WO2018121730A1 - 视频监控和人脸识别方法、装置及系统 - Google Patents

视频监控和人脸识别方法、装置及系统 Download PDF

Info

Publication number
WO2018121730A1
WO2018121730A1 PCT/CN2017/119825 CN2017119825W WO2018121730A1 WO 2018121730 A1 WO2018121730 A1 WO 2018121730A1 CN 2017119825 W CN2017119825 W CN 2017119825W WO 2018121730 A1 WO2018121730 A1 WO 2018121730A1
Authority
WO
WIPO (PCT)
Prior art keywords
face
video
photo
face recognition
instruction
Prior art date
Application number
PCT/CN2017/119825
Other languages
English (en)
French (fr)
Inventor
熊友军
周志平
陈林
Original Assignee
深圳市优必选科技有限公司
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 深圳市优必选科技有限公司 filed Critical 深圳市优必选科技有限公司
Publication of WO2018121730A1 publication Critical patent/WO2018121730A1/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
    • 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

Definitions

  • the present invention relates to the field of smart devices, and in particular, to a video surveillance and face recognition method and apparatus.
  • the present invention aims to provide a video surveillance and face recognition method and apparatus capable of viewing the position of a robot in real time through video surveillance, and seeing the world in front of it and identifying people through the perspective of the robot. face.
  • Video surveillance and face recognition methods including:
  • the face recognition command being an instruction to recognize a captured video or a face in the photo
  • a face recognition result corresponding to the face recognition request is received.
  • the method further includes:
  • the invention also relates to another video surveillance and face recognition method, comprising:
  • the face is compared with a pre-registered face to identify the corresponding face.
  • the method further includes:
  • the name of the recognized face is displayed and face tracking is performed.
  • the invention also relates to a video monitoring and face recognition device, comprising: a first receiving module, a shooting module, a first sending module and a second receiving module;
  • the first receiving module is configured to receive an imaging instruction
  • the photographing module is configured to turn on the camera and take a video or a photo according to the image capturing instruction
  • the first sending module is configured to send the captured video or photo and send a face recognition instruction, where the face recognition command is an instruction for recognizing a captured video or a face in the photo;
  • the second receiving module is configured to receive a face recognition result corresponding to the face recognition request.
  • the method further includes: a third receiving module and an adjusting module;
  • the third receiving module is configured to receive a camera angle adjustment instruction
  • the adjustment module is configured to adjust a camera according to a face position.
  • the invention further relates to another video monitoring and face recognition device, comprising: a fourth receiving module, a fifth receiving module, a judging module and an identifying module;
  • the fourth receiving module is configured to receive a video or a photo and render the received video or photo
  • the fifth receiving module is configured to receive a face recognition instruction, and enable face recognition according to the face recognition instruction;
  • the determining module is configured to determine whether a face is received in the received video or photo
  • the identification module is configured to compare the face with a pre-registered face to identify a corresponding face if the received video or a human face in the photo.
  • the method further includes: a display module;
  • the display module is configured to display the name of the recognized face and perform face tracking.
  • the invention also relates to a video surveillance and face recognition system, comprising a first terminal and a second terminal;
  • the first terminal is configured to receive an imaging instruction, turn on the camera according to the imaging instruction, and take a video or a photo;
  • the first terminal is further configured to send the captured video or photo and send a face recognition instruction, where the face recognition instruction is an instruction for recognizing a captured video or a face in the photo;
  • the second terminal is configured to receive a video or a photo and render the received video or photo; receive a face recognition instruction, and enable face recognition according to the face recognition instruction;
  • the second terminal is further configured to determine whether a face is received in the received video or photo, and if the received video or a face in the photo is used, the face is compared with a pre-registered face to identify the corresponding face. ;
  • the first terminal is further configured to receive a face recognition result corresponding to the face recognition request.
  • the invention also relates to another video surveillance and face recognition method, comprising:
  • the first terminal receives the camera instruction, turns on the camera according to the camera instruction, and takes a video or a photo;
  • the first terminal sends the captured video or photo and sends a face recognition command, where the face recognition command is an instruction for recognizing the captured video or a face in the photo;
  • the second terminal receives the video or the photo and renders the received video or photo; and opens the face recognition according to the face recognition instruction;
  • the second terminal determines whether there is a face in the received video or photo. If the received video or a face in the photo, the face is compared with the pre-registered face to identify the corresponding face;
  • the first terminal receives a face recognition result corresponding to the face recognition request
  • the present invention has the beneficial effects of providing a video monitoring and face recognition method and device, which can watch the position of the robot in real time through video surveillance, and see the world in front of the robot and recognize the person through the perspective of the robot. face.
  • FIG. 1 is a flowchart of a video monitoring and face recognition method according to an embodiment of the present invention
  • FIG. 2 is a flowchart of a video surveillance and face recognition method according to another embodiment of the present invention.
  • FIG. 3 is a flowchart of a method for video surveillance and face recognition according to another embodiment of the present invention.
  • FIG. 4 is a flowchart of a method for video surveillance and face recognition according to another embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of a video monitoring and face recognition apparatus according to an embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram of a video monitoring and face recognition apparatus according to another embodiment of the present invention.
  • FIG. 7 is a schematic structural diagram of a video monitoring and a face recognition system according to an embodiment of the present invention.
  • FIG. 8 is a flowchart of a method for video surveillance and face recognition according to another embodiment of the present invention.
  • a video surveillance and a face recognition method includes:
  • Step S101 Receive an imaging instruction.
  • the robot receives the connection instruction of the second terminal, and after receiving the connection relationship with the second terminal, receives the camera instruction issued by the second terminal.
  • the second terminal is a PC end or a mobile terminal.
  • Step S102 Turn on the camera according to the imaging instruction and take a video or a photo.
  • the robot turns on the camera according to the camera instruction, and captures a video or a photo according to the instruction of the second terminal to implement video monitoring.
  • Step S103 The robot sends the captured video or photo and sends a face recognition command, which is an instruction for recognizing the captured video or the face in the photo.
  • the robot sends the video or photo taken according to the second terminal instruction to the second terminal to implement video monitoring.
  • the second terminal turns on face recognition, receives a video or a photo, determines whether the face is recognized, and identifies the face and the database. Compare the photos stored in the file to determine whether to register.
  • Step S104 Receive a face recognition result corresponding to the face recognition request.
  • the robot receives whether the face is recognized by the second terminal, whether the face is registered, and the face tracking instruction issued by the second terminal is executed.
  • the robot collects complex images, acquires faces and executes instructions. It realizes video surveillance and face recognition. It views the world in front of the robot through the perspective of the robot, and recognizes the recognized person through the tone of the robot.
  • a video surveillance and a face recognition method includes:
  • Step S201 receiving an imaging instruction
  • Step S202 Turn on the camera according to the imaging instruction and take a video or a photo.
  • steps S201 to S202 are the same as the steps S101 to S102 in the previous embodiment, and are not described herein again.
  • Step S203 Receive a camera angle adjustment instruction.
  • the plurality of cameras adjust the viewing angle according to the instruction issued by the second terminal to implement all-round monitoring.
  • Step S204 Adjust the camera according to the face position.
  • the robot talks with the user, adjusts the camera position to track the face, and faces the face.
  • Step S205 transmitting the captured video or photo and transmitting a face recognition instruction, where the face recognition command is an instruction for recognizing a captured video or a face in the photo;
  • Step S206 Receive a face recognition result corresponding to the face recognition request.
  • steps S205 to S206 are the same as the steps S103-S104 in the previous embodiment, and are not described herein again.
  • Multiple cameras receive commands to adjust the angle of view to achieve omnidirectional monitoring.
  • the camera position is adjusted to be more intelligent.
  • a video surveillance and face recognition method includes:
  • Step S301 Receive a video or a photo and render the received video or photo.
  • the PC end or the mobile terminal receives the video or photo taken by the first terminal for rendering, and directly views on the display screen or projects onto the extended screen.
  • the first terminal may be a robot or a smart device.
  • Step S302 Receive a face recognition instruction, and enable face recognition according to the face recognition instruction.
  • the PC end or the mobile terminal receives the face recognition command sent by the first terminal, and turns on face recognition. Before the face recognition is turned on, the face photo is stored in the database in advance and the face photo is registered.
  • Step S303 determining whether there is a face in the received video or photo.
  • the PC or the mobile terminal determines whether there is a face according to the video or photo fed back by the first terminal. If the face is recognized, the next step is performed. If the face is not recognized, the recognition result is directly fed back to the first terminal. .
  • Step S304 If a received video or a human face in the photo is compared, the face is compared with a pre-registered face to identify the corresponding face.
  • the recognized face is compared with a pre-registered face, and if the face is registered, the face is recognized and the face is selected, and the recognition result is sent to The first terminal; if the face is not registered, the face is selected, and the face image is sent to the database for storage and registration.
  • PC or mobile terminal as the client responsible for robot control, face recognition and video rendering, can be multi-PC or multiple PCs in the same PC for video rendering, real-time pan/tilt control of multiple cameras, video surveillance and face detection Identification.
  • a video surveillance and a face recognition method includes:
  • Step S401 receiving a video or a photo and rendering the received video or photo
  • Step S402 Receive a face recognition instruction, and enable face recognition according to the face recognition instruction;
  • Step S403 determining whether there is a face in the received video or photo
  • Step S404 If a received video or a face is in a photo, the face is compared with a pre-registered face to identify a corresponding face;
  • steps S401 to S404 are the same as the steps S301-S304 in the previous embodiment, and are not described herein again.
  • Step S405 Display the name of the recognized face and perform face tracking.
  • the recognized face is registered, the face is selected, the name is displayed on the screen, and the face is tracked.
  • the recognized face is compared with the registered face in the database, the name of the registered face is displayed and the face is tracked, and the recognized person is recognized by the robot's tone.
  • the video surveillance and face recognition apparatus includes: a first receiving module 11, a shooting module 12, a first sending module 13, and a second receiving module 14;
  • the first receiving module 11 is configured to receive an imaging instruction
  • the photographing module 12 is configured to turn on the camera and take a video or a photo according to the image capturing instruction;
  • the first sending module 13 is configured to send a captured video or photo and send a face recognition command, where the face recognition command is an instruction for recognizing a captured video or a face in a photo;
  • the second receiving module 14 is configured to receive a face recognition result corresponding to the face recognition request.
  • the video monitoring and face recognition device further includes: a third receiving module 15 and an adjustment module 16;
  • the third receiving module 15 is configured to receive a camera angle adjustment instruction
  • the adjustment module 16 is configured to adjust the camera according to the position of the face.
  • a video surveillance and face recognition apparatus includes: a fourth receiving module 21, a fifth receiving module 22, a determining module 23, and an identifying module 24;
  • the fourth receiving module 21 is configured to receive a video or a photo and render the received video or photo;
  • the fifth receiving module 22 is configured to receive a face recognition instruction, and enable face recognition according to the face recognition instruction;
  • the determining module 23 is configured to determine whether a face is received in the received video or photo
  • the identification module 24 is configured to compare the face with a pre-registered face to identify a corresponding face if the received video or a human face in the photo.
  • the video monitoring and face recognition device further includes: a display module 25;
  • the display module 25 is configured to display the name of the recognized face and perform face tracking.
  • the device in this embodiment and the video monitoring and face recognition methods in the foregoing embodiments are based on two aspects under the same inventive concept.
  • the method implementation process has been described in detail above, so that those skilled in the art can
  • the foregoing description clearly understands the structure and implementation process of the device in this embodiment. For the sake of brevity of the description, no further details are provided herein.
  • the present invention can be implemented by means of software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present invention, which is essential or contributes to the prior art, may be embodied in the form of a software product, which may be stored in a storage medium such as a ROM/RAM or a disk. , an optical disk, etc., includes instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods described in various embodiments of the present invention or portions of the embodiments.
  • a computer device which may be a personal computer, server, or network device, etc.
  • the video surveillance and face recognition system provided by the embodiment of the present invention includes a first terminal 31 and a second terminal 32;
  • the first terminal 31 is configured to receive an imaging instruction, turn on the camera according to the imaging instruction, and take a video or a photo;
  • the first terminal 32 is configured to send a captured video or photo and send a face recognition instruction, where the face recognition instruction is an instruction for recognizing a captured video or a face in the photo;
  • the second terminal 32 is configured to receive a video or a photo and render the received video or photo; receive a face recognition instruction, and enable face recognition according to the face recognition instruction;
  • the second terminal 32 is configured to determine whether a face is received in the received video or photo, and if the received video or a human face in the photo, the face is compared with a pre-registered face to identify the corresponding face. ;
  • the first terminal 31 is configured to receive a face recognition result corresponding to the face recognition request.
  • a video surveillance and a face recognition method includes:
  • the first terminal receives the camera instruction, turns on the camera according to the camera instruction, and takes a video or a photo;
  • the first terminal sends the captured video or photo and sends a face recognition command, where the face recognition command is an instruction for recognizing the captured video or a face in the photo;
  • the second terminal receives the video or the photo and renders the received video or photo; and opens the face recognition according to the face recognition instruction;
  • the second terminal determines whether there is a face in the received video or photo. If the received video or a face in the photo, the face is compared with the pre-registered face to identify the corresponding face;
  • the first terminal receives a face recognition result corresponding to the face recognition request.
  • the invention provides a video monitoring and face recognition method, device and system, which can watch the position of the robot in real time through video monitoring, and see the world in front of it and recognize the human face through the perspective of the robot.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Studio Devices (AREA)

Abstract

本发明公开了视频监控和人脸识别方法，包括：接收摄像指令；根据所述摄像指令开启摄像头并拍摄视频或者照片；发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；接收与所述人脸识别请求相对应的人脸识别结果。本发明提供视频监控和人脸识别方法能通过视频监控，实时观看机器人的位置，并通过机器人视角，看到它眼前的世界并识别人脸。

Description

视频监控和人脸识别方法、装置及系统 技术领域
本发明涉及智能设备领域，尤其涉及视频监控和人脸识别方法及装置。
背景技术
对于机器人，仅仅能够闲聊和做动作是不够的，机器人必须拥有自己的视角和认知，这就促使我们研究机器人的视频监控和人脸识别，在与机器人语音对话的过程中，可轻松通过语音控制所有操作，并通过机器人的视角来观看眼前的世界，通过机器人的角度来对识别到的人进行认知。
发明内容
为了克服现有技术的不足，本发明的目的在于提供视频监控和人脸识别方法和装置，其能通过视频监控，实时观看机器人的位置，并通过机器人视角，看到它眼前的世界并识别人脸。
本发明的目的采用以下技术方案实现：
视频监控和人脸识别方法，包括：
接收摄像指令；
根据所述摄像指令开启摄像头并拍摄视频或者照片；
发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；
接收与所述人脸识别请求相对应的人脸识别结果。
优选的，根据所述摄像指令开启摄像头并拍摄视频或者照片之后 还包括：
接收摄像头视角调节指令；
根据人脸位置调整摄像头。
本发明还涉及另一视频监控和人脸识别方法，包括：
接收视频或者照片并对接收到的视频或者照片进行渲染；
接收人脸识别指令，根据所述人脸识别指令开启人脸识别；
判断接收的视频或者照片中是否有人脸；
若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸。
优选的，若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸之后还包括：
显示识别出的人脸的名字并执行人脸追踪。
本发明还涉及视频监控和人脸识别装置，包括：第一接收模块、拍摄模块、第一发送模块和第二接收模块；
所述第一接收模块，用于接收摄像指令；
所述拍摄模块，用于根据所述摄像指令开启摄像头并拍摄视频或者照片；
所述第一发送模块，用于发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；
所述第二接收模块，用于接收与所述人脸识别请求相对应的人脸识别结果。
优选的，还包括：第三接收模块和调整模块；
所述第三接收模块，用于接收摄像头视角调节指令；
所述调整模块，用于根据人脸位置调整摄像头。
本发明还涉及另一视频监控和人脸识别装置，包括：第四接收模块、第五接收模块、判断模块和识别模块；
所述第四接收模块，用于接收视频或者照片并对接收到的视频或者照片进行渲染；
所述第五接收模块，用于接收人脸识别指令，根据所述人脸识别指令开启人脸识别；
所述判断模块，用于判断接收的视频或者照片中是否有人脸；
所述识别模块，用于若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸。
优选的，还包括：显示模块；
所述显示模块，用于显示识别出的人脸的名字并执行人脸追踪。
本发明还涉及视频监控和人脸识别系统，包括第一终端和第二终端；
所述第一终端用于接收摄像指令，根据所述摄像指令开启摄像头并拍摄视频或者照片；
所述第一终端还用于发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；
所述第二终端用于接收视频或者照片并对接收到的视频或者照 片进行渲染；接收人脸识别指令，根据所述人脸识别指令开启人脸识别；
所述第二终端还用于判断接收的视频或者照片中是否有人脸，若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸；
所述第一终端还用于接收与所述人脸识别请求相对应的人脸识别结果。
本发明还涉及另一视频监控和人脸识别方法，包括：
第一终端接收摄像指令，根据所述摄像指令开启摄像头并拍摄视频或者照片；
第一终端发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；
第二终端接收视频或者照片并对接收到的视频或者照片进行渲染；根据所述人脸识别指令开启人脸识别；
第二终端判断接收的视频或者照片中是否有人脸，若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸；
第一终端接收与所述人脸识别请求相对应的人脸识别结果
相比现有技术，本发明的有益效果在于：提供视频监控和人脸识别方法和装置，其能通过视频监控，实时观看机器人的位置，并通过机器人视角，看到它眼前的世界并识别人脸。
附图说明
图1为本发明一实施例提供的一视频监控和人脸识别方法流程图；
图2为本发明另一实施例提供的视频监控和人脸识别方法流程图；
图3为本发明另一实施例提供的视频监控和人脸识别方法流程图；
图4为本发明另一实施例提供的视频监控和人脸识别方法流程图；
图5为本发明一实施例提供的视频监控和人脸识别装置结构示意图；
图6为本发明另一实施例提供的视频监控和人脸识别装置结构示意图；
图7为本发明实施例提供的视频监控和人脸识别系统结构示意图；
图8为本发明另一实施例提供的视频监控和人脸识别方法流程图。
具体实施方式
下面，结合附图以及具体实施方式，对本发明做进一步描述：
如图1所示，本发明一实施例提供的视频监控和人脸识别方法，包括：
步骤S101：接收摄像指令。
具体的，机器人接收第二终端的连接指令，与第二终端建立连接 关系后接收第二终端发出的摄像指令。本发明实施例中，所述第二终端为PC端或者移动终端等。
步骤S102：根据所述摄像指令开启摄像头并拍摄视频或者照片。
具体的，机器人根据摄像指令开启摄像头，根据第二终端的指令拍摄视频或者照片实现视频监控。
步骤S103：机器人发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令。
具体的，机器人将根据第二终端指令拍摄的视频或照片发送到第二终端实现视频监控。当接收到用户发出的人脸识别指令时，向第二终端发送人脸识别请求，第二终端开启人脸识别，接收视频或者照片，判断是否识别到人脸，将识别到的人脸与数据库中存储的照片对比，判断是否注册。
步骤S104：接收与所述人脸识别请求相对应的人脸识别结果。
具体的，机器人接收第二终端反馈的是否识别到人脸、人脸是否注册，并执行第二终端发出的人脸追踪指令。
机器人作为服务端，复杂视频的采集、人脸的获取以及指令的执行，实现视频监控及人脸识别，通过机器人的视角观看眼前世界，通过机器人的口吻来对识别到的人进行认知。
如图2所示，本发明另一实施例提供的视频监控和人脸识别方法，包括：
步骤S201：接收摄像指令；
步骤S202：根据所述摄像指令开启摄像头并拍摄视频或者照片。
上述步骤S201-步骤S202与上一实施例中步骤S101-S102相同，在此不再赘述。
步骤S203：接收摄像头视角调节指令。
具体的，多个摄像头根据第二终端发出的指令调整视角，实现全方位监控。
步骤S204：根据人脸位置调整摄像头。
具体的，机器人接收到用户语音指令时，与用户对话，并调整摄像头位置追踪人脸，正视人脸。
步骤S205：发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；
步骤S206：接收与所述人脸识别请求相对应的人脸识别结果。
上述步骤S205-步骤S206与上一实施例中步骤S103-S104相同，在此不再赘述。
多个摄像头接收指令调整视角，实现全方位监控，机器人在执行人脸识别和接收语音指令时，调整摄像头位置，更智能化。
如图3所示，本发明又一实施例提供的视频监控和人脸识别方法，包括：
步骤S301：接收视频或者照片并对接收到的视频或者照片进行渲染。
具体的，PC端或者移动终端接收第一终端拍摄的视频或者照片进行渲染，直接在显示屏上观看或者投影到扩展屏上。本发明实施例中，所述第一终端可以为机器人或者智能设备。
步骤S302：接收人脸识别指令，根据所述人脸识别指令开启人脸识别。
具体的，PC端或者移动终端接收第一终端发出的人脸识别指令，开启人脸识别。开启人脸识别之前，预先在数据库中存放人脸照片并对人脸照片注册。
步骤S303：判断接收的视频或者照片中是否有人脸。
具体的，PC端或者移动终端根据第一终端反馈的视频或者照片判断是否有人脸，若识别到人脸，则执行下一步，若没有识别到人脸，则直接将识别结果反馈到第一终端。
步骤S304：若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸。
具体的，若接收的视频或者照片中有人脸，将识别到的人脸与预先注册的人脸进行对比，若人脸注册，则识别出人脸并框选人脸，并将识别结果发送到第一终端；若人脸没有注册，框选人脸，并将人脸图片发送至数据库存储以及注册。
PC端或者移动终端作为客户端，负责机器人的控制、人脸识别和视频渲染，可以多台PC或同一台PC多个地方视频渲染，对多个摄像头实时云台控制，实现视频监控和人脸识别。
如图4所示，本发明又一实施例提供的视频监控和人脸识别方法，包括：
步骤S401：接收视频或者照片并对接收到的视频或者照片进行渲染；
步骤S402：接收人脸识别指令，根据所述人脸识别指令开启人脸识别；
步骤S403：判断接收的视频或者照片中是否有人脸；
步骤S404：若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸；
上述步骤S401-步骤S404与上一实施例中步骤S301-S304相同，在此不再赘述。
步骤S405：显示识别出的人脸的名字并执行人脸追踪。
具体的，若识别出的人脸已注册，框选人脸，将人名显示在屏幕上并追踪人脸。
将识别出的人脸与数据库中注册的人脸对比，对已注册的人脸显示人名并追踪人脸，通过机器人的口吻对识别到的人进行认知。
如图5所示，本发明实施例提供的视频监控和人脸识别装置，包括：第一接收模块11、拍摄模块12、第一发送模块13和第二接收模块14；
所述第一接收模块11，用于接收摄像指令；
所述拍摄模块12，用于根据所述摄像指令开启摄像头并拍摄视频或者照片；
所述第一发送模块13，用于发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；
所述第二接收模块14，用于接收与所述人脸识别请求相对应的 人脸识别结果。
优选的，所述视频监控和人脸识别装置还包括：第三接收模块15和调整模块16；
所述第三接收模块15，用于接收摄像头视角调节指令；
所述调整模块16，用于根据人脸位置调整摄像头。
如图6所示，本发明另一实施例提供的一视频监控和人脸识别装置，包括：第四接收模块21、第五接收模块22、判断模块23和识别模块24；
所述第四接收模块21，用于接收视频或者照片并对接收到的视频或者照片进行渲染；
所述第五接收模块22，用于接收人脸识别指令，根据所述人脸识别指令开启人脸识别；
所述判断模块23，用于判断接收的视频或者照片中是否有人脸；
所述识别模块24，用于若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸。
优选的，所述视频监控和人脸识别装置还包括：显示模块25；
所述显示模块25，用于显示识别出的人脸的名字并执行人脸追踪。
本实施例中的装置与前述实施例中的视频监控和人脸识别方法是基于同一发明构思下的两个方面，在前面已经对方法实施过程作了详细的描述，所以本领域技术人员可根据前述描述清楚地了解本实施例中的装置的结构及实施过程，为了说明书的简洁，在此就不再赘述。
为了描述的方便，描述以上装置时以功能分为各种模块分别描述。当然，在实施本发明时可以把各模块的功能在同一个或多个软件和/或硬件中实现。
通过以上的实施方式的描述可知，本领域的技术人员可以清楚地了解到本发明可借助软件加必需的通用硬件平台的方式来实现。基于这样的理解，本发明的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)执行本发明各个实施例或者实施例的某些部分所述的方法。
如图7所示，本发明实施例提供的视频监控和人脸识别系统，包括第一终端31和第二终端32；
所述第一终端31用于接收摄像指令，根据所述摄像指令开启摄像头并拍摄视频或者照片；
所述第一终端32用于发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；
所述第二终端32用于接收视频或者照片并对接收到的视频或者照片进行渲染；接收人脸识别指令，根据所述人脸识别指令开启人脸识别；
所述第二终端32用于判断接收的视频或者照片中是否有人脸，若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进 行对比，识别出对应的人脸；
所述第一终端31用于接收与所述人脸识别请求相对应的人脸识别结果。
本实施例中的系统与前述实施例中的视频监控和人脸识别方法是基于同一发明构思下的两个方面，在前面已经对方法实施过程作了详细的描述，所以本领域技术人员可根据前述描述清楚地了解本实施例中的系统的结构及实施过程，为了说明书的简洁，在此就不再赘述。
如图8所示，本发明另一实施例提供的视频监控和人脸识别方法，包括：
第一终端接收摄像指令，根据所述摄像指令开启摄像头并拍摄视频或者照片；
第一终端发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；
第二终端接收视频或者照片并对接收到的视频或者照片进行渲染；根据所述人脸识别指令开启人脸识别；
第二终端判断接收的视频或者照片中是否有人脸，若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸；
第一终端接收与所述人脸识别请求相对应的人脸识别结果。
本实施例中的方法与前述实施例中的系统是基于同一发明构思下的两个方面，在前面已经对系统作了详细的描述，所以本领域技术人员可根据前述描述清楚地了解本实施例中的方法，为了说明书的简 洁，在此就不再赘述。
本发明提供视频监控和人脸识别方法、装置及系统，能通过视频监控，实时观看机器人的位置，并通过机器人视角，看到它眼前的世界并识别人脸。
对本领域的技术人员来说，可根据以上描述的技术方案以及构思，做出其它各种相应的改变以及形变，而所有的这些改变以及形变都应该属于本发明权利要求的保护范围之内。

Claims (10)

  1. 视频监控和人脸识别方法，其特征在于，包括：
    接收摄像指令；
    根据所述摄像指令开启摄像头并拍摄视频或者照片；
    发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；
    接收与所述人脸识别请求相对应的人脸识别结果。
  2. 根据权利要求1所述的视频监控和人脸识别方法，其特征在于，根据所述摄像指令开启摄像头并拍摄视频或者照片之后还包括：
    接收摄像头视角调节指令；
    根据人脸位置调整摄像头。
  3. 视频监控和人脸识别方法，其特征在于，包括：
    接收视频或者照片并对接收到的视频或者照片进行渲染；
    接收人脸识别指令，根据所述人脸识别指令开启人脸识别；
    判断接收的视频或者照片中是否有人脸；
    若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸。
  4. 根据权利要求3所述的视频监控和人脸识别方法，其特征在于，若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸之后还包括：
    显示识别出的人脸的名字并执行人脸追踪。
  5. 视频监控和人脸识别装置，其特征在于，包括：第一接收模块、拍摄模块、第一发送模块和第二接收模块；
    所述第一接收模块，用于接收摄像指令；
    所述拍摄模块，用于根据所述摄像指令开启摄像头并拍摄视频或者照片；
    所述第一发送模块，用于发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；
    所述第二接收模块，用于接收与所述人脸识别请求相对应的人脸识别结果。
  6. 根据权利要求5所述的视频监控和人脸识别装置，其特征在于，还包括：第三接收模块和调整模块；
    所述第三接收模块，用于接收摄像头视角调节指令；
    所述调整模块，用于根据人脸位置调整摄像头。
  7. 视频监控和人脸识别装置，其特征在于，包括：第四接收模块、第五接收模块、判断模块和识别模块；
    所述第四接收模块，用于接收视频或者照片并对接收到的视频或者照片进行渲染；
    所述第五接收模块，用于接收人脸识别指令，根据所述人脸识别指令开启人脸识别；
    所述判断模块，用于判断接收的视频或者照片中是否有人脸；
    所述识别模块，用于若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸。
  8. 根据权利要求7所述的视频监控和人脸识别方法，其特征在于， 还包括：显示模块；
    所述显示模块，用于显示识别出的人脸的名字并执行人脸追踪。
  9. 视频监控和人脸识别系统，其特征在于，包括第一终端和第二终端；
    所述第一终端用于接收摄像指令，根据所述摄像指令开启摄像头并拍摄视频或者照片；
    所述第一终端还用于发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；
    所述第二终端用于接收视频或者照片并对接收到的视频或者照片进行渲染；接收人脸识别指令，根据所述人脸识别指令开启人脸识别；
    所述第二终端还用于判断接收的视频或者照片中是否有人脸，若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸；
    所述第一终端还用于接收与所述人脸识别请求相对应的人脸识别结果。
  10. 视频监控和人脸识别方法，其特征在于，包括：
    第一终端接收摄像指令，根据所述摄像指令开启摄像头并拍摄视频或者照片；
    第一终端发送拍摄的视频或者照片并发送人脸识别指令，所述人脸识别指令为识别拍摄的视频或者照片中的人脸的指令；
    第二终端接收视频或者照片并对接收到的视频或者照片进行渲染；根据所述人脸识别指令开启人脸识别；
    第二终端判断接收的视频或者照片中是否有人脸，若接收的视频或者照片中有人脸，将所述的人脸与预先注册的人脸进行对比，识别出对应的人脸；
    第一终端接收与所述人脸识别请求相对应的人脸识别结果。
PCT/CN2017/119825 2016-12-31 2017-12-29 视频监控和人脸识别方法、装置及系统 WO2018121730A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201611263417.2A CN106791681A (zh) 2016-12-31 2016-12-31 视频监控和人脸识别方法、装置及系统
CN201611263417.2 2016-12-31

Publications (1)

Publication Number Publication Date
WO2018121730A1 true WO2018121730A1 (zh) 2018-07-05

Family

ID=58955002

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/119825 WO2018121730A1 (zh) 2016-12-31 2017-12-29 视频监控和人脸识别方法、装置及系统

Country Status (2)

Country Link
CN (1) CN106791681A (zh)
WO (1) WO2018121730A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106791681A (zh) * 2016-12-31 2017-05-31 深圳市优必选科技有限公司 视频监控和人脸识别方法、装置及系统
CN107609703A (zh) * 2017-09-15 2018-01-19 泾县麦蓝网络技术服务有限公司 一种应用于实体零售店的商品定位方法和系统
CN107766834B (zh) * 2017-11-01 2023-09-26 北京蓝海华业工程技术有限公司 一种人脸识别方法与系统
CN107832799A (zh) * 2017-11-20 2018-03-23 北京奇虎科技有限公司 基于摄像头场景的对象识别方法及装置、计算设备

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002041254A1 (fr) * 2000-11-17 2002-05-23 Sony Corporation Dispositif robot et procede d'identification faciale, et dispositif et procede d'identification d'images
JP2008087140A (ja) * 2006-10-05 2008-04-17 Toyota Motor Corp 音声認識ロボットおよび音声認識ロボットの制御方法
US20100185990A1 (en) * 2009-01-20 2010-07-22 Samsung Electronics Co., Ltd. Movable display apparatus, robot having movable display apparatus and display method thereof
CN104284136A (zh) * 2013-07-07 2015-01-14 上海科宇营销策划有限公司 一种移动监控机器人
CN105116994A (zh) * 2015-07-07 2015-12-02 百度在线网络技术（北京）有限公司 基于人工智能的智能机器人追踪方法和追踪装置
CN105807693A (zh) * 2016-03-10 2016-07-27 魏凯 一种智能视频机器人控制系统及控制方法
CN106042005A (zh) * 2016-06-01 2016-10-26 山东科技大学 仿生眼定位追踪系统及其工作方法
CN106791681A (zh) * 2016-12-31 2017-05-31 深圳市优必选科技有限公司 视频监控和人脸识别方法、装置及系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004302785A (ja) * 2003-03-31 2004-10-28 Honda Motor Co Ltd 移動ロボットの画像送信装置
JP5718973B2 (ja) * 2013-05-21 2015-05-13 富士ソフト株式会社 顔認識装置、顔認識方法、およびコンピュータプログラム
CN103984315A (zh) * 2014-05-15 2014-08-13 成都百威讯科技有限责任公司 一种家用多功能智能机器人
CN205334503U (zh) * 2016-01-22 2016-06-22 深圳光启合众科技有限公司 具有人脸识别功能的机器人
CN205507540U (zh) * 2016-03-28 2016-08-24 山东国兴智能科技有限公司 一种带人脸识别和学习功能的智能巡逻机器人

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002041254A1 (fr) * 2000-11-17 2002-05-23 Sony Corporation Dispositif robot et procede d'identification faciale, et dispositif et procede d'identification d'images
JP2008087140A (ja) * 2006-10-05 2008-04-17 Toyota Motor Corp 音声認識ロボットおよび音声認識ロボットの制御方法
US20100185990A1 (en) * 2009-01-20 2010-07-22 Samsung Electronics Co., Ltd. Movable display apparatus, robot having movable display apparatus and display method thereof
CN104284136A (zh) * 2013-07-07 2015-01-14 上海科宇营销策划有限公司 一种移动监控机器人
CN105116994A (zh) * 2015-07-07 2015-12-02 百度在线网络技术（北京）有限公司 基于人工智能的智能机器人追踪方法和追踪装置
CN105807693A (zh) * 2016-03-10 2016-07-27 魏凯 一种智能视频机器人控制系统及控制方法
CN106042005A (zh) * 2016-06-01 2016-10-26 山东科技大学 仿生眼定位追踪系统及其工作方法
CN106791681A (zh) * 2016-12-31 2017-05-31 深圳市优必选科技有限公司 视频监控和人脸识别方法、装置及系统

Also Published As

Publication number Publication date
CN106791681A (zh) 2017-05-31

Similar Documents

Publication Publication Date Title
WO2018121730A1 (zh) 视频监控和人脸识别方法、装置及系统
EP3130138B1 (en) Use of face and motion detection for best view framing in video conference endpoint
US20220319032A1 (en) Optimal view selection in a teleconferencing system with cascaded cameras
CN109032039B (zh) 一种语音控制的方法及装置
US8749607B2 (en) Face equalization in video conferencing
WO2016187985A1 (zh) 拍摄设备、跟踪拍摄方法和系统、以及计算机存储介质
CN103685906B (zh) 一种控制方法、控制装置及控制设备
CN105554372B (zh) 一种拍摄方法以及装置
CN111062234A (zh) 一种监控方法、智能终端及计算机可读存储介质
WO2019128098A1 (zh) 一种基于定位追踪的投影方法、装置、投影仪及投影系统
CN108200340A (zh) 能够检测眼睛视线的拍照装置及拍照方法
WO2015042897A1 (zh) 一种控制方法、控制装置及控制设备
JP2009089324A (ja) テレビ会議システムおよびプログラム、記録媒体
US9065975B2 (en) Method and apparatus for hands-free control of a far end camera
WO2020227996A1 (zh) 一种拍摄控制方法、装置及控制设备、拍摄设备
CN112312042A (zh) 显示控制方法、装置、电子设备及存储介质
EP4075794A1 (en) Region of interest based adjustment of camera parameters in a teleconferencing environment
US20220319034A1 (en) Head Pose Estimation in a Multi-Camera Teleconferencing System
CN110933297A (zh) 智能摄影系统的摄影控制方法、装置、存储介质及系统
US7986336B2 (en) Image capture apparatus with indicator
CN103139457B (zh) 一种图像获得控制方法及电子设备
CN108156387A (zh) 通过检测眼睛视线自动结束摄像的装置及方法
CN112507798A (zh) 活体检测方法、电子设备与存储介质
CN112333391A (zh) 基于声音的人像自动追踪方法、装置、智能终端及介质
TWI626849B (zh) 視訊會議控制方法及裝置

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: 17886364

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17886364

Country of ref document: EP

Kind code of ref document: A1