WO2017166469A1 - 一种基于智能电视机的安防方法、装置 - Google Patents

一种基于智能电视机的安防方法、装置 Download PDF

Info

Publication number
WO2017166469A1
WO2017166469A1 PCT/CN2016/088193 CN2016088193W WO2017166469A1 WO 2017166469 A1 WO2017166469 A1 WO 2017166469A1 CN 2016088193 W CN2016088193 W CN 2016088193W WO 2017166469 A1 WO2017166469 A1 WO 2017166469A1
Authority
WO
WIPO (PCT)
Prior art keywords
image data
human body
infrared camera
image
security
Prior art date
Application number
PCT/CN2016/088193
Other languages
English (en)
French (fr)
Inventor
李水旺
Original Assignee
乐视控股（北京）有限公司
乐视致新电子科技（天津）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 乐视控股（北京）有限公司, 乐视致新电子科技（天津）有限公司 filed Critical 乐视控股（北京）有限公司
Publication of WO2017166469A1 publication Critical patent/WO2017166469A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
    • G08B13/189—Actuation 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
    • G08B13/194—Actuation 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
    • G08B13/196—Actuation 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
    • G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
    • G08B13/19606—Discriminating between target movement or movement in an area of interest and other non-signicative movements, e.g. target movements induced by camera shake or movements of pets, falling leaves, rotating fan
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/80—Camera processing pipelines; Components thereof
    • H04N23/815—Camera processing pipelines; Components thereof for controlling the resolution by using a single image
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/188—Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position

Definitions

  • the embodiments of the present invention relate to the field of smart television technologies, and in particular, to a security method and apparatus based on a smart television.
  • the purpose of the embodiment of the present application is to provide a security method and device based on a smart TV, which solves the problem that the implementation of the home security in the prior art needs to be installed by a professional, and the cost is high.
  • the embodiment of the present application provides a security method based on a smart television, and the method includes:
  • the infrared camera of the somatosensory device When the security function of the television is turned on, the infrared camera of the somatosensory device is turned on;
  • the infrared camera monitors the human body, turn on the RGB camera of the somatosensory device and acquire the image data of the person;
  • the image data is sent to a designated client terminal.
  • the method before the sending the image data to a specified client terminal, the method further comprises:
  • the step of transmitting the image data to a designated client terminal is performed.
  • a method as described above before the RGB camera of the somatosensory device is turned on and the image data of the person is acquired, the method further includes:
  • the step of turning on the RGB camera of the somatosensory device and acquiring the image data of the person is performed.
  • the method further includes: after the sending the image data to the specified client terminal, the method further includes:
  • the method further provides a method as described above, after the infrared camera of the somatosensory device is turned on, the method further includes:
  • the human body is tracked and photographed in a monitoring area of the somatosensory device.
  • the embodiment of the present application also provides a computer readable recording medium on which a program for executing the above method is recorded.
  • the embodiment of the present application further provides a security device based on a smart TV, the device comprising:
  • the infrared camera opening module is configured to open the infrared camera of the somatosensory device after the security function of the television is turned on;
  • the RGB camera opening module is configured to: when the infrared camera monitors the human body, turn on the RGB camera of the somatosensory device and acquire the image data of the person;
  • a sending module configured to send the image data to a specified client terminal.
  • the device further comprising:
  • a face recognition module configured to identify a face in the image data to acquire a person Facial image of the face
  • the facial feature comparison module is configured to compare the feature data of the acquired facial image with the feature data of the pre-stored facial image, and determine whether the acquired facial image is included in the pre-stored facial image;
  • the sending module is further configured to: when the acquired facial image is not included in the pre-stored facial image, send the image data to a designated client terminal.
  • the device further comprising:
  • a motion recognition module configured to analyze an action of the human body monitored by the infrared camera before the RGB camera of the somatosensory device is turned on and the image data of the person is acquired;
  • the RGB camera opening module is further configured to, when the action of the human body is included in the pre-stored action list, the step of opening the RGB camera of the somatosensory device and acquiring the image data of the person.
  • the apparatus as described above is further provided, wherein the sending module is further configured to send an alarm signal; or
  • the device also includes:
  • a receiving module configured to receive an alarm indication sent by the client terminal
  • the sending module is further configured to issue an alarm signal according to the alarm indication.
  • the device further comprising:
  • the rotation control module is configured to control the somatosensory device to rotate within a preset angle after the infrared camera of the somatosensory device is turned on; and/or to control the somatosensory device to perform tracking and photographing of the human body in the monitoring region.
  • the security method based on the smart television of the embodiment after the security function of the television is turned on, the infrared camera of the somatosensory device is used to monitor the human body, and the RGB camera is turned on when the human body is monitored. Take a photo and send the acquired image data to the designated client terminal to promptly remind the user to handle the suspicious situation.
  • the smart TV when the smart TV is equipped with the somatosensory device of the somatosensory game, the home security can be realized without adding additional equipment, the security cost of the user is reduced, and since the infrared camera can have the night vision function, it can be realized all the time. Security Monitoring.
  • FIG. 1 is a flowchart of a security method based on a smart TV according to Embodiment 1 of the present application;
  • FIG. 2 is a schematic structural diagram of a module of a security device based on a smart TV according to Embodiment 2 of the present application;
  • FIG. 3 is a flowchart of a security method based on a smart TV provided in Embodiment 3 of the present application;
  • FIG. 4 is a schematic diagram showing a selection structure of a somatosensory device according to Embodiment 3 of the present application.
  • FIG. 5 is a schematic structural diagram of a module of a security device based on a smart TV according to Embodiment 4 of the present application;
  • FIG. 5 is a schematic structural diagram of a module of a security device based on a smart TV according to Embodiment 4 of the present application;
  • FIG. 6 is a flowchart of a security method based on a smart TV provided in Embodiment 5 of the present application;
  • FIG. 7 is a schematic structural diagram of a module of a security device based on a smart TV provided in Embodiment 6 of the present application.
  • the first embodiment of the present application provides a smart TV-based security method, which is configured as a smart TV with a somatosensory device.
  • the method flow includes:
  • Step S102 Determine whether the infrared camera monitors the human body, and when the human body is monitored, Step S103;
  • the somatosensory device often includes a camera module and an infrared transceiver module, and the infrared transceiver module includes an infrared emitter and an infrared receiver.
  • the infrared receiver can be an infrared camera, and the infrared camera can distinguish the person and the object in front of the TV according to the temperature of the object.
  • the character image data may be a captured video or a photo.
  • the infrared camera of the somatosensory device is used to monitor the human body, and when the human body is detected, the RGB camera is turned on to take a photo, and the acquired image data is sent to The designated client terminal promptly reminds the user to handle the suspicious situation.
  • the smart TV is equipped with the somatosensory device of the somatosensory game, the home security can be realized without adding additional equipment, the security cost of the user is reduced, and since the infrared camera can have the night vision function, it can be realized all the time. Security Monitoring.
  • the embodiment of the present application also provides a computer readable recording medium on which a program for executing the above method is recorded.
  • the computer readable recording medium includes any mechanism for storing or transmitting information in a form readable by a computer (eg, a computer).
  • a machine-readable medium includes read only memory (ROM), random access memory (RAM), magnetic disk storage media, optical storage media, flash storage media, electrical, optical, acoustic, or other forms of propagation signals (eg, carrier waves) , infrared signals, digital signals, etc.).
  • the second embodiment of the present application provides a security device based on a smart TV.
  • the security device includes:
  • the infrared camera opening module 201 is configured to turn on the infrared camera of the somatosensory device after the security function of the television is turned on;
  • the RGB camera opening module 202 is configured to open the RGB camera of the somatosensory device and acquire the image data of the person when the infrared camera monitors the human body.
  • the character image data may be a captured video or a photo.
  • the sending module 203 is configured to send the acquired image data to the designated client terminal.
  • the security device based on the smart TV of the embodiment after turning on the security function of the television, uses the infrared camera of the somatosensory device to monitor the human body, and when the human body is monitored, the RGB camera is turned on to take a photo, and the acquired image data is sent to The designated client terminal promptly reminds the user to handle the suspicious situation.
  • the smart TV when the smart TV is equipped with the somatosensory device of the somatosensory game, the home security can be realized without adding additional equipment, the security cost of the user is reduced, and since the infrared camera can have the night vision function, it can be realized all the time. Security Monitoring.
  • Embodiment 3 of the present application provides another security method based on a smart TV.
  • the method flow includes:
  • the security function option may include an association option by which the user can pre-designate the associated client terminal
  • the client terminal may be a personal computer, a mobile phone, or the like.
  • the security function option may also include a camera monitoring mode option, such as selecting the infrared camera to be in a normally open state or an intermittent scanning state.
  • a camera monitoring mode option such as selecting the infrared camera to be in a normally open state or an intermittent scanning state.
  • S302 Turn on the security function according to the instruction input by the user.
  • the user can input an instruction to turn on the security function by operating a remote controller or a panel button of the television.
  • step S304 When the infrared camera monitors the human body, analyze the motion of the human body monitored by the infrared camera. If the motion of the human body is included in the pre-stored action list, step S305 is performed.
  • the infrared emitting module of the somatosensory device emits a set of infrared light sources, and the infrared camera receives the reflected light spot of the object or the human body against the infrared rays to obtain a depth image.
  • the human body is extracted from the background environment of the depth image.
  • This process is a process of extracting useful information from noise.
  • the human body image is finally taken from the background. Distinguish from the environment.
  • Each pixel that extracts the human body image is transmitted into a machine learning system that identifies the body part of the body to identify which body part a particular pixel belongs to.
  • a human skeleton system is generated based on the tracked multiple joint points, for example, 20 joint points.
  • Step 1 Collect spatial position information of human bone joint points at different times
  • Step 2 determining whether the spatial position information of the human bone joint point at each moment is matched with the initial position information of the preset various human motions; if yes, the moment is recorded as the initial moment, and step 3 is performed. Otherwise, return to step 1;
  • Step 3 Starting from the initial time, determine whether the spatial position information of the human bone joint point acquired in the subsequent time period satisfies the determination criteria of various human body actions preset in the action list; if yes, perform step 4.
  • Step 4 Identify the action of the target human body.
  • the human body actions in the preset action list include kicking, swinging, waving arms, parabolic and other fighting actions, which are stored in the action list through the corresponding skeleton system.
  • the pre-stored action list may be defined by the user. In this case, the user needs to perform different actions in advance of the somatosensory device, so that the somatosensory device learns the actions, so that the corresponding skeleton system is stored in the action list, or directly Get a list of common actions from the server.
  • the acquired image data of the person may be a photograph taken or a photographed video.
  • FIG. 4 is an improved rotating functional body. Schematic diagram of the structure.
  • a first motor 403 is disposed between the body 401 of the somatosensory device and the bracket 402. The first motor 403 can be controlled to rotate the body 401 in the up and down direction.
  • the second motor 405 is disposed between the bracket 402 and the base 404. A motor 405 can realize the rotation of the body 401 in the left and right direction.
  • the image of the current frame of RGB can be divided into four regions, and then the human body in the image is recognized. According to the identified region where the human body is currently located and the preset initial region, the computer body 401 needs to be rotated. The angle and direction then control the first motor and/or the second motor to effect the selection of the body 401.
  • the initial area preset in the actual application may be the center of the image or other set position, and is generally the preferred area in which the selected person is selected in the image.
  • the monitoring angle can also be set in the security function option, thereby controlling the somatosensory device to rotate within a preset angle, expanding the monitoring area, and then, when the human body is monitored, the video captured by the RGB camera is in the monitoring area to the human body. Take a tracking shot.
  • the image data can be sent to the user terminal of the user through a cloud server connected to the smart TV.
  • the client and the cloud server are connected to each other, and after receiving the image data, the cloud server parses the identification data carried in the image data, matches the user data saved in the cloud server, and determines which user the alarm information comes from, and then
  • the image data is sent to the customer receiving terminal of the user by the telecommunication service provider, and specifically, may be sent by means of MMS or email.
  • the user After receiving the image data, the user can judge whether it is necessary to issue an alarm indication according to the specific situation. For example, if the user finds that the person in the image data is a stranger, the user needs to send an alarm indication to the smart TV; if the user finds that the person in the image data is a certain Family members will not give an alarm indication to the smart TV.
  • an alarm sound can be generated by a speaker that drives the television.
  • the security device of the smart TV can also be established to communicate with the security system of the community or the community.
  • the alarm signal sent at this time can also be sent to the security department of the community or community.
  • the alarm signal is processed by the security system staff.
  • the security device can also directly issue an alarm signal without the user sending an alarm indication for authorization.
  • the infrared camera of the somatosensory device is used to monitor the human body, and when the human body is detected, the RGB camera is turned on to take a photo, and the acquired image data is sent to The designated client terminal promptly reminds the user to handle the suspicious situation.
  • the smart TV is equipped with the somatosensory device of the somatosensory game, the home security can be realized without adding additional equipment, the security cost of the user is reduced, and since the infrared camera can have the night vision function, it can be realized all the time. Security Monitoring.
  • the fourth embodiment of the present application provides a security device based on a smart TV.
  • the security device includes:
  • the setting module 501 is configured to set a security function option in a menu option of the smart TV in advance;
  • the setting function opening module 502 is configured to enable the security function according to an instruction input by the user
  • the infrared camera opening module 503 is configured to turn on the infrared camera of the somatosensory device after the security function of the television is turned on;
  • the motion recognition module 504 is configured to analyze an action of the human body monitored by the infrared camera when the infrared camera monitors the human body;
  • the action recognition module 504 may include: a collection sub-module configured to collect spatial position information of a human bone joint point at different times; and a determination sub-module configured to acquire a human bone joint point at each moment of the acquisition
  • the spatial position information is judged whether it matches the initial position information of the preset various human body actions, and the time is recorded as the initial time when the match is matched, and is configured to start from the initial time and determine the acquired time after the time period.
  • the identification sub-module is configured to determine that the spatial position information of the acquired human bone joint point meets the judgment of the person in the judgment sub-module When the criterion of the body motion is determined, the motion of the target human body is recognized.
  • the RGB camera opening module 505 is configured to open the RGB camera of the somatosensory device and acquire the image data of the person;
  • the sending module 506 is configured to send the image data to the designated client terminal
  • the receiving module 507 receives an alarm indication sent by the client terminal
  • the alarm module 508 is configured to issue an alarm signal.
  • the security device may further include a rotation control module configured to control the somatosensory device to rotate within a preset angle after the infrared camera of the somatosensory device is turned on And/or tracking the human body in the monitored area of the somatosensory device.
  • the security device based on the smart TV of the embodiment after turning on the security function of the television, uses the infrared camera of the somatosensory device to monitor the human body, and when the human body is monitored, the RGB camera is turned on to take a photo, and the acquired image data is sent to The designated client terminal promptly reminds the user to handle the suspicious situation.
  • the smart TV when the smart TV is equipped with the somatosensory device of the somatosensory game, the home security can be realized without adding additional equipment, the security cost of the user is reduced, and since the infrared camera can have the night vision function, it can be realized all the time. Security Monitoring.
  • Embodiment 5 of the present application provides another security method based on a smart TV.
  • the method flow includes:
  • S602 Turn on the security function according to an instruction input by the user.
  • the RGB camera of the somatosensory device When the infrared camera monitors the human body, the RGB camera of the somatosensory device is turned on and the image data of the person is acquired.
  • the acquired image data of the person may be a photograph taken or a photographed video.
  • the recognized person can also be tracked and photographed, and the mechanical part of the somatosensory device needs to be appropriately modified to be rotatable in the security mode.
  • the specific implementation can be seen in Figure 4, which can realize panoramic security.
  • the image data acquired by the RGB camera may be image data or video data.
  • the picture can be directly recognized by the face; if it is a video material, the video frame of the current time needs to be extracted from the captured video to obtain a still picture of the current frame, and then the still picture is performed. Face recognition.
  • the method for face recognition includes:
  • the method first designs a template of one or several standard faces, and then calculates the degree of matching between the sample collected by the test and the standard template, and judges whether there is a face through the threshold;
  • the method extracts these features to generate corresponding rules to determine whether the test sample contains a human face.
  • This method uses the artificial neural network method in pattern recognition, that is, the classifier is generated by learning the face image sample set and the non-face image sample set.
  • This method is based on the law that the skin color distribution is relatively concentrated in the color space.
  • This method treats all face image sets as one face image subspace and determines whether there is a face image based on the distance between the detected sample and its projection between the child holes.
  • step S606 comparing the acquired feature data of the face image with the feature data of the pre-stored face image, and determining whether the acquired face image is included in the pre-stored face image, and if not included in the pre-stored face image, Then step S607 is performed.
  • the features of the face are usually divided into visual features, pixel statistical features, face image transform coefficient features, face image algebra features, and the like.
  • the extraction of feature data of facial images is performed on certain features of the face, which is the process of modeling the features of the face.
  • the extraction of the feature data of the face mainly includes: a knowledge-based representation method and a representation method based on algebraic features or statistical learning.
  • the photo of the specified user may be imported into the system in advance, including importing through an existing photo file, or directly shooting through an RGB camera to generate a feature template.
  • the facial image is acquired, the facial feature data to be identified is compared with the feature template, and the identity information of the face is determined according to the degree of similarity.
  • users can import photos from multiple different users.
  • the security device can also directly issue an alarm signal without the user sending an alarm indication for authorization.
  • the acquired image data can also be directly stored in the local storage module, and the user can directly use the smart TV to view the image data.
  • step S604 when the infrared camera monitors the human body, the motion of the human body monitored by the infrared camera may be analyzed, and it is recognized that when the motion of the human body is included in the pre-stored action list, step S604 is performed.
  • the method for analyzing the motion of the human body monitored by the infrared camera, and the method for identifying whether the motion of the human body is included in the pre-stored action list is substantially the same as the step S304 of the third embodiment, and details are not described herein again.
  • the security device based on the smart TV of the embodiment turns on the security function of the television After that, the infrared camera of the somatosensory device is used to monitor the human body, and when the human body is monitored, the RGB camera is turned on to take a photo, and the acquired image data is sent to the designated client terminal, and the user is promptly reminded to handle the suspicious situation.
  • the smart TV is equipped with the somatosensory device of the somatosensory game
  • the home security can be realized without adding additional equipment, the security cost of the user is reduced, and since the infrared camera can have the night vision function, it can be realized all the time. Security Monitoring.
  • the sixth embodiment of the present application provides a security device based on a smart TV.
  • the security device includes:
  • the setting module 701 is configured to set a security function option in a menu option of the smart TV in advance;
  • the opening module 702 is configured to enable the security function according to an instruction input by the user
  • the infrared camera opening module 703 is configured to turn on the infrared camera of the somatosensory device after the security function of the television is turned on;
  • the RGB camera opening module 704 is configured to open the RGB camera of the somatosensory device and acquire the image data of the person;
  • the face recognition module 705 is configured to identify a face in the image data, and acquire a face image of the face;
  • the facial feature comparison module 706 is configured to compare the feature data of the acquired facial image with the feature data of the pre-stored facial image, and determine whether the acquired facial image is included in the pre-stored facial image;
  • the sending module 707 is configured to send the image data to the designated client terminal
  • the receiving module 708 receives an alarm indication sent by the client terminal
  • the alarm module 709 is configured to issue an alarm signal.
  • the security device may further include a rotation control module configured to control the somatosensory device to rotate within a preset angle after the infrared camera of the somatosensory device is turned on And/or tracking the human body in the monitored area of the somatosensory device.
  • the infrared camera of the somatosensory device is used to monitor the human body, and the RGB is turned on when the human body is monitored.
  • the camera takes a picture and sends the acquired image data to the designated client terminal to promptly remind the user to handle the suspicious situation.
  • the smart TV is equipped with the somatosensory device of the somatosensory game, the home security can be realized without adding additional equipment, the security cost of the user is reduced, and since the infrared camera can have the night vision function, it can be realized all the time. Security Monitoring.
  • the device embodiments described above are merely illustrative, wherein the modules described as separate components may or may not be physically separate, and the components displayed as modules may or may not be physical modules, ie may be located A place, or it can be distributed to multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without deliberate labor.

Abstract

一种基于智能电视机的安防方法及装置，属于智能电视技术领域。方法流程包括：当电视机的安防功能开启后，开启体感装置的红外摄像头；若所述红外摄像头监测到人体，开启所述体感装置的RGB摄像头并获取人物图像资料；将所述图像资料发送到指定的客户终端。一种基于智能电视机的安防方法及装置不需要由专业人员进行安装，成本较低。

Description

一种基于智能电视机的安防方法、装置
本申请要求于2016年3月29日提交中国专利局、申请号为201610185050.0，发明名称为“一种基于智能电视机的安防方法、装置”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
本申请实施例涉及智能电视技术领域，尤其涉及一种基于智能电视机的安防方法、装置。
背景技术
随着人们生活水平的提高以及安全防范意识的提高，安全防护越来越深入人心。现有技术中也出现了针对家庭的安防系统，目前的家用安防系统大多使用专用的安防器材，比如家庭网络视频监控，通过网络安防摄像头摄取画面并将相关安防数据存储在本地。然而现有的家庭安防需要购买专门的安防产品，并由专业人员进行安装，成本较高，因此，如何通过现有的设备实现家庭安防也是现有技术亟待解决的问题。
因此，在实现本申请过程中，发明人发现有必要提供一种基于智能电视机的安防方法及装置。
发明内容
本申请实施例的目的在于提供一种基于智能电视机的安防方法及装置，用以解决现有技术中家庭安防的实现需要由专业人员进行安装，成本较高的问题。
本申请实施例采用的技术方案如下：
本申请实施例提供一种基于智能电视机的安防方法，所述方法包括：
当电视机的安防功能开启后，开启体感装置的红外摄像头；
若所述红外摄像头监测到人体，开启所述体感装置的RGB摄像头并获取人物图像资料；
将所述图像资料发送到指定的客户终端。
具体的，还提供一种如上所述的方法，所述将所述图像资料发送到指定的客户终端之前，所述方法还包：
对所述图像资料中的人脸进行识别，获取人脸的面部图像；
将获取的面部图像的特征数据与预存的面部图像的特征数据进行比对，判断获取的面部图像是否包含在所述预存的面部图像之中；
若未包含在所述预存的面部图像之中，则执行所述将所述图像资料发送到指定的客户终端的步骤。
具体的，还提供一种如上所述的方法，所述开启所述体感装置的RGB摄像头并获取人物图像资料之前，所述方法还包：
对所述红外摄像头监测到的人体的动作进行分析；
若所述人体的动作包括在预存的动作列表内，则执行所述开启所述体感装置的RGB摄像头并获取人物图像资料的步骤。
具体的，还提供一种如上所述的方法，所述将所述图像资料发送到指定的客户终端之后，所述方法还包括：
发出报警信号；或者
接收所述客户终端发送的报警指示，并根据所述报警指示发出报警信号。
具体的，还提供一种如上所述的方法，所述开启体感装置的红外摄像头之后，所述方法还包括：
控制所述体感装置在预设的角度内旋转；和/或
在所述体感装置的监控区域内对所述人体进行追踪拍摄。
本申请实施例还提供了一种在其上记录有用于执行上述方法的程序的计算机可读记录介质。
本申请实施例还提供了一种基于智能电视机的安防装置，所述装置包括：
红外摄像头开启模块，配置为在电视机的安防功能开启后，开启体感装置的红外摄像头；
RGB摄像头开启模块，配置为在所述红外摄像头监测到人体时，开启所述体感装置的RGB摄像头并获取人物图像资料；
发送模块，配置为将所述图像资料发送到指定的客户终端。
具体的，还提供一种如上所述的装置，所述装置还包括：
人脸识别模块，配置为对所述图像资料中的人脸进行识别，获取人 脸的面部图像；
面部特征比对模块，配置为将获取的面部图像的特征数据与预存的面部图像的特征数据进行比对，判断获取的面部图像是否包含在所述预存的面部图像之中；
所述发送模块，还配置为在所述获取的面部图像若未包含在所述预存的面部图像之中时，将所述图像资料发送到指定的客户终端。
具体的，还提供一种如上所述的装置，所述装置还包括：
动作识别模块，配置为开启所述体感装置的RGB摄像头并获取人物图像资料之前，对所述红外摄像头监测到的人体的动作进行分析；
所述RGB摄像头开启模块，还配置为在所述人体的动作包括在预存的动作列表内时，开启所述体感装置的RGB摄像头并获取人物图像资料的步骤。
具体的，还提供一种如上所述的装置，所述发送模块，还配置为发出报警信号；或者
所述装置还包括：
接收模块，配置为接收所述客户终端发送的报警指示；
所述发送模块，还配置为根据所述报警指示发出报警信号。
具体的，还提供一种如上所述的装置，所述装置还包括：
旋转控制模块，配置为在开启体感装置的红外摄像头之后，控制所述体感装置在预设的角度内旋转；和/或配置为控制所述体感装置在监控区域内对所述人体进行追踪拍摄。
本申请实施例的技术方案具有以下优点：本实施例的基于智能电视机的安防方法，在开启电视机的安防功能后，利用体感装置的红外摄像头监测人体，并在监测到人体时打开RGB摄像头来拍照，并把获取的图像资料发送到指定的客户终端，及时提醒用户对可疑情况进行处理。本实施例在智能电视配备了体感游戏的体感装置时，无需增加额外的设备便能够实现家庭的安防，降低了用户的安防成本，并且由于红外摄像头可以具有夜视功能，因此，可以实现全天候的安防监控。
附图说明
为了更清楚地说明本申请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一简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，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获得其他的附图。
图1为本申请实施例一提供的一种基于智能电视机的安防方法的流程图；
图2为本申请实施例二提供的一种基于智能电视机的安防装置的模块结构示意图；
图3为本申请实施例三提供的一种基于智能电视机的安防方法的流程图；
图4为本申请实施例三中的体感装置的选择结构示意图；
图5为本申请实施例四提供的一种基于智能电视机的安防装置的模块结构示意图；
图6为本申请实施例五提供的一种基于智能电视机的安防方法的流程图；
图7为本申请实施例六提供的一种基于智能电视机的安防装置的模块结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，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，都属于本申请保护的范围。
本申请实施例一提供一种基于智能电视机的安防方法，适配置为安装了体感装置的智能电视，请参阅图1，方法流程包括：
S101、当电视机的安防功能开启后，开启体感装置的红外摄像头；
S102、判断该红外摄像头是否监测到人体，并在监测到人体时，执 行步骤S103；
体感装置往往包含摄像头模组和红外线收发模组，红外线收发模组包括红外线发射器和红外线接收器。实际应用中，红外线接收器可以是红外摄像头，通过红外摄像头根据物体温度可以将电视机前的人和物进行区分。
S103、开启该体感装置的RGB摄像头并获取人物图像资料。
实际应用中，人物图像资料可以是拍摄的视频或者照片。
S104、将该图像资料发送到指定的客户终端。
本实施例的基于智能电视机的安防方法，在开启电视机的安防功能后，利用体感装置的红外摄像头监测人体，并在监测到人体时打开RGB摄像头来拍照，并把获取的图像资料发送到指定的客户终端，及时提醒用户对可疑情况进行处理。本实施例在智能电视配备了体感游戏的体感装置时，无需增加额外的设备便能够实现家庭的安防，降低了用户的安防成本，并且由于红外摄像头可以具有夜视功能，因此，可以实现全天候的安防监控。
本申请实施例还提供了一种在其上记录有用于执行上述方法的程序的计算机可读记录介质。
所述计算机可读记录介质包括用于以计算机(例如计算机)可读的形式存储或传送信息的任何机制。例如，机器可读介质包括只读存储器(ROM)、随机存取存储器(RAM)、磁盘存储介质、光存储介质、闪速存储介质、电、光、声或其他形式的传播信号(例如，载波、红外信号、数字信号等)等。
在上述实施例的基础上，本申请实施例二提供了一种基于智能电视机的安防装置，请参阅图2，该安防装置包括：
红外摄像头开启模块201，配置为在电视机的安防功能开启后，开启体感装置的红外摄像头；
RGB摄像头开启模块202，配置为在红外摄像头监测到人体时，开启该体感装置的RGB摄像头并获取人物图像资料。
实际应用中，人物图像资料可以是拍摄的视频或者照片。
发送模块203，配置为将获取的图像资料发送到指定的客户终端。
本实施例的基于智能电视机的安防装置，在开启电视机的安防功能后，利用体感装置的红外摄像头监测人体，并在监测到人体时打开RGB摄像头来拍照，并把获取的图像资料发送到指定的客户终端，及时提醒用户对可疑情况进行处理。本实施例在智能电视配备了体感游戏的体感装置时，无需增加额外的设备便能够实现家庭的安防，降低了用户的安防成本，并且由于红外摄像头可以具有夜视功能，因此，可以实现全天候的安防监控。
本申请实施例三提供了另一种基于智能电视机的安防方法，请参阅图3，方法流程包括：
S301、预先在智能电视机的菜单选项中设置安防功能选项。
具体的，该安防功能选项可以包括关联选项，用户可以通过该选项预先指定关联的客户终端，客户终端可以是个人电脑、或手机等。
具体的，该安防功能选项也可以包括摄像头监测方式选项，比如选择红外摄像头是处于常开状态或者是间歇性扫描状态。
S302、根据用户输入的指令开启安防功能。
具体的，用户可以通过操作遥控器或电视机面板按键输入开启安防功能的指令。
S303、开启体感装置的红外摄像头。
S304、当红外摄像头监测到人体时，对该红外摄像头监测到的人体的动作进行分析，若该人体的动作包括在预存的动作列表内，执行步骤S305。
具体的，红外摄像头开启时，体感装置的红外发射模组将发射一组红外线光源，红外摄像头接收物体或人体对红外线的反射光斑，获得深度图像。
然后将人体从深度图像的背景环境中提取出来，该过程是从噪音中提取有用信息的过程，通过边缘检测、噪声阈值处理、对人体目标特征点的分类等计算处理，最终将人体图像从背景环境中区分出来。然后， 将提取人体图像的每一个像素都被传送进一个辨别人体部位的机器学习系统中，以辨识某个特定像素属于哪个身体部位。最后，使用之前阶段输出的结果，根据追踪到的多个关节点，例如20个关节点来生成一幅人体骨架系统。
在分析人体的动作时，可以通过如下步骤进行：
步骤1、对不同时刻的人体骨骼关节点的空间位置信息进行采集；
步骤2、针对获取的每个时刻的人体骨骼关节点的空间位置信息，判断其是否与预设的各种人体动作的初始位置信息相匹配；若是，将该时刻记为初始时刻，执行步骤3，否则，返回步骤1；
步骤3、从初始时刻开始，判断其后一段时间内获取的人体骨骼关节点的空间位置信息是否满足动作列表中预设的各种人体动作的判定标准；若是，执行步骤4。
步骤4、识别出目标人体的动作。
实际应用中，预先设定的动作列表中的人体动作包括踢腿、挥拳、挥动手臂、抛物等打斗动作，这些动作通过对应的骨架系统存储在动作列表中。具体的，可以由用户自己定义预存的动作列表，此时需要用户预先在体感装置前做出不同的动作，使体感装置学习这些动作，从而获取对应的骨骼系统存储到动作列表中，也可以直接从服务器中获取通用的动作列表。
S305、开启该体感装置的RGB摄像头并获取人物图像资料。
实际应用中，获取的人物图像资料可以是拍摄的照片也可以是拍摄的视频。
为了在夜间或光照条件不好的情况下也能够获得清晰的图像资料，可以在开启RGB摄像头时，同时开启电视机的显示屏，比如开启显示屏后使之在较高或最高亮度下显示白色背景，这样可以借助显示屏的亮光进行拍摄。
如果获取的人物图像资料是拍摄的视频，还可以对识别出的人物进行追踪拍摄，此时需要对体感装置的机械部分进行适当的改进，使其在安防模式下可以旋转。请参阅图4，是一种改进后的具有旋转功能体感装 置的结构示意图。该体感装置的机体401与支架402之间设有第一电机403；控制该第一电机403可以实现机体401上下方向的转动；支架402与底座404之间设有第二电机405，控制该第一电机405可以实现机体401左右方向的转动。
在进行追踪拍摄时，可以将RGB当前帧的图像划分为四个区域，然后对该图像中的人体进行识别，根据识别出的人体当前所在的区域以及预设的初始区域，计算机体401需要旋转的角度和方向，然后控制第一电机和/或第二电机实现机体401的选转。实际应用中预设的初始区域可以是该图像的中心或其他设定的位置，一般是选择被追踪人物在图像中的较佳所处区域。
实际应用中，也可以在安防功能选项中设置监控角度，从而控制体感装置在预设的角度内旋转，扩大监控区域，然后在监测到人体时，通过RGB摄像头拍摄的视频在监控区域内对人体进行追踪拍摄。
S306、将该图像资料发送到指定的客户终端。
实际应用中，可以通过与智能电视机通讯连接的云服务器将图像资料发送至用户的客户终端。具体而言，客户端与云端服务器相互连接，云端服务器接收到图像资料后，解析出图像资料中携带的标识数据，与云端服务器中保存的用户数据进行匹配，并判断报警信息来自哪个用户，然后通过电信服务商向此用户的客户接收终端发送图像资料，具体的，可以通过彩信或电子邮件的方式发送。
S307、接收该客户终端发送的报警指示。
用户在接收到图像资料后，可以根据具体情况判断是否需要发出报警指示，比如用户发现图像资料中的人为陌生人，则需要向智能电视机发出报警指示；如果用户发现图像资料中的人是某个家庭成员则不会向智能电视机发出报警指示。
S308、发出报警信号。
具体的，可以通过驱动电视机的喇叭发出报警声响。
实际应用中，也可以将智能电视机的安防装置与小区或社区的安防系统建立通讯，此时发出的报警信号也可以发送给小区或社区的安防系 统，由安防系统的工作人员对该报警信号进行处理。
实际应用中，安防装置也可以直接发出报警信号而无需用户发送报警指示进行授权。
本实施例的基于智能电视机的安防方法，在开启电视机的安防功能后，利用体感装置的红外摄像头监测人体，并在监测到人体时打开RGB摄像头来拍照，并把获取的图像资料发送到指定的客户终端，及时提醒用户对可疑情况进行处理。本实施例在智能电视配备了体感游戏的体感装置时，无需增加额外的设备便能够实现家庭的安防，降低了用户的安防成本，并且由于红外摄像头可以具有夜视功能，因此，可以实现全天候的安防监控。
在上述实施例的基础上，本申请实施例四提供了基于智能电视机的安防装置，请参阅图5，该安防装置包括：
设置模块501，配置为预先在智能电视机的菜单选项中设置安防功能选项；
安放功能开启模块502，配置为根据用户输入的指令开启安防功能；
红外摄像头开启模块503，配置为在电视机的安防功能开启后，开启体感装置的红外摄像头；
动作识别模块504，配置为在红外摄像头监测到人体时，对该红外摄像头监测到的人体的动作进行分析；
具体的，该动作识别模块504可以包括：采集子模块，配置为对不同时刻的人体骨骼关节点的空间位置信息进行采集；判断子模块，配置为针对获取的每个时刻的人体骨骼关节点的空间位置信息，判断其是否与预设的各种人体动作的初始位置信息相匹配，并在匹配时将该时刻记为初始时刻，以及配置为从初始时刻开始，判断其后一段时间内获取的人体骨骼关节点的空间位置信息是否满足动作列表中预设的各种人体动作的判定标准；识别子模块，配置为在判断子模块判断出获取的人体骨骼关节点的空间位置信息满足判某个人体动作的判定标准时，识别出目标人体的动作。
RGB摄像头开启模块505，配置为开启该体感装置的RGB摄像头并获取人物图像资料；
发送模块506，配置为将该图像资料发送到指定的客户终端；
接收模块507，接收该客户终端发送的报警指示；
报警模块508，配置为发出报警信号。
在本实施例的一个具体的方案中，若体感装置设有旋转结构，安防装置还可以包括旋转控制模块，配置为在开启体感装置的红外摄像头之后，控制该体感装置在预设的角度内旋转；和/或在该体感装置的监控区域内对该人体进行追踪拍摄。
本实施例的基于智能电视机的安防装置，在开启电视机的安防功能后，利用体感装置的红外摄像头监测人体，并在监测到人体时打开RGB摄像头来拍照，并把获取的图像资料发送到指定的客户终端，及时提醒用户对可疑情况进行处理。本实施例在智能电视配备了体感游戏的体感装置时，无需增加额外的设备便能够实现家庭的安防，降低了用户的安防成本，并且由于红外摄像头可以具有夜视功能，因此，可以实现全天候的安防监控。
本申请实施例五提供了另一种基于智能电视机的安防方法，请参阅图6，方法流程包括：
S601、预先在智能电视机的菜单选项中设置安防功能选项。
S602、根据用户输入的指令开启安防功能。
S603、开启体感装置的红外摄像头。
具体的，上述步骤S601至步骤S603的实现方式与实施例三的步骤S301至步骤S303基本相同，这里不再赘述。
S604、当红外摄像头监测到人体时，开启该体感装置的RGB摄像头并获取人物图像资料。
为了在夜间或光照条件不好的情况下也能够获得清晰的图像资料，可以在开启RGB摄像头时，同时开启电视机的显示屏，比如开启显示屏后使之在较高或最高亮度下显示白色背景，这样可以借助显示屏的亮光 进行拍摄。
实际应用中，获取的人物图像资料可以是拍摄的照片也可以是拍摄的视频。具体的，如果获取的人物图像资料是拍摄的视频，还可以对识别出的人物进行追踪拍摄，此时需要对体感装置的机械部分进行适当的改进，使其在安防模式下可以旋转。具体实现方式可参阅图4，可实现全景安防。
S605、对该图像资料中的人脸进行识别，获取人脸的面部图像；
实际应用中，RGB摄像头获取的图像资料可以是图片资料或者视频资料。
如果只拍摄一张图片，则可以直接对该图片进行人脸识别；如果是视频资料，需要从拍摄的视频中提取当前时刻的视频帧，从而获取当前帧的静态图片，再对该静态图片进行人脸识别。
具体的，人脸识别的方法包括：
1、参考模板法
该方法首先设计一个或数个标准人脸的模板，然后计算测试采集的样品与标准模板之间的匹配程度，并通过阈值来判断是否存在人脸；
2、人脸规则法
由于人脸具有一定的结构分布特征，而该方法即提取这些特征生成相应的规则以判断测试样品是否包含人脸。
3、样品学习法
这种方法即采用模式识别中人工神经网络的方法，即通过对面像样品集和非面像样品集的学习产生分类器。
4、肤色模型法
这种方法是依据面貌肤色在色彩空间中分布相对集中的规律来进行检测。
5、特征子脸法
这种方法是将所有面像集合视为一个面像子空间，并基于检测样品与其在子孔间的投影之间的距离判断是否存在面像。
需要说明的是，上述5种方法在实际应用中也可综合使用。
S606、将获取的面部图像的特征数据与预存的面部图像的特征数据进行比对，判断获取的面部图像是否包含在该预存的面部图像之中，若未包含在该预存的面部图像之中，则执行步骤S607。
实际应用中，人脸的特征通常分为视觉特征、像素统计特征、人脸图像变换系数特征、人脸图像代数特征等。面部图像的特征数据的提取就是针对人脸的某些特征进行的，它是对人脸进行特征建模的过程。具体的，人脸的特征数据的提取主要包括：基于知识的表征方法及基于代数特征或统计学习的表征方法。
具体的，可以预先将指定用户的照片导入到系统中，包括通过已有照片文件导入，或直接通过RGB摄像头进行拍摄，生成特征模板。在获取到面部图像时，将待识别的面部特征数据与的特征模板进行比较，根据相似程度对人脸的身份信息进行判断。实际应用中，用户可以导入多个不同的用户的照片。
S607、将该图像资料发送到指定的客户终端。
S608、接收该客户终端发送的报警指示。
S609、发出报警信号。
具体的，上述步骤S607至步骤S609的实现方式与实施例三的步骤S307至步骤S308基本相同，这里不再赘述。
实际应用中，安防装置也可以直接发出报警信号而无需用户发送报警指示进行授权。
需要说明的是，实际应用中，也可以将获取的图像资料直接存储在本地的存储模块中，此时用户可以直接利用智能电视对图像资料进行查阅。
实际应用中，也可以在红外摄像头监测到人体时，对该红外摄像头监测到的人体的动作进行分析，并识别出在该人体的动作包括在预存的动作列表内时，才执行步骤S604。具体的，对红外摄像头监测到的人体的动作进行分析，识别该人体的动作是否包括在预存的动作列表内的方法与实施例三的步骤S304基本相同，这里不再赘述。
本实施例的基于智能电视机的安防装置，在开启电视机的安防功能 后，利用体感装置的红外摄像头监测人体，并在监测到人体时打开RGB摄像头来拍照，并把获取的图像资料发送到指定的客户终端，及时提醒用户对可疑情况进行处理。本实施例在智能电视配备了体感游戏的体感装置时，无需增加额外的设备便能够实现家庭的安防，降低了用户的安防成本，并且由于红外摄像头可以具有夜视功能，因此，可以实现全天候的安防监控。
在上述实施例的基础上，本申请实施例六提供了基于智能电视机的安防装置，请参阅图7，该安防装置包括：
设置模块701，配置为预先在智能电视机的菜单选项中设置安防功能选项；
开启模块702，配置为根据用户输入的指令开启安防功能；
红外摄像头开启模块703，配置为在电视机的安防功能开启后，开启体感装置的红外摄像头；
RGB摄像头开启模块704，配置为开启该体感装置的RGB摄像头并获取人物图像资料；
人脸识别模块705，配置为对该图像资料中的人脸进行识别，获取人脸的面部图像；
面部特征比对模块706、配置为将获取的面部图像的特征数据与预存的面部图像的特征数据进行比对，判断获取的面部图像是否包含在该预存的面部图像之中；
发送模块707，配置为将该图像资料发送到指定的客户终端；
接收模块708，接收该客户终端发送的报警指示；
报警模块709，配置为发出报警信号。
在本实施例的一个具体的方案中，若体感装置设有旋转结构，安防装置还可以包括旋转控制模块，配置为在开启体感装置的红外摄像头之后，控制该体感装置在预设的角度内旋转；和/或在该体感装置的监控区域内对该人体进行追踪拍摄。
本实施例的基于智能电视机的安防方法，在开启电视机的安防功能后，利用体感装置的红外摄像头监测人体，并在监测到人体时打开RGB 摄像头来拍照，并把获取的图像资料发送到指定的客户终端，及时提醒用户对可疑情况进行处理。本实施例在智能电视配备了体感游戏的体感装置时，无需增加额外的设备便能够实现家庭的安防，降低了用户的安防成本，并且由于红外摄像头可以具有夜视功能，因此，可以实现全天候的安防监控。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (11)

  1. 一种基于智能电视机的安防方法，其特征在于，所述方法包括：
    当电视机的安防功能开启后，开启体感装置的红外摄像头；
    若所述红外摄像头监测到人体，开启所述体感装置的RGB摄像头并获取人物图像资料；
    将所述图像资料发送到指定的客户终端。
  2. 根据权利要求1所述的方法，其特征在于，所述将所述图像资料发送到指定的客户终端之前，所述方法还包：
    对所述图像资料中的人脸进行识别，获取人脸的面部图像；
    将获取的面部图像的特征数据与预存的面部图像的特征数据进行比对，判断获取的面部图像是否包含在所述预存的面部图像之中；
    若未包含在所述预存的面部图像之中，则执行所述将所述图像资料发送到指定的客户终端的步骤。
  3. 根据权利要求1或2所述的方法，其特征在于，所述开启所述体感装置的RGB摄像头并获取人物图像资料之前，所述方法还包括：
    对所述红外摄像头监测到的人体的动作进行分析；
    若所述人体的动作包括在预存的动作列表内，则执行所述开启所述体感装置的RGB摄像头并获取人物图像资料的步骤。
  4. 根据权利要求3所述的方法，其特征在于，所述将所述图像资料发送到指定的客户终端之后，所述方法还包括：
    发出报警信号；或者
    接收所述客户终端发送的报警指示，并根据所述报警指示发出报警信号。
  5. 根据权利要求1所述的方法，其特征在于，所述开启体感装置的红外摄像头之后，所述方法还包括：
    控制所述体感装置在预设的角度内旋转；和/或
    控制所述体感装置在监控区域内对所述人体进行追踪拍摄。
  6. 一种基于智能电视机的安防装置，其特征在于，所述装置包括：
    红外摄像头开启模块，配置为在电视机的安防功能开启后，开启体 感装置的红外摄像头；
    RGB摄像头开启模块，配置为在所述红外摄像头监测到人体时，开启所述体感装置的RGB摄像头并获取人物图像资料；
    发送模块，配置为将所述图像资料发送到指定的客户终端。
  7. 根据权利要求6所述的装置，其特征在于，所述装置还包括：
    人脸识别模块，配置为对所述图像资料中的人脸进行识别，获取人脸的面部图像；
    面部特征比对模块，配置为将获取的面部图像的特征数据与预存的面部图像的特征数据进行比对，判断获取的面部图像是否包含在所述预存的面部图像之中；
    所述发送模块，还配置为在所述获取的面部图像若未包含在所述预存的面部图像之中时，将所述图像资料发送到指定的客户终端。
  8. 根据权利要求6或7所述的装置，其特征在于，所述装置还包括：
    动作识别模块，配置为在开启所述体感装置的RGB摄像头并获取人物图像资料之前，对所述红外摄像头监测到的人体的动作进行分析；
    所述RGB摄像头开启模块，还配置为在所述人体的动作包括在预存的动作列表内时，开启所述体感装置的RGB摄像头并获取人物图像资料的步骤。
  9. 根据权利要求8所述的装置，其特征在于，
    所述发送模块，还配置为发出报警信号；或者
    所述装置还包括：
    接收模块，配置为接收所述客户终端发送的报警指示；
    所述发送模块，还配置为根据所述报警指示发出报警信号。
  10. 根据权利要求6所述的装置，其特征在于，所述装置还包括：
    旋转控制模块，配置为在开启体感装置的红外摄像头之后，控制所述体感装置在预设的角度内旋转；和/或配置为控制所述体感装置在监控区域内对所述人体进行追踪拍摄。
  11. 一种在其上记录有用于执行权利要求1所述方法的程序的计算机可读记录介质。
PCT/CN2016/088193 2016-03-29 2016-07-01 一种基于智能电视机的安防方法、装置 WO2017166469A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610185050.0A CN105872456A (zh) 2016-03-29 2016-03-29 一种基于智能电视机的安防方法及装置
CN201610185050.0 2016-03-29

Publications (1)

Publication Number Publication Date
WO2017166469A1 true WO2017166469A1 (zh) 2017-10-05

Family

ID=56626172

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/088193 WO2017166469A1 (zh) 2016-03-29 2016-07-01 一种基于智能电视机的安防方法、装置

Country Status (2)

Country Link
CN (1) CN105872456A (zh)
WO (1) WO2017166469A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112073638A (zh) * 2020-09-10 2020-12-11 深圳创维－Rgb电子有限公司 摄像头角度控制方法、装置、设备及计算机存储介质
CN112601054A (zh) * 2020-12-14 2021-04-02 珠海格力电器股份有限公司 摄像画面的采集方法及装置、存储介质、电子设备

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106652291A (zh) * 2016-12-09 2017-05-10 华南理工大学 一种基于Kinect的室内简易监控报警系统及方法
CN106817612A (zh) * 2016-12-09 2017-06-09 北海职业学院 一种具有监督功能的电视机的控制方法
CN106686353A (zh) * 2016-12-30 2017-05-17 佛山亚图信息技术有限公司 基于云端的安防控制系统及其方法
CN106846750A (zh) * 2017-03-30 2017-06-13 姚嘉 一种自动布防撤防系统及方法
CN107292749A (zh) * 2017-08-04 2017-10-24 平安科技（深圳）有限公司 车损证件照片的分类方法、系统及可读存储介质
CN107861391A (zh) * 2017-10-19 2018-03-30 广东美的制冷设备有限公司 家电设备的控制方法、装置、家电设备及可读存储介质
CN107704845A (zh) * 2017-10-26 2018-02-16 深圳佳力拓科技有限公司 一种机顶盒体感智能识别陌生人的方法及系统
CN110781750A (zh) * 2019-09-25 2020-02-11 万翼科技有限公司 危险人物监控处理方法、装置、计算机设备和存储介质
CN110933478A (zh) * 2019-12-19 2020-03-27 深圳创维－Rgb电子有限公司 一种安防系统
CN112188049A (zh) * 2020-09-10 2021-01-05 深圳波导智慧科技有限公司 一种自动追踪人脸设备及其方法
CN112509264B (zh) * 2020-11-19 2022-11-18 深圳市欧瑞博科技股份有限公司 异常入侵智能拍摄方法、装置、电子设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130023308A1 (en) * 2011-07-22 2013-01-24 Heran Co., Ltd. Display device with mobile communication
CN103425997A (zh) * 2013-08-13 2013-12-04 惠州Tcl移动通信有限公司 一种基于脸部识别的环境私密性保护处理方法及系统
CN103731633A (zh) * 2013-11-29 2014-04-16 乐视致新电子科技（天津）有限公司 一种可进行远程监控的电视装置及其控制方法
CN104135642A (zh) * 2014-07-31 2014-11-05 青岛歌尔声学科技有限公司 一种智能监控方法及相关设备
CN105023005A (zh) * 2015-08-05 2015-11-04 王丽婷 人脸识别装置及其识别方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101440676B (zh) * 2008-12-22 2013-10-16 北京中星微电子有限公司 一种基于摄像头的智能防盗门锁及其报警处理方法
CN103747205A (zh) * 2013-12-02 2014-04-23 乐视致新电子科技（天津）有限公司 通过智能电视进行监控的方法和系统
CN104639907B (zh) * 2015-02-04 2018-02-13 惠州Tcl移动通信有限公司 一种基于移动终端的智能安防方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130023308A1 (en) * 2011-07-22 2013-01-24 Heran Co., Ltd. Display device with mobile communication
CN103425997A (zh) * 2013-08-13 2013-12-04 惠州Tcl移动通信有限公司 一种基于脸部识别的环境私密性保护处理方法及系统
CN103731633A (zh) * 2013-11-29 2014-04-16 乐视致新电子科技（天津）有限公司 一种可进行远程监控的电视装置及其控制方法
CN104135642A (zh) * 2014-07-31 2014-11-05 青岛歌尔声学科技有限公司 一种智能监控方法及相关设备
CN105023005A (zh) * 2015-08-05 2015-11-04 王丽婷 人脸识别装置及其识别方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112073638A (zh) * 2020-09-10 2020-12-11 深圳创维－Rgb电子有限公司 摄像头角度控制方法、装置、设备及计算机存储介质
CN112601054A (zh) * 2020-12-14 2021-04-02 珠海格力电器股份有限公司 摄像画面的采集方法及装置、存储介质、电子设备

Also Published As

Publication number Publication date
CN105872456A (zh) 2016-08-17

Similar Documents

Publication Publication Date Title
WO2017166469A1 (zh) 一种基于智能电视机的安防方法、装置
US11158067B1 (en) Neighborhood alert mode for triggering multi-device recording, multi-camera locating, and multi-camera event stitching for audio/video recording and communication devices
US11399157B2 (en) Augmenting and sharing data from audio/video recording and communication devices
US11941874B2 (en) User interfaces to configure a thermal imaging system
US11735018B2 (en) Security system with face recognition
US20180233010A1 (en) Neighborhood alert mode for triggering multi-device recording, multi-camera motion tracking, and multi-camera event stitching for audio/video recording and communication devices
US11062577B2 (en) Parcel theft deterrence for A/V recording and communication devices
WO2017071085A1 (zh) 报警方法及装置
US10511810B2 (en) Accessing cameras of audio/video recording and communication devices based on location
WO2020019760A1 (zh) 活体检测方法、装置及系统、电子设备和存储介质
US11659144B1 (en) Security video data processing systems and methods
US20180151039A1 (en) Neighborhood Security Cameras
US9965612B2 (en) Method and system for visual authentication
US11736665B1 (en) Custom and automated audio prompts for devices
US11393108B1 (en) Neighborhood alert mode for triggering multi-device recording, multi-camera locating, and multi-camera event stitching for audio/video recording and communication devices
JP2018156453A (ja) 画像提供システム、画像提供方法、および画像提供プログラム
WO2018187451A1 (en) Augmenting and sharing data from audio/video recording and communication devices
US10863146B1 (en) Setup and configuration of audio/video recording and communication devices
WO2021084895A1 (en) A method, an apparatus and a system for managing an event to generate an alert indicating a subject is likely to be unauthorized
CN114332975A (zh) 识别利用模拟覆盖物部分覆盖的对象
CN111382612A (zh) 动物面部检测方法及装置

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 16896242

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16896242

Country of ref document: EP

Kind code of ref document: A1