-
公开(公告)号：KR102046521B1
公开(公告)日：2019-12-04
申请号：KR1020190013856
申请日：2019-02-01
Applicant: 한국전자통신연구원 , 경희대학교 산학협력단
IPC: H04N19/107 , H04N19/124 , H04N19/105 , H04N19/176 , H04N19/593
-
公开(公告)号：KR101877802B1
公开(公告)日：2018-07-13
申请号：KR1020110064250
申请日：2011-06-30
Applicant: 한국전자통신연구원
CPC classification number: H04N13/349 , H04N13/128 , H04N13/139 , H04N13/161
Abstract: 3차원디스플레이영상을위한영상확대장치및 방법이제공된다. 영상확대장치는, 원본시점영상들에서 3차원디스플레이영상의확대영역에대응하는검출영역을검출하는영역지정검출부, 확대영역의확대비율을결정하는확대비율결정부및 검출영역을부분다중화하는부분다중화부를포함한다. 영상확대장치는 3차원디스플레이에서해상도의저하없는영상확대를가능하게한다.
-
公开(公告)号：KR101868017B1
公开(公告)日：2018-06-18
申请号：KR1020120049304
申请日：2012-05-09
Applicant: 한국전자통신연구원
IPC: H04N13/00
Abstract: 본발명에따른스테레오매칭방법은, 최대변이값을기반으로, 기준영상내의기준블록에대응하는탐색대상영상내의복수의탐색대상블록을결정하는단계, 복수의탐색대상블록각각에대해, 기준블록과의블록단위상관도값을도출하는단계, 블록단위상관도값 중에서최대상관도값을결정하고, 최대상관도값에대응하는탐색대상픽셀을기준픽셀에대한매칭픽셀로결정하는단계및 매칭픽셀에대응하는변이값을기준픽셀의변이값으로결정하는단계를포함한다. 본발명에의하면, 스테레오매칭효율이향상될수 있다.
-
公开(公告)号：KR1020170059266A
公开(公告)日：2017-05-30
申请号：KR1020150163420
申请日：2015-11-20
Applicant: 한국전자통신연구원
IPC: G06K9/00
CPC classification number: G01C3/08 , G06K9/00295 , G06K9/00335 , G06K9/03 , G06K9/3241 , G06K9/4671 , G06K9/52 , G06K9/6267 , G06K2009/3291 , G06T7/292 , G06T7/60 , G06T2207/10016 , G06T2207/30201 , G06T2207/30221 , G06T2207/30241 , H04N5/247
Abstract: 본발명은객체추적방법및 그방법을수행하는객체추적장치에관한것으로, 객체추적방법은전역카메라를이용하여객체탐색영역내에다수의관심객체의위치를추출하고, 추출된관심객체중 사용자에의해선택된관심객체를식별하며, 식별된관심객체에대한추적오류를판단및 보정하는방법에관한것이다.
Abstract translation: 物体追踪方法和用于执行该方法的物体追踪装置技术领域本发明涉及一种用于执行该方法的物体追踪方法和物体追踪装置，该物体追踪方法使用全局相机提取物体检索区域中的多个相关物体 识别选定的感兴趣对象，并确定和校正所识别的感兴趣对象的跟踪误差。
-
公开(公告)号：KR1020140113066A
公开(公告)日：2014-09-24
申请号：KR1020130027970
申请日：2013-03-15
Applicant: 한국전자통신연구원
IPC: H04N13/00
CPC classification number: H04N13/271 , H04N13/111
Abstract: The present invention relates to a method and an apparatus for generating a multi-view image based on shielded area information. The method for generating a multi-view image, according to the present invention, comprises the steps of: calculating a variation between the left and right images; determining a weight based on the variation information; and generating a virtual viewpoint image by applying the weight.
Abstract translation: 本发明涉及一种基于屏蔽区域信息生成多视点图像的方法和装置。 根据本发明的用于生成多视点图像的方法包括以下步骤：计算左图像和右图像之间的变化; 基于变化信息确定权重; 以及通过应用所述权重来生成虚拟视点图像。
-
Patent Agency Ranking
公开(公告)号：KR1020140001358A
公开(公告)日：2014-01-07
申请号：KR1020120068649
申请日：2012-06-26
Applicant: 한국전자통신연구원 , 광운대학교 산학협력단
CPC classification number: H04N13/128 , H04N13/122 , H04N13/271
Abstract: The present invention relates to a stereo image processing method and, more specifically, to an image processing method for filtering an occlusion area in a stereo image. The method comprises the following steps of: calculating an optical flow based disparity from a stereo image; obtaining feature point based disparity saliency from the stereo image; generating a disparity saliency map based on the calculated optical flow disparity (saliency) and the feature point based disparity saliency; and filtering an occlusion area on the disparity saliency map. In the step of filtering an occlusion area on the disparity saliency map, a disparity is once calculated based on one side of the stereo image and a disparity is calculated again based on the other side of the stereo image. If a difference between two disparities of a particular pixel is greater than a given limit, the particular pixel is detected as an occlusion area pixel, and the disparity value of the particular pixel on the disparity saliency map is corrected to have a minimum value among disparity values between the particular pixel and adjacent pixels. [Reference numerals] (S100) Image input (stereo image); (S110) Optical flow based disparity (saliency); (S120) Feature point based disparity saliency; (S130) Disparity saliency map; (S140) Occlusion area filtering
Abstract translation: 立体图像处理方法技术领域本发明涉及立体图像处理方法，更具体地，涉及用于对立体图像中的遮挡区域进行滤波的图像处理方法。 该方法包括以下步骤：从立体图像计算基于光流的视差; 从立体图像获得基于特征点的视差显着性; 基于计算的光流差异（显着性）和基于特征点的视差显着性产生视差显着图; 并在差异显着图上过滤遮挡区域。 在对视差显着图进行遮挡区域的滤波的步骤中，基于立体图像的一侧一次计算视差，并且基于立体图像的另一侧再次计算视差。 如果特定像素的两个差异之间的差异大于给定极限，则将特定像素检测为遮挡区域像素，并且将视差显着图上的特定像素的视差值校正为具有视差之间的最小值 特定像素和相邻像素之间的值。 （附图标记）（S100）图像输入（立体图像）; （S110）基于光流的差异（显着性）; （S120）基于特征点的视差显着性; （S130）差异显着图; （S140）闭塞区域过滤
-
公开(公告)号：KR1020130068182A
公开(公告)日：2013-06-26
申请号：KR1020110134674
申请日：2011-12-14
Applicant: 한국전자통신연구원
CPC classification number: H04N13/349 , H04N21/440245 , H04N2013/0085 , H04N2013/0092
Abstract: PURPOSE: A method of extracting a salient region and an apparatus using the same are provided to detect a salient region in a scene for maintenance of depth perception when generating a multi-view image, thereby improving depth perception of a stereo image. CONSTITUTION: A method of extracting a salient region by a salient region determining apparatus comprises the steps of: segmenting a stereo image(S130); producing a sparse disparity(S150); producing an average disparity of each segment(S160); normalizing and storing the average disparity of each segment(S165); producing an average motion of each segment(S170); and producing a saliency of each segment(S180). [Reference numerals] (AA) Input right and left stereo images; (S100) Extract a salient region and calculate variation between salient regions; (S110) Calculate illumination-based low-resolution stereo image variation; (S120) Calculate the movement between frames for each right and left image; (S130) Divide a stereo image and extract a segment; (S140) Combine variations; (S145) Remove an outlier; (S150) Calculate and store a sparse variation; (S160) Calculate an average variation of a segment; (S165) Normalize and store an average variation of each segment; (S170) Calculate, normalize and store an average movement of each segment; (S180) Calculate an overall importance of each segment
Abstract translation: 目的：提供一种提取突出区域的方法和使用该方法的装置，以便在生成多视点图像时检测场景中的显着区域以维持深度感知，从而改善立体图像的深度感知。 构成：通过突出区域确定装置提取突出区域的方法包括以下步骤：分割立体图像（S130）; 产生稀疏差异（S150）; 产生每个片段的平均差异（S160）; 归一化和存储每个段的平均差异（S165）; 产生每个段的平均运动（S170）; 并产生每个细分市场的显着性（S180）。 （附图标记）（AA）输入左右立体图像; （S100）提取突出区域并计算显着区域之间的变化; （S110）计算基于照明的低分辨率立体图像变化; （S120）计算每张左右图像的帧间运动; （S130）分割立体图像并提取片段; （S140）组合变体; （S145）移除异常值; （S150）计算和存储稀疏变化; （S160）计算段的平均变化; （S165）归一化并存储每个段的平均变化; （S170）计算，归一化和存储每个段的平均移动; （S180）计算每个细分的整体重要性
-
公开(公告)号：KR1020130003155A
公开(公告)日：2013-01-09
申请号：KR1020110064250
申请日：2011-06-30
Applicant: 한국전자통신연구원
CPC classification number: H04N13/349 , H04N13/128 , H04N13/139 , H04N13/161 , H04N13/00 , G06T3/40
Abstract: PURPOSE: An image expansion device in a 3D display and a method thereof are provided to expand an image without degradation of resolution in the 3D display. CONSTITUTION: An area designation detection unit(410) detects an detection area corresponding to an expansion area in a 3D display image from original view images. An expansion rate determination unit(420) determines an expansion rate in the expansion area. A partial multiplexing unit(430) multiplexes an area excluding the detection area in the original view images with predetermined resolution. [Reference numerals] (410) Area designation detection unit; (420) Expansion rate determination unit; (430) Partial multiplexing unit; (AA) Partially expanded 3D display image
Abstract translation: 目的：提供3D显示器中的图像扩展装置及其方法，以在3D显示中不会降低分辨率的情况下展开图像。 构成：区域指定检测单元（410）从原始视图图像检测与3D显示图像中的扩展区域对应的检测区域。 膨胀率确定单元（420）确定膨胀区域中的膨胀率。 部分复用单元（430）以预定分辨率复用原始视野图像中的检测区域之外的区域。 （附图标记）（410）区域指定检测单元; （420）扩展速率确定单元; （430）部分多路复用单元; （AA）部分展开的3D显示图像
-
公开(公告)号：KR1020120125970A
公开(公告)日：2012-11-19
申请号：KR1020120049304
申请日：2012-05-09
Applicant: 한국전자통신연구원
IPC: H04N13/00
CPC classification number: H04N13/128 , H04N13/106
Abstract: PURPOSE: A stereo matching method and an apparatus thereof are provided to increase the efficiency of stereo matching by obtaining depth information and disparity value in real time. CONSTITUTION: A stereo matching apparatus calculates correlation about each disparity value candidate(S510). The stereo matching apparatus deducts the disparity value of the reference pixel(S520). If the disparity value is deducted, the stereo matching apparatus generates depth information based on a camera parameter(S530). [Reference numerals] (S510) Calculating correlation about each disparity value candidate; (S520) Deducting the disparity value of the reference pixel; (S530) Generating depth information based on a camera parameter
Abstract translation: 目的：提供立体匹配方法及其装置，通过实时获取深度信息和视差值来提高立体匹配的效率。 构成：立体匹配装置计算关于每个视差值候选的相关性（S510）。 立体匹配装置扣除参考像素的视差值（S520）。 如果扣除视差值，则立体匹配装置基于相机参数生成深度信息（S530）。 （参考号）（S510）计算关于每个视差值候选的相关性; （S520）扣除参考像素的视差值; （S530）根据摄像机参数生成深度信息
-
公开(公告)号：KR1020120069799A
公开(公告)日：2012-06-29
申请号：KR1020100131099
申请日：2010-12-21
Applicant: 한국전자통신연구원
CPC classification number: H04N13/20 , H04N13/128 , G06T15/00 , G06T15/10 , G06T17/00 , G06T17/005 , G06T17/10 , G06T17/20 , H04N13/139 , H04N13/161 , H04N13/271 , H04N2213/005
Abstract: PURPOSE: A depth sensitivity controlling method, an apparatus thereof, a terminal including the same, and an operation method are provided to detect a user location based on a depth sensor and to control depth sensitivity of a three-dimensional image which is rendered according to the detected user location. CONSTITUTION: A color and depth image obtaining unit(10) obtains a color and a depth image of a user. A user location detecting unit(70) detects a user location based on the obtained image of the user. A depth sensitivity controlling unit(80) calculates the range of the maximum depth and the minimum depth in a three-dimensional image. The depth sensitivity controlling unit controls stereoscopic image generation interval.
Abstract translation: 目的：提供一种深度敏感度控制方法，其装置，包括该深度敏感度控制方法的终端和操作方法，用于基于深度传感器来检测用户位置，并且控制根据深度传感器呈现的三维图像的深度敏感度。 检测到的用户位置。 构成：颜色和深度图像获取单元（10）获得用户的颜色和深度图像。 用户位置检测单元（70）基于获得的用户图像来检测用户位置。 深度敏感度控制单元（80）计算三维图像中的最大深度和最小深度的范围。 深度敏感度控制单元控制立体图像生成间隔。
-
-
-
-
-
-
-
-
-
Search Results
128
records
(took 0.029 seconds)
