了智能安防设备的功耗。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图示出的结构获得其他的附图。
图1为本发明智能安防控制方法一实施例的方法步骤流程图;
图2为本发明智能安防控制方法另一实施例的方法步骤流程图;
图3为本发明智能安防控制方法又一实施例的方法步骤流程图;
图4为本发明智能安防控制方法再一实施例的方法步骤流程图;
图5为本发明智能安防控制方法另一实施例的方法步骤流程图;
图6为本发明智能安防控制方法又一实施例的方法步骤流程图;
图7为本发明智能安防控制方法再一实施例的方法步骤流程图;
图8为本发明智能安防控制方法另一实施例的方法步骤流程图;
图9为本发明智能安防控制方法一实施例的方法具体执行示意图;
图10为本发明智能安防控制方法一实施例的方法具体执行示意图;
图11为本发明智能安防设备一实施例的功能模块示意图;
图12为成端射阵列的前麦克风和后麦克风的示意图。
附图标号说明:
Figure PCTCN2022088325-appb-000001
本发明目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明的一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
需要说明,本发明实施例中所有方向性指示(诸如上、下、左、右、前、后……)仅用于解释在某一特定姿态(如附图所示)下各部件之间的相对位 置关系、运动情况等,如果该特定姿态发生改变时,则该方向性指示也相应地随之改变。
应该理解的是,虽然本申请实施例中的流程图中的各个步骤按照箭头的指示依次显示,但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明,这些步骤的执行并没有严格的顺序限制,其可以以其他的顺序执行。而且,图中的至少一部分步骤可以包括多个子步骤或者多个阶段,这些子步骤或者阶段并不必然是在同一时刻执行完成,而是可以在不同的时刻执行,其执行顺序也不必然是依次进行,而是可以与其他步骤或者其他步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。
需要说明的是,在本文中,采用了诸如S100、S200等步骤代号,其目的是为了更清楚简要地表述相应内容,不构成顺序上的实质性限制,本领域技术人员在具体实施时,可能会先执行S200后执行S100等,但这些均应在本申请的保护范围之内。
需要理解的是,现在很多场所都使用了智能安防设备,如智能门铃、智能监控摄像头等,在检测到有人进入待检测区后,便开启摄像头、麦克风和喇叭模块,但往往只是无关人路过,而不是要进行语音对话,此时如果喇叭模块开启,其内部的放大电路一般都在瓦级以上,这样会加大智能安防设备的耗电量。
为此,本发明提出一种智能安防控制方法,应用于智能安防设备,智能安防设备包括喇叭模块。
在本实施例中,喇叭模块包括扬声器和与其电连接的放大电路。
在本发明一实施例中,参考图1,本发明提出一种智能安防控制方法包括:
步骤S100、检测是否有人员进入待检测区;
步骤S200、在确定有人员进入待检测区时,采集待检测区内人员的行为状态,并生成相应的行为状态信息;
步骤S300、在根据行为状态信息,确定待检测区内人员有通话意图时,控制喇叭模块开启。
在本实施例中,智能安防设备可以包括一人员进入检测组件和与其电连接的控制器,人员进入检测组件用于检测是否有人进入了待检测区内,即智 能安防设备的可识别区域内。可以理解的是,待检测区的具体范围可以由研发人员进行设置,也可以由用户根据需求进行设置。
可选地,人员进入检测组件可以采用红外感应器件来实现,例如红外传感器,红外传感器可以获取待检测区内的,即红外传感器预设的检测范围内的红外辐射值,并生成红外辐射检测信息至控制器,由于人体会对外辐射红外线,因此控制器可以根据红外辐射检测信息确定待检测区内的红外辐射值在常规人体红外辐射值左右时,确定有人进入。
可选地,人员检测组件还可以采用光电传感器来实现,例如在待检测区内设置一组光栅,当待检测区内有人员进入时,会挡住光电传感器的发射端和接收端之间的路径,使接收端无法接收到发射端发射出的红外光,此时光电传感器输出一有人进入信号至控制器,例如低电平信号,当无人进入待检测区内,接收端能够正常接收发射端发射出的红外光,此时光电传感器会输出一无人进入信号至控制器,例如高电平信号,控制器便可以根据光电传感器传来的信号确定是否有人进入待检测区。
在本实施例中,控制器与喇叭模块电连接,在确定有人员进入待检测区内时,可以通过检测并采集人员的行为状态,例如“说话的声音大小、面部动作、手势动作”等行为状态,以生成相应的行为状态信息,并根据行为状态信息判断当前待检测区内的人员是否需要与智能安防设备的用户侧进行通话,即判断待检测区内的人员是否有通话意图。当控制器判断当前待检测区内的人员有说话意图时,便会控制当前喇叭模块开始工作,以满足用户与待检测区内人员沟通的实际需求。
可以理解的是,参考图6,在本发明一实施例中,智能安防控制方法还包括:
步骤S400、在根据行为状态信息,确定待检测区内人员没有通话意图时,控制喇叭模块处于停止状态。
在本实施例中,若根据人员的行为状态信息,例如待检测区内人员说话的声音大小,或者是待检测区内人员的嘴部的动作,确定当前待检测区内的人员不需要进行通话时,智能安防设备内的控制器便不会控制喇叭模块开启,也就不会使喇叭模块内部的放大电路开始工作,有效地降低了智能安防设备的功耗。
本发明技术方案中,先检测是否有人员进入待检测区,并在确定有人员进入所述待检测区时,采集所述待检测区内人员的行为状态,并生成相应的行为状态信息,并在根据所述行为状态信息,确定所述待检测区内人员有通话意图时,控制喇叭模块开启。如此,便能够在确定有人进入待检测区内时,先不第一时间开启喇叭模块,而是在确定待检测区内人员有说话意图时,再控制喇叭模块开启,并在确认待检测区内人员没有说话意图时,控制喇叭模块保持停止工作状态,从而有效地降低了智能安防设备的功耗。
可选的,参考图3,在本发明一实施例中,智能安防设备包括图像传感组件,步骤S200包括:
步骤S220、在确定有人员进入待检测区时,开启图像传感组件,拍摄待检测区内人员的图像信息;
步骤S230、对图像信息进行动作识别,生成相应的人员动作信息;
在本实施例中,控制器内还可以集成有人脸识别模块,在确定待检测区内有人员时,智能安防设备内的控制器先控制图像传感器组件,例如摄像头开启,在拍摄待检测区内人员的图像,确定人员位置的同时,还会对图像信息进行动作识别,例如面部动作识别,并生成相应的人员动作信息。
步骤S300具体为:
步骤S310、根据人员动作信息,确定待检测区内的人员的嘴部动作为说话动作时,控制喇叭模块开始工作。
在本实施例中,若根据人员动作信息,能够正常识别到人脸图像,并且识别到待检测区内的人员的嘴部动作为说话动作时,确定当前待检测区内的人员有通话意图,便控制喇叭模块开始工作。例如在一定预设时间内,待检测区内人员的嘴部张比动作次数达到了预设次数时,则确定当前待检测区内的人员的嘴部动作为说话动作,便控制喇叭模块开始工作。
此外,在另一实施例中,若控制器根据人员动作信息,并不能够正常的识别到待检测区内的人脸图像,例如当前待检测区内的人员只是路过的路人,则不会识别到待检区内的人员的人脸图像,或者是识别到待检测区内的人员的嘴部动作不是说话动作时,则确定当前待检测区内的人员并无通话意图。此时,控制器便会控制喇叭模块保持停止工作状态。如此,便能够通过人员 动作识别来判断当前待检测区内的人员是否有通话意图,并在无通话意图时,控制喇叭模块不启动,从而降低智能安防设备的功耗。
可选的,参考图4,在本发明一实施例中,智能安防设备包括麦克风,步骤S200包括:
步骤S240、在确定有人员进入待检测区时,开启麦克风,获取待检测区内的音频,并输出相应的待检测区音频信息;
步骤S300具体为:
步骤S320、根据待检测区音频信息,确定待检测区的音频幅值达到预设音频幅值时,控制喇叭模块开始工作。
在本实施例中,控制器与麦克风电连接,麦克风可以拾取待检测区内的音频,并将拾取到的为模拟信号的音频信号进行模数转换后生成为数字信号的待检测区音频信息,控制器会根据待检测区音频信息,确定当前待检测区的音频幅值,若音频幅值达到了预设幅值,例如,预设幅值表征的声音强度为30分贝,若音频幅值所表征的声音强度为40分贝,则可以确定当前待检测区内的人员有通话需求,便会开启喇叭模块,以满足用户和待检测区内人员的通话需求。
此外,在另一实施例中,可以理解是的,若当前音频幅值未达到了预设幅值,则可能说明当前待检测区内的人员只是在和其他人说话,并没有与智能安防设备的用户侧进行通话的需求,则控制器不会启动喇叭模块,从而降低智能安防设备的功耗。
可选的,参考图5,智能安防设备包括麦克风和图像传感组件,步骤S200包括:
步骤S250、在确定有人员进入待检测区时,开启图像传感组件,拍摄待检测区内人员的图像信息;
步骤S260、对图像信息进行动作识别,生成相应的人员动作信息,并根据人员动作信息确定待检测区内的人员的嘴部动作为说话动作时,控制麦克风开启,以获取待检测区内的音频,并输出相应的待检测区音频信息;
步骤S300具体为:
步骤S330、根据待检测区音频信息,在确定待检测区的音频幅值达到预设音频幅值且待检测区内的人员的嘴部动作为说话动作时,控制喇叭模块开 始工作。
在本实施例中,可以理解的是,为了提高检测待检测区内人员是否有通话意图的准确性,还可以同时采用上述两种实施例结合的方案来实现对待检测区内人员通话意图的检测。
在本实施例中,由上述实施例内容可知,在确定有人员进入待检测区时,控制器会控制图像传感组件,例如摄像头开启,以拍摄当前的待检测区内人员的图像信息,并对图像信息进行动作识别后,生成相应的人员动作信息,当根据人员动作信息确定待检测区内的人员的嘴部动作为说话动作时,控制器便会再开启麦克风,再如上述实施例内容根据待检测区音频信息,确定待检测区内的音频幅值是否达到了预设幅值。
若确定待检测区的音频幅值达到预设音频幅值且待检测区内的人员的嘴部动作为说话动作时,则控制喇叭模块开始工作,以满足待检测区内人员与用户的通话需求;若确定待检测区的音频幅值没有达到预设音频幅值,则判断待检测区内人员并未说话意图,故控制喇叭模块保持停止工作状态,以降低智能安防设备的功耗。通过判断当前待测区内的人员的行为是否同时满足有嘴部说话动作以及说话声音的强度达到预设幅值表征的分贝,可以有效地提高智能安防设备判断人员是否有通话需求的准确性,更进一步的保证了智能安防设备工作的可靠性与稳定性,防止了因为误判导致智能安防设备误启动喇叭模块导致功耗变高的情况发生。
此外,在另一实施例中,若当前控制器根据人员动作信息确定待检测区内的人员的嘴部动作不为说话动作时,即确定待检测区内的人员并没有任何的说话意图时,不会开启麦克风,,从而更进一步降低智能安防设备的功耗。
参考图2,在本发明一实施例中,智能安防设备包括有红外传感器,步骤S100具体为:
步骤S110、检测待检测区内的红外辐射值,并生成红外检测信息;
在确定有人员进入待检测区的步骤具体为:
步骤S210、在根据红外检测信息,确定待检测区内的红外辐射值在预设人体辐射值区间时,确定有人员进入待检测区。
在本实施例中,红外传感器会检测待检测区内的红外辐射值,并生成相 应的红外检测信息至控制器。当有人员进入红外检测区域时,由于人体会对外辐射红外线,因此控制器在根据红外检测信息确定当前待检测区内的红外辐射在预设人体辐射值区间时,控制器便能够确定当前有人员进入了待检测区。其中,预设人体辐射值区间可以由研发人员根据人体红外辐射值的常规值进行预设并存储在智能安防设备的控制器内。如此,便能够通过红外识别的方式,检测是否有人员进入待检测区。同时,采用红外传感器进行是否有人员进入待检测区域,相比较采用监控摄像头,能够有效的降低整个智能安防设备的功耗。
需要理解的是,在智能安防设备的实际使用中,若使用者旁边有其他人说话,或者是存在环境干扰音,会使得用户侧听不清智能安防设备前的人员的说话内容,导致通话质量下降。
为此,参考图7,在本发明一实施例中,智能安防设备包括整机以及与整机驱动连接的驱动组件,整机内设置有成端射阵列的前麦克风和后麦克风;
在本实施例中,需要理解的是,参考图10和图12,前麦克风和后麦克风成端射阵列,即前麦克风和后麦克风在整机内设置在同一直线上,前麦克风设置于整机的前端,后麦克风设置于整机的后端。在实际工作中,为了提高通话质量,降低周围噪声的影响,可以采用双麦克风端射阵列形成的波束成形,如果阵列中前方麦克风的信号与后方麦克风的反相延迟信号相加,则会形成“差分”。如果声音来自0°,则叠加后声音变成2倍,即语音增强区,声音来自的角度越靠近0°则最后由前后麦克风叠加生成的待检测区音频信息的音频幅值越高且其中的噪声越小;如果声音来自90°,则叠加后正好相互抵消,即语音衰减区。可选地,前麦克风也可以由多个小麦克风组成前麦克风阵列,同理,后麦克风也可以由多个小麦克风组成后麦克风阵列。
在执行步骤S300后,智能安防控制方法还包括:
步骤S500、获取待检测区内人员的位置;
在本实施例中,智能安防设备还包括一用于检测人员位置的人员位置检测组件,人员位置检测组件与控制器电连接,在控制器确定当前人员进入了待检测区以后,控制器可以控制人员位置检测组件检测待检测区内的人员位置。
可选地,人员位置检测组件可以采用摄像头来实现,控制器内可集成有图像识别芯片。摄像头能够在人员进入待检测区内时,拍摄待检测区内的图像并生成相应的图像信息至控制器,控制器不仅仅将图像信息显示在智能安防设备的用户侧或者是通过内部通讯组件上传至外部终端例如用户的手机,控制器还可以根据图像信息识别待检测区内图像中的人员图像的位置,从而确定待检测区内的人员位置。
可选地,人员位置检测组件除了直接采用用于拍摄待检测区内图像的摄像头外,还可以采用超声波定位组件或者微波定位组件来实现,控制器可以在确认有人员进入待检测区后,启动超声波定位组件,超声波定位组件可以通过超声波定位的方式定位当前人员所处的待检测区的位置。
步骤S600、根据待检测区内人员的位置控制驱动组件驱动整机移动,以使前麦克风、后麦克风与待检测区内人员处于同一直线上。
在本实施例中,由上述内容可知,由于前麦克风和后麦克风成端射阵列,因此前后麦克风所在的直线和人员与整机之间所在的直线的夹角角度越接近0°,则最终通过喇叭模块输出的待检测区音频信息的音频幅值越接近待检测区人员发出声音信号幅值的2倍,以及越清晰。
在本实施例中,控制器会接收到前麦克风拾取的第一音频信号和后麦克风拾取的第二音频信号。可选的,控制器会将接收到的为模拟信号的第一音频信号和第二音频信号转换为数字信号,再将为数字信号的第二音频信号按照预设延时时间进行延迟后再反相处理,并与为数字信号的第一音频信号叠加后形成待检测区音频信息;可选的,前麦克风和后麦克风还可自带模数转换器,从而使输出的第一音频信号和第二音频信号均为数字信号。其中,预设延时时间可以由研发人员根据前麦克风和后麦克风之间的距离进行多次实验而获得并预设在控制器内。
由上述实施例内容可知,控制器会根据待检测区音频信息确定当前待检测区内人员是否有说话意图,可以理解的是,在本实施例中,控制可以将第二音频信号按照预设延时时间进行反相延迟处理后,与第一音频信号叠加生成待检测区音频信息。并根据待检测区音频信息,确定当前待检测区内的音频幅值,再根据待检测区内的音频幅值和预设幅值的大小关系,确定当前待检测区内人员是否有说话意图。
可选地,驱动组件可以为电机,电机可以驱动整机三百六十度旋转,控制器可以根据检测到的待检测区内人员的位置,控制电机驱动整机旋转,直至整机的前方正对待检测区内的人员位置,由于前后麦克风在整机内成端射阵列,因此此时前麦克风也会正对待检测区内的人员,即前后麦克风所在的直线和人员与整机之间所在的直线的夹角角度为0°,从而使得最终通过喇叭模块输出的待检测区音频信息的音频幅值为待检测区内人员发出声音信号辅助的2倍,同时还可以减小待检测区内的噪音,起到降噪作用,从而提高输出的待检测区音频信息的音频清晰度。
可选地,驱动组件还可以采用机械手来实现,控制器可以对上述实施例中摄像头拍摄到的图片进行人脸识别,识别待检测区内人员的脸部位置,并控制机械手驱动整机始终正对待检测区内人员的面部。从而使得前后麦克风所在的直线和人员与整机之间所在的直线的夹角角度始终为0°如此,便能够使待检测区内的说话的人员所站立的位置正好处于成端射阵列的前后麦克风的语音增强区,从而能够有效的降低了获取到的待检测区音频信息中的噪音成分,即待检测区内人员发出的声音信号中的噪音成分,并且有效地提高了人员发出的声音信号的音频幅值,从而使智能安防设备的用户侧听到的待检测区内的人员的说话声音更加的清楚,提高了用户使用智能安防设备的便利性以及提高了智能安防设备的通话质量。
参考图8-图10,在本发明一实施例中,整机内设置有图像传感组件,图像传感组件包括图像传感器和透镜,步骤S500具体为:
步骤S510、开启图像传感组件拍摄待检测区内人员,并获取图像传感器上成像位置与图像传感器的中心点之间的距离信息;
步骤S520、根据距离信息和图像传感器与透镜之间的距离,计算得到待检测区内人员与整机的站立角度,并生成站立角度信息;
在本实施例中,图像传感组件可以为上述实施例中的图像传感组件,即在上述实施例中确认有人员进入待检测区开启图像传感组件拍摄待检测区内人员的图像信息时,也可以同时获取图像传感器上成像位置与图像传感器的中心点之间的距离信息。
在本实施例中,图像传感组件可以为摄像头,其中摄像头内的图像传感 器为多个感光元件组成的感光元件阵列,图像传感器可以根据在感光元件阵列上的成像位置,自行计算得到成像位置与感光元件阵列中心点之间的距离,并生成相应的距离信息输出至智能安防设备中的控制器,控制器会根据透镜和图像传感器之间的距离(需要理解的是,该距离可以由研发人员在研发期间进行测量并预存储在控制器内),计算得到待检测区内人员与整机的站立角度,并生成站立角度信息。
步骤S600具体为:
步骤S610、根据站立角度信息,控制驱动组件驱动整机移动,直至站立角度为0度,以使前麦克风、后麦克风与待检测区内人员处于同一直线上。
在本实施例中,可选的,驱动组件可采用电机来实现,由上述实施例中内容可知,当待检测区内的人员正对着前麦克风讲话时,会处于成端射阵列的前麦克风和后麦克风的语音增强区。因此,控制器会根据计算得到生成的站立角度信息控制驱动组件带动整机转动,直至站立角度为0度,即当前整机正对着待检测区内的人员,由于前麦克风和后麦克风在整机内成端射阵列,因此前麦克风也会此时正对待检测人员。如此,便能够使得待检测人员处于成端射阵列的前麦克风和后麦克风的语音增强区内。
具体地,参考图9和图10,α为整机和待检测区内人员的站立角度,d为图像传感器上成像位置和图像传感器中心点之间的距离,L为图像传感器和透镜之间的距离,根据d和L以及反正切函数公式:α=arctan(d/L),控制器便可以得到当前待检测区内的人员与整机的之间的站立角度,并根据站立角度控制驱动组件调整整机的朝向角度,直至站立角度为0°,即当前整机内的前麦克风正好正对待检测区内人员。
参考图11,本发明还提出一种智能安防设备控制器,智能安防设备控制器包括:
存储器10;
处理器20,处理器20与存储器10电连接;以及
存储在存储器10上并被处理器20执行的智能安防控制程序,智能安防控制程序在被处理器20执行时,实现如上述任一项的智能安防控制方法。
值得注意的是,由于本发明智能安防设备控制器基于上述的智能安防控 制方法,因此,本发明智能安防设备控制器的实施例包括上述智能安防控制方法全部实施例的全部技术方案,且所达到的技术效果也完全相同,在此不再赘述。
参考图11,本发明还提出一种智能安防设备,智能安防设备包括:
整机00;
上述的智能安防设备控制器,智能安防设备控制器设置于整机00内;
驱动组件80,驱动组件80与整机00驱动连接,驱动组件80与智能安防设备控制器电连接;
喇叭模块70,喇叭模块设置于整机00内,喇叭模块与智能安防设备控制器电连接;
前麦克风30和后麦克风40,前麦克风30与后麦克风40成端射阵列设置于整机00内,前麦克风30与后麦克风40均与智能安防设备控制器电连接;
人员进入检测组件50,人员进入检测组件50设置于整机00内,人员进入检测组件50与智能安防设备控制器电连接;
图像传感组件60,图像传感组件60设置于整机00内,图像传感组件60包括图像传感器61和透镜62,图像传感组件60与智能安防设备控制器电连接;
其中,前麦克风30、后麦克风40和图像传感组件60设置于整机00的中间位置。
在本实施例中,智能安防设备控制器可以选用MCU、DSP(Digital Signal Process,数字信号处理芯片)、FPGA(Field Programmable Gate Array,可编程逻辑门阵列芯片)来实现。
在本实施例中,智能安防设备控制器中的处理器20分别与驱动组件80、喇叭模块70、前麦克风30、后麦克风40、人员进入检测组件50和图像传感器61电连接。可选的,驱动组件80可以采用电机来实现,例如伺服电机、步进电机等;喇叭模块70可以采用扬声器和与其电连接的放大电路来实现;人员进入检测组件50可以采用红外传感器、光栅传感器等来实现,图像传感组件60可以为摄像头来实现,摄像头中设置有图像传感器61和透镜62。
在本实施例中,通过将前麦克风30、后麦克风40和图像传感组件60设置 于整机00的中间位置,即这三个器件的中点都位于整机00的中线上,如此,在根据站立角度信息旋转整机00时,能够使成端射阵列的前麦克风30和后麦克风40与待检测区内的人员的实际角度更加接近0°,从而取得更好的收音效果,更进一步提高智能安防设备的通话质量。
值得注意的是,由于本发明智能安防设备基于上述的智能安防设备控制器和智能安防控制方法,因此,本发明智能安防设备的实施例包括上述智能安防设备控制器和智能安防控制方法全部实施例的全部技术方案,且所达到的技术效果也完全相同,在此不再赘述。
以上仅为本发明的可选实施例,并非因此限制本发明的专利范围,凡是在本发明的发明构思下,利用本发明说明书及附图内容所作的等效结构变换,或直接/间接运用在其他相关的技术领域均包括在本发明的专利保护范围内。

Claims (10)

  1. 一种智能安防控制方法,应用于智能安防设备,其特征在于,所述智能安防设备包括喇叭模块,所述智能安防控制方法包括:
    步骤S100、检测是否有人员进入待检测区;
    步骤S200、在确定有人员进入所述待检测区时,采集所述待检测区内人员的行为状态,并生成相应的行为状态信息;
    步骤S300、在根据所述行为状态信息,确定所述待检测区内人员有通话意图时,控制喇叭模块开启。
  2. 如权利要求1所述的智能安防控制方法,其特征在于,所述智能安防设备包括有红外传感器,所述步骤S100具体为:
    步骤S110、检测所述待检测区内的红外辐射值,并生成红外检测信息;
    所述在确定有人员进入所述待检测区的步骤具体为:
    步骤S210、在根据所述红外检测信息,确定所述待检测区内的红外辐射值在预设人体辐射值区间时,确定有人员进入所述待检测区。
  3. 如权利要求1所述的智能安防控制方法,其特征在于,所述智能安防设备包括图像传感组件,所述步骤S200包括:
    步骤S220、在确定有人员进入所述待检测区时,开启图像传感组件,拍摄所述待检测区内人员的图像信息;
    步骤S230、对所述图像信息进行动作识别,生成相应的人员动作信息;
    所述步骤S300具体为:
    步骤S310、根据所述人员动作信息,确定所述待检测区内的人员的嘴部动作为说话动作时,控制所述喇叭模块开始工作。
  4. 如权利要求1所述的智能安防控制方法,其特征在于,所述智能安防设备包括麦克风,所述步骤S200包括:
    步骤S240、在确定有人员进入所述待检测区时,开启麦克风,获取待检测区内的音频,并输出相应的待检测区音频信息;
    所述步骤S300具体为:
    步骤S320、根据所述待检测区音频信息,确定所述待检测区的音频幅值达到预设音频幅值时,控制所述喇叭模块开始工作。
  5. 如权利要求1所述的智能安防控制方法,其特征在于,所述智能安防设备包括麦克风和图像传感组件,所述步骤S200包括:
    步骤S250、在确定有人员进入所述待检测区时,开启图像传感组件,拍摄所述待检测区内人员的图像信息;
    步骤S260、对所述图像信息进行动作识别,生成相应的人员动作信息,并根据所述人员动作信息确定所述待检测区内的人员的嘴部动作为说话动作时,控制所述麦克风开启,以获取待检测区内的音频,并输出相应的待检测区音频信息;
    所述步骤S300具体为:
    步骤S330、根据所述待检测区音频信息,在确定所述待检测区的音频幅值达到预设音频幅值且所述待检测区内的人员的嘴部动作为说话动作时,控制所述喇叭模块开始工作。
  6. 如权利要求1所述的智能安防控制方法,其特征在于,所述智能安防控制方法还包括:
    步骤S400、在根据所述行为状态信息,确定所述待检测区内人员没有通话意图时,控制所述喇叭模块处于停止状态。
  7. 如权利要求1所述的智能安防控制方法,其特征在于,所述智能安防设备包括整机以及与所述整机驱动连接的驱动组件,所述整机内设置有成端射阵列的前麦克风和后麦克风,在执行所述步骤S300后,所述智能安防控制方法还包括:
    步骤S500、获取所述待检测区内人员的位置;
    步骤S600、根据所述待检测区内人员的位置控制所述驱动组件驱动所述整机移动,以使所述前麦克风、所述后麦克风与所述待检测区内人员处于同一直线上。
  8. 如权利要求7所述的智能安防控制方法,其特征在于,所述整机内设置有图像传感组件,所述图像传感组件包括图像传感器和透镜,所述步骤S500具体为:
    步骤S510、开启图像传感组件拍摄所述待检测区内人员,并获取所述图像传感器上成像位置与所述图像传感器的中心点之间的距离信息;
    步骤S520、根据所述距离信息和所述图像传感器与所述透镜之间的距离,计算得到所述待检测区内人员与所述整机的站立角度,并生成站立角度信息;
    所述步骤S600具体为:
    步骤S610、根据所述站立角度信息,控制所述驱动组件驱动整机移动,直至所述站立角度为0度,以使所述前麦克风、所述后麦克风与所述待检测区内人员处于同一直线上。
  9. 一种智能安防设备控制器,其特征在于,所述智能安防设备控制器包括:
    存储器;
    处理器;以及
    存储在所述存储器上并被所述处理器执行的智能安防控制程序,所述智能安防控制程序在被所述处理器执行时,实现如权利要求1-8任一项所述的智能安防控制方法。
  10. 一种智能安防设备,其特征在于,所述智能安防设备包括:
    整机;
    如权利要求9所述的智能安防设备控制器,所述智能安防设备控制器设置于所述整机内;
    驱动组件,所述驱动组件与所述整机驱动连接,所述驱动组件与所述智能安防设备控制器电连接;
    喇叭模块,所述喇叭模块设置于所述整机内,所述喇叭模块与所述智能安防设备控制器电连接;
    前麦克风和后麦克风,所述前麦克风与所述后麦克风成端射阵列设置于 所述整机内,所述前麦克风与所述后麦克风均与所述智能安防设备控制器电连接;
    人员进入检测组件,所述人员进入检测组件设置于所述整机内,所述人员进入检测组件与所述智能安防设备控制器电连接;
    图像传感组件,所述图像传感组件设置于所述整机内,所述图像传感组件包括图像传感器和透镜,所述图像传感组件与所述智能安防设备控制器电连接;
    其中,所述前麦克风、所述后麦克风和所述图像传感组件设置于所述整机的中间位置。
PCT/CN2022/088325 2021-11-30 2022-04-22 智能安防控制方法、智能安防设备及控制器 WO2023097951A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111445765.2 2021-11-30
CN202111445765.2A CN114268337A (zh) 2021-11-30 2021-11-30 智能安防控制方法、智能安防设备及控制器

Publications (1)

Publication Number Publication Date
WO2023097951A1 true WO2023097951A1 (zh) 2023-06-08

Family

ID=80826107

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/088325 WO2023097951A1 (zh) 2021-11-30 2022-04-22 智能安防控制方法、智能安防设备及控制器

Country Status (2)

Country Link
CN (1) CN114268337A (zh)
WO (1) WO2023097951A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114268337A (zh) * 2021-11-30 2022-04-01 歌尔科技有限公司 智能安防控制方法、智能安防设备及控制器

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08280005A (ja) * 1995-04-04 1996-10-22 Matsushita Electric Ind Co Ltd テレビドアホン装置
CN201307873Y (zh) * 2008-11-12 2009-09-09 宇龙计算机通信科技(深圳)有限公司 一种移动终端
CN202406158U (zh) * 2011-12-22 2012-08-29 成都理想科技开发有限公司 一种报警控制器的对讲电路
CN107170159A (zh) * 2017-06-29 2017-09-15 苏州见真物联科技有限公司 一种智能门铃
CN207691941U (zh) * 2017-12-22 2018-08-03 东莞市天络电子科技有限公司 Wifi可视门铃系统
WO2018232922A1 (zh) * 2017-06-23 2018-12-27 深圳市盛路物联通讯技术有限公司 一种家居安防方法及系统
CN109977811A (zh) * 2019-03-12 2019-07-05 四川长虹电器股份有限公司 基于嘴部关键位置特征检测实现免语音唤醒的系统及方法
CN110159956A (zh) * 2019-05-28 2019-08-23 佛山市田昌灯饰有限公司 一种带视频监测功能的智能照明装置
CN110335603A (zh) * 2019-07-12 2019-10-15 四川长虹电器股份有限公司 应用于电视场景的多模态交互方法
CN111583937A (zh) * 2020-04-30 2020-08-25 珠海格力电器股份有限公司 一种语音控制唤醒方法及存储介质、处理器、语音设备、智能家电
CN113113009A (zh) * 2021-04-08 2021-07-13 思必驰科技股份有限公司 多模态语音唤醒和打断方法及装置
CN114255557A (zh) * 2021-11-30 2022-03-29 歌尔科技有限公司 智能安防控制方法、智能安防设备及控制器
CN114255556A (zh) * 2021-11-30 2022-03-29 歌尔科技有限公司 智能安防控制方法、智能安防设备及控制器
CN114268337A (zh) * 2021-11-30 2022-04-01 歌尔科技有限公司 智能安防控制方法、智能安防设备及控制器

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100559409C (zh) * 2008-08-15 2009-11-11 南京视威电子有限公司 一体化网络智能安防监控报警方法及装置
CN104284485A (zh) * 2014-09-26 2015-01-14 生迪光电科技股份有限公司 智能照明装置、照明系统及智能照明控制方法
CN206077573U (zh) * 2016-06-07 2017-04-05 杭州虹云网络科技有限公司 一种低功耗可视智能门铃
CN108733420B (zh) * 2018-03-21 2022-04-29 北京猎户星空科技有限公司 智能设备的唤醒方法、装置、智能设备和存储介质
CN111823241A (zh) * 2019-05-27 2020-10-27 广东小天才科技有限公司 一种智能安防机器人、方法、装置、存储介质
CN112698711A (zh) * 2020-12-23 2021-04-23 深圳市凯迪仕智能科技有限公司 一种智能检测方法及智能锁

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08280005A (ja) * 1995-04-04 1996-10-22 Matsushita Electric Ind Co Ltd テレビドアホン装置
CN201307873Y (zh) * 2008-11-12 2009-09-09 宇龙计算机通信科技(深圳)有限公司 一种移动终端
CN202406158U (zh) * 2011-12-22 2012-08-29 成都理想科技开发有限公司 一种报警控制器的对讲电路
WO2018232922A1 (zh) * 2017-06-23 2018-12-27 深圳市盛路物联通讯技术有限公司 一种家居安防方法及系统
CN107170159A (zh) * 2017-06-29 2017-09-15 苏州见真物联科技有限公司 一种智能门铃
CN207691941U (zh) * 2017-12-22 2018-08-03 东莞市天络电子科技有限公司 Wifi可视门铃系统
CN109977811A (zh) * 2019-03-12 2019-07-05 四川长虹电器股份有限公司 基于嘴部关键位置特征检测实现免语音唤醒的系统及方法
CN110159956A (zh) * 2019-05-28 2019-08-23 佛山市田昌灯饰有限公司 一种带视频监测功能的智能照明装置
CN110335603A (zh) * 2019-07-12 2019-10-15 四川长虹电器股份有限公司 应用于电视场景的多模态交互方法
CN111583937A (zh) * 2020-04-30 2020-08-25 珠海格力电器股份有限公司 一种语音控制唤醒方法及存储介质、处理器、语音设备、智能家电
CN113113009A (zh) * 2021-04-08 2021-07-13 思必驰科技股份有限公司 多模态语音唤醒和打断方法及装置
CN114255557A (zh) * 2021-11-30 2022-03-29 歌尔科技有限公司 智能安防控制方法、智能安防设备及控制器
CN114255556A (zh) * 2021-11-30 2022-03-29 歌尔科技有限公司 智能安防控制方法、智能安防设备及控制器
CN114268337A (zh) * 2021-11-30 2022-04-01 歌尔科技有限公司 智能安防控制方法、智能安防设备及控制器

Also Published As

Publication number Publication date
CN114268337A (zh) 2022-04-01

Similar Documents

Publication Publication Date Title
JP7133789B2 (ja) 収音装置、収音システム、収音方法、プログラム、及びキャリブレーション方法
EP1489596B1 (en) Device and method for voice activity detection
US6516066B2 (en) Apparatus for detecting direction of sound source and turning microphone toward sound source
EP1681670A1 (en) Voice activation
CN111034222A (zh) 拾音装置、拾音方法以及程序
US10154363B2 (en) Electronic apparatus and sound output control method
EP1117076A2 (en) Self-service terminal
JP7122556B2 (ja) 撮影装置および撮影方法
JP4797330B2 (ja) ロボット
WO2023097951A1 (zh) 智能安防控制方法、智能安防设备及控制器
CN112995838B (zh) 拾音设备、拾音系统和音频处理方法
US7525575B2 (en) Voice activated image capture device and method
WO2016000585A1 (zh) 提高免提通话设备通话质量的方法、装置和免提通话设备
TWI725340B (zh) 可攜式通訊裝置的座體及其操作方法
KR100622891B1 (ko) 영상인식 센서를 이용한 리시버위치 최적화 기능을 갖는이동통신 단말기 및 그 방법
EP1257146A2 (en) Method and system of sound processing
JP2011087218A (ja) 拡声システム
US11856387B2 (en) Video conferencing system and method thereof
CN114255557A (zh) 智能安防控制方法、智能安防设备及控制器
CN114255556A (zh) 智能安防控制方法、智能安防设备及控制器
WO2022068608A1 (zh) 信号处理的方法和电子设备
JP2009147783A (ja) 電子機器
JP2021141572A (ja) 情報端末、インターホンシステム、処理方法及びプログラム
US8831681B1 (en) Image guided audio processing
CN115981173A (zh) 设备控制方法、终端设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22899774

Country of ref document: EP

Kind code of ref document: A1