-
Patent Agency Ranking
公开(公告)号：KR1020120072146A
公开(公告)日：2012-07-03
申请号：KR1020100133958
申请日：2010-12-23
Applicant: 한국전자통신연구원
CPC classification number: H04N13/111 , G06T3/00 , G06T15/00 , H04N5/23238 , H04N5/265 , H04N13/128 , H04N13/221 , H04N13/261
Abstract: PURPOSE: A 3D image generating device using a panorama image and a method thereof are provided to simply generate a binocular parallax image about each frame based on a rotative moving picture. CONSTITUTION: An image generating unit(100) generates a rotative moving picture at a fixed location. A panorama image generating unit(200) converts frame images of the rotative moving picture into one panorama image using a cylinder warping function. A panorama binocular parallax image generating unit(300) generates a panorama binocular parallax image about the panoramic image. The panorama binocular parallax image is changed into the binocular parallax image about each frame image using the cylinder warping function.
Abstract translation: 目的：提供使用全景图像的3D图像生成装置及其方法，以简单地基于旋转运动图像生成关于每个帧的双目视差图像。 构成：图像生成单元（100）在固定位置生成旋转运动图像。 全景图像生成单元（200）使用圆筒扭曲功能将旋转运动图像的帧图像转换为一幅全景图像。 全景双目视差图像生成单元（300）生成关于全景图像的全景双目视差图像。 使用圆筒翘曲功能将全景双目视差图像改变为关于每个帧图像的双目视差图像。
-
-
公开(公告)号：KR1020150097251A
公开(公告)日：2015-08-26
申请号：KR1020140018541
申请日：2014-02-18
Applicant: 한국전자통신연구원
Inventor： 장경호
CPC classification number: G06T7/0042 , G06T7/579 , G06T7/73 , G06T2207/10021 , G06T2207/20072 , G06T2207/30232 , G06T2207/30244
Abstract: 다중 영상간의 대응점 정보를 이용하여 카메라를 정렬하는 방법이 개시된다. 본 발명의 일 면에 따른 다중 영상간 대응점을 이용한 카메라 정렬 방법은 다중 카메라 시스템에서 촬영된 영상들 간의 대응관계를 정의하는 단계; 상기 영상들 간의 대응관계와, SFM(Structure From Motion) 알고리즘을 이용하여 카메라의 초기 위치를 추정하는 단계; 상기 카메라의 초기 위치 추정 결과 변경된 영상간의 대응관계를 번들 에지(bundle edge)를 이용하여 재정의하여 최적 에지(Optimal edge)를 생성하는 단계; 및 상기 최적 에지를 기반으로 카메라 위치를 보정하는 단계를 포함한다.
Abstract translation: 公开了使用关于多图像之间的对应点的信息的相机对准方法。 根据本发明的实施例的使用多图像之间的对应点的相机对准方法包括：定义从多相机系统拍摄的图像之间的对应关系的步骤; 使用图像与来自运动（SFM）算法的结构之间的对应关系来估计相机的初始位置的步骤; 通过重新定义由通过使用束边缘的相机的初始位置的估计结果修改的图像之间的对应关系来产生最优边缘的步骤; 以及基于最优边缘来校正摄像机位置的步骤。
-
公开(公告)号：KR1020130102895A
公开(公告)日：2013-09-23
申请号：KR1020120024077
申请日：2012-03-08
Applicant: 한국전자통신연구원
CPC classification number: G06T7/0097 , G06T7/248 , G06T2207/10016 , G06T2207/10024 , G06T2207/20036 , G06T2207/30196
Abstract: PURPOSE: An apparatus and a method for extracting a foreground layer in an image sequence are provided to automatically track a layer area in subsequent frames through user's setting in a start frame in the image sequence in which the depth values of the foreground and the background are discontinuous, thereby extracting the foreground layer area in which the drift phenomenon and the flickering phenomenon are reduced. CONSTITUTION: An image sequence receiving unit (110) receives an original image sequence photographed by a camera. An initial area designating unit (120) designates a plurality of control points on a contour of a layer area in image data for each frame based on a selection input. A layer area tracking unit (130) generates a foreground layer area by connecting the designated control points and tacks the generated foreground layer for each frame. An alpha map generating unit (150) connects respective control point coordinates by a curve generation scheme in all frames in which the layer area is tracked, and generates an alpha map by determining an internal area as the layer area. [Reference numerals] (110) Image sequence receiving unit; (120) Initial area designating unit; (130) Layer area tracking unit; (140) Post processing unit; (150) Alpha map generating unit
Abstract translation: 目的：提供一种用于提取图像序列中的前景层的装置和方法，用于通过用户在前景和背景的深度值的起始帧中的设置来自动跟踪后续帧中的层区域 不连续，从而提取漂移现象和闪烁现象减少的前景层区域。 构成：图像序列接收单元（110）接收由相机拍摄的原始图像序列。 初始区域指定单元（120）基于选择输入，为每个帧的图像数据中的层区域的轮廓上的多个控制点指定。 层区域跟踪单元（130）通过连接指定的控制点并且为每个帧扣留所生成的前景层来生成前景层区域。 阿尔法地图生成单元（150）通过在其中跟踪层区域的所有帧中的曲线生成方案来连接各个控制点坐标，并且通过确定作为层区域的内部区域来生成α图。 （附图标记）（110）图像序列接收单元; （120）初始区指定单位; （130）层面跟踪单元; （140）后处理单元; （150）Alpha地图生成单元
-
公开(公告)号：KR1020130068609A
公开(公告)日：2013-06-26
申请号：KR1020110135902
申请日：2011-12-15
Applicant: 한국전자통신연구원
CPC classification number: G06F17/5009 , H04N2213/002 , H04N2213/005
Abstract: PURPOSE: A stereoscopic image pre-visualization device is provided to offer a simulation result minimizing visual fatigue about a modified and produced part by generating production information about a part difficult to produce when producing a stereoscopic image through a stereoscopic free biz in a pre-production stage and comparing difference from pre-visualization in an image production process. CONSTITUTION: A visual fatigue adjustment unit(110) adjusts visual fatigue with respect to a predetermined scene according to a scenario or a continuity. A depth information generation unit(120) generates depth value information to be reflected in a stereoscopic image related to the scene using the adjusted visual fatigue. A stereoscopic image pre-visualization unit(130) performs a pre-visualization of the stereoscopic image and the information related to the stereoscopic image using the generated depth value information. [Reference numerals] (110) Visual fatigue adjustment unit; (120) Depth information generation unit; (130) Stereoscopic image pre-visualization unit; (140) Power supply unit; (150) Master control unit; (160) Stereoscopic set-up unit; (170) Stereoscopic simulation unit
Abstract translation: 目的：提供一种立体图像预可视化装置，以提供模拟结果，通过在预制作中通过立体视觉生产产生立体图像来生成难以产生的部分的生产信息，从而最小化对经修改和生产的部件的视觉疲劳 并在图像生产过程中比较与预可视化的差异。 构成：视觉疲劳调节单元（110）根据场景或连续性调整相对于预定场景的视觉疲劳。 深度信息生成单元（120）使用调整后的视觉疲劳生成要反映在与场景相关的立体图像中的深度值信息。 立体图像预可视化单元（130）使用生成的深度值信息来执行立体图像的预可视化和与立体图像相关的信息。 （附图标记）（110）视觉疲劳调节单元; （120）深度信息生成部; （130）立体图像预可视化单元; （140）电源单元; （150）主控单元; （160）立体设置单元; （170）立体模拟单元
-
-
-
-
Search Results
25
records
(took 0.019 seconds)
