-
公开(公告)号：KR1020110059239A
公开(公告)日：2011-06-02
申请号：KR1020090115903
申请日：2009-11-27
Applicant: 한국전자통신연구원
IPC: H04W4/04
CPC classification number: G08G1/096716 , G01C21/26 , G08G1/096741 , G08G1/096775
Abstract: PURPOSE: A vehicle control method and a system using network are provided to offer information about obstacles on driving and a driving status for free driving and automatic leading of vehicles. CONSTITUTION: A local server 1 detects sense information(S700,S702). The local server 1 detects an object vehicle within a section(S704). The local server 1 collects corresponding sensing information and target vehicle information. The local server 1 creates local route points(S706). The local server 1 transmits the created local route points to a vehicle control terminal through an interface unit(S708).
Abstract translation: 目的：提供车辆控制方法和使用网络的系统，提供有关驾驶障碍物以及驾驶自动驾驶状况和自动驾驶车辆信息的信息。 规定：本地服务器1检测感测信息（S700，S702）。 本地服务器1在一部分内检测到对象车辆（S704）。 本地服务器1收集相应的感测信息和目标车辆信息。 本地服务器1创建本地路由点（S706）。 本地服务器1通过接口单元将创建的本地路由点发送到车辆控制终端（S708）。
-
公开(公告)号：KR1020110042800A
公开(公告)日：2011-04-27
申请号：KR1020090099636
申请日：2009-10-20
Abstract: PURPOSE: A wireless display device which distinguishes a color difference signal and color difference information and method thereof are provided to conveniently restores an original signal which transmits in a transmit side from a color difference signal. CONSTITUTION: A signal separating unit(103) converts an original color signal into a color signal difference signal. The signal separating unit separates the color difference signal into a blue-brightness signal and red-brightness signal. A signal inserting unit(105) inserts a color difference distinguishing signal in the blue-brightness signal and the red-brightness signal. A signal transmission unit(107) transmits the blue-brightness signal and the red-brightness signal which the color difference distinguish signal is inserted.
Abstract translation: 目的：提供区分色差信号和色差信息的无线显示装置及其方法，以方便地从色差信号恢复在发送侧发送的原始信号。 构成：信号分离单元（103）将原始颜色信号转换为彩色信号差分信号。 信号分离单元将色差信号分离成蓝色亮度信号和红色亮度信号。 信号插入单元（105）在蓝色亮度信号和红色亮度信号中插入色差识别信号。 信号发送单元（107）发送插入了色差识别信号的蓝色亮度信号和红色亮度信号。
-
公开(公告)号：KR100873474B1
公开(公告)日：2008-12-15
申请号：KR1020060121758
申请日：2006-12-04
Applicant: 한국전자통신연구원 , (주)한국공간정보통신
IPC: G08G1/0968 , G08G1/04 , G06K9/00 , G06K9/62
Abstract: An apparatus and a method for estimating the location of vehicles using the pixel size and the location of facilities as images are provided to enhance user convenience by compensating for GPS(Global Positioning System) signals through map matching with lanes. Images of current position is photographed through a video camera mounted on vehicles and traffic facilities are identified based on the photographed images of current position(201). Types of traffic facilities are identified by comparing the identified facilities with stored facilities, and the pixel size and the location of the facilities are extracted(202). The distance between the facilities and vehicles are identified by comparing the distances on pixel sizes of extracted facilities with stored facilities(203). Lanes are corrected according to the comparison of lane information and the location of the extracted facilities(204). The position of the vehicles is predicted based on the distance information, the lane information, and traveling information of the vehicles(205).
Abstract translation: 提供了使用像素大小和设施位置作为图像来估计车辆的位置的设备和方法，以通过通过与车道的地图匹配来补偿GPS（全球定位系统）信号来增强用户便利性。 当前位置的图像通过安装在车辆上的摄像机拍摄，并且基于当前位置的拍摄图像来识别交通设施（201）。 交通设施的类型通过将所识别的设施与存储的设施进行比较来识别，并且提取像素大小和设施的位置（202）。 设施和车辆之间的距离通过比较提取设施与存储设施的像素尺寸的距离（203）来识别。 车道根据车道信息和提取的设施的位置的比较来校正（204）。 基于车辆的距离信息，车道信息和行驶信息来预测车辆的位置（205）。
-
公开(公告)号：KR1020070053536A
公开(公告)日：2007-05-25
申请号：KR1020050111419
申请日：2005-11-21
Applicant: 한국전자통신연구원
IPC: H04N5/232
CPC classification number: H04N5/23264 , H04N5/23251
Abstract: 본 발명은 디지털 카메라 촬영시 느린 셔터 속도에서 선명한 영상을 얻기 위한 방법 및 장치에 관한 것으로서, 렌즈가 열려있는 동안 n개의 영상 프레임을 순차적으로 입력받고 관리하기 위한 영상 취득부; 렌즈가 열린 순간 최초로 찍힌 영상을 기준 프레임으로 설정하고, 블록 정합 알고리듬에 기초하여 기준 프레임에 대하여 2번째부터 n번째 영상 프레임 각각의 움직임 정도를 순차적으로 검출하는 움직임 검출부; 검출된 움직임 정도가 기설정된 임계치 이내인 경우 기준 프레임 영역과 임계치 이내의 움직임이 검출된 영상 프레임 영역을 비교하여 영상을 보정하는 영상 보정부;및 기준 프레임과 영상 보정부에서 보정된 영상 프레임들을 조합하여 최종 프레임을 생성하는 영상 생성부;를 포함한다.
셔터 속도, 흔들림-
公开(公告)号：KR1020060132302A
公开(公告)日：2006-12-21
申请号：KR1020050052585
申请日：2005-06-17
Applicant: 한국전자통신연구원
IPC: G06K9/00 , G01C21/36 , G08G1/0968
CPC classification number: G06K9/00798 , G01C21/3602 , G01C21/3658 , G08G1/0968
Abstract: A method and an apparatus for correcting a car position in a car navigation system are provided to facilitate detecting of the car position by combining present position information of a car with peripheral information of a road. An apparatus for correcting a car position in a car navigation system includes a car position detecting unit(210) detecting the position of a car by using a satellite navigation device; a map database(220) storing geographical information and information on objects having specified position; a photographing unit(230) taking images of the objects located at the peripheral region of the driveway and generating image signals; and a correcting unit(240) matching the object information and the object extracted by analyzing the image signal, and correcting the car position detected by the car position detecting unit on the basis of the position information of the objects.
Abstract translation: 提供一种用于校正汽车导航系统中的轿厢位置的方法和装置，以便通过将汽车的当前位置信息与道路的周边信息相结合来便于检测轿厢位置。 一种用于在汽车导航系统中校正轿厢位置的设备包括：轿厢位置检测单元，通过使用卫星导航装置检测汽车的位置; 存储关于具有指定位置的对象的地理信息和信息的地图数据库（220） 拍摄单元（230）拍摄位于车道的周边区域的物体的图像并产生图像信号; 以及校正单元（240），其通过分析图像信号而提取的对象信息和对象匹配，并且基于对象的位置信息来校正由轿厢位置检测单元检测到的轿厢位置。
-
Patent Agency Ranking
公开(公告)号：KR100571429B1
公开(公告)日：2006-04-17
申请号：KR1020030097650
申请日：2003-12-26
Applicant: 한국전자통신연구원
IPC: G06Q50/00
CPC classification number: G06T5/006 , G06T2207/30181
Abstract: 본 발명은 항공기나 위성에 의해 수집된 영상의 기하 왜곡을 보정하기 위해 사용되는 지상기준점(GCP : Ground Control Point) 관련 정보를 인터넷 망을 통하여 온라인으로 제공하여 원격지에 있는 사용자가 기하보정 또는 정사보정을 수행할 수 있도록 하는 온라인 기하보정 서비스 제공 방법에 관한 것으로서, 기하보정 과정에서 지상기준점 관련 영상 정보는 제공하되 기준점 자체의 정밀한 지리 좌표 정보는 제공하지 않음으로 인하여 보안 사항으로 취급되는 상세 지리 정보의 은닉성을 유지하는 것을 특징으로 한다.
지상기준점, GCP(Ground Control Point) 칩, 클라이언트-서버, 항공 사진, 위성 영상, 기하 보정, 정사 보정, 온라인 서비스Abstract translation: 通过因特网从远程几何校正或正射校正的可用在线用户的信息：被用于校正由飞机或卫星（地面控制点GCP）的图像拾取的几何失真本发明地面控制点 本发明涉及提供用于执行地理信息的地理校正的在线几何校正服务的方法， 从而保持隐藏属性。
-
公开(公告)号：KR100545742B1
公开(公告)日：2006-01-24
申请号：KR1020030093666
申请日：2003-12-19
Applicant: 한국전자통신연구원
IPC: G06F17/40
Abstract: 본 발명은 네트워크를 이용한 다중분광영상(Multispectral imagery)의 자동 분류 방법에 관한 것으로, 영상 훈련부를 통해 다중분광영상을 분할하고, 객체에서 정해진 분류 클래스(Class)에 대한 특징(Feature)을 데이터베이스화하여 훈련자료로서 설정하며, 설정된 훈련자료의 분류결과에 대한 정밀도 검사(Accuracy assessment)를 수행하고, 데이터베이스화된 특징 정보를 네트워크를 통해 다중분광영상의 분류를 목적으로 하는 사용자에게 제공하며, 데이터베이스화된 특징 정보를 외부로 표시하여 사용자로 하여금 영상 분류부에 대한 기능 설정 과정을 유도하는 것을 특징으로 한다. 본 발명에 의하면, 다중분광영상을 이용한 지표피복분류 등에 있어서 네트워크를 통한 데이터베이스를 사용하고 사용자측에서 별도의 훈련자료 설정 작업이 필요하지 않기 때문에 사용자의 적은 노력으로도 높은 분류 정밀도를 얻을 수 있다.
다중분광영상(Multispectral imagery), 영상분류(Image classification), 영상분할(Image segmentation), 객체기반 영상분류(Object-based image classification), 훈련자료(Training data)Abstract translation: 本发明涉及一种多光谱图像（多光谱图像）的自动分类使用的网络中，通过图像和训练分割多光谱图像，以及特征（功能）的分类的类别的数据库（类）由对象设定 将其设置为训练数据，对设定的训练数据的分类结果进行精度评估，并将数据库特征信息提供给用户，以便通过网络对多光谱图像进行分类。 特征信息被显示在外部，由此引起用户为图像分类器设置功能。 根据本发明，使用多光谱图像使用在网络上的数据库以较少的努力，并获得用户较高的分类准确度，因为它不需要单独的一组训练材料，在用户侧的工作是在这类指标覆盖分类可能的。
-
公开(公告)号：KR1020040050569A
公开(公告)日：2004-06-16
申请号：KR1020020078426
申请日：2002-12-10
Applicant: 한국전자통신연구원
IPC: H05K13/08
CPC classification number: G06T7/66 , G06T7/73 , G06T2207/30141
Abstract: PURPOSE: A method for measuring a center position of a fiducial mark is provided to calculate accurately the center position of the fiducial mark as much as sub-pixel units without using the standard pattern information and the geometric information. CONSTITUTION: A method for measuring a center position of a fiducial mark includes a target region calculation process, a mark range calculation process, a pixel unit center calculation process, and a sub-pixel unit center calculation process. The target region calculation process is performed to calculate a target region including a fiducial mark of an image(100). The mark range calculation process is performed to calculate a predetermined region including the fiducial mark within the target region(200). The pixel unit center calculation process is performed to calculate a center position of the fiducial mark as accuracy of unit pixel within the predetermined region(300). The sub-pixel unit center calculation process is performed to calculate the center position of the fiducial mark as the accuracy of sub-pixel(400).
Abstract translation: 目的：提供一种用于测量基准标记的中心位置的方法，以准确地计算基准标记的中心位置多达子像素单位，而不使用标准图案信息和几何信息。 构成：用于测量基准标记的中心位置的方法包括目标区域计算处理，标记范围计算处理，像素单元中心计算处理和子像素单元中心计算处理。 执行目标区域计算处理以计算包括图像的基准标记的目标区域（100）。 执行标记范围计算处理以计算包括目标区域（200）内的基准标记的预定区域。 执行像素单元中心计算处理，以计算基准标记的中心位置作为预定区域（300）内的单位像素的精度。 执行子像素单元中心计算处理，以计算基准标记的中心位置作为子像素（400）的精度。
-
公开(公告)号：KR1020030054106A
公开(公告)日：2003-07-02
申请号：KR1020010084212
申请日：2001-12-24
Applicant: 한국전자통신연구원
IPC: H04N7/18
Abstract: PURPOSE: A system for calculating light flow and camera motion from motion pictures using correlation matching and a system model is provided to obtain light flow from continuous motion pictures to calculate camera motion. CONSTITUTION: A characteristic point extractor(100) extracts characteristic points of continuous images including previous and current images. A light flow calculator(110) calculates light flow using the extracted characteristic points. The first camera motion calculator(120) calculates camera motion using the calculated light flow. The second camera motion calculator(130) removes light flow erroneously calculated and than re-calculates camera motion information. A light flow position estimator(140) estimates a distance difference between a characteristic point estimation position in the previous image and current characteristic point position according to the camera motion calculated by the second camera motion calculator to provide the distance difference information to the light flow calculator. A weight calculator(150) sets weights of correlation matching, position error matching and edge intensity matching according to the camera motion calculated by the second camera motion calculator to supply the weights to the light flow calculator.
Abstract translation: 目的：提供使用相关匹配和系统模型从运动图像计算光流和相机运动的系统，以获得来自连续运动图像的光流，以计算相机运动。 构成：特征点提取器（100）提取包括先前和当前图像的连续图像的特征点。 光流计算器（110）使用所提取的特征点来计算光流。 第一相机运动计算器（120）使用所计算的光流计算相机运动。 第二相机运动计算器（130）去除错误计算的光流，并重新计算相机运动信息。 光流位置估计器（140）根据由第二相机运动计算器计算的相机运动估计先前图像中的特征点估计位置与当前特征点位置之间的距离差，以向距离差异信息提供距离差信息给光流计算器 。 权重计算器（150）根据由第二相机运动计算器计算的相机运动设置相关匹配，位置误差匹配和边缘强度匹配的权重，以将权重提供给光流计算器。
-
公开(公告)号：KR1020130120730A
公开(公告)日：2013-11-05
申请号：KR1020120043845
申请日：2012-04-26
Applicant: 한국전자통신연구원
Inventor： 조성익
IPC: H04N13/02
CPC classification number: G06K9/46 , G06K9/6201 , G06T7/593 , G06T2207/10012
Abstract: The present invention relates to a method for processing inherent geometric information included in a disparity space image generated using at least two stereo images, in which information near a disparity surface included in an original disparity space image is emphasized through a process of stressing the similarity of real symmetrical points using the cohesiveness and symmetry. The method for processing the disparity space image comprises: an image photographing step for photographing stereo images which satisfy epipolar geometry conditions using at least two cameras with parallax; a disparity space image generation step for generating pixels of a three-dimensional disparity space image on the basis of the photographed image; a cohesiveness emphasis step for reducing the dispersion of the brightness distribution of the disparity space image at a level at which information included in the disparity space image is maintained; a symmetry emphasis step for generating a disparity space image with emphasized symmetry by stressing the similarity of pixels at the position at which the pixels are reflected to be symmetrical to each other in a direction in which the disparity changes in the disparity space image; and a surface extraction step for extracting a disparity surface by connection three or more corresponding points in the disparity space image with emphasized symmetry. [Reference numerals] (AA) Start;(BB) End;(S100) Take images;(S200) Create a modification space image;(S300) Perform a coherence-highlighting process;(S400) Perform a symmetry-highlighting process;(S500) Extract curves
Abstract translation: 本发明涉及一种用于处理包括在使用至少两个立体图像产生的视差空间图像中的固有几何信息的方法，其中通过强调包含在原始视差空间图像中的视差表面附近的信息被强调了 使用粘性和对称性的真实对称点。 用于处理视差空间图像的方法包括：图像拍摄步骤，用于使用至少两个具有视差的相机拍摄满足对极几何条件的立体图像; 视差空间图像生成步骤，用于基于所拍摄的图像生成三维视差空间图像的像素; 粘度强调步骤，用于减小视差空间图像的亮度分布在维持在视差空间图像中的信息的水平的色散; 对称强调步骤，用于通过在视差空间图像中的视差变化的方向上强调像素被反射的位置处的像素彼此对称的方式来产生具有强调对称性的视差空间图像; 以及表面提取步骤，用于通过连接具有强调对称性的视差空间图像中的三个或更多对应点来提取视差表面。 （AA）开始;（BB）结束;（S100）拍摄图像;（S200）创建修改空间图像;（S300）进行相干突出处理;（S400）进行对称突出处理; S500）提取曲线
-
-
-
-
-
-
-
-
-
Search Results
55
records
(took 0.045 seconds)
