公开(公告)号：US08401242B2

公开(公告)日：2013-03-19

申请号：US13017587

申请日：2011-01-31

申请人： Richard Newcombe ,  Shahram Izadi ,  David Molyneaux ,  Otmar Hilliges ,  David Kim ,  Jamie Daniel Joseph Shotton ,  Pushmeet Kohli ,  Andrew Fitzgibbon ,  Stephen Edward Hodges ,  David Alexander Butler

发明人： Richard Newcombe ,  Shahram Izadi ,  David Molyneaux ,  Otmar Hilliges ,  David Kim ,  Jamie Daniel Joseph Shotton ,  Pushmeet Kohli ,  Andrew Fitzgibbon ,  Stephen Edward Hodges ,  David Alexander Butler

IPC分类号： G06K9/00

CPC分类号： A63F13/00 ,  A63F13/06 ,  A63F2300/1087 ,  A63F2300/69 ,  G06K9/00 ,  G06K9/00664 ,  G06T7/251 ,  G06T7/30 ,  G06T2207/10028 ,  G06T2207/10048 ,  G06T2207/30244

摘要： Real-time camera tracking using depth maps is described. In an embodiment depth map frames are captured by a mobile depth camera at over 20 frames per second and used to dynamically update in real-time a set of registration parameters which specify how the mobile depth camera has moved. In examples the real-time camera tracking output is used for computer game applications and robotics. In an example, an iterative closest point process is used with projective data association and a point-to-plane error metric in order to compute the updated registration parameters. In an example, a graphics processing unit (GPU) implementation is used to optimize the error metric in real-time. In some embodiments, a dense 3D model of the mobile camera environment is used.

摘要翻译： 描述使用深度图的实时相机跟踪。 在一个实施例中，深度图帧由移动深度相机以每秒20帧的速度捕获，并且用于实时动态地更新一组注册参数，这些参数指定移动深度相机已经移动。 在实例中，实时相机跟踪输出用于计算机游戏应用和机器人。 在一个例子中，迭代最近点处理与投影数据关联和点到平面误差度量一起使用，以便计算更新的注册参数。 在一个例子中，使用图形处理单元（GPU）实现来实时优化误差度量。 在一些实施例中，使用移动照相机环境的密集3D模型。

公开(公告)号：US20120239174A1

公开(公告)日：2012-09-20

申请号：US13050858

申请日：2011-03-17

申请人： Jamie Daniel Joseph Shotton ,  Pushmeet Kohli ,  Ross Brook Girshick ,  Andrew Fitzgibbon ,  Antonio Criminisi

发明人： Jamie Daniel Joseph Shotton ,  Pushmeet Kohli ,  Ross Brook Girshick ,  Andrew Fitzgibbon ,  Antonio Criminisi

IPC分类号： G06F19/00 ,  G06K9/62 ,  G06K9/68

CPC分类号： G06F3/017 ,  G06K9/00362 ,  G06N5/025

摘要： Predicting joint positions is described, for example, to find joint positions of humans or animals (or parts thereof) in an image to control a computer game or for other applications. In an embodiment image elements of a depth image make joint position votes so that for example, an image element depicting part of a torso may vote for a position of a neck joint, a left knee joint and a right knee joint. A random decision forest may be trained to enable image elements to vote for the positions of one or more joints and the training process may use training images of bodies with specified joint positions. In an example a joint position vote is expressed as a vector representing a distance and a direction of a joint position from an image element making the vote. The random decision forest may be trained using a mixture of objectives.

摘要翻译： 例如，描述关节位置的描述是为了在图像中找到人或动物（或其部分）的联合位置，以控制计算机游戏或用于其他应用。 在一个实施例中，深度图像的图像元素进行联合位置投票，使得例如描绘躯干的一部分的图像元素可以投射颈部关节，左膝关节和右膝关节的位置。 可以对随机决策林进行训练，以使图像元素能够对一个或多个关节的位置进行投票，并且训练过程可以使用具有指定关节位置的身体的训练图像。 在一个例子中，联合立场表决被表示为表示从投票的图像元素的联合位置的距离和方向的向量。 可以使用目标混合来训练随机决策林。

公开(公告)号：US20120194650A1

公开(公告)日：2012-08-02

申请号：US13017518

申请日：2011-01-31

申请人： Shahram Izadi ,  David Molyneaux ,  Otmar Hilliges ,  David Kim ,  Jamie Daniel Joseph Shotton ,  Stephen Edward Hodges ,  David Alexander Butler ,  Andrew Fitzgibbon ,  Pushmeet Kohli

发明人： Shahram Izadi ,  David Molyneaux ,  Otmar Hilliges ,  David Kim ,  Jamie Daniel Joseph Shotton ,  Stephen Edward Hodges ,  David Alexander Butler ,  Andrew Fitzgibbon ,  Pushmeet Kohli

IPC分类号： H04N13/02

CPC分类号： G06T7/55 ,  G01B9/08 ,  G01B11/22 ,  H04N5/23229 ,  H04N5/247 ,  H04N5/33 ,  H04N5/332 ,  H04N13/271

摘要： Systems and methods for reducing interference between multiple infra-red depth cameras are described. In an embodiment, the system comprises multiple infra-red sources, each of which projects a structured light pattern into the environment. A controller is used to control the sources in order to reduce the interference caused by overlapping light patterns. Various methods are described including: cycling between the different sources, where the cycle used may be fixed or may change dynamically based on the scene detected using the cameras; setting the wavelength of each source so that overlapping patterns are at different wavelengths; moving source-camera pairs in independent motion patterns; and adjusting the shape of the projected light patterns to minimize overlap. These methods may also be combined in any way. In another embodiment, the system comprises a single source and a mirror system is used to cast the projected structured light pattern around the environment.

摘要翻译： 描述了用于减少多个红外深度摄像机之间的干扰的系统和方法。 在一个实施例中，系统包括多个红外源，每个红外源将结构化的光图案投射到环境中。 控制器用于控制源，以减少由重叠的光图案引起的干扰。 描述了各种方法，包括：在不同的源之间循环，其中使用的周期可以是固定的，或者可以基于使用相机检测的场景动态地改变; 设置每个源的波长，使得重叠图案处于不同的波长; 以独立运动模式移动源摄像机对; 并调整投影光图案的形状以最小化重叠。 这些方法也可以以任何方式组合。 在另一个实施例中，系统包括单个源，并且使用镜子系统将投射的结构化光图案围绕环境投射。

公开(公告)号：US20110228976A1

公开(公告)日：2011-09-22

申请号：US12727787

申请日：2010-03-19

申请人： Andrew Fitzgibbon ,  Jamie Shotton ,  Mat Cook ,  Richard Moore ,  Mark Finnochio

发明人： Andrew Fitzgibbon ,  Jamie Shotton ,  Mat Cook ,  Richard Moore ,  Mark Finnochio

IPC分类号： G06K9/62 ,  G06K9/00

CPC分类号： G06K9/6256 ,  G06K9/00335 ,  G06K9/6206

摘要： Synthesized body images are generated for a machine learning algorithm of a body joint tracking system. Frames from motion capture sequences are retargeted to several different body types, to leverage the motion capture sequences. To avoid providing redundant or similar frames to the machine learning algorithm, and to provide a compact yet highly variegated set of images, dissimilar frames can be identified using a similarity metric. The similarity metric is used to locate frames which are sufficiently distinct, according to a threshold distance. For realism, noise is added to the depth images based on noise sources which a real world depth camera would often experience. Other random variations can be introduced as well. For example, a degree of randomness can be added to retargeting. For each frame, the depth image and a corresponding classification image, with labeled body parts, are provided. 3-D scene elements can also be provided.

摘要翻译： 为身体关节跟踪系统的机器学习算法生成合成身体图像。 来自运动捕捉序列的帧被重定向到几种不同的身体类型，以利用运动捕捉序列。 为了避免向机器学习算法提供冗余或相似的帧，并且为了提供紧凑但高度变化的图像集合，可以使用相似性度量来识别不同的帧。 相似性度量用于根据阈值距离定位足够明显的帧。 对于现实主义，基于真实世界深度相机经常会遇到的噪声源，将噪声添加到深度图像。 也可以引入其他随机变化。 例如，可以添加一定程度的随机性来重定向。 对于每个帧，提供深度图像和具有标记的身体部分的相应分类图像。 也可以提供3-D场景元素。

公开(公告)号：US07671891B2

公开(公告)日：2010-03-02

申请号：US11751932

申请日：2007-05-22

申请人： Andrew Fitzgibbon ,  Antonio Criminisi ,  Srikumar Ramalingam

发明人： Andrew Fitzgibbon ,  Antonio Criminisi ,  Srikumar Ramalingam

IPC分类号： H04N17/00

CPC分类号： H04N17/002 ,  G06K9/209

摘要： Online camera calibration methods have been proposed whereby calibration information is extracted from the images that the system captures during normal operation and is used to continually update system parameters. However, such existing methods do not cope well with structure-poor scenes having little texture and/or 3D structure such as in a home or office environment. By considering camera families (a set of cameras that are manufactured at least partially in a common manner) it is possible to provide calibration methods which are suitable for use with structure-poor scenes. A prior distribution of camera parameters for a family of cameras is estimated and used to obtain accurate calibration results for individual cameras of the camera family even where the calibration is carried out online, in an environment which is structure-poor.

摘要翻译： 已经提出在线摄像机校准方法，其中从正常操作期间系统捕获的图像中提取校准信息，并用于不断地更新系统参数。 然而，这样的现有方法不能很好地解决具有很少纹理和/或3D结构的结构差的场景，例如在家庭或办公环境中。 通过考虑相机系列（一组至少部分以一般方式制造的相机），可以提供适合与结构不良的场景一起使用的校准方法。 对于一系列相机的相机参数的事先分配被估计并用于获得相机系列的各个照相机的精确校准结果，即使在结构差的环境中在线执行校准。

公开(公告)号：US08587583B2

公开(公告)日：2013-11-19

申请号：US13017690

申请日：2011-01-31

申请人： Richard Newcombe ,  Shahram Izadi ,  David Molyneaux ,  Otmar Hilliges ,  David Kim ,  Jamie Daniel Joseph Shotton ,  Stephen Edward Hodges ,  David Alexander Butler ,  Andrew Fitzgibbon ,  Pushmeet Kohli

发明人： Richard Newcombe ,  Shahram Izadi ,  David Molyneaux ,  Otmar Hilliges ,  David Kim ,  Jamie Daniel Joseph Shotton ,  Stephen Edward Hodges ,  David Alexander Butler ,  Andrew Fitzgibbon ,  Pushmeet Kohli

IPC分类号： G06T17/05 ,  G06T19/00

CPC分类号： G06T17/00 ,  G06T2200/08

摘要： Three-dimensional environment reconstruction is described. In an example, a 3D model of a real-world environment is generated in a 3D volume made up of voxels stored on a memory device. The model is built from data describing a camera location and orientation, and a depth image with pixels indicating a distance from the camera to a point in the environment. A separate execution thread is assigned to each voxel in a plane of the volume. Each thread uses the camera location and orientation to determine a corresponding depth image location for its associated voxel, determines a factor relating to the distance between the associated voxel and the point in the environment at the corresponding location, and updates a stored value at the associated voxel using the factor. Each thread iterates through an equivalent voxel in the remaining planes of the volume, repeating the process to update the stored value.

摘要翻译： 描述了三维环境重建。 在一个示例中，在由存储在存储器件上的体素组成的3D体积中生成真实世界环境的3D模型。 该模型是从描述相机位置和方向的数据构建的，以及具有指示从相机到环境中的点的距离的像素的深度图像。 单独的执行线程被分配给卷的平面中的每个体素。 每个线程使用摄像机位置和方向来确定其相关体素的相应深度图像位置，确定与相关体素和相应位置处的环境中的点之间的距离有关的因子，并更新相关联的体素的存储值 体素使用因子。 每个线程遍历卷的剩余平面中的等效体素，重复更新存储值的过程。

公开(公告)号：US08379919B2

公开(公告)日：2013-02-19

申请号：US12770394

申请日：2010-04-29

申请人： Matthew Bronder ,  Oliver Williams ,  Ryan Geiss ,  Andrew Fitzgibbon ,  Jamie Shotton

发明人： Matthew Bronder ,  Oliver Williams ,  Ryan Geiss ,  Andrew Fitzgibbon ,  Jamie Shotton

IPC分类号： G06K9/00

CPC分类号： G06K9/00375 ,  G06F3/017 ,  G06K9/342 ,  G06K9/6219 ,  H04N19/436

摘要： Systems and methods are disclosed for identifying objects captured by a depth camera by condensing classified image data into centroids of probability that captured objects are correctly identified entities. Output exemplars are processed to detect spatially localized clusters of non-zero probability pixels. For each cluster, a centroid is generated, generally resulting in multiple centroids for each differentiated object. Each centroid may be assigned a confidence value, indicating the likelihood that it corresponds to a true object, based on the size and shape of the cluster, as well as the probabilities of its constituent pixels.

摘要翻译： 公开了系统和方法，用于通过将分类的图像数据聚焦成捕获的对象被正确识别的实体的概率的质心来识别由深度相机捕获的对象。 处理输出样本以检测非零概率像素的空间局部集群。 对于每个聚类，生成质心，通常会为每个不同对象产生多个质心。 可以根据群集的大小和形状以及其组成像素的概率为每个质心分配置信度值，指示其对应于真实对象的可能性。

公开(公告)号：US20120195471A1

公开(公告)日：2012-08-02

申请号：US13017626

申请日：2011-01-31

申请人： Richard NEWCOMBE ,  Shahram IZADI ,  Otmar HILLIGES ,  David KIM ,  David MOLYNEAUX ,  Jamie Daniel Joseph SHOTTON ,  Pushmeet KOHLI ,  Andrew FITZGIBBON ,  Stephen Edward HODGES ,  David Alexander BUTLER

发明人： Richard NEWCOMBE ,  Shahram IZADI ,  Otmar HILLIGES ,  David KIM ,  David MOLYNEAUX ,  Jamie Daniel Joseph SHOTTON ,  Pushmeet KOHLI ,  Andrew FITZGIBBON ,  Stephen Edward HODGES ,  David Alexander BUTLER

IPC分类号： G06K9/00

CPC分类号： G06T7/215 ,  G06T7/194 ,  G06T2207/10028 ,  G06T2207/30244

摘要： Moving object segmentation using depth images is described. In an example, a moving object is segmented from the background of a depth image of a scene received from a mobile depth camera. A previous depth image of the scene is retrieved, and compared to the current depth image using an iterative closest point algorithm. The iterative closest point algorithm includes a determination of a set of points that correspond between the current depth image and the previous depth image. During the determination of the set of points, one or more outlying points are detected that do not correspond between the two depth images, and the image elements at these outlying points are labeled as belonging to the moving object. In examples, the iterative closest point algorithm is executed as part of an algorithm for tracking the mobile depth camera, and hence the segmentation does not add substantial additional computational complexity.

摘要翻译： 描述使用深度图像来移动物体分割。 在一个示例中，从从移动深度相机接收的场景的深度图像的背景中分割移动物体。 检索场景的先前深度图像，并使用迭代最近点算法与当前深度图像进行比较。 迭代最近点算法包括对当前深度图像和先前深度图像之间对应的一组点的确定。 在确定点集合期间，检测到一个或多个在两个深度图像之间不对应的离开点，并且将这些离散点处的图像元素标记为属于移动对象。 在示例中，迭代最近点算法作为用于跟踪移动深度相机的算法的一部分被执行，因此分割不会增加实质的额外的计算复杂度。

公开(公告)号：US20120194517A1

公开(公告)日：2012-08-02

申请号：US13017729

申请日：2011-01-31

申请人： Shahram Izadi ,  David Molyneaux ,  Otmar Hilliges ,  David Kim ,  Jamie Daniel Joseph Shotton ,  Pushmeet Kohli ,  Andrew Fitzgibbon ,  Stephen Edward Hodges ,  David Alexander Butler

发明人： Shahram Izadi ,  David Molyneaux ,  Otmar Hilliges ,  David Kim ,  Jamie Daniel Joseph Shotton ,  Pushmeet Kohli ,  Andrew Fitzgibbon ,  Stephen Edward Hodges ,  David Alexander Butler

IPC分类号： G06T17/00

CPC分类号： G06F3/011 ,  A63F13/65 ,  A63F2300/1087 ,  A63F2300/6009 ,  G06T7/20 ,  G06T17/00 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/30244

摘要： Use of a 3D environment model in gameplay is described. In an embodiment, a mobile depth camera is used to capture a series of depth images as it is moved around and a dense 3D model of the environment is generated from this series of depth images. This dense 3D model is incorporated within an interactive application, such as a game. The mobile depth camera is then placed in a static position for an interactive phase, which in some examples is gameplay, and the system detects motion of a user within a part of the environment from a second series of depth images captured by the camera. This motion provides a user input to the interactive application, such as a game. In further embodiments, automatic recognition and identification of objects within the 3D model may be performed and these identified objects then change the way that the interactive application operates.

摘要翻译： 描述了在游戏中使用3D环境模型。 在一个实施例中，移动深度相机被用来捕获一系列深度图像，因为它被移动，并且从该系列深度图像生成环境的密集3D模型。 这种密集的3D模型被并入在诸如游戏的交互式应用中。 然后将移动深度相机放置在用于交互式相位的静态位置，在一些示例中为游戏画面，并且系统从相机拍摄的第二系列深度图像中检测环境部分内的用户的运动。 该运动向诸如游戏的交互式应用提供用户输入。 在另外的实施例中，可以执行3D模型内的对象的自动识别和识别，并且这些识别的对象然后改变交互式应用程序的操作方式。

公开(公告)号：US20120194516A1

公开(公告)日：2012-08-02

申请号：US13017690

申请日：2011-01-31

申请人： Richard Newcombe ,  Shahram Izadi ,  David Molyneaux ,  Otmar Hilliges ,  David Kim ,  Jamie Daniel Joseph Shotton ,  Stephen Edward Hodges ,  David Alexander Butler ,  Andrew Fitzgibbon ,  Pushmeet Kohli

发明人： Richard Newcombe ,  Shahram Izadi ,  David Molyneaux ,  Otmar Hilliges ,  David Kim ,  Jamie Daniel Joseph Shotton ,  Stephen Edward Hodges ,  David Alexander Butler ,  Andrew Fitzgibbon ,  Pushmeet Kohli

IPC分类号： G06T17/00

CPC分类号： G06T17/00 ,  G06T2200/08

摘要： Three-dimensional environment reconstruction is described. In an example, a 3D model of a real-world environment is generated in a 3D volume made up of voxels stored on a memory device. The model is built from data describing a camera location and orientation, and a depth image with pixels indicating a distance from the camera to a point in the environment. A separate execution thread is assigned to each voxel in a plane of the volume. Each thread uses the camera location and orientation to determine a corresponding depth image location for its associated voxel, determines a factor relating to the distance between the associated voxel and the point in the environment at the corresponding location, and updates a stored value at the associated voxel using the factor. Each thread iterates through an equivalent voxel in the remaining planes of the volume, repeating the process to update the stored value.

摘要翻译： 描述了三维环境重建。 在一个示例中，在由存储在存储器件上的体素组成的3D体积中生成真实世界环境的3D模型。 该模型是从描述相机位置和方向的数据构建的，以及具有指示从相机到环境中的点的距离的像素的深度图像。 单独的执行线程被分配给卷的平面中的每个体素。 每个线程使用摄像机位置和方向来确定其相关体素的相应深度图像位置，确定与相关体素和相应位置处的环境中的点之间的距离有关的因子，并更新相关联的体素的存储值 体素使用因素。 每个线程遍历卷的剩余平面中的等效体素，重复更新存储值的过程。