-
公开(公告)号：KR101463194B1
公开(公告)日：2014-11-21
申请号：KR1020130052718
申请日：2013-05-09
Applicant: 한국과학기술원
Abstract: 이미지 블러 제거 장치가 이미지 블러를 제거하기 위하여 이진의 르장드르 시퀀스를 생성하고, 생성한 르장드르 시퀀스를 토대로 모션 블러 이미지를 캡쳐한다. 캡쳐한 모션 블러 이미지를 매팅한 후, 모션을 생성하고 생성한 모션으로부터 모션 블러 정보를 확인한 후, 이를 토대로 PSF(Point Spread Function)를 최적화하여 이미지에 대한 블러를 제거한다.
-
公开(公告)号：KR1020140064471A
公开(公告)日：2014-05-28
申请号：KR1020120131860
申请日：2012-11-20
Applicant: 한국과학기술원
CPC classification number: G06F17/30705 , G06F17/16
Abstract: The present invention relates to a big data clustering method. The big data clustering method according to an embodiment of the present invention includes the steps of: performing distributed data processing with received data; reducing data dimensions by analyzing sub-spaces regarding the data processed in the distributed data processing; and integrating ensemble clusters to cluster the data.
Abstract translation: 本发明涉及一种大数据聚类方法。 根据本发明实施例的大数据聚类方法包括以下步骤：利用接收到的数据执行分布式数据处理; 通过分析关于在分布式数据处理中处理的数据的子空间来减少数据维度; 并集成集群来集群数据。
-
公开(公告)号：KR1020140049677A
公开(公告)日：2014-04-28
申请号：KR1020120115781
申请日：2012-10-18
Applicant: 한국과학기술원
Abstract: The present invention relates to a method for removing a watermark using a correlation between channels of a color image and to a method of reconstructing an image in a watermark area naturally by referring to a structure of an original image after converting the color image into a new image coordinate that the watermark and the original image are separated and removing the watermark. According to the present invention, the loss of information stored in the original image can be minimized by effectively removing the watermark putting over the original image. Therefore, the image can be naturally reconstructed compared to the existing method by preserving the information of the original image.
Abstract translation: 本发明涉及一种使用彩色图像的通道之间的相关性去除水印的方法以及在将彩色图像转换成新的图像之后参照原始图像的结构自然地重建水印区域中的图像的方法 水印和原始图像分离并去除水印的图像坐标。 根据本发明，可以通过有效地去除原始图像上的水印，来最小化存储在原始图像中的信息的丢失。 因此，通过保存原始图像的信息，与现有方法相比，可以自然地重构图像。
-
公开(公告)号：KR1020140009737A
公开(公告)日：2014-01-23
申请号：KR1020120076299
申请日：2012-07-12
Applicant: 한국과학기술원
Abstract: The present invention provides a position recognition method of hybrid map based robots to effectively respond to situations such as kidnap problems in an environment without GPS and to accurately recognize current positions, including processes of acquiring information on surrounding environments using a laser sensor and a camera; determining laser key frames from the laser information acquired through the laser sensor to generate a metric map; determining image key frames capable of expressing each feature from the image information acquired through a camera to generate a topological map; connecting the laser key frames and the image key frames by determining weights according to the sensor characteristics along with determination of integrated key frames; and connecting a local metric map prepared by using ICP algorithm between integrated frames with each laser and image key frame according to differences in a distance from the integrated key frames, thereby recognizing the current position. [Reference numerals] (S12) Laser information acquisition; (S14) Image information acquisition; (S20) Metric map generation; (S30) Topological map generation; (S40) Integrated key frame determination; (S50) Current position recognition
Abstract translation: 本发明提供了一种基于混合地图的机器人的位置识别方法，以有效地响应在没有GPS的环境中的绑架问题等情况，并准确地识别当前位置，包括使用激光传感器和相机获取关于周围环境的信息的处理; 从通过激光传感器获取的激光信息确定激光关键帧以产生度量图; 确定能够从通过照相机获取的图像信息中表达每个特征的图像关键帧，以生成拓扑图; 通过根据传感器特征确定权重以及确定集成关键帧来连接激光关键帧和图像关键帧; 并且根据与集成关键帧的距离的差异，将通过使用ICP算法准备的局部度量图与每个激光和图像关键帧连接在一起，从而识别当前位置。 （附图标记）（S12）激光信息获取; （S14）图像信息采集; （S20）公制图生成; （S30）拓扑图生成; （S40）综合关键帧确定; （S50）当前位置识别
-
公开(公告)号：KR101126626B1
公开(公告)日：2012-03-26
申请号：KR1020100018433
申请日：2010-03-02
Applicant: 한국과학기술원
Abstract: 본 발명은 제1 및 제2 레이저 센서, 상기 제1 및 제2 레이저 센서의 좌우에 각각 배치되는 제1 내지 제4 카메라, 상기 제1 내지 제4 카메라로부터의 영상과 상기 제1 및 제2 레이저 센서에 의한 레이저 점의 움직임을 이용하여 3차원 복원을 수행하는 3차원 복원 장치를 포함하되, 상기 제1 레이저 센서와 제1 및 제2 카메라가 한 세트가 되고, 상기 제2 레이저 센서와 제3 및 제4 카메라가 한 세트가 되어 두 세트가 직각으로 배치되고, 상기 3차원 복원 장치가 상기 제1 내지 제4 카메라를 통해 획득된 영상에 상기 레이저 센서에 의한 레이저 점을 투영 및 트래킹하여 움직임을 추정하고, 상기 추정된 움직임과 상기 레이저 센서에 의한 레이저 데이터를 이용하여 3차원 복원을 수행하는 것으로, 2차원 레이저 센서와 카메라로부터 얻은 데이터를 융합하여 시스템의 이동 경로 및 주변 환경의 3차원 복원을 정확하게 수행할 수 있다.
-
Patent Agency Ranking
公开(公告)号：KR1020120014992A
公开(公告)日：2012-02-21
申请号：KR1020100077146
申请日：2010-08-11
CPC classification number: H04N13/106 , G06T17/00 , H04N13/158 , H04N13/161 , H04N13/356
Abstract: PURPOSE: An image processing device and a method thereof are provided to generate a stereoscopic image or a multi view image at any time using a 3D model. CONSTITUTION: A mode determining unit(110) determines an image processing mode by referring to frame images of input video data and a target timing for rendering. When the image processing mode is a first mode for generating a 3D model using some of the frame images, a 3D model generating unit(120) generates a 3D model using at least some of the frame images. When it is a second mode for 2D conversion, a statistic image adjusting unit(130) performs 2D conversion using some of the frame images. The statistic image adjusting unit generates 2D information corresponding to the target timing.
Abstract translation: 目的：提供一种图像处理装置及其方法，用于使用3D模型随时生成立体图像或多视图图像。 构成：模式确定单元（110）通过参考输入视频数据的帧图像和用于渲染的目标定时来确定图像处理模式。 当图像处理模式是用于使用一些帧图像生成3D模型的第一模式时，3D模型生成单元（120）使用至少一些帧图像来生成3D模型。 当它是用于2D转换的第二模式时，统计图像调整单元（130）使用一些帧图像来执行2D转换。 统计图像调整单元生成对应于目标定时的2D信息。
-
公开(公告)号：KR1020100055662A
公开(公告)日：2010-05-27
申请号：KR1020080114492
申请日：2008-11-18
Applicant: 한국과학기술원
CPC classification number: G06Q50/10 , G06F3/14 , G06F17/30 , G06Q30/0601
Abstract: PURPOSE: A client terminal device, a performance enjoying service device, a performance enjoying service system and a method thereof through wire/wireless communication network are provided to enjoy performance online without directly visiting a performance place by generating performance data according to the information. CONSTITUTION: A communication module unit(106) performs a performance enjoying service device. A digital signal processor(108) displays performance enjoying service related information. The digital signal processor reproduces performance enjoying data according to each service package. A controller(104) sets up the impression service information through the received performance information. The controller controls performance enjoying service data.
Abstract translation: 目的：提供通过有线/无线通信网络的客户终端设备，表演享受服务设备，演奏享受服务系统及其方法，以通过根据该信息生成演奏数据来直接访问演出场所来享受在线表现。 构成：通信模块单元（106）执行演奏享受服务设备。 数字信号处理器（108）显示享受服务相关信息的性能。 数字信号处理器根据每个服务包重现性能享受数据。 控制器（104）通过所接收的演奏信息设置印象服务信息。 控制器控制性能享受服务数据。
-
公开(公告)号：KR1020090122810A
公开(公告)日：2009-12-01
申请号：KR1020080048795
申请日：2008-05-26
IPC: H04N7/18
Abstract: PURPOSE: An image acquiring method and a system thereof signal reflection mirror of a security area is provided to cover the security area of a multifunctional camera through one camera. CONSTITUTION: A variable determining unit(210) determines variation related to the security area which a first camera and a second camera take a picture through a hole of a first mirror. A design unit(220) designs a mirror system by extracting constraints related with the first mirror and the second mirror. An image acquiring unit(230) obtains the top image of the security area and the side image of the security area.
Abstract translation: 目的：提供安全区域的图像获取方法及其系统信号反射镜，以通过一个照相机覆盖多功能相机的安全区域。 构成：可变确定单元（210）确定与第一照相机和第二照相机通过第一镜的孔拍摄照片的安全区域相关的变化。 设计单元（220）通过提取与第一镜和第二镜相关的约束设计镜系统。 图像获取单元（230）获得安全区域的顶部图像和安全区域的侧面图像。
-
公开(公告)号：KR100715026B1
公开(公告)日：2007-05-09
申请号：KR1020050044467
申请日：2005-05-26
Applicant: 한국과학기술원
IPC: H04N13/02
CPC classification number: G03B35/08 , G03B37/06 , H04N13/218
Abstract: 본 발명은 단일카메라 전방향 양안시 영상획득 장치에 관한 것으로서, 그 장치는 제1 시점으로부터의 전방향 주위 환경을 반사시키는 제1 반사부; 상기 제1 반사부와 동축상에 이격되어 위치하며, 제2 시점으로부터의 전방향 주위 환경을 반사시키는 제2 반사부; 및 상기 제1 반사부 및 제2 반사부와 동축상에 위치하며, 상기 제1 반사부 및 제2 반사부로부터 제공받은 각각의 상기 반사된 상들을 포착하여, 상기 포착된 제1 영상 및 제2 영상을 출력하는 영상촬상부를 포함함을 특징으로 한다.
본 발명에 의하면 3차원 복원 해상도가 높고, 장치의 소형화가 가능하며, 두 영상간의 대응점 획득을 용이하게 할 수 있다.-
公开(公告)号：KR1020010084387A
公开(公告)日：2001-09-06
申请号：KR1020000009400
申请日：2000-02-25
Applicant: 한국과학기술원
IPC: G01B11/24
Abstract: PURPOSE: A measuring system for a shape of a three-dimensional welding unit is provided to simplify structure and to measure the shape of the welding unit by using a physical characteristic of a material. CONSTITUTION: A measuring system is formed by a CCD(Charge Coupled Device) camera(30) installed at an ark welding torch(1), a bi-prism(40) located at a front direction of the CCD camera, and an optical filter attached on a lens of the CCD camera. A supporter(10) is installed at an intermediate portion of the welding torch, and a rotating plate(20) is combined to an end portion of the supporter. A protect glass is fixed at a front surface of the prism while installing the optical filter on the lens of the CCD camera. A shape of a molten pool(8) is divided into two images by the bi-prism for being projected to the CCD camera through the optical filter. Herein, a real distance from the CCD camera to each portion of the molten pool by using a distance between corresponding points, internal variable of the camera, diffraction angle and inclined angle of the bi-prism, and relative locations of the bi-prism and the CCD camera. Therefore, a three-dimensional shape of the molten pool is recognized.
Abstract translation: 目的：提供一种用于三维焊接单元形状的测量系统，以简化结构，并通过使用材料的物理特性来测量焊接单元的形状。 构成：测量系统由安装在方向焊枪（1）的CCD（电荷耦合器件）照相机（30），位于CCD照相机前方的双棱镜（40）和光学滤光器 附在CCD相机的镜头上。 支撑件（10）安装在焊炬的中间部分，并且旋转板（20）组合到支撑件的端部。 保护玻璃固定在棱镜的前表面，同时将滤光器安装在CCD摄像机的镜头上。 熔池（8）的形状通过双棱镜被分成两个图像，以通过滤光器投影到CCD照相机。 这里，通过使用相应点之间的距离，相机的内部变量，双棱镜的衍射角和倾斜角以及双棱镜和双棱镜的相对位置，从CCD照相机到熔池的每个部分的实际距离 CCD相机。 因此，认识到熔池的三维形状。
-
-
-
-
-
-
-
-
-
Search Results
100
records
(took 0.027 seconds)
