-
公开(公告)号：KR101288979B1
公开(公告)日：2013-08-07
申请号：KR1020120025670
申请日：2012-03-13
Applicant: 한국과학기술연구원
Abstract: PURPOSE: An apparatus and a method of reconstructing a 3D shape based on a single-shot photo image are provided to conspicuously reduce the time required for obtaining a 3D shape of an object by using one image. CONSTITUTION: An apparatus of reconstructing a 3D shape of an object comprises a lighting unit casting light on the object; a light modulation device (120) modulating the light having penetrated the object into a regular pattern at a spatial domain; a photographing unit (130) taking a 2D image of the object modulated by the light modulation device; a signal processing unit (150) dividing the 2D image of the object into several unit images and restoring the 3D shape of the object by reconstructing several unit images.
Abstract translation: 目的：提供基于单次照片图像重建3D形状的装置和方法，以显着减少通过使用一个图像获得对象的3D形状所需的时间。 构成：重建对象的3D形状的装置包括在对象上投射光的照明单元; 光调制装置（120），其将具有穿透所述物体的光在空间域调制成规则图案; 拍摄单元（130），拍摄由所述光调制装置调制的对象的2D图像; 信号处理单元，其将所述对象的2D图像划分为若干单位图像，并且通过重构多个单位图像来恢复所述对象的3D形状。
-
公开(公告)号：KR1020130019167A
公开(公告)日：2013-02-26
申请号：KR1020110081157
申请日：2011-08-16
Applicant: 한국과학기술연구원
CPC classification number: G06F17/30247 , G06F17/30265 , G06T3/4053
Abstract: PURPOSE: A method for reforming a high resolution image and a system thereof are provided to automatically reform a high resolution image by using images collected through the Internet. CONSTITUTION: A high resolution reforming system receives a request for enlarging a selected area(S120). The system collects images including the selected area from the Internet(S140). The system revises resolution based on the collected images while enlarging the selected area(S150). The system displays the enlarged image on an electronic device(S170). [Reference numerals] (AA) Start; (BB) End; (S110) Displaying an image; (S120) Designating an area selected to enlarge from an obtained image; (S130) Transmitting an enlarging request and information about the selected area to a remote server; (S140) Collecting images including scenes of the selected area from the internet; (S150) Step of enlarging the selected area and correcting the resolution based on the collected images; (S160) Transmitting the enlarged image to a user terminal; (S170) Displaying the enlarged image on the user terminal
Abstract translation: 目的：提供一种用于重构高分辨率图像的方法及其系统，以通过使用通过因特网收集的图像自动地改写高分辨率图像。 构成：高分辨率重整系统接收到放大选定区域的请求（S120）。 系统从因特网收集包括所选区域的图像（S140）。 系统根据所收集的图像修改分辨率，同时放大所选区域（S150）。 系统在电子设备上显示放大的图像（S170）。 （附图标记）（AA）开始; （BB）结束; （S110）显示图像; （S120）指定从所获得的图像中选择放大的区域; （S130）向远程服务器发送放大请求和有关所选区域的信息; （S140）从互联网收集包括所选区域的场景的图像; （S150）基于所收集的图像扩大所选区域并校正分辨率的步骤; （S160）将放大后的图像发送到用户终端; （S170）在用户终端上显示放大图像
-
公开(公告)号：KR101139287B1
公开(公告)日：2012-04-26
申请号：KR1020100022874
申请日：2010-03-15
Applicant: 한국과학기술연구원
Abstract: 파노라마 영상 장치는, 파노라마 영상을 재생하는 재생부, 오브젝트의 위치 또는 회전각도 변화를 감지하는 카메라부, 상기 카메라부에서 감지된 오브젝트의 위치 또는 회전각도 변화에 대한 정보를 이용하여, 상기 오브젝트의 움직임을 연산하는 연산부 및 상기 재생부가 재생하는 파노라마 영상에 상기 연산 결과를 반영하여 재생하도록 제어하는 제어부를 포함한다.
-
公开(公告)号：KR1020090106069A
公开(公告)日：2009-10-08
申请号：KR1020080031565
申请日：2008-04-04
Applicant: 한국과학기술연구원
CPC classification number: G06T19/006 , G01S19/01 , G06T7/33 , G06T2207/10032
Abstract: PURPOSE: An information processor using an augmented reality technique and an information input and searching method are provided to supply information of high quality to a user by supplying a display method about the recognized image. CONSTITUTION: An information processor using an augmented reality technique and an information input and searching method are as follows. The image for recognizing an object is obtained(11). The visual feature vector is extracted from the image(12). The tagged information in which we obtain the image is received from a visual feature vector. The tagged information and the object are displayed by matching the tagged information(14).
Abstract translation: 目的：提供一种使用增强现实技术和信息输入和搜索方法的信息处理器，通过提供关于识别的图像的显示方法向用户提供高质量的信息。 构成：使用增强现实技术和信息输入和搜索方法的信息处理器如下。 获得用于识别对象的图像（11）。 从图像（12）提取视觉特征向量。 从视觉特征向量接收我们获取图像的标记信息。 通过匹配标记信息（14）来显示标记信息和对象。
-
公开(公告)号：KR100824312B1
公开(公告)日：2008-04-22
申请号：KR1020070076362
申请日：2007-07-30
Abstract: A system and a method for identifying a gender of a voice signal are provided to obtain a feature vector by using group delay of a voice signal phase spectrum and compare the obtained feature vector with a Gaussian mixture model of each gender voice signal according to an expectation maximization algorithm, thereby effectively detecting the gender of the voice signal. A gender identifying system comprises the followings. A storage unit(40) stores a Gaussian mixture model of each gender voice signal. An input unit(10) receives a signal including a voice signal. An analyzing unit(30) detects a gender of the inputted voice signal by comparing a feature vector, obtained by using group delay of the inputted voice signal, with the Gaussian mixture model stored in the storage unit. The gender identifying system comprises a voice detector(20) which extracts only a voice signal from the signal inputted in the input unit and transmits the extracted voice signal to the analyzing unit.
Abstract translation: 提供用于识别语音信号的性别的系统和方法，以通过使用语音信号相位谱的组延迟来获得特征向量，并且根据期望值将获得的特征向量与每个性别语音信号的高斯混合模型进行比较 最大化算法，从而有效检测语音信号的性别。 性别识别系统包括以下内容。 存储单元（40）存储每个性别语音信号的高斯混合模型。 输入单元（10）接收包括语音信号的信号。 分析单元（30）通过将通过使用输入的语音信号的组延迟获得的特征向量与存储在存储单元中的高斯混合模型进行比较来检测输入的语音信号的性别。 性别识别系统包括语音检测器（20），其仅从输入单元中输入的信号中提取语音信号，并将提取的语音信号发送到分析单元。
-
Patent Agency Ranking
公开(公告)号：KR100822024B1
公开(公告)日：2008-04-15
申请号：KR1020070076335
申请日：2007-07-30
Abstract: An acoustic signal based environment recognizing method for a context-aware communication terminal is provided to perform environment recognition without a special feature vector extracting process by using only an important parameter automatically in an encoding process. An environment recognizing method comprises the following steps of: configuring a Gaussian mixture model by using one or more feature vectors extracted from a real time voice signal during an SMV(Selectable Mode Vocoder) encoding process; obtaining likelihood for the real time voice signal by using the pre-trained Gaussian mixture model; and selecting an environment flag corresponding to the maximum likelihood value.
Abstract translation: 提供了一种用于上下文感知通信终端的基于声学信号的环境识别方法，用于在编码处理中仅使用自动重要参数来执行环境识别，而无需特殊特征向量提取处理。 环境识别方法包括以下步骤：在SMV（可选模式声码器）编码处理期间，通过使用从实时语音信号提取的一个或多个特征向量来配置高斯混合模型; 通过使用预先训练的高斯混合模型获得实时语音信号的可能性; 以及选择与最大似然值相对应的环境标志。
-
公开(公告)号：KR100537028B1
公开(公告)日：2005-12-16
申请号：KR1020030015199
申请日：2003-03-11
Applicant: 한국과학기술연구원
IPC: H04N5/262
Abstract: 카메라에 의해 물체를 실시간 구분하는 방법은 고효율 압축, 영상 합성 등 다양한 분야에서 많이 응용되고 기술로서, 종래에는 주로 단일 색상 배경을 이용해 물체와 배경의 색상이 다르다는 것을 이용하는 크로마키(Chroma Key) 방식이 주로 이용되어 왔다.
그러나 크로마키 방식은 물체가 배경의 색상을 포함하면 동작하지 못하며 조명등에 매우 민감하게 반응하여 사용환경에 매우 제한적이었다.
본 발명의 적외선-키 방식은 이러한 제안을 모두 제거하는 방법으로 특히 어두운 조명 환경에서도 잘 동작하는 특성을 갖는다.
상기 적외선-키 방식은 적외선 반사 특성을 갖는 배경과 이를 검출하는 능동 적외선 카메라로 구성되고, 능동 적외선 카메라는 상용 캠코더에 적외선 카메라와 적외선 LED를 부착하여 간단히 만들 수 있으므로 매우 경제적이다.
또한 이를 이용한 실시간 영상 합성 방식을 제안한다.-
公开(公告)号：KR100324255B1
公开(公告)日：2002-02-25
申请号：KR1019990063460
申请日：1999-12-28
Applicant: 한국과학기술연구원
IPC: H04N9/12
Abstract: 본발명은내용기반동영상검색방법에관한것으로특히, 컬러특징과모션특징을추출함으로써동영상의검색효율을증대시킬수 있도록함에목적이있다. 이러한목적을달성하기위한본 발명은입력영상을숏(shot) 단위로분할한후 서브숏(sub-shot) 단위로재분할하는제1 단계와, 상기에서서브숏(sub-shot) 단위로재분할된영상을컬러양자화하는제2 단계와, 상기에서컬러양자화된영상에대해서브숏단위로컬러히스토그램행렬을생성하는제3 단계와, 상기에서컬러양자화된영상에대해각 컬러그룹좌표의평균값과분산값을계산하는제4 단계와, 입력영상에서의각각의 P 프레임으로부터컬러그룹단위의순방향움직임벡터를추출하는제5 단계와, 상기에서추출한순방향움직임벡터를양자화하여인접화소에대한각 컬러그룹단위의움직임벡터비율을연산하는제6 단계와, 상기에서각 컬러그룹좌표의분산값과각 컬러그룹단위의움직임벡터비율을참조하여유사성이높은동영상을검색하는제7 단계를수행함을특징으로한다.
-
公开(公告)号：KR102249663B1
公开(公告)日：2021-05-10
申请号：KR1020190041958
申请日：2019-04-10
Applicant: 한국과학기술연구원
Abstract: 본발명의실시예들은대상자의영상을획득하는단계; 상기대상자의영상에서귀 영역영상을검출하는단계; 상기귀 영역영상에서대상자의귀가갖는복수의특성을각각나타내는복수의특징벡터를추출하는단계; 상기대상자의특징벡터와후보자의특징벡터에기초하여상기대상자의귀의특성과후보자의귀의특성간의유사도를산출하는단계; 및상기유사도산출결과에기초하여신원을확인하는단계를포함한귀 인식기반신원확인방법및 이를수행하는귀 인식기반신원확인시스템에관련된다
-
-
-
-
-
-
-
-
-
Search Results
149
records
(took 0.083 seconds)
