公开(公告)号：EP3407245A1

公开(公告)日：2018-11-28

申请号：EP17740960.4

申请日：2017-01-09

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： WANG, Chengjie

IPC分类号： G06K9/00

CPC分类号： G06T7/73 ,  G06K9/00248 ,  G06K9/00275 ,  G06K9/00281 ,  G06K9/00302 ,  G06T7/0002 ,  G06T2207/30201

摘要： A method and device for determining the rotation angle of a human face, and a computer storage medium. The method comprises: obtaining first position information of preset multiple human face characteristic points in a to-be-determined human face image, the number of the multiple human face characteristic points being an odd number, and the multiple human face characteristic points comprising multiple pairs of symmetrical human face characteristic points and one first human face characteristic point, and the multiple human face characteristic points being not located on a same plane (101); obtaining first position information of a symmetrical middle point of each pair of human face characteristic points according to the first position information of the human face characteristic point comprised in each pair of human face characteristic points among the multiple pairs of human face characteristic points (102), and determining the rotation angle of the to-be-determined human face image according to the first position information of the symmetrical middle point of each pair of human face characteristic points and the first position information of the first human face characteristic point (103).

公开(公告)号：EP3363348A1

公开(公告)日：2018-08-22

申请号：EP16855569.6

申请日：2016-10-17

申请人： Daikin Industries, Ltd. ,  Tokyo Institute of Technology

发明人： ARAI, Junichiro ,  GOTOU, Takashi ,  IWAKAME, Makoto ,  HINO, Kenichi ,  HIRANO, Tomoya ,  HIRAYAMA, Takahiro ,  KOTANI, Yasunori ,  OHGAMI, Yoshimi ,  TOMATSU, Taro

IPC分类号： A61B5/00 ,  A61B5/01 ,  A61B10/00

CPC分类号： A61B5/7275 ,  A61B5/00 ,  A61B5/01 ,  A61B5/165 ,  A61B5/4064 ,  A61B10/00 ,  G06K9/00302 ,  G06T7/0012 ,  G06T2207/30201

摘要： A physiological state determination device (10, 110, 400) includes a facial change information acquisition unit (20, 120, 415, 442), a facial change information decomposition unit (30, 130, 443), and a physiological state determination unit (200, 445). The facial change information acquisition unit (20, 120, 415, 442) acquires facial change information indicating time-series changes in facial data of a subject. The facial change information decomposition unit (30, 130, 443) decomposes the facial change information into a plurality of components by singular value decomposition, principal component analysis, or independent component analysis. The physiological state determination unit (200, 445) determines the mental or physical physiological state of the subject on the basis of a determination component extracted from the plurality of components.

公开(公告)号：EP3361467A1

公开(公告)日：2018-08-15

申请号：EP17182457.6

申请日：2017-07-20

申请人： Find Solution Artificial Intelligence Limited

发明人： DOLSMA, Johan Matthijs ,  LAM, Yuen Lee Viola

IPC分类号： G09B7/04 ,  A61B5/16

CPC分类号： G06K9/00302 ,  A61B5/165 ,  G06K9/00718 ,  G06K9/66 ,  G06N99/005 ,  G09B5/06 ,  G09B5/10 ,  G09B7/04 ,  G10L17/26 ,  G10L25/63

摘要： A system for delivering and managing learning and training programmes comprising optical sensors for capturing subject's facial expression, eye movements, point-of-gaze, and head pose of a student subject during a learning session; a domain knowledge data repository comprising concept data entities, each having knowledge and skill content items, and task data entities, each having lecture content material items; a student module configured to estimate the student subject's affective state and cognitive state using the sensory data collected from the optical sensors; and a trainer module configured to select a task data entity for delivery and presentment to the student subject after each completion of a task data entity based on a probability of the student subject's understanding of the associated concept data entity's knowledge and skill content items; wherein the probability of the student subject's understanding is computed using the student subject's estimated affective state and cognitive state.

公开(公告)号：EP3343175A1

公开(公告)日：2018-07-04

申请号：EP17205094.0

申请日：2017-12-04

申请人： TOYOTA JIDOSHA KABUSHIKI KAISHA

发明人： SEKIZAWA, Shogo ,  OHTSUKA, Shinichiro ,  IDO, Daisuke ,  OKABE, Makoto ,  KIMATA, Takanori

IPC分类号： G01C21/34 ,  G01C21/36

CPC分类号： G01C21/3484 ,  G01C21/3461 ,  G01C21/3602 ,  G01C21/3608 ,  G01C21/3617 ,  G01C21/3623 ,  G01C21/3667 ,  G06K9/00302

摘要： An in-vehicle device (100) includes a recognition unit (109) configured to recognize a host vehicle user, an acquisition unit (101) configured to acquire a current location and a destination of the host vehicle, a transmission unit configured to transmit a first signal indicating the host vehicle user, the current location, and the destination to an external device (20) outside the host vehicle, a reception unit configured to receive a second signal indicating a traveling route from the current location to the destination from the external device, the traveling route being searched using i) a first feeling map and ii) a second feeling map in the external device, and a presentation unit (104) configured to present the traveling route indicated by the second signal.

公开(公告)号：EP3210096A4

公开(公告)日：2018-07-04

申请号：EP15852028

申请日：2015-10-21

申请人： BOSCH GMBH ROBERT

发明人： WENG FULIANG ,  SHEN ZHONGNAN

IPC分类号： G06F3/01

CPC分类号： G06F3/015 ,  G06K9/00295 ,  G06K9/00302 ,  G06K2209/27

摘要： A dialog system includes a processor. The system can further include a dialog manager. The dialog manager can be configured to receive input from a user using the processor. The system can further include a user category classification and detection module, which is configured to identify categories for the user from the received input. The system can further include a user mood detection and tracking module configured to identify a mood of the user. The system can further include a user physical and mind state and energy level detection module configured to identify a mental status of the user. The system can further include a user acquaintance module configured to identify an acquaintance status of the user. The system can further include user personality detection and tracking module configured to identify a personality status of the user. The system can further include a conversational context detection and response generation module.

公开(公告)号：EP3313068A1

公开(公告)日：2018-04-25

申请号：EP16810907.2

申请日：2016-05-30

申请人： Hangzhou Ezviz Network Co., Ltd.

发明人： HUANG, Sheng ,  DU, Anqiang ,  BAO, Dunqiao ,  JIN, Shengyang ,  JIANG, Haiqing

IPC分类号： H04N7/18

CPC分类号： H04N7/188 ,  G06F17/30064 ,  G06K9/00302 ,  H04N7/18 ,  H04N7/185

摘要： Provided are a video monitoring method and system based on smart home. In the method and the system, a triggering condition of image capturing is preset and stored, wherein the triggering condition is appearance of a specific person in an image and specific performance of the specific person; whether a current image meets the triggering condition or not is detected in real time; when a detecting result is that the current image meets the triggering condition, the current image is captured, the captured image is classified according to different specific performance of the specific person, and the classified image is stored in a timeline form; and an access right and a sending right are set for the classified image stored in the timeline form. According to the present disclosure, the images meeting the triggering condition are captured, the captured images are classified according to different emotions, the classified images are stored according to a time sequence, and different access rights and sending rights are set for the stored images, so that a mobile terminal or client can receive or access in real time the images of the specific person in different emotions.

摘要翻译： 提供了一种基于智能家居的视频监控方法和系统。 在该方法和系统中，预设并存储图像采集的触发条件，其中触发条件为图像中特定人物的出现和特定人物的具体表现; 实时检测当前图像是否满足触发条件; 当检测结果为当前图像满足触发条件时，捕获当前图像，根据特定人物的不同具体表现对拍摄图像进行分类，将分类图像以时间轴形式存储; 并为存储在时间线表格中的分类图像设置访问权限和发送权限。 根据本发明，捕获满足触发条件的图像，根据不同的情绪对捕获的图像进行分类，按照时间顺序存储分类后的图像，对存储的图像设置不同的访问权限和发送权限， 以便移动终端或客户端可以实时接收或访问不同情绪下特定人物的图像。

公开(公告)号：EP3080678A4

公开(公告)日：2018-01-24

申请号：EP14870553

申请日：2014-11-04

申请人： LG ELECTRONICS INC

发明人： LEE JUWAN ,  KIM LAGYOUNG ,  SHIN TAEDONG ,  SEO DAEGEUN

IPC分类号： G06F3/00 ,  G06F3/01 ,  G06F3/16 ,  G10L15/26

CPC分类号： G10L15/22 ,  G06F3/00 ,  G06F3/01 ,  G06F3/167 ,  G06K9/00228 ,  G06K9/00302 ,  G10L13/027 ,  G10L15/08 ,  G10L15/24 ,  G10L15/26 ,  G10L17/24 ,  G10L21/0208 ,  G10L25/63 ,  G10L25/84 ,  G10L2015/088 ,  G10L2015/223 ,  G10L2015/227 ,  H04L12/2803

摘要： Provided is a smart home appliance. The smart home appliance includes: a voice input unit collecting a voice; a voice recognition unit recognizing a text corresponding to the voice collected through the voice input unit; a capturing unit collecting an image for detecting a user's visage or face; a memory unit mapping the text recognized by the voice recognition unit and a setting function and storing the mapped information; and a control unit determining whether to perform a voice recognition service on the basis of at least one information of image information collected by the capturing unit and voice information collected by the voice input unit.

公开(公告)号：EP3218879A1

公开(公告)日：2017-09-20

申请号：EP14905858.8

申请日：2014-11-10

申请人： Intel Corporation

发明人： SHEN, Xiaolu ,  ZHANG, Lidan ,  LI, Wenlong ,  DU, Yangzhou ,  ZENG, Fucen ,  LI, Qiang ,  TONG, Xiaofeng

IPC分类号： G06T13/00 ,  G06K9/00

CPC分类号： G06K9/00248 ,  G06K9/00228 ,  G06K9/00302 ,  G06K9/00335 ,  G06K9/00677 ,  G06K9/00912 ,  G06K9/036 ,  G06K9/20 ,  G06K9/228 ,  G06K9/4604

摘要： Apparatuses, methods and storage medium associated with capturing images are disclosed herein. In embodiments, the apparatus may include a face tracker to receive an image frame, analyze the image frame for a face, and on identification of a face in the image frame, evaluate the face to determine whether the image frame comprises an acceptable or unacceptable face pose. Further, the face tracker may be configured to provide instructions for taking another image frame, on determination of the image frame having an unacceptable face pose, with the instructions designed to improve likelihood that the other image frame will comprise an acceptable face pose. Other embodiments may be described and/or claimed.

摘要翻译： 本文公开了与捕捉图像相关联的设备，方法和存储介质。 在实施例中，该装置可以包括面部追踪器，用于接收图像帧，分析图像帧的脸部以及识别图像帧中的脸部，评估脸部以确定图像帧是否包括可接受或不可接受的脸部 姿势。 此外，面部追踪器可以被配置为在确定具有不可接受的面部姿态的图像帧时提供用于拍摄另一图像帧的指令，其中该指令被设计成改善其他图像帧将包括可接受的面部姿势的可能性。 其他实施例可以被描述和/或要求保护。

公开(公告)号：EP3217370A1

公开(公告)日：2017-09-13

申请号：EP15857475.6

申请日：2015-10-20

申请人： Samsung Electronics Co., Ltd.

发明人： DU, Xiaoyi ,  LUO, Hengliang ,  DENG, Haifeng ,  ZHANG, Li

IPC分类号： G08B21/02 ,  G08B21/18 ,  G08B3/10

CPC分类号： G06K9/00671 ,  G06F3/012 ,  G06K9/00302 ,  G08B13/1672 ,  G08B13/194 ,  G08B21/02 ,  G08B25/08 ,  G08B25/10

摘要： Provided are a method and an apparatus for early warning of danger, the method including acquiring image information of a target object through a first wearable device worn by a user, detecting a physical characteristic of the target object based on the acquired image information, determining a degree of danger that is a degree to which safety of the user is endangered, by using the detected physical characteristic, and providing a warning to the user based on the determined degree of danger of an event.

摘要翻译： 本发明提供一种危险预警的方法和装置，该方法包括：通过用户穿戴的第一可穿戴设备获取目标物体的图像信息;基于获取的图像信息检测目标物体的物理特性; 通过使用检测到的身体特征来确定危及用户安全的程度的危险程度，并且基于所确定的事件危险程度向用户提供警告。

公开(公告)号：EP2793167A3

公开(公告)日：2017-01-11

申请号：EP14158067.0

申请日：2014-03-06

申请人： OMRON CORPORATION

发明人： Murakami, Tatsuya ,  Ohta, Takashi

IPC分类号： G06K9/00

CPC分类号： G06T7/20 ,  G06K9/00302 ,  G06K9/00315 ,  G06K9/00355 ,  G06K9/72 ,  G06K2209/27 ,  G06T2207/30196 ,  G06T2207/30201

摘要： To enhance accuracy of expression estimation, an expression estimation device includes a face score acquisition unit that generates a face score indicating an expression of a person in an image, a motion detector that determines a type of motion of the person, and an expression decision unit that generates a result score indicating the expression according to the face score and the type of motion.