专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20120121202A1 Methods and Apparatus for De-blurring Images Using Lucky Frames 有权
标题翻译：使用幸运框架去模糊图像的方法和装置
公开(公告)号：US20120121202A1
公开(公告)日：2012-05-17
申请号：US12957298
申请日：2010-11-30
申请人： Jue Wang , David P. Simons , Seungyong Lee , Sunghyun Cho
发明人： Jue Wang , David P. Simons , Seungyong Lee , Sunghyun Cho
IPC分类号： G06K9/40
CPC分类号： G06T5/003 , G06T5/20 , G06T2207/10016 , G06T2207/20092 , H04N5/23254 , H04N5/23277
摘要： A sharp frame and a blurred frame are detected from among a plurality of frames. A blur kernel is estimated. The blur kernel represents a motion-transform between the sharp frame and the blurred frame. Using the blur kernel, a static region measure for the sharp frame and the blurred frame is estimated. A de-blurred frame is generated by replacing one or more pixels of the blurred frame as indicated by the static region measure.
摘要翻译：从多个帧中检测到清晰帧和模糊帧。估计一个模糊内核。模糊核心代表了锐利帧和模糊帧之间的运动变换。使用模糊内核，估计了锐帧和模糊帧的静态区域测量。通过替换由静态区域度量所指示的模糊帧的一个或多个像素来生成去模糊帧。

2. 发明授权

US08532421B2 Methods and apparatus for de-blurring images using lucky frames 有权
标题翻译：使用幸运帧去除图像的方法和装置
公开(公告)号：US08532421B2
公开(公告)日：2013-09-10
申请号：US12957298
申请日：2010-11-30
申请人： Jue Wang , David P. Simons , Seungyong Lee , Sunghyun Cho
发明人： Jue Wang , David P. Simons , Seungyong Lee , Sunghyun Cho
IPC分类号： G06K9/40
CPC分类号： G06T5/003 , G06T5/20 , G06T2207/10016 , G06T2207/20092 , H04N5/23254 , H04N5/23277
摘要： A sharp frame and a blurred frame are detected from among a plurality of frames. A blur kernel is estimated. The blur kernel represents a motion-transform between the sharp frame and the blurred frame. Using the blur kernel, a static region measure for the sharp frame and the blurred frame is estimated. A de-blurred frame is generated by replacing one or more pixels of the blurred frame as indicated by the static region measure.
摘要翻译：从多个帧中检测到清晰帧和模糊帧。估计一个模糊内核。模糊核心代表了锐帧和模糊帧之间的运动变换。使用模糊内核，估计了锐帧和模糊帧的静态区域测量。通过替换由静态区域度量所指示的模糊帧的一个或多个像素来生成去模糊帧。

3. 发明授权

US08411980B1 Removing motion blur from unaligned multiple blurred images 有权
标题翻译：从未对齐的多个模糊图像中删除运动模糊
公开(公告)号：US08411980B1
公开(公告)日：2013-04-02
申请号：US13034461
申请日：2011-02-24
申请人： Jue Wang , Sunghyun Cho , Seungyong Lee
发明人： Jue Wang , Sunghyun Cho , Seungyong Lee
IPC分类号： G06K9/48 , G06K9/40 , H04N5/228 , H04N9/74
CPC分类号： G06T5/003 , G06T2207/10016 , G06T2207/20201
摘要： Various embodiments of methods and apparatus for removing motion blur are disclosed. A homography is estimated for each of a plurality of images. Two or more images of the plurality are unaligned. An estimated latent image for the plurality of images selected for recovery of the latent image is deconvolved. A point spread function for the each of the plurality of images is calculated. The homography for the each of the plurality of images, the estimated latent image, and the point spread function for the each of the plurality of images are iteratively updated until the homography for each of the plurality of images stabilizes. The iteratively updating includes updating one of the homography for the each of the plurality of images, the estimated latent image, and the point spread function for the each of the plurality of images while holding the remainder constant.
摘要翻译：公开了用于去除运动模糊的方法和装置的各种实施例。对于多个图像中的每一个估计单应性。多个图像的两个或更多个是未对齐的。解压缩为选择用于恢复潜像的多个图像的估计潜像。计算多个图像中的每一个的点扩散函数。迭代地更新多个图像中的每一个的每个图像的单应性，估计的潜像和点扩散函数，直到多个图像中的每个图像的单对应性稳定为止。迭代更新包括在保持余数恒定的同时更新多个图像中的每一个的多个图像中的每一个的单应性，估计潜像和点扩散函数中的每一个。

4. 发明申请

US20130058587A1 Motion Deblurring for Text Images 有权
标题翻译：文本图像的运动解像
公开(公告)号：US20130058587A1
公开(公告)日：2013-03-07
申请号：US13475483
申请日：2012-05-18
申请人： Jue Wang , Hojin Cho , Jen-Chan Chien , Sarah A. Kong , Seungyong Lee
发明人： Jue Wang , Hojin Cho , Jen-Chan Chien , Sarah A. Kong , Seungyong Lee
IPC分类号： G06K9/40
CPC分类号： G06T5/003
摘要： Various embodiments of methods and apparatus for motion deblurring in text images are disclosed. In one embodiment, a threshold-based text prediction for a blurred image is generated. A point spread function for the blurred image is estimated. A result of the threshold-based text prediction function is deconvolved based on the point spread function. The generating, estimating, and deconvolving are iterated at a plurality of scales, and a final deconvolution of a result of the iteratively deconvolving is executed.
摘要翻译：公开了用于文本图像中的运动去模糊的方法和装置的各种实施例。在一个实施例中，生成用于模糊图像的基于阈值的文本预测。估计模糊图像的点扩散函数。基于阈值的文本预测函数的结果基于点扩散函数被去卷积。生成，估计和解卷积以多个尺度迭代，并且执行迭代去卷积的结果的最终去卷积。

5. 发明授权

US08792718B2 Temporal matte filter for video matting 有权
标题翻译：用于视频消光的时间无光泽滤光片
公开(公告)号：US08792718B2
公开(公告)日：2014-07-29
申请号：US13538712
申请日：2012-06-29
申请人： Xue Bai , Jue Wang , David P. Simons
发明人： Xue Bai , Jue Wang , David P. Simons
IPC分类号： G06K9/34 , G06K9/48 , G06K9/40
CPC分类号： H04N5/21 , G06T7/11 , G06T7/174 , G06T7/194 , G06T2207/10016 , G06T2207/10024 , G06T2207/20104 , G06T2207/20161
摘要： Methods and apparatus for temporal matte filtering. Temporal matte filtering methods are described that improve the temporal coherence of alpha mattes for a video sequence while maintaining the matte structures on individual frames. The temporal matte filter may implement a level-set-based matte averaging method. In the level-set-based matte averaging method, two or more input alpha mattes are obtained. Level set curves are generated for the two or more alpha mattes. An averaged level set is computed from the two or more level sets according to a distance-transform-based technique. A temporally smoothed alpha matte may then be reconstructed by interpolating pixel alpha values between the inner and outer level set curves of the averaged level set. The alpha mattes can be optionally warped towards a center frame according to an optical flow technique before the averaging operation performed by the temporal matte filter.
摘要翻译：时间哑光滤波的方法和装置。描述了时间无光泽滤波方法，其改善了视频序列的α遮罩的时间相干性，同时保持了单个帧上的消光结构。时间哑光滤波器可以实现基于电平集的无光均衡方法。在基于水平集的遮罩平均方法中，获得两个或更多个输入alpha遮罩。为两个或更多个alpha遮罩生成级别设置曲线。根据基于距离变换的技术，从两个或多个级别集计算平均级别集合。然后可以通过在平均水平集的内部和外部水平设置曲线之间内插像素α值来重构时间平滑的阿尔法无光泽。在由时间哑光滤波器执行的平均化操作之前，可以根据光学流技术，将alpha哑光可选地朝向中心框架弯曲。

6. 发明授权

US08520975B2 Methods and apparatus for chatter reduction in video object segmentation using optical flow assisted gaussholding 有权
标题翻译：使用光流辅助高斯视频对象分割的颤振减少的方法和装置
公开(公告)号：US08520975B2
公开(公告)日：2013-08-27
申请号：US12871719
申请日：2010-08-30
申请人： Jue Wang , David P. Simons , Daniel M. Wilk , Xue Bai
发明人： Jue Wang , David P. Simons , Daniel M. Wilk , Xue Bai
IPC分类号： G06K9/34 , G06K9/00 , G06K9/62 , G06K9/20 , G06K9/36 , H04N1/387 , H04N5/225 , H04N7/12 , H04N11/02 , H04N11/04 , H04B1/66 , G09G5/00
CPC分类号： G06T7/20 , G06K9/6277 , G06T7/12 , G06T7/143 , G06T7/149 , G06T2207/10024 , G06T2207/20121 , G06T2207/20124 , G06T2207/30196
摘要： Systems, methods, and computer-readable storage media for chatter reduction in video object segmentation using optical flow assisted gaussholding. An optical flow assisted gaussholding method may be applied to segmentation masks generated for a video sequence. For each frame of at least some frames in a video sequence, for each of one or more other frames prior to and one or more other frames after the current frame, optical flow is computed for the other frame in relation to the current frame and used to warp the contour of the segmentation mask of the other frame to generate warped segmentation mask for the other frames. The weighted average of the warpedsegmentation masks and the segmentation mask of the current frame is then computed; this weighted average may be blurred spatially, for example using a Gaussian filter. The initial smoothed mask may be thresholded to produce a binary smoothed mask.
摘要翻译：系统，方法和计算机可读存储介质，用于使用光流辅助高斯跟踪的视频对象分割中的抖动减少。可以将光流辅助高斯跟踪方法应用于为视频序列生成的分割掩码。对于视频序列中的至少一些帧的每帧，对于在当前帧之前和之后的一个或多个其他帧之前的一个或多个其他帧中的每一帧，针对当前帧针对另一帧计算光流，并使用以扭曲另一帧的分割掩模的轮廓以产生其他帧的翘曲分割掩码。然后计算翘曲分割蒙版的加权平均值和当前帧的分割蒙版; 该加权平均值可能在空间上模糊，例如使用高斯滤波器。初始平滑掩模可以被阈值化以产生二进制平滑掩模。

7. 发明申请

US20140002746A1 Temporal Matte Filter for Video Matting 有权
标题翻译：视频消光的时域滤光片
公开(公告)号：US20140002746A1
公开(公告)日：2014-01-02
申请号：US13538712
申请日：2012-06-29
申请人： Xue Bai , Jue Wang , David P. Simons
发明人： Xue Bai , Jue Wang , David P. Simons
IPC分类号： H04N5/21
CPC分类号： H04N5/21 , G06T7/11 , G06T7/174 , G06T7/194 , G06T2207/10016 , G06T2207/10024 , G06T2207/20104 , G06T2207/20161
摘要： Methods and apparatus for temporal matte filtering. Temporal matte filtering methods are described that improve the temporal coherence of alpha mattes for a video sequence while maintaining the matte structures on individual frames. The temporal matte filter may implement a level-set-based matte averaging method. In the level-set-based matte averaging method, two or more input alpha mattes are obtained. Level set curves are generated for the two or more alpha mattes. An averaged level set is computed from the two or more level sets according to a distance-transform-based technique. A temporally smoothed alpha matte may then be reconstructed by interpolating pixel alpha values between the inner and outer level set curves of the averaged level set. The alpha mattes can be optionally warped towards a center frame according to an optical flow technique before the averaging operation performed by the temporal matte filter.
摘要翻译：时间哑光滤波的方法和装置。描述了时间无光泽滤波方法，其改善了视频序列的α遮罩的时间相干性，同时保持了单个帧上的消光结构。时间哑光滤波器可以实现基于电平集的无光均衡方法。在基于水平集的遮罩平均方法中，获得两个或更多个输入alpha遮罩。为两个或更多个alpha遮罩生成级别设置曲线。根据基于距离变换的技术，从两个或多个级别集计算平均级别集合。然后可以通过在平均水平集的内部和外部水平设置曲线之间内插像素α值来重构时间平滑的阿尔法无光泽。在由时间哑光滤波器执行的平均化操作之前，可以根据光学流技术，将alpha哑光可选地朝向中心框架弯曲。

8. 发明授权

US08290253B1 Method and apparatus for applying Gaussian Mixture Models to local image patches using an adaptive color lookup table 有权
标题翻译：使用自适应颜色查找表将高斯混合模型应用于局部图像补丁的方法和装置
公开(公告)号：US08290253B1
公开(公告)日：2012-10-16
申请号：US12609590
申请日：2009-10-30
申请人： Jue Wang , David P. Simons , Xue Bai
发明人： Jue Wang , David P. Simons , Xue Bai
IPC分类号： G06K9/00
CPC分类号： G06K9/6221 , G06K9/4652 , G06T7/11 , G06T7/149
摘要： A method, system, and computer-readable storage medium for applying Gaussian Mixture Models (GMMs) to local image patches using an adaptive color lookup table. Per-channel color quantization may be performed to find representative colors for a local image patch. Each combination of the representative values corresponds to a representative color. The probabilities of the representative colors may be computed using a local GMM color model and stored to corresponding entries in an adaptive color lookup table. For every pixel in an image patch, the closest representative color may be found, and the corresponding probability may be retrieved from the lookup table and used for the pixel. The method may, for example, be applied to each local window in a method for automatically determining segmentation in a digital video image sequence to calculate the foreground probabilities for the pixels in a propagated classifier via a GMM.
摘要翻译：一种用于使用自适应颜色查找表将高斯混合模型（GMM）应用于本地图像块的方法，系统和计算机可读存储介质。可以执行每通道颜色量化以找到局部图像贴片的代表性颜色。代表值的每个组合对应于代表性颜色。代表颜色的概率可以使用本地GMM颜色模型计算并存储到自适应颜色查找表中的相应条目。对于图像补丁中的每个像素，可以找到最接近的代表颜色，并且可以从查找表中检索相应的概率并将其用于该像素。例如，该方法可以在用于自动确定数字视频图像序列中的分割的方法中应用于每个局部窗口，以通过GMM计算传播分类器中的像素的前景概率。

9. 发明授权

US08897562B2 Adaptive trimap propagation for video matting 有权
标题翻译：用于视频消光的自适应色差传播
公开(公告)号：US08897562B2
公开(公告)日：2014-11-25
申请号：US13538718
申请日：2012-06-29
申请人： Xue Bai , Jue Wang , David P. Simons
发明人： Xue Bai , Jue Wang , David P. Simons
IPC分类号： G06K9/34
CPC分类号： G06T7/269 , G06T7/194 , G06T2207/10016
摘要： Methods and apparatus for adaptive trimap propagation. Methods are described that allow a trimap to be propagated from one frame to the next in a temporally coherent way. A radius-based method propagates automatically computed local trimap radii from frame to frame. A mesh-based method employs pins on the binary segmentation boundary and a mesh generated for the unknown region; the pins are tracked from one frame to the next according to an optical flow technique, the mesh is deformed from one frame to the next according to the movement of the pins, and the adaptive trimap is then warped according to the deformed mesh. These methods can be used separately, or the first method can be used to propagate some regions of the adaptive trimap, and the second method can be used to propagate other regions of the adaptive trimap.
摘要翻译：自适应微分法传播的方法和装置。描述了允许以时间上相干的方式从一个帧传播到下一个帧的方法。基于半径的方法自动传播计算的局部微分半径从帧到帧。基于网格的方法使用二进制分割边界上的引脚和为未知区域生成的网格; 根据光流技术，针脚从一帧到下一个跟踪，根据销的移动，网格从一帧变形到下一帧，然后根据变形的网格扭曲自适应微调。这些方法可以单独使用，或者第一种方法可以用于传播自适应微调的一些区域，第二种方法可以用于传播自适应微调的其他区域。

10. 发明申请

US20130121577A1 Methods and Apparatus for Chatter Reduction in Video Object Segmentation Using Optical Flow Assisted Gaussholding 有权
标题翻译：使用光流辅助Gaussholding的视频对象分割中抖动减少的方法和装置
公开(公告)号：US20130121577A1
公开(公告)日：2013-05-16
申请号：US12871719
申请日：2010-08-30
申请人： Jue Wang , David P. Simons , Daniel M. Wilk , Xue Bai
发明人： Jue Wang , David P. Simons , Daniel M. Wilk , Xue Bai
IPC分类号： G06K9/34
CPC分类号： G06T7/20 , G06K9/6277 , G06T7/12 , G06T7/143 , G06T7/149 , G06T2207/10024 , G06T2207/20121 , G06T2207/20124 , G06T2207/30196
摘要： Systems, methods, and computer-readable storage media for chatter reduction in video object segmentation using optical flow assisted gaussholding. An optical flow assisted gaussholding method may be applied to segmentation masks generated for a video sequence. For each frame of at least some frames in a video sequence, for each of one or more other frames prior to and one or more other frames after the current frame, optical flow is computed for the other frame in relation to the current frame and used to warp the contour of the segmentation mask of the other frame to generate warped segmentation mask for the other frames. The weighted average of the warpedsegmentation masks and the segmentation mask of the current frame is then computed; this weighted average may be blurred spatially, for example using a Gaussian filter. The initial smoothed mask may be thresholded to produce a binary smoothed mask.
摘要翻译：系统，方法和计算机可读存储介质，用于使用光流辅助高斯跟踪的视频对象分割中的抖动减少。光流辅助高斯保留方法可以应用于为视频序列生成的分割掩码。对于视频序列中的至少一些帧的每帧，对于在当前帧之前和之后的一个或多个其他帧之前的一个或多个其他帧中的每一帧，针对当前帧针对另一帧计算光流，并使用以扭曲另一帧的分割掩模的轮廓以产生其他帧的翘曲分割掩码。然后计算翘曲分割蒙版的加权平均值和当前帧的分割蒙版; 该加权平均值可能在空间上模糊，例如使用高斯滤波器。初始平滑掩模可以被阈值化以产生二进制平滑掩模。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式