-
公开(公告)号：US08644609B2
公开(公告)日：2014-02-04
申请号：US13847436
申请日：2013-03-19
Applicant: Microsoft Corporation
Inventor： Carsten Curt Eckard Rother , Toby Sharp
Abstract: A method of up-sampling binary images for segmentation is described. In an embodiment, digital images are down-sampled before segmentation. The resulting initial binary segmentation, which has a lower resolution than the original image, is then up-sampled and smoothed to generate an interim non-binary solution which has a higher resolution than the initial binary segmentation. The final binary segmentation for the image is then computed from the interim non-binary solution based on a threshold. This method does not use the original image data in inferring the final binary segmentation solution from the initial binary segmentation. In an embodiment, the method may be applied to all images and in another embodiment, the method may be used for images which comprise a large number of pixels in total or in single dimension and smaller images may not be down-sampled before segmentation.
Abstract translation: 描述了用于分割的二进制图像的上采样方法。 在一个实施例中，在分割之前对数字图像进行下采样。 然后，所得到的具有比原始图像更低分辨率的初始二进制分割被上采样和平滑以产生具有比初始二进制分割更高分辨率的临时非二进制解。 然后基于阈值从临时非二进制解决方案计算图像的最终二进制分割。 该方法不使用原始图像数据从最初的二进制分割推断最终的二进制分割解决方案。 在一个实施例中，该方法可以应用于所有图像，并且在另一个实施例中，该方法可以用于总共或单个维度中包含大量像素的图像，并且在分割之前可能不会对较小的图像进行下采样。
-
公开(公告)号：US20140208274A1
公开(公告)日：2014-07-24
申请号：US13744823
申请日：2013-01-18
Applicant: MICROSOFT CORPORATION
Inventor： Samuel Gavin Smyth , Peter John Ansell , Christopher Jozef O'Prey , Mitchel Alan Goldberg , Jamie Daniel Joseph Shotton , Toby Sharp , Shahram Izadi , Abigail Jane Sellen , Richard Malcolm Banks , Kenton O'Hara , Richard Harry Robert Harper , Eric John Greveson , David Alexander Butler , Stephen E Hodges
IPC: G06F3/01
CPC classification number: G06F3/017 , G06F3/0304 , G06F3/0426 , G06K9/00389 , G06K9/6219 , G06K9/6278
Abstract: Methods and system for controlling a computing-based device using both input received from a traditional input device (e.g. keyboard) and hand gestures made on or near a reference object (e.g. keyboard). In some examples, the hand gestures may comprise one or more hand touch gestures and/or one or more hand air gestures.
Abstract translation: 用于使用从传统输入设备（例如键盘）接收的输入和在参考对象（例如键盘）上或附近制作的手势来控制基于计算的设备的方法和系统。 在一些示例中，手势可以包括一个或多个手触摸手势和/或一个或多个手空气手势。
-
公开(公告)号：US20160085310A1
公开(公告)日：2016-03-24
申请号：US14494431
申请日：2014-09-23
Applicant: Microsoft Corporation
Inventor： Jamie Daniel Joseph Shotton , Cem Keskin , Jonathan James Taylor , Toby Sharp , Shahram Izadi , Andrew William Fitzgibbon , Pushmeet Kohli , Duncan Paul Robertson
CPC classification number: G06K9/00335 , G06F3/011 , G06F3/017 , G06F3/0304 , G06K9/00342 , G06K9/00355 , G06K9/52 , G06K9/6219 , G06K9/6263 , G06K9/6267 , G06K9/6282 , G06K9/66
Abstract: Tracking hand or body pose from image data is described, for example, to control a game system, natural user interface or for augmented reality. In various examples a prediction engine takes a single frame of image data and predicts a distribution over a pose of a hand or body depicted in the image data. In examples, a stochastic optimizer has a pool of candidate poses of the hand or body which it iteratively refines, and samples from the predicted distribution are used to replace some candidate poses in the pool. In some examples a best candidate pose from the pool is selected as the current tracked pose and the selection processes uses a 3D model of the hand or body.
Abstract translation: 描述从图像数据跟踪手或身体姿势，例如，控制游戏系统，自然用户界面或增强现实。 在各种示例中，预测引擎采用单帧图像数据并且预测在图像数据中描绘的手或身体的姿势上的分布。 在示例中，随机优化器具有反复精炼的手或身体的候选姿势池，并且来自预测分布的样本用于替换池中的一些候选姿势。 在一些示例中，来自池的最佳候选姿势被选择为当前跟踪姿势，并且选择过程使用手或身体的3D模型。
-
公开(公告)号：US09251590B2
公开(公告)日：2016-02-02
申请号：US13749497
申请日：2013-01-24
Applicant: Microsoft Corporation
Inventor： Toby Sharp , Andrew William Fitzgibbon , Shahram Izadi
IPC: A63F9/24 , G06T7/00 , A63F13/00 , G06T19/00 , A63F13/213
CPC classification number: G06T7/0075 , A63F13/00 , A63F13/213 , A63F2009/2435 , G06T7/50 , G06T7/521 , G06T7/593 , G06T7/74 , G06T7/75 , G06T7/80 , G06T19/006 , G06T2207/10024 , G06T2207/10028 , G06T2207/30244
Abstract: Camera pose estimation for 3D reconstruction is described, for example, to enable position and orientation of a depth camera moving in an environment to be tracked for robotics, gaming and other applications. In various embodiments, depth observations from the mobile depth camera are aligned with surfaces of a 3D model of the environment in order to find an updated position and orientation of the mobile depth camera which facilitates the alignment. For example, the mobile depth camera is moved through the environment in order to build a 3D reconstruction of surfaces in the environment which may be stored as the 3D model. In examples, an initial estimate of the pose of the mobile depth camera is obtained and then updated by using a parallelized optimization process in real time.
Abstract translation: 例如，描述了用于3D重建的相机姿态估计，以使得能够在用于机器人，游戏和其他应用的跟踪环境中移动的深度相机的位置和取向。 在各种实施例中，来自移动深度相机的深度观察结果与环境的3D模型的表面对准，以便找到便于对准的移动深度相机的更新的位置和取向。 例如，移动深度相机移动通过环境，以便构建可以存储为3D模型的环境中的表面的3D重建。 在实例中，获得移动深度相机姿态的初始估计，然后通过实时并行优化处理来更新。
-
公开(公告)号：US20140206443A1
公开(公告)日：2014-07-24
申请号：US13749497
申请日：2013-01-24
Applicant: MICROSOFT CORPORATION
Inventor： Toby Sharp , Andrew William Fitzgibbon , Shahram Izadi
CPC classification number: G06T7/0075 , A63F13/00 , A63F13/213 , A63F2009/2435 , G06T7/50 , G06T7/521 , G06T7/593 , G06T7/74 , G06T7/75 , G06T7/80 , G06T19/006 , G06T2207/10024 , G06T2207/10028 , G06T2207/30244
Abstract: Camera pose estimation for 3D reconstruction is described, for example, to enable position and orientation of a depth camera moving in an environment to be tracked for robotics, gaming and other applications. In various embodiments, depth observations from the mobile depth camera are aligned with surfaces of a 3D model of the environment in order to find an updated position and orientation of the mobile depth camera which facilitates the alignment. For example, the mobile depth camera is moved through the environment in order to build a 3D reconstruction of surfaces in the environment which may be stored as the 3D model. In examples, an initial estimate of the pose of the mobile depth camera is obtained and then updated by using a parallelized optimization process in real time.
Abstract translation: 例如，描述了用于3D重建的相机姿态估计，以使得能够在用于机器人，游戏和其他应用的跟踪环境中移动的深度相机的位置和取向。 在各种实施例中，来自移动深度相机的深度观察结果与环境的3D模型的表面对准，以便找到便于对准的移动深度相机的更新的位置和取向。 例如，移动深度相机移动通过环境，以便构建可以存储为3D模型的环境中的表面的3D重建。 在实例中，获得移动深度相机姿态的初始估计，然后通过实时并行优化处理来更新。
-
Patent Agency Ranking
公开(公告)号：US20130208983A1
公开(公告)日：2013-08-15
申请号：US13847436
申请日：2013-03-19
Applicant: Microsoft Corporation
Inventor： Carsten Curt Eckard Rother , Toby Sharp
IPC: G06T7/00
Abstract: A method of up-sampling binary images for segmentation is described. In an embodiment, digital images are down-sampled before segmentation. The resulting initial binary segmentation, which has a lower resolution than the original image, is then up-sampled and smoothed to generate an interim non-binary solution which has a higher resolution than the initial binary segmentation. The final binary segmentation for the image is then computed from the interim non-binary solution based on a threshold. This method does not use the original image data in inferring the final binary segmentation solution from the initial binary segmentation. In an embodiment, the method may be applied to all images and in another embodiment, the method may be used for images which comprise a large number of pixels in total or in single dimension and smaller images may not be down-sampled before segmentation.
Abstract translation: 描述了用于分割的二进制图像的上采样方法。 在一个实施例中，在分割之前对数字图像进行下采样。 然后，所得到的具有比原始图像更低分辨率的初始二进制分割被上采样和平滑以产生具有比初始二进制分割更高分辨率的临时非二进制解。 然后基于阈值从临时非二进制解决方案计算图像的最终二进制分割。 该方法不使用原始图像数据从最初的二进制分割推断最终的二进制分割解决方案。 在一个实施例中，该方法可以应用于所有图像，并且在另一个实施例中，该方法可以用于总共或单个维度中包含大量像素的图像，并且在分割之前可能不会对较小的图像进行下采样。
-
公开(公告)号：US20160086025A1
公开(公告)日：2016-03-24
申请号：US14494385
申请日：2014-09-23
Applicant: Microsoft Corporation
Inventor： Jamie Daniel Joseph Shotton , Toby Sharp , Duncan Paul Robertson , Andrew William Fitzgibbon
CPC classification number: G06K9/00369 , G06F3/017 , G06K9/00134 , G06K9/0014 , G06K9/00147 , G06K9/00208 , G06K9/00241 , G06K9/00335 , G06K9/00375 , G06K9/52 , G06K2009/366 , G06K2209/05 , G06K2209/21 , G06T2207/10004 , G06T2207/30201 , G06T2207/30204
Abstract: Tracking pose of an articulated entity from image data is described, for example, to control a game system, natural user interface or for augmented reality. In various examples a plurality of threads execute on a parallel computing unit, each thread processing data from an individual frame of a plurality of frames of image data captured by an image capture device. In examples, each thread is computing an iterative optimization process whereby a pool of partially optimized candidate poses is being updated. In examples, one or more candidate poses from an individual thread are sent to one or more of the other threads and used to replace or add to candidate poses at the receiving thread(s).
Abstract translation: 例如，描述了从图像数据中的关节实体的跟踪姿态来控制游戏系统，自然用户界面或增强现实。 在各种示例中，多个线程在并行计算单元上执行，每个线程处理来自由图像捕获设备捕获的多个图像数据帧的单独帧的数据。 在示例中，每个线程正在计算迭代优化过程，由此正在更新部分优化的候选姿势池。 在示例中，来自单独线程的一个或多个候选姿势被发送到一个或多个其他线程，并用于在接收线程处替换或添加到候选姿势。
-
公开(公告)号：US08787658B2
公开(公告)日：2014-07-22
申请号：US13847455
申请日：2013-03-19
Applicant: Microsoft Corporation
Inventor： Carsten Curt Eckard Rother , Toby Sharp , Andrew Blake , Vladimir Kolmogorov
IPC: G06K9/34
Abstract: Methods of image segmentation using reduced foreground training data are described. In an embodiment, the foreground and background training data for use in segmentation of an image is determined by optimization of a modified energy function. The modified energy function is the energy function used in image segmentation with an additional term comprising a scalar value. The optimization is performed for different values of the scalar to produce multiple initial segmentations and one of these segmentations is selected based on pre-defined criteria. The training data is then used in segmenting the image. In other embodiments further methods are described: one places an ellipse inside the user-defined bounding box to define the background training data and another uses a comparison of properties of neighboring image elements, where one is outside the user-defined bounding box, to reduce the foreground training data.
Abstract translation: 描述使用减少的前景训练数据的图像分割方法。 在一个实施例中，用于图像分割的前景和背景训练数据通过改进的能量函数的优化来确定。 修改的能量函数是在图像分割中使用的能量函数，附加项包括标量值。 对标量的不同值执行优化以产生多个初始分段，并且基于预定义的标准来选择这些分段之一。 然后训练数据用于分割图像。 在其他实施例中，描述了进一步的方法：一个在用户定义的边界框内放置一个椭圆以定义背景训练数据，另一个使用相邻图像元素的属性的比较，其中一个在用户定义的界限框之外，以减少 前台训练数据。
-
公开(公告)号：US20140126821A1
公开(公告)日：2014-05-08
申请号：US14148404
申请日：2014-01-06
Applicant: Microsoft Corporation
Inventor： Antonio Criminisi , Jamie Daniel Joseph Shotton , Andrew Fitzgibbon , Toby Sharp , Matthew Darius Cook
IPC: G06K9/34
CPC classification number: G06K9/34 , G06K9/38 , G06T7/11 , G06T7/168 , G06T7/187 , G06T7/194 , G06T2207/10016 , G06T2207/20048 , G06T2207/20156 , G06T2207/30196 , H04N13/239
Abstract: Foreground and background image segmentation is described. In an example, a seed region is selected in a foreground portion of an image, and a geodesic distance is calculated from each image element to the seed region. A subset of the image elements having a geodesic distance less than a threshold is determined, and this subset of image elements are labeled as foreground. In another example, an image element from an image showing at least a user, a foreground object in proximity to the user, and a background is applied to trained decision trees to obtain probabilities of the image element representing one of these items, and a corresponding classification assigned to the image element. This is repeated for each image element. Image elements classified as belonging to the user are labeled as foreground, and image elements classified as foreground objects or background are labeled as background.
Abstract translation: 描述了前景和背景图像分割。 在一个示例中，在图像的前景部分中选择种子区域，并且从每个图像元素计算到种子区域的测地距离。 确定具有小于阈值的测地距离的图像元素的子集，并且该图像元素的子集被标记为前景。 在另一示例中，将来自显示至少用户的图像，邻近用户的前景对象和背景的图像元素应用于经过训练的决策树，以获得表示这些项目之一的图像元素的概率，以及相应的 分类到图像元素的分类。 对于每个图像元素重复这一点。 分类为属于用户的图像元素被标记为前景，并且被分类为前景对象或背景的图像元素被标记为背景。
-
公开(公告)号：US20130216127A1
公开(公告)日：2013-08-22
申请号：US13847455
申请日：2013-03-19
Applicant: Microsoft Corporation
Inventor： Carsten Curt Eckard Rother , Toby Sharp , Andrew Blake , Vladimir Kolmogorov
IPC: G06K9/34
Abstract: Methods of image segmentation using reduced foreground training data are described. In an embodiment, the foreground and background training data for use in segmentation of an image is determined by optimization of a modified energy function. The modified energy function is the energy function used in image segmentation with an additional term comprising a scalar value. The optimization is performed for different values of the scalar to produce multiple initial segmentations and one of these segmentations is selected based on pre-defined criteria. The training data is then used in segmenting the image. In other embodiments further methods are described: one places an ellipse inside the user-defined bounding box to define the background training data and another uses a comparison of properties of neighboring image elements, where one is outside the user-defined bounding box, to reduce the foreground training data.
Abstract translation: 描述使用减少的前景训练数据的图像分割方法。 在一个实施例中，用于图像分割的前景和背景训练数据通过改进的能量函数的优化来确定。 修改的能量函数是在图像分割中使用的能量函数，附加项包括标量值。 对标量的不同值执行优化以产生多个初始分段，并且基于预定义的标准来选择这些分段之一。 然后训练数据用于分割图像。 在其他实施例中，描述了进一步的方法：一个在用户定义的边界框内放置一个椭圆以定义背景训练数据，另一个使用相邻图像元素的属性的比较，其中一个在用户定义的界限框之外，以减少 前台训练数据。
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.018 seconds)
