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。

公开(公告)号：US08731329B2

公开(公告)日：2014-05-20

申请号：US13550031

申请日：2012-07-16

申请人： David P. Simons ,  Daniel Wilk ,  Xue Bai

发明人： David P. Simons ,  Daniel Wilk ,  Xue Bai

IPC分类号： G06K9/36 ,  G06T3/40 ,  H04N1/387

CPC分类号： G06T3/4038 ,  G06T3/0093 ,  G06T5/003 ,  H04N1/3876

摘要： Systems and methods for rolling shutter artifact repair are disclosed. For example, one disclosed method includes the steps of receiving two frames (F0, F2) of a video, identifying a first plurality of features in frame F0 and a second plurality of features in frame F2, determining movements of corresponding features in the first and second pluralities of features, generating a mesh based on the first and second pluralities of features and the movements, and generating a warped frame (F0′) based on the mesh

摘要翻译： 公开了用于滚动快门伪影修复的系统和方法。 例如，一种公开的方法包括以下步骤：接收视频的两个帧（F0，F2），识别帧F0中的第一多个特征和帧F2中的第二多个特征，确定第一和第二帧中相应特征的运动， 第二多个特征，基于第一和第二多个特征和运动生成网格，并且基于网格生成翘曲框架（F0'）

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。

公开(公告)号：US08358691B1

公开(公告)日：2013-01-22

申请号：US12871724

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： H04N7/26 ,  G06K9/00 ,  G06K9/48

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 a variable bandwidth search region. A variable bandwidth search region generation method may be applied to a uniform search region to generate a variable bandwidth search region that reduces the search range for segmentation methods such as a graph cut method. The method may identify parts of the contour that are moving slowly, and reduce the search region bandwidth in those places to stabilize the segmentation. This method may determine a bandwidth for each of a plurality of local windows of an image according to an estimate of how much an object in the image has moved from a previous image. The method may blend the bandwidths for the plurality of local windows to generate a blended map. The method may then generate a variable bandwidth search region for an object according to the blended map.

公开(公告)号：US20120213432A1

公开(公告)日：2012-08-23

申请号：US13448162

申请日：2012-04-16

申请人： Jue Wang ,  Xue Bai

发明人： Jue Wang ,  Xue Bai

IPC分类号： G06K9/34

CPC分类号： G06T7/12 ,  G06T2207/10016 ,  G06T2207/30196

摘要： A method, system, and computer-readable storage medium for automatic segmentation of a video sequence. A segmentation shape prediction and a segmentation color model are determined for a current image of a video sequence based on existing segmentation information for at least one previous image of the video sequence. A segmentation of the current image is automatically generated based on a weighted combination of the segmentation shape prediction and the segmentation color model. The segmentation of the current image is stored in a memory medium.

摘要翻译： 一种用于视频序列的自动分割的方法，系统和计算机可读存储介质。 基于视频序列的至少一个先前图像的现有分割信息，为视频序列的当前图像确定分割形状预测和分割颜色模型。 基于分割形状预测和分割颜色模型的加权组合自动生成当前图像的分割。 当前图像的分割被存储在存储介质中。

公开(公告)号：US20070157192A1

公开(公告)日：2007-07-05

申请号：US11324734

申请日：2005-12-30

申请人： Dorothea Hoefler ,  Jan Jansen ,  Herbert Stegmueller ,  Laicher Karolin ,  Xiaolong Chen ,  Chongyao Wang ,  Xue Bai

发明人： Dorothea Hoefler ,  Jan Jansen ,  Herbert Stegmueller ,  Laicher Karolin ,  Xiaolong Chen ,  Chongyao Wang ,  Xue Bai

IPC分类号： G06F9/44

CPC分类号： G06F8/65

摘要： A data collection and/or monitoring service residing at a client system collects and sends client system information to a backend system. The client system information is used to update a maintained repository of client system information that is associated with software installed at the client system. The maintained repository is used to determine one or more software update recommendations which are sent to the client system. In response to a trigger event, one or more software updates associated with the update recommendations are automatically downloaded and deployed at the client system. The download and deployment of software updates can be scheduled at the client system.

摘要翻译： 驻留在客户端系统的数据收集和/或监控服务收集并发送客户端系统信息到后端系统。 客户端系统信息用于更新与客户端系统上安装的软件相关联的客户端系统信息的维护存储库。 维护的存储库用于确定发送到客户端系统的一个或多个软件更新建议。 响应于触发事件，与客户端系统自动下载并部署与更新建议相关联的一个或多个软件更新。 可以在客户端系统上安排软件更新的下载和部署。

公开(公告)号：US08682063B2

公开(公告)日：2014-03-25

申请号：US12953650

申请日：2010-11-24

申请人： Jue Wang ,  Xue Bai ,  Guillermo R. Sapiro

发明人： Jue Wang ,  Xue Bai ,  Guillermo R. Sapiro

IPC分类号： G06K9/00 ,  G06K9/34

CPC分类号： G06K9/6278 ,  G06T7/194 ,  G06T7/269 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20076 ,  G06T2207/20104

摘要： Methods, apparatus, and computer-readable storage media for dynamic color flow modeling. A dynamic color flow model that incorporates motion estimation in a probabilistic fashion is described. By automatically and adaptively changing model parameters based on the inferred local motion uncertainty, the dynamic color flow model accurately and reliably models the object appearance, and improves the foreground color probability estimation when compared to conventional methods. The dynamic color flow model may, for example, be applied to both foreground and background layers (or to additional layers) for video object segmentation, obtaining significantly improved results when compared to conventional methods.

摘要翻译： 用于动态颜色流建模的方法，装置和计算机可读存储介质。 描述了以概率方式并入运动估计的动态色彩流模型。 通过基于推断的局部运动不确定性自动和自适应地改变模型参数，动态色彩流模型准确可靠地建模对象外观，并与传统方法相比改进了前景色概率估计。 例如，动态色彩流模型可以应用于用于视频对象分割的前景层和背景层（或附加层），与常规方法相比，获得显着改进的结果。

公开(公告)号：US20130129205A1

公开(公告)日：2013-05-23

申请号：US12953650

申请日：2010-11-24

申请人： Jue Wang ,  Xue Bai ,  Guillermo R. Sapiro

发明人： Jue Wang ,  Xue Bai ,  Guillermo R. Sapiro

IPC分类号： G06K9/34

CPC分类号： G06K9/6278 ,  G06T7/194 ,  G06T7/269 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20076 ,  G06T2207/20104

摘要： Methods, apparatus, and computer-readable storage media for dynamic color flow modeling. A dynamic color flow model that incorporates motion estimation in a probabilistic fashion is described. By automatically and adaptively changing model parameters based on the inferred local motion uncertainty, the dynamic color flow model accurately and reliably models the object appearance, and improves the foreground color probability estimation when compared to conventional methods. The dynamic color flow model may, for example, be applied to both foreground and background layers (or to additional layers) for video object segmentation, obtaining significantly improved results when compared to conventional methods.

摘要翻译： 用于动态颜色流建模的方法，装置和计算机可读存储介质。 描述了以概率方式并入运动估计的动态色彩流模型。 通过基于推断的局部运动不确定性自动和自适应地改变模型参数，动态色彩流模型准确可靠地建模对象外观，并与传统方法相比改进了前景色概率估计。 例如，动态色彩流模型可以应用于用于视频对象分割的前景层和背景层（或附加层），与常规方法相比，获得显着改进的结果。

公开(公告)号：US08422775B2

公开(公告)日：2013-04-16

申请号：US13448162

申请日：2012-04-16

申请人： Jue Wang ,  Xue Bai

发明人： Jue Wang ,  Xue Bai

IPC分类号： G06K9/34

CPC分类号： G06T7/12 ,  G06T2207/10016 ,  G06T2207/30196

摘要： A method, system, and computer-readable storage medium for automatic segmentation of a video sequence. A segmentation shape prediction and a segmentation color model are determined for a current image of a video sequence based on existing segmentation information for at least one previous image of the video sequence. A segmentation of the current image is automatically generated based on a weighted combination of the segmentation shape prediction and the segmentation color model. The segmentation of the current image is stored in a memory medium.

摘要翻译： 一种用于视频序列的自动分割的方法，系统和计算机可读存储介质。 基于视频序列的至少一个先前图像的现有分割信息，为视频序列的当前图像确定分割形状预测和分割颜色模型。 基于分割形状预测和分割颜色模型的加权组合自动生成当前图像的分割。 当前图像的分割被存储在存储介质中。

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。