公开(公告)号：KR1020110070056A

公开(公告)日：2011-06-24

申请号：KR1020090126710

申请日：2009-12-18

Applicant: 한국전자통신연구원

Inventor： 이지형 ,  최윤석 ,  김도형 ,  박일규 ,  차영미 ,  박정철 ,  구본기

IPC: G06T15/00

CPC classification number: G06T17/00 ,  G06K9/00221

Abstract: PURPOSE: A customized high-quality 3d avatar forming method and an apparatus thereof are provided to offer a high-quality 3D avatar for a user easily and quickly. CONSTITUTION: An apparatus extracts the feature point of a face(S50). The apparatus generates texture data which is mapped to the face of a 3D avatar(S60). The apparatus combines 3D body data and face data. The apparatus generates a user avatar(S80). The apparatus applies face animation, and muscle or body animation to the generated 3D avatar of the user. The apparatus renders the 3D avatar in high quality(S90).

Abstract translation: 目的：提供定制的高质量3D头像形成方法及其装置，以便容易且快速地为用户提供高质量的3D头像。 构成：设备提取脸部的特征点（S50）。 该装置产生映射到3D头像的面部的纹理数据（S60）。 该装置结合3D身体数据和脸部数据。 该装置生成用户头像（S80）。 该设备将脸部动画以及肌肉或身体动画应用于所生成的3D头像的用户。 该装置以高质量呈现3D头像（S90）。

公开(公告)号：KR1020110040169A

公开(公告)日：2011-04-20

申请号：KR1020090097335

申请日：2009-10-13

Applicant: 한국전자통신연구원

Inventor： 김도형

IPC: H04W4/02 ,  H04B1/40 ,  G06Q50/30

Abstract: PURPOSE: A departure notification service using a mobile terminal is provided to offer a departure time to a station. CONSTITUTION: A location information detection unit(102) detects the location information of a user. An information receiving unit(110) receives predicted arrival time information corresponding to selected traffic information from a traffic information providing server(150). A moving time detection unit(112) receives moving time information from the current location of the user to the target destination from a map searching server(160). A start notification setting unit(114) establishes the calculated start notification time to a mobile terminal(100).

Abstract translation: 目的：提供使用移动终端的出发通知服务，以提供到车站的出发时间。 构成：位置信息检测单元（102）检测用户的位置信息。 信息接收单元（110）从交通信息提供服务器（150）接收与所选择的交通信息相对应的预测到达时间信息。 移动时间检测单元（112）从地图搜索服务器（160）接收从用户的当前位置到目标目的地的移动时间信息。 开始通知设定单元（114）向移动终端（100）建立计算出的开始通知时间。

公开(公告)号：KR1020100124949A

公开(公告)日：2010-11-30

申请号：KR1020090043914

申请日：2009-05-20

Applicant: 한국전자통신연구원

Inventor： 김도형 ,  윤우한 ,  이재연 ,  윤호섭 ,  김혜진 ,  윤영우 ,  황대환

IPC: H04N5/262

CPC classification number: G06K9/00255 ,  G06K9/00261 ,  G06T7/277 ,  G06T2207/30201

Abstract: PURPOSE: A device and a method for tracking a face at a long distance are provided to accurately detect and track a far-distanced very small face at a low resolution in order to prevent the wrong detection which tracks a non-facial portion. CONSTITUTION: An image input unit(110) generates continuous image frames by inputting a video image, and a face tracking initializing unit(130) detects an omega region and a facial region of a human from the image frames. The face tracking initializing unit sets the estimated facial region as tracking start region information. A remote face tracker(150) detects a facial region at a short distance within the facial detection region.

Abstract translation: 目的：提供用于跟踪远距离脸部的装置和方法，以便以低分辨率准确地检测和跟踪远距离的非常小的脸部，以防止跟踪非面部部分的错误检测。 构成：图像输入单元（110）通过输入视频图像来生成连续的图像帧，并且面部追踪初始化单元（130）从图像帧中检测人的Ω区域和面部区域。 面部跟踪初始化单元将估计的面部区域设置为跟踪开始区域信息。 远程脸部跟踪器（150）在脸部检测区域内检测距离较短距离的面部区域。

公开(公告)号：KR1020100102949A

公开(公告)日：2010-09-27

申请号：KR1020090021279

申请日：2009-03-12

Applicant: 한국전자통신연구원

Inventor： 윤우한 ,  김도형 ,  윤호섭 ,  이재연 ,  황대환

IPC: G06T7/40

CPC classification number: G06K9/00275 ,  G06K9/6234 ,  G06K9/6247 ,  G06T7/11 ,  G06T2207/20021

Abstract: PURPOSE: A method and an apparatus for recognizing a face by a block unit are provided to determine similarity by comparing face images by a block unit, thereby producing various combinations of images to increase variety of face images. CONSTITUTION: A query face image is divided into fixed blocks and a feature value is extracted from each block. A feature value extracting unit(200) extracts a feature value from an inputted face image by a fixed block unit. A block similarity calculating unit(410) calculates block similarity between the query face image and a registration face image. The block similarity calculating unit compares a feature value of a fixed block of the query face image with a feature value of a block of the registration image corresponding to a fixed block of the query face image.

Abstract translation: 目的：提供一种用于通过块单元识别面部的方法和装置，以通过以块为单位比较面部图像来确定相似度，从而产生图像的各种组合以增加脸部图像的多样性。 构成：将查询面部图像分为固定块，并从每个块中提取特征值。 特征值提取单元（200）通过固定块单元从输入的面部图像提取特征值。 块相似度计算单元（410）计算查询面部图像与登记面部图像之间的块相似度。 块相似度计算单元将查询面部图像的固定块的特征值与对应于查询面部图像的固定块的登记图像的块的特征值进行比较。

公开(公告)号：KR1020100072772A

公开(公告)日：2010-07-01

申请号：KR1020080131279

申请日：2008-12-22

Applicant: 한국전자통신연구원

Inventor： 최승민 ,  조재일 ,  장지호 ,  황대환 ,  김도형

IPC: G06T7/40 ,  G06T7/00

CPC classification number: G06K9/4642 ,  G06K9/00228

Abstract: PURPOSE: A method and an apparatus for real-time face detection using a stereo vision are provided to perform face detection in foreground including face pattern from whole video by stereo vision processor thereby widely reducing face detection processing time. CONSTITUTION: A vision processing unit(320) calculates distance information by usage of a plurality of images including face pattern. Based on the distance information, the vision processing unit divides foreground image including the face pattern and background image not including the face pattern. According to distance information, a face detection unit(330) adjusts video size of the foreground image. The face detection unit detects the face pattern from adjusted foreground image.

Abstract translation: 目的：提供一种使用立体视觉进行实时脸部检测的方法和装置，用于在前景执行面部检测，包括立体视觉处理器的整个视频的脸部图案，从而大大减少脸部检测处理时间。 构成：视觉处理单元（320）通过使用包括脸部图案的多个图像来计算距离信息。 基于距离信息，视觉处理单元将包括脸部图案的前景图像和不包括脸部图案的背景图像分割开。 根据距离信息，面部检测单元（330）调整前景图像的视频大小。 面部检测单元从调整前景图像检测脸部图案。

公开(公告)号：KR1020100015167A

公开(公告)日：2010-02-12

申请号：KR1020080076098

申请日：2008-08-04

Applicant: 한국전자통신연구원

Inventor： 최승민 ,  장지호 ,  조재일 ,  황대환 ,  이재연 ,  김도형 ,  임을균 ,  신호철

IPC: G06K9/00 ,  G01H1/00

CPC classification number: G01H17/00 ,  G06K9/00348 ,  G06K9/0053

Abstract: PURPOSE: A user recognition device and a user recognition method are provided to use a walking pattern as ID information of a user, thereby improving a recognition rate of the user through simple configuration. CONSTITUTION: A sensing unit(110) senses vibration due to walking of a user to output an electrical signal. A pattern calculator(130) obtains a walking pattern of a pedestrian from the electrical signal. A user decider(150) compares the walking pattern with reference date. The user decider identifies a user based on the comparison result.

Abstract translation: 目的：提供用户识别装置和用户识别方法以使用步行模式作为用户的ID信息，从而通过简单的配置提高用户的识别率。 构成：感测单元（110）感测由于用户的行走而产生的振动以输出电信号。 图案计算器（130）从电信号中获取行人的步行图案。 用户决定器（150）将步行模式与参考日期进行比较。 用户决定器基于比较结果识别用户。

公开(公告)号：KR100928998B1

公开(公告)日：2009-11-26

申请号：KR1020070128923

申请日：2007-12-12

Applicant: 한국전자통신연구원

Inventor： 김원태 ,  김도형 ,  이환구 ,  곽지영 ,  이경희 ,  박승민

IPC: H04N21/40

CPC classification number: H04L67/34 ,  H04L65/1083 ,  H04L65/607

Abstract: Disclosed are an adaptive multimedia system for providing multimedia contents and a codec to a user terminal, and a method thereof. The adaptive multimedia system includes: a media server controller that receives profile information from an open codec player of the user terminal, and when a codec for decoding the multimedia contents does not exist in the user terminal, transmits a control message to allow the multimedia contents and the decoding codec to be transmitted together; and at least one transmission frame generator that encodes the multimedia contents through a transcoder and an encoding module according to the control message transmitted from the media server controller, generates a transmission frame including the encoded multimedia contents and the decoding codec, and transmits the generated transmission frame to the open codec player.

Abstract translation: 公开了一种用于向用户终端提供多媒体内容和编解码器的自适应多媒体系统及其方法。 自适应多媒体系统包括：媒体服务器控制器，其从用户终端的开放编解码器播放器接收简档信息，并且当用于解码多媒体内容的编解码器不存在于用户终端中时，发送控制消息以允许多媒体内容 和解码编解码器一起发送; 以及至少一个传输帧生成器，其根据从媒体服务器控制器传输的控制消息，通过代码转换器和编码模块对多媒体内容进行编码，生成包括编码的多媒体内容和解码编解码器的传输帧，并将生成的传输 帧打开编解码器播放器。

公开(公告)号：KR1020090026879A

公开(公告)日：2009-03-16

申请号：KR1020070091933

申请日：2007-09-11

Applicant: 한국전자통신연구원

Inventor： 윤우한 ,  김도형 ,  윤호섭 ,  배경숙

IPC: G06K9/46 ,  G06T7/40

CPC classification number: G06K9/00234 ,  G06K9/00275 ,  G06K9/00288 ,  G06K9/44

Abstract: A feature extracting apparatus for face recognition based on a color image and a method thereof are provided to detect a peculiar face based on the color image and perform the face registration and recognition based on the detected peculiar face. A normalization part(100) normalizes plurality of RGB color images in a preset size. That is, it performs the inclination and size revision by using the pupil position information of a person in the color images, and then extracts an image of a preset size from the whole face image on the basis of the both eyes. After performing the linear conversion for the normalized respective RGB color images, a conversion unit(102) performs a histogram equalization process. An average image calculating unit(104) produces the average images for the plural images outputted from the conversion unit. A peculiar face generating unit(106) produces the covariance matrix of color images based on the average images calculated in the average image calculating unit, and the generates a peculiar face based on the calculated covariance matrix.

Abstract translation: 提供了一种基于彩色图像的用于人脸识别的特征提取装置及其方法，用于基于彩色图像检测特有的面部，并且基于检测到的特殊面进行面部登记和识别。 归一化部分（100）以预设大小归一化多个RGB彩色图像。 也就是说，通过使用彩色图像中的人的瞳孔位置信息来执行倾斜和尺寸修正，然后基于双眼从整个脸部图像中提取预设大小的图像。 在对归一化的各个RGB彩色图像执行线性转换之后，转换单元（102）执行直方图均衡处理。 平均图像计算单元（104）产生从转换单元输出的多个图像的平均图像。 特殊面部生成部（106）基于平均图像计算部中计算出的平均图像，生成彩色图像的协方差矩阵，根据所计算的协方差矩阵生成特殊面。

公开(公告)号：KR100867998B1

公开(公告)日：2008-11-10

申请号：KR1020070045112

申请日：2007-05-09

Applicant: 한국전자통신연구원 ,  한양대학교 산학협력단

Inventor： 김원태 ,  김선자 ,  김도형 ,  이환구 ,  김재평 ,  조인휘

IPC: H04B7/26 ,  H04L12/66

CPC classification number: H04W36/04 ,  H04W52/0232 ,  H04W88/06 ,  Y02D70/142 ,  H04W36/14 ,  H04W52/0261 ,  Y02D70/00

Abstract: A handover method between dualized network based on power consumption and an apparatus thereof are provided to generate candidate network list by calculating prospect power consumption calculated by network and traffic class and to prevent unnecessary hand over. A network list capable of handover based on power consumption of the mobile terminal prospected about traffic class and each network among dualized network is made(S120). A handover network is selected based on the user preference and the traffic class in network on the list(S130). The minimum usage time of the terminal is predicted by the remainder of a battery about prospect power consumption calculated based on the interface capacity of network and traffic class of the mobile terminal.

Abstract translation: 提供基于功耗的二元化网络与其装置之间的切换方法，通过计算由网络和流量级计算的潜在功耗并防止不必要的切换来生成候选网络列表。 进行能够基于在双向化网络中考虑到关于业务类别和每个网络的移动终端的功耗的切换的网络列表（S120）。 基于用户偏好和列表中的网络中的流量类别来选择切换网络（S130）。 终端的最小使用时间由电池的剩余部分预测，基于移动终端的网络和流量类别的接口容量计算的前景功耗。

公开(公告)号：KR1020080097798A

公开(公告)日：2008-11-06

申请号：KR1020070043108

申请日：2007-05-03

Applicant: 삼성전자주식회사 ,  한국전자통신연구원

Inventor： 김현수 ,  윤제한 ,  심현식 ,  박영희 ,  김도형 ,  윤우한

IPC: G06K9/66 ,  G06K9/46 ,  G06K9/80 ,  G06T7/40

CPC classification number: G06K9/00295

Abstract: A system for recognizing a user's face based on adaptive learning, and a method thereof are provided to recognize a user's face by learning the user's face gradually, thereby recognizing a user's face even in the user is in action. A specific person detecting and tracking unit(120) detects the specific person on the moving picture and traces it. A facial feature extraction part(130) extracts a plurality of face characteristic vectors from the detected and the traced specific features of the person. A face recognition part(140) compares the extracted face characteristic vector with the registered model stored in the user registration model database, and searches the corresponding registered model in the database. A learning subject selection part(160) selects the face characteristic vector to be added to the corresponding registered model record among the extracted face characteristic vectors. A registered model studying part(170) adds the selected face characteristic vector to the record of the registered model and renews it.

Abstract translation: 基于自适应学习识别用户面部的系统及其方法被提供以通过逐渐学习用户的脸部来识别用户的脸部，从而即使在用户中也能识别用户的脸部。 具体的人检测跟踪单元（120）检测运动图像上的特定人物并追踪它。 面部特征提取部分（130）从人的检测和跟踪的特定特征提取多个面部特征向量。 面部识别部（140）将所提取的面部特征矢量与存储在用户登记模型数据库中的登记模型进行比较，并在数据库中搜索对应的注册模型。 学习对象选择部（160）在所提取的面部特征向量中选择要添加到对应的登记模型记录的面部特征向量。 注册模型学习部分（170）将所选择的面部特征向量添加到注册模型的记录并更新。