-
公开(公告)号：US08861836B2
公开(公告)日：2014-10-14
申请号：US13007411
申请日：2011-01-14
申请人： Jianing Wei , Alexander Berestov , Chuen-Chien Lee , Xue Tu , Xiaoling Wang
发明人： Jianing Wei , Alexander Berestov , Chuen-Chien Lee , Xue Tu , Xiaoling Wang
CPC分类号： H04N13/261 , G06K9/00234
摘要： A method for converting a 2D image into a 3D image includes receiving the 2D image; determining whether the received 2D image is a portrait, wherein the portrait can be a face portrait or a non-face portrait; if the received 2D image is determined to be a portrait, creating a disparity between a left eye image and a right eye image based on a local gradient and a spatial location; generating the 3D image based on the created disparity; and outputting the generated 3D image.
摘要翻译： 将2D图像转换为3D图像的方法包括：接收2D图像; 确定所接收的2D图像是否是肖像，其中所述肖像可以是脸部肖像或非人脸肖像; 如果接收到的2D图像被确定为肖像，则基于局部渐变和空间位置创建左眼图像和右眼图像之间的视差; 基于创建的差异生成3D图像; 并输出所生成的3D图像。
-
公开(公告)号：US08472746B2
公开(公告)日：2013-06-25
申请号：US13042182
申请日：2011-03-07
申请人： Jianing Wei , Xue Tu , Xiaoling Wang , Alexander Berestov
发明人： Jianing Wei , Xue Tu , Xiaoling Wang , Alexander Berestov
IPC分类号： G06K9/40
CPC分类号： G06K9/40
摘要： A method for generating a depth map for a 2D image includes receiving the 2D image; analyzing content of the received 2D image; determining a depth map based on a result of the content analysis; refining the determined depth map using an edge-preserving and noise reducing smoothing filter; and providing the refined depth map.
摘要翻译： 用于生成2D图像的深度图的方法包括：接收2D图像; 分析所接收的2D图像的内容; 基于内容分析的结果确定深度图; 使用边缘保持和降噪平滑滤波器来精化确定的深度图; 并提供精细的深度图。
-
13.发明申请Method And Apparatus For Converting A Two-Dimensional Image Into A Three-Dimensional Stereoscopic Image 有权用于将二维图像转换为三维立体图像的方法和装置公开(公告)号：US20120086775A1
公开(公告)日：2012-04-12
申请号：US12900053
申请日：2010-10-07
申请人： Soo Hyun Bae , Farhan Baqai , Alexander Berestov
发明人： Soo Hyun Bae , Farhan Baqai , Alexander Berestov
CPC分类号： H04N13/261 , G06T15/40 , H04N13/122 , H04N2013/0081
摘要： A method and apparatus for converting a two-dimensional image into a stereoscopic three-dimensional image. In one embodiment, a computer implemented method of converting a two-dimensional image into a stereoscopic three-dimensional image including for each pixel within a right eye image, identifying at least one corresponding pixel from a left eye image and determining a depth and an intensity value for the each pixel within the right eye image using the at least one corresponding pixel, wherein the depth value is stored in a right eye depth map and the intensity value is stored in the right eye image and inpainting at least one occluded region within the right eye image using the right eye depth map.
摘要翻译： 一种用于将二维图像转换成立体三维图像的方法和装置。 在一个实施例中，一种计算机实现的方法，其将二维图像转换为包括右眼图像内的每个像素的立体三维图像，从左眼图像识别至少一个相应像素，并确定深度和强度 使用所述至少一个对应像素在所述右眼图像内的每个像素的值，其中所述深度值存储在右眼深度图中，并且所述强度值被存储在所述右眼图像中并且在所述至少一个遮挡区域内修复 右眼图像使用右眼深度图。
-
公开(公告)号：US08144190B2
公开(公告)日：2012-03-27
申请号：US12470443
申请日：2009-05-21
申请人： Alexander Berestov
发明人： Alexander Berestov
IPC分类号： H04N13/02
CPC分类号： H04N13/239 , H04N13/214
摘要： In one embodiment, an apparatus for three-dimensional (3-D) image acquisition can include: (i) first and second lenses configured to receive light from a scene; (ii) first, second, third, and fourth sensors; (iii) a first beam splitter arranged proximate to the first lens, where the first beam splitter can provide a first split beam to the first sensor, and a second split beam to the second sensor; and (iv) a second beam splitter arranged proximate to the second lens, where the second beam splitter can provide a third split beam to the third sensor, and a fourth and split beam to the fourth sensor. For example, the sensors can include charge-coupled devices (CCDs) or CMOS sensors.
摘要翻译： 在一个实施例中，用于三维（3-D）图像采集的装置可以包括：（i）被配置为从场景接收光的第一和第二透镜; （ii）第一，第二，第三和第四传感器; （iii）靠近所述第一透镜布置的第一分束器，其中所述第一分束器可以向所述第一传感器提供第一分束，以及向所述第二传感器提供第二分束; 和（iv）靠近第二透镜布置的第二分束器，其中第二分束器可以向第三传感器提供第三分束，以及向第四传感器提供第四分束。 例如，传感器可以包括电荷耦合器件（CCD）或CMOS传感器。
-
15.发明授权公开(公告)号：US08077205B2
公开(公告)日：2011-12-13
申请号：US11818795
申请日：2007-06-14
申请人： Alexander Berestov , Ted J. Cooper
发明人： Alexander Berestov , Ted J. Cooper
CPC分类号： H04N1/6033
摘要： A method of and system for calibrating an imaging device is described herein. An iterative method that attempts to find the best calibration parameters conditional upon an error metric is used. Regression is used to estimate values in a color space where the calibration is performed based upon a training data set. More calculation steps are required than would be for a regression in raw RGB space, but the convergence is faster in the color space where the calibration is performed, and the advantages using boundary conditions in the color space is able to provide improved calibration.
摘要翻译： 本文描述了用于校准成像装置的方法和系统。 使用迭代方法，尝试以错误度量为条件找到最佳校准参数。 回归用于估计基于训练数据集执行校准的色彩空间中的值。 需要比原始RGB空间中的回归更多的计算步骤，但是在执行校准的色彩空间中的收敛更快，并且使用颜色空间中的边界条件的优点能够提供改进的校准。
-
公开(公告)号：US20110188773A1
公开(公告)日：2011-08-04
申请号：US13042182
申请日：2011-03-07
申请人： Jianing Wei , Xue Tu , Xiaoling Wang , Alexander Berestov
发明人： Jianing Wei , Xue Tu , Xiaoling Wang , Alexander Berestov
IPC分类号： G06K9/40
CPC分类号： G06K9/40
摘要： A method for generating a depth map for a 2D image includes receiving the 2D image; analyzing content of the received 2D image; determining a depth map based on a result of the content analysis; refining the determined depth map using an edge-preserving and noise reducing smoothing filter; and providing the refined depth map.
摘要翻译： 用于生成2D图像的深度图的方法包括：接收2D图像; 分析所接收的2D图像的内容; 基于内容分析的结果确定深度图; 使用边缘保持和降噪平滑滤波器来精化确定的深度图; 并提供精细的深度图。
-
17.发明申请THREE OR HIGHER DIMENSIONAL GRAPHICAL USER INTERFACE FOR TV MENU AND DOCUMENT NAVIGATION 审中-公开三维或更高尺寸的图形用户界面，用于电视菜单和文件导航公开(公告)号：US20110179376A1
公开(公告)日：2011-07-21
申请号：US12691609
申请日：2010-01-21
IPC分类号： G06F3/048
CPC分类号： G06F3/017 , G06F3/0482
摘要： A three or more dimensional (3+D) graphical user interface (GUI) uses detected three dimensional (3D) hand movements or other input devices to navigate a displayed two dimensional (2D), three dimensional, or 3+D representation of a corresponding menu, document, or data set. Specific hand motions may be used that correspond to navigational commands, including, but not limited to: up, down, left, right, select, exit, back, new search, start, close, and deselect. The GUI displays two initially perpendicular axes, with additional axes sufficiently off angle that their navigation is apparent, rather than hidden. The 3+D GUI may be used for navigating large complex data sets, such as search results, document library storage, or simpler data sets, such as TV menus, music selection, photographs, videos, etc.
摘要翻译： 三维或更多维（3 + D）图形用户界面（GUI）使用检测到的三维（3D）手迹或其它输入设备来导航所显示的对应的二维（2D），三维或三维 菜单，文档或数据集。 可以使用与导航命令相对应的特定手动，包括但不限于：向上，向下，向左，向右，选择，退出，返回，新搜索，开始，关闭和取消选择。 GUI显示两个初始垂直轴，附加轴足够偏离角度，导航显而易见，而不是隐藏。 3 + D GUI可用于导航大型复杂数据集，例如搜索结果，文档库存储或更简单的数据集，如电视菜单，音乐选择，照片，视频等。
-
公开(公告)号：US07773257B2
公开(公告)日：2010-08-10
申请号：US11591662
申请日：2006-10-30
IPC分类号： G06F15/00
摘要： A method of evaluating halo artifacts is described herein. The method utilizes a pattern of color patches, a color space and color difference metrics to analyze color changes which correlate to the amount of halo. The pattern of color patches is utilized in the CIE L*a*b* color space to determine an area of patch unaffected by halo of the pattern of color patches. After the area of patch unaffected by halo is determined, a Reference Value is computed by averaging the CIE L*a*b* color for the area of patch unaffected by halo. Then an Artifact Value is calculated either by averaging the CIE L*a*b* color for the area outside the area of patch unaffected by halo but before the margin or by averaging the CIE L*a*b* color on the edge of the patch. Once these values are determined, the halo quantity is calculated.
摘要翻译： 本文描述了评估晕轮假象的方法。 该方法利用颜色图案，色彩空间和色差度量来分析与光环数量相关的颜色变化。 彩色图案在CIE L * a * b *颜色空间中被使用，以确定不受色块图案的光晕影响的贴片区域。 在不受光晕影响的贴片区域之后，通过对不受光环影响的贴片区域的CIE L * a * b *颜色进行平均来计算参考值。 然后通过平均CIE L * a * b *颜色来计算人造物价值，该CIE L * a * b *颜色用于不受光环影响但在边缘之前但通过平均CIE L * a * b *颜色的区域之外的区域 补丁。 一旦确定了这些值，就计算光晕量。
-
公开(公告)号：US20090237493A1
公开(公告)日：2009-09-24
申请号：US12470443
申请日：2009-05-21
申请人： Alexander Berestov
发明人： Alexander Berestov
IPC分类号： H04N13/02
CPC分类号： H04N13/239 , H04N13/214
摘要： In one embodiment, an apparatus for three-dimensional (3-D) image acquisition can include: (i) first and second lenses configured to receive light from a scene; (ii) first, second, third, and fourth sensors; (iii) a first beam splitter arranged proximate to the first lens, where the first beam splitter can provide a first split beam to the first sensor, and a second split beam to the second sensor; and (iv) a second beam splitter arranged proximate to the second lens, where the second beam splitter can provide a third split beam to the third sensor, and a fourth and split beam to the fourth sensor. For example, the sensors can include charge-coupled devices (CCDs) or CMOS sensors.
摘要翻译： 在一个实施例中，用于三维（3-D）图像采集的装置可以包括：（i）被配置为从场景接收光的第一和第二透镜; （ii）第一，第二，第三和第四传感器; （iii）靠近所述第一透镜布置的第一分束器，其中所述第一分束器可以向所述第一传感器提供第一分束，以及向所述第二传感器提供第二分束; 和（iv）靠近第二透镜布置的第二分束器，其中第二分束器可以向第三传感器提供第三分束，以及向第四传感器提供第四分束。 例如，传感器可以包括电荷耦合器件（CCD）或CMOS传感器。
-
公开(公告)号：US20070223057A1
公开(公告)日：2007-09-27
申请号：US11386230
申请日：2006-03-21
申请人： Alexander Berestov
发明人： Alexander Berestov
IPC分类号： H04N1/38
CPC分类号： G06T5/002 , G06T7/44 , G06T2207/20192
摘要： A noise prediction scheme provides a method of predicting an output noise variance resulting from a spatial filtering transformation. For a given input image signal with a known input noise variance, a periodic model is developed. The periodic model defines periodic boundary conditions for the input image signal based on the principal that the input image signal is repeated in each direction. In this manner, pixel values are defined about either side of the input image signal boundaries in either one, two, or three dimensions. A spatial filtering transformation includes convoluting the input image signal with an impulse response of a filter. Autocavariances at different points in time or lags of the input image signal are also determined. The number of autocovariances is determined by the nature of the spatial filtering transformation. The noise prediction scheme predicts an output noise variance resulting from the spatial filtering transformation based on the input noise variance, the autocovariances, and the periodic boundary conditions of the input image signal.
摘要翻译： 噪声预测方案提供了一种预测由空间滤波变换产生的输出噪声方差的方法。 对于具有已知输入噪声方差的给定输入图像信号，开发周期模型。 周期模型基于输入图像信号在每个方向上重复的原理来定义输入图像信号的周期边界条件。 以这种方式，像素值被定义为输入图像信号边界的任何一侧在一维，二维或三维中。 空间滤波变换包括用输入图像信号与滤波器的脉冲响应进行卷积。 还确定了不同时间点或输入图像信号滞后的自动变化。 自动协方差的数量由空间滤波变换的性质决定。 噪声预测方案基于输入图像信号的输入噪声方差，自协方差和周期边界条件来预测由空间滤波变换产生的输出噪声方差。
-
-
-
-
-
-
-
-
-
搜索结果
72 条记录 (耗时 0.024 秒)
