-
公开(公告)号：US06668080B1
公开(公告)日：2003-12-23
申请号：US09399897
申请日：1999-09-21
IPC分类号： G06K934
CPC分类号： G06T17/10 , G06T7/55 , G06T2200/08
摘要： Automated layer extraction from 2D images making up a 3D scene, and automated image pixel assignment to layers, to provide for scene modeling, is disclosed. In one embodiment, a computer-implemented method determines a number of planes, or layers, and assigns pixels to the planes. The method can determine the number of planes by first determining the high-entropy pixels of the images, and then determining a 1-plane through a predetermined n-plane estimation, such as via a robust estimation, and a most likely x-plane estimation, where x is between 1 and n, such as via a Bayesian approach. Furthermore, the method can assign pixels via an iterative EM approach based on classifying criteria.
摘要翻译： 公开了从组成3D场景的2D图像中自动层提取，以及自动图像像素分配给图层，以提供场景建模。 在一个实施例中，计算机实现的方法确定多个平面或层，并将像素分配给平面。 该方法可以通过首先确定图像的高熵像素来确定平面的数量，然后通过预定的n平面估计（诸如通过鲁棒估计）和最可能的x平面估计来确定1平面 ，其中x在1和n之间，例如通过贝叶斯方法。 此外，该方法可以通过基于分类标准的迭代EM方法分配像素。
-
公开(公告)号：US06487304B1
公开(公告)日：2002-11-26
申请号：US09334857
申请日：1999-06-16
申请人： Richard S. Szeliski
发明人： Richard S. Szeliski
IPC分类号： G06K900
CPC分类号： G06K9/20 , G06K2209/40 , G06T7/246 , G06T2207/10012 , G06T2207/10021 , H04N13/189 , H04N2013/0081 , H04N2013/0085
摘要： A system and process for computing motion or depth estimates from multiple images. In general terms this is accomplished by associating a depth or motion map with each input image (or some subset of the images equal or greater than two), rather that computing a single map for all the images. In addition, consistency between the estimates associated with different images is ensured. More particularly, this involves minimizing a three-part cost function, which consists of an intensity (or color) compatibility constraint, a motion/depth compatibility constraint, and a flow smoothness constraint. In addition, a visibility term is added to the intensity (or color) compatibility and motion/depth compatibility constraints to prevent the matching of pixels into areas that are occluded. In operation, the cost function is computed in two phases. During an initializing phase, the motion or depth for each image being examined are estimated independently. Since there are not yet any estimates for other frames to employ in the calculation, the motion or depth compatibility term is ignored. In addition, no visibilities are computed and it is assumed all pixels are visible. Once an initial set of motion estimates have been computed, the visibilities are computed and the motion or depth estimates recalculated using the visibility terms and the motion or depth compatibility constraint. The foregoing process can then be repeated several times using the revised estimates from the previous iteration as the initializing estimates for the new iteration, to obtain better estimates of motion/depth values and visibility.
摘要翻译： 用于从多个图像计算运动或深度估计的系统和过程。 一般来说，这是通过将深度或运动图与每个输入图像（或图像的一些子集等于或大于两个）相关联来实现的，而不是计算所有图像的单个图。 此外，确保与不同图像相关联的估计之间的一致性。 更具体地，这包括最小化三部分成本函数，其由强度（或颜色）兼容性约束，运动/深度兼容性约束和流平滑度约束组成。 另外，将强度（或颜色）兼容性和运动/深度兼容性约束添加了可视性术语，以防止像素匹配到被遮挡的区域。 在运行中，成本函数分两个阶段计算。 在初始化阶段，独立地估计正在检查的每个图像的运动或深度。 由于在计算中还没有其他帧使用的任何估计，因此忽略运动或深度兼容性项。 另外，没有计算出可见性，并且假定所有像素都是可见的。 一旦计算了一组初始运动估计值，就会计算出可见度，并使用可视性项和运动或深度兼容性约束重新计算运动或深度估计。 然后可以使用上一次迭代的修订估计作为新迭代的初始化估计值来重复上述过程，以获得运动/深度值和可见性的更好估计。
-
公开(公告)号：US20110109755A1
公开(公告)日：2011-05-12
申请号：US12616782
申请日：2009-11-12
CPC分类号： H04N5/23248 , H04N5/23258 , H04N5/23267
摘要： The described implementations relate to deblurring images. One system includes an imaging device configured to capture an image, a linear motion detector and a rotational motion detector. This system also includes a controller configured to receive a signal from the imaging device relating to capture of the image and to responsively cause the linear motion detector and the rotational motion detector to detect motion-related information. Finally, this particular system includes a motion calculator configured to recover camera motion associated with the image based upon the detected motion-related information and to infer imaging device motion induced blur of the image and an image deblurring component configured to reduce imaging device induced blur from the image utilizing the inferred camera motion induced blur.
摘要翻译： 所描述的实现涉及去模糊图像。 一个系统包括被配置为捕获图像的成像装置，线性运动检测器和旋转运动检测器。 该系统还包括控制器，其被配置为从成像装置接收与捕获图像有关的信号，并且响应地使线性运动检测器和旋转运动检测器检测运动相关信息。 最后，该特定系统包括运动计算器，该运动计算器被配置为基于检测到的运动相关信息来恢复与图像相关联的摄像机运动，并且推断图像的成像装置运动引起的模糊，以及被配置成减少成像装置引起的模糊的图像去模糊部件 该图像利用推测的相机运动引起的模糊。
-
公开(公告)号：US07903883B2
公开(公告)日：2011-03-08
申请号：US11694938
申请日：2007-03-30
IPC分类号： G06K9/00
CPC分类号： G06K9/468 , G06K9/6296
摘要： A local bi-gram model object recognition system and method for constructing a local bi-gram model and using the model to recognize objects in a query image. In a learning phase, the local bi-gram model is constructed that represents objects found in a set of training images. The local bi-gram model is a local spatial model that only models the relationship of neighboring features without any knowledge of their global context. Object recognition is performed by finding a set of matching primitives in the query image. A tree structure of matching primitives is generated and a search is performed to find a tree structure of matching primitives that obeys the local bi-gram model. The local bi-gram model can be found using unsupervised learning. The system and method also can be used to recognize objects unsupervised that are undergoing non-rigid transformations for both object instance recognition and category recognition.
摘要翻译： 一种局部双向模型对象识别系统和方法，用于构建局部双向模型，并使用该模型来识别查询图像中的对象。 在学习阶段，构建了表示在一组训练图像中发现的对象的局部双语模型。 当地的双语模型是一种局部空间模型，它只对相邻特征的关系进行建模，而无需了解其全局环境。 通过在查询图像中找到一组匹配的基元来执行对象识别。 生成匹配原语的树形结构，并执行搜索以找到符合本地双语模型的匹配原语的树结构。 可以使用无监督学习找到当地的双语模型。 系统和方法也可用于识别无监督的对象实例识别和类别识别正在进行非刚性转换的对象。
-
公开(公告)号：US20100302280A1
公开(公告)日：2010-12-02
申请号：US12476810
申请日：2009-06-02
IPC分类号： G09G5/00
CPC分类号： G06T19/003 , G06T7/33 , G06T13/80 , G06T15/30 , G06T2200/32 , G06T2207/10016 , G06T2207/30196
摘要： Techniques and systems are disclosed for navigating human scale image data using aligned perspective images. A consecutive sequence of digital images is stacked together by aligning consecutive images laterally with an image offset between edges of consecutive images corresponding to a distance between respective view windows of the consecutive images. A view window of an image in the sequence is rendered, where the view window of the image corresponds to a desired location. Offset portions of the view window of a desired number of images in the sequence are rendered, for example, alongside the full view of the image at the desired location.
摘要翻译： 公开了用于使用对准的透视图导航人体尺度图像数据的技术和系统。 通过将连续图像横向对准连续图像的边缘之间的图像偏移，对应于连续图像的各个视图窗口之间的距离，将连续的数字图像序列堆叠在一起。 呈现序列中的图像的视窗，其中图像的视图窗口对应于期望的位置。 该序列中所需数量的图像的视窗的偏移部分，例如，在所需位置处的图像的全视图旁边被渲染。
-
公开(公告)号：US20080027985A1
公开(公告)日：2008-01-31
申请号：US11461311
申请日：2006-07-31
IPC分类号： G06F17/00
CPC分类号： G06F16/29
摘要： A method, system and media for generating and querying spatial multimedia indices are provided. A multimedia corpus representing varying view points and distributed across a large network, such as the Internet, is crawled to extract properties from the multimedia. The extracted properties and relationships among multimedia are stored and indexed in clusters associated with a space-scale hierarchy. Accordingly, a spatial multimedia service may utilize the space-scale hierarchy to update the spatial multimedia indices and to respond to user queries.
摘要翻译： 提供了一种用于生成和查询空间多媒体索引的方法，系统和媒体。 代表不同视点并分布在诸如因特网的大型网络上的多媒体语料库被爬行以从多媒体提取属性。 提取的属性和多媒体之间的关系存储在与空间级别相关联的簇中索引。 因此，空间多媒体服务可以利用空间尺度层级来更新空间多媒体索引并响应用户查询。
-
公开(公告)号：US06636220B1
公开(公告)日：2003-10-21
申请号：US09583313
申请日：2000-05-30
申请人： Richard S. Szeliski , David Salesin , Arno Schödl
发明人： Richard S. Szeliski , David Salesin , Arno Schödl
IPC分类号： G06T1570
CPC分类号： G06T13/80
摘要： A system and process for generating a new video sequence from frames taken from an input video clip. Generally, this involves computing a similarity value between each of the frames of the input video clip and each of the other frames. For each frame, the similarity values associated therewith are analyzed to identify potentially acceptable transitions between it and the remaining frames. A transition is considered acceptable if it would appear smooth to a person viewing a video containing the frames, or at least if the transition is one of the best available. A new video sequence is then synthesized using the identified transitions to specify an order in which the frames associated with these transitions are to be played. Finally, the new video sequence is rendered by playing the frames of the input video clip in the order specified in the synthesizing procedure. This rendering procedure can include a smoothing action in which those transitions that were deemed acceptable, but would not appear smooth to a viewer, are smoothed to lessen the discontinuity. This general process can be used to generate continuous video sequences or fixed-length, loopable sequences. In addition, the process can be extended to process areas of independent motion in the input video clip separately and then recombine them during the rendering procedure, separate video texture elements from their backgrounds so that they can be used as video sprites.
摘要翻译： 用于从从输入视频剪辑获取的帧中生成新的视频序列的系统和过程。 通常，这涉及计算输入视频剪辑的每个帧和每个其他帧之间的相似度值。 对于每个帧，分析与其相关联的相似性值以识别其与剩余帧之间的潜在可接受的转换。 如果观看包含帧的视频的人看起来平滑，或者至少如果转换是最好的转换之一，则转换被认为是可以接受的。 然后使用所识别的转换来合成新的视频序列，以指定与这些转换相关联的帧将被播放的顺序。 最后，通过以合成过程中指定的顺序播放输入视频剪辑的帧来呈现新的视频序列。 该渲染过程可以包括平滑动作，其中被认为可接受但对观看者不会平滑的那些转换被平滑以减少不连续性。 该通用过程可用于产生连续视频序列或固定长度的可循环序列。 此外，该过程可以分别扩展到输入视频剪辑中独立运动的处理区域，然后在渲染过程中将它们重新组合，从背景中分离视频纹理元素，以便它们可以用作视频精灵。
-
公开(公告)号：US06469710B1
公开(公告)日：2002-10-22
申请号：US09160311
申请日：1998-09-25
IPC分类号： G09G500
CPC分类号： G06T15/04
摘要： A system and method for inverse texture mapping in which given a 3D model and several images from different viewpoints, a texture map is extracted for each planar surface in the 3D model. The system and method employs a unique weighted pyramid feathering scheme for blending multiple images to form the texture map, even where the images are taken from different viewpoints, at different scales, and with different exposures. This scheme also makes it possible to blend images with cut-out regions which may be present due to occlusions or moving objects. It further advantageously employs weight maps to improve the quality of the blended image.
摘要翻译： 一种用于逆纹理映射的系统和方法，其中给定3D模型和来自不同视点的若干图像，为3D模型中的每个平面提取纹理贴图。 该系统和方法采用独特的加权金字塔羽化方案，用于混合多个图像以形成纹理图，即使在不同视角，不同尺度和不同曝光下拍摄图像。 该方案还使得可以将图像与由于遮挡或移动物体可能存在的切出区域进行混合。 它进一步有利地使用权重映射来提高混合图像的质量。
-
29.发明授权公开(公告)号：US06271855B1
公开(公告)日：2001-08-07
申请号：US09099098
申请日：1998-06-18
申请人： Heung-Yeung Shum , Mei Han , Richard S. Szeliski
发明人： Heung-Yeung Shum , Mei Han , Richard S. Szeliski
IPC分类号： G06T1510
CPC分类号： G06T17/00
摘要： An interactive system and process for constructing a model of a 3D scene from a panoramic view of the scene. In the constructed model, the 3D scene is represented by sets of connected planes. The modeling begins by providing the user with a display of an image of the panoramic view. The user is then required to specify information concerning certain geometric features of the scene. A computer program recovers a camera orientation matrix of the panoramic view based on the features specified by the user. Plane normals and line directions for planes in the 3D scene are estimated using this matrix as well as the user-specified information. A camera translation is also recovered, as are plane distances and vertex point locations for planes in the 3D scene, using the user-supplied information, camera orientation matrix, and the estimated plane normals and line directions. The model of the 3D scene is then constructed based on the plane normal and plane distance, and/or the vertex point locations, of each plane in the set. Preferably, the plane distances and vertex point locations, and optionally the camera translation, are recovered by creating a system of equations based on the geometric constraints of the 3D scene. The constraint equation are characterized as hard is they include a user-designated parameter, otherwise they are considered soft constraints. The systems of equations is solved in a manner which gives priority to hard constraint equations. A decomposing process can also be employed prior to solving the systems of equation to ensure their solvability.
摘要翻译： 一种用于从场景全景构建3D场景的模型的交互式系统和过程。 在构造的模型中，3D场景由连接平面的集合表示。 该建模开始于向用户提供全景图像的显示。 然后，用户需要指定关于场景的某些几何特征的信息。 计算机程序基于用户指定的特征来恢复全景照相机方向矩阵。 使用该矩阵以及用户指定的信息来估计3D场景中的平面的平面法线和线方向。 还可以使用用户提供的信息，照相机方向矩阵和估计的平面法线和线方向恢复相机平移以及3D场景中的平面的平面距离和顶点位置。 然后基于该组中每个平面的平面法线和平面距离和/或顶点位置来构建3D场景的模型。 优选地，通过基于3D场景的几何约束创建方程式系统来恢复平面距离和顶点位置以及可选地相机平移。 约束方程的特征是硬包括用户指定的参数，否则它们被认为是软约束。 以优先考虑硬约束方程的方式解决方程组。 在解决方程组之前也可以采用分解过程，以确保其可解性。
-
30.发明授权
公开(公告)号：US6137491A
公开(公告)日：2000-10-24
申请号：US092721
申请日：1998-06-05
申请人： Richard S. Szeliski
发明人： Richard S. Szeliski
CPC分类号： G06T7/0065 , G06K9/209 , G06T7/004
摘要： The invention is embodied in a method for reconstructing 3-dimensional geometry by computing 3-dimensional points on an object or a scene including many objects visible in images taken from different views of the object or scene. The method includes identifying at least one set of initial pixels visible in both the views lying on a generally planar surface on the object, computing from the set of initial pixels an estimated homography between the views, defining at least an additional pixel on the one surface in one of the images and computing from the estimated homography a corresponding additional pixel in the other view, computing an optimal homography and an epipole from the initial and additional pixels (including at least some points not on the planar surface), and computing from the homography and the epipole 3-dimensional locations of points on the object by triangulation between the views of corresponding ones of the pixels. Each of the initial pixels in one of the views corresponds to one of the initial pixels in the other of the views and both correspond to a point on the object.
摘要翻译： 本发明体现在一种用于通过计算物体或场景上的3维点重建三维几何的方法，包括从对象或场景的不同视图拍摄的图像中可见的许多对象。 该方法包括识别在位于物体上的大体上平坦的表面上的两个视图中可见的至少一组初始像素集合，从该组初始像素计算视图之间的估计的单应性，定义至少一个表面上的附加像素 在一个图像中并且从估计的单应性中计算出另一视图中的相应的附加像素，从初始和附加像素（包括至少一些不在平面表面上的点）计算最佳单应性和近似值，以及从 通过对应的像素的视图之间的三角测量，对象上的点的对立三维位置。 其中一个视图中的每个初始像素对应于另一个视图中的一个初始像素，并且都对应于物体上的一个点。
-
-
-
-
-
-
-
-
-
搜索结果
57 条记录 (耗时 0.036 秒)
