-
21.发明申请ENCODING OF A PICTURE IN A VIDEO SEQUENCE BY EXAMPLE-BASED DATA PRUNING USING INTRA-FRAME PATCH SIMILARITY 审中-公开通过使用帧内匹配的基于示例的数据预处理图像在视频序列中的编码相似度公开(公告)号：US20130170564A1
公开(公告)日：2013-07-04
申请号：US13821357
申请日：2011-09-09
申请人： Dong-Qing Zhang , Sitaram Bhagavathy , Shan He
发明人： Dong-Qing Zhang , Sitaram Bhagavathy , Shan He
IPC分类号： H04N7/26
CPC分类号： H04N19/85 , G06T5/001 , H04N19/132 , H04N19/14 , H04N19/176 , H04N19/196 , H04N19/44 , H04N19/46 , H04N19/463 , H04N19/587 , H04N19/59 , H04N19/593 , H04N19/61 , H04N19/97
摘要： Method and apparatus for encoding a picture in video sequence are disclosed. An apparatus includes a library creator for creating a first library from an original version of the picture and a second library from a reconstructed version of the picture. Each library includes high resolution replacement patches for replacing pruned blocks during a recovery of a pruned version of the picture. A pruner generates the pruned version from the first library. A metadata generator generates metadata from the second library for recovering the pruned version. An encoder encodes the pruned version and metadata. The first library includes patch clusters. The pruned version is generated by dividing the original version into overlapping blocks and searching for candidate patch clusters for each block. A patch dependency graph having nodes and edges is used for the searching. Each node represents a respective block, and each edge represents a respective dependency of the respective block.
摘要翻译： 公开了以视频序列编码图像的方法和装置。 一种装置包括用于从图像的原始版本创建第一库的库创建器，以及来自图像的重构版本的第二库。 每个库包括高分辨率替换补丁，用于在恢复修剪版本的图片期间替换已修剪的块。 修剪器从第一个库生成修剪版本。 元数据生成器从第二个库生成元数据，以恢复修剪版本。 编码器对已修剪的版本和元数据进行编码。 第一个库包括补丁集群。 修剪版本通过将原始版本划分为重叠块并搜索每个块的候选修补程序簇来生成。 具有节点和边缘的补丁依赖图用于搜索。 每个节点表示相应的块，并且每个边缘表示相应块的相应依赖性。
-
22.发明申请Temporally consistent caption detection on videos using a 3D spatiotemporal method 有权使用3D时空方法对视频进行暂时一致的字幕检测公开(公告)号：US20100201871A1
公开(公告)日：2010-08-12
申请号：US12658264
申请日：2010-02-09
CPC分类号： G06K9/3266
摘要： A caption detection system wherein all detected caption boxes over time for one caption area are identical, thereby reducing temporal instability and inconsistency. This is achieved by grouping candidate pixels in the 3D spatiotemporal space and generating a 3D bounding box for one caption area. 2D bounding boxes are obtained by slicing the 3D bounding boxes, thereby reducing temporal instability as all 2D bounding boxes corresponding to a caption area are sliced from one 3D bounding box and are therefore identical over time.
摘要翻译： 字幕检测系统，其中所有检测到的字幕盒随着时间的推移对于一个字幕区域是相同的，从而减少时间不稳定性和不一致性。 这通过在3D时空中分组候选像素并为一个字幕区域生成3D边界框来实现。 通过对3D边界框进行切片来获得2D边界框，从而减少时间不稳定性，因为与一个3D边界框对应的所有2D边界框都被切割，因此随着时间的推移相同。
-
23.发明授权公开(公告)号：US09659382B2
公开(公告)日：2017-05-23
申请号：US12994894
申请日：2008-05-28
申请人： Dong-Qing Zhang , Izzat Izzat , Youngshik Yoon
发明人： Dong-Qing Zhang , Izzat Izzat , Youngshik Yoon
CPC分类号： G06T7/593 , G06T7/579 , G06T2207/10012 , G06T2207/10021
摘要： A system and method for spatiotemporal depth extraction of images with forward and backward depth prediction are provided. The system and method of the present disclosure provide for acquiring a plurality of frames, generating a first depth map of a current frame in the plurality of frames based on a depth map of a previous frame in the plurality of frames, generating a second depth map of the current frame in the plurality of frames based on a depth map of a subsequent frame in the plurality of frames, and processing the first depth map and the second depth map to produce a third depth map for the current frame.
-
公开(公告)号：US09246830B2
公开(公告)日：2016-01-26
申请号：US13253654
申请日：2011-10-05
申请人： Zhu Li , Yong Wang , Dong-Qing Zhang , Hong Heather Yu
发明人： Zhu Li , Yong Wang , Dong-Qing Zhang , Hong Heather Yu
IPC分类号： H04L12/28 , H04L12/823 , H04L12/835 , H04L29/06 , H04N21/647
CPC分类号： H04L47/323 , H04L47/30 , H04L65/80 , H04N21/64738 , H04N21/64769
摘要： Methods and systems for a multimedia queue management solution that maintaining graceful Quality of Experience (QoE) degradation are provided. The method selects a frame from all weighted queues based on a gradient function indicating a network performance rate change and a distortion rate caused by the frame and its related frames in the queue, and dropping the selected frame and all its related frames, and continues to drop similarly chosen frame until a network performance rate change caused by the dropping frame and its related frames meets a predetermined performance metric. A frame gradient is a distortion rate divided by a network performance rate change caused by the frame and its related frames, and a distortion rate is based on a sum of each individual frame distortion rate when the frame and its related frames are replaced by some other frames derived from remaining frames based on a replacement method.
摘要翻译： 提供了维护优雅的体验质量（QoE）降级的多媒体队列管理解决方案和方法。 该方法基于指示网络性能速率变化的梯度函数和由帧及其相关帧在队列中引起的失真率，并且丢弃所选帧及其所有相关帧，从所有加权队列中选择一帧，并继续 丢弃类似地选择的帧，直到由丢弃帧及其相关帧引起的网络性能速率变化满足预定的性能度量。 帧梯度是由帧及其相关帧引起的网络性能速率变化除以失真率，并且当帧和其相关帧被其他一些替换时，失真率基于每个单独的帧失真率的和 基于替换方法从剩余帧导出的帧。
-
25.发明授权公开(公告)号：US09137518B2
公开(公告)日：2015-09-15
申请号：US12735402
申请日：2008-01-29
CPC分类号： H04N13/261
摘要： Methods and Systems are provided for converting a two-dimensional image sequence into a three-dimensional image. In one embodiment, a method for converting a two-dimensional image sequence into a three-dimensional image includes determining camera motion parameters between consecutive images in a monoscopic sequence of reference 2D images, wherein the consecutive images comprise a current reference image and an adjacent image, determining a horizontal disparity map for a target image using the camera motion parameters, determining a disparity probability value for each disparity vector of the disparity map, and determining a target image as a weighted average of pixel values in the current reference image using the disparity probability values, such that the target image and current reference image comprise a stereoscopic image pair.
摘要翻译： 提供了将二维图像序列转换为三维图像的方法和系统。 在一个实施例中，将二维图像序列转换成三维图像的方法包括在参考2D图像的单视场序列中确定连续图像之间的相机运动参数，其中连续图像包括当前参考图像和相邻图像 使用相机运动参数确定目标图像的水平视差图，确定视差图的每个视差矢量的视差概率值，以及使用视差来确定目标图像作为当前参考图像中的像素值的加权平均值 概率值，使得目标图像和当前参考图像包括立体图像对。
-
26.发明授权System and method for recovering three-dimensional particle systems from two-dimensional images 有权从二维图像中恢复三维粒子系统的系统和方法公开(公告)号：US08619073B2
公开(公告)日：2013-12-31
申请号：US12447029
申请日：2006-10-27
IPC分类号： G06T15/00
CPC分类号： G06T7/50 , G06T13/20 , G06T2210/56
摘要： A system and method for recovering three-dimensional (3D) particle systems from two-dimensional (2D) images are provided. The system and method of the present invention provide for identifying a fuzzy object in a two-dimensional (2D) image; selecting a particle system from a plurality of predetermined particle systems, the selected particle system relating to a predefined fuzzy object; generating at least one particle of the selected particle system; simulating the at least one particle to update states of the at least one particle; rendering the selected particle system; comparing the rendered particle system to the identified fuzzy object in the 2D image; and storing the selected particle system if the comparison result is within an acceptable threshold, wherein the stored particle system represents the recovered geometry of the fuzzy object.
摘要翻译： 提供了一种用于从二维（2D）图像中恢复三维（3D）粒子系统的系统和方法。 本发明的系统和方法提供用于识别二维（2D）图像中的模糊对象; 从多个预定粒子系统中选择粒子系统，所选粒子系统与预定义的模糊对象相关; 产生所选择的粒子系统的至少一个粒子; 模拟所述至少一个粒子以更新所述至少一个粒子的状态; 渲染选定的粒子系统; 将渲染的粒子系统与2D图像中识别的模糊对象进行比较; 以及如果所述比较结果在可接受的阈值内，则存储所选择的粒子系统，其中所述存储的粒子系统表示所述模糊对象的恢复的几何形状。
-
公开(公告)号：US08483540B2
公开(公告)日：2013-07-09
申请号：US12312362
申请日：2006-12-12
申请人： Ingo Doser , Ana Belen Benitez , Dong-Qing Zhang
发明人： Ingo Doser , Ana Belen Benitez , Dong-Qing Zhang
CPC分类号： G11B27/28 , G11B27/10 , H04N5/76 , H04N9/802 , H04N21/2368 , H04N21/4307 , H04N21/4334 , H04N21/4341
摘要： A method, apparatus and system for synchronizing between two recording modes includes identifying a common event in the two recording modes. The event in time is recognized for a higher accuracy mode of the two modes. The event is predicted in a lower accuracy mode of the two modes by determining a time when the event occurred between frames in the lower accuracy mode. The event in the higher accuracy mode is synchronized to the lower accuracy mode to provide sub-frame accuracy alignment between the two modes. In one embodiment of the invention, the common event includes the closing of a clap slate, and the two modes include audio and video recording modes.
摘要翻译： 用于在两种记录模式之间同步的方法，装置和系统包括识别两种记录模式中的公共事件。 对于两种模式的更高精度模式，识别出时间上的事件。 通过确定在较低精度模式中的帧之间发生事件的时间，在两种模式的较低精度模式中预测该事件。 在较高精度模式下的事件与较低精度模式同步，以提供两种模式之间的子帧精度对准。 在本发明的一个实施例中，公共事件包括拍子拍板的关闭，并且两种模式包括音频和视频记录模式。
-
公开(公告)号：US20110085739A1
公开(公告)日：2011-04-14
申请号：US12996424
申请日：2008-06-06
申请人： Dong-Qing Zhang , Rajan Joshi , Ju Guo , Ana B. Benitez , Ying Luo
发明人： Dong-Qing Zhang , Rajan Joshi , Ju Guo , Ana B. Benitez , Ying Luo
CPC分类号： G06F16/58 , G06F16/583
摘要： A system and method for an efficient semantic similarity search of images with a classification structure are provided. The system and method provide for building a semantic classification-search tree for the plurality of images, the classification tree including at least two categories of images, each category of images representing a subset of the plurality of images, receiving a query image, classifying the query image to select one of the at least two categories of images, and restricting the search for the image of interest using the query image to the selected one of the at least two categories of images.
摘要翻译： 提供了一种用于具有分类结构的图像的有效语义相似性搜索的系统和方法。 该系统和方法提供用于构建多个图像的语义分类搜索树，分类树包括至少两个图像类别，每个类别的图像表示多个图像的子集，接收查询图像，分类 查询图像以选择所述至少两个类别的图像中的一个，并且使用查询图像将所搜索的图像搜索到所选择的至少两个图像类别中。
-
公开(公告)号：US20100290697A1
公开(公告)日：2010-11-18
申请号：US12311839
申请日：2006-10-21
摘要： A system and method for color correction of 3D images including at least two separate image streams captured for a same scene include determining three-dimensional properties of at least a portion of a selected image stream, the three-dimensional properties including light and surface reflectance properties, surface color, reflectance properties, scene geometry and the like. A look of the portion of the selected image stream is then modified by altering the value of at least one of the determined three-dimensional properties and, in one embodiment, applying image formation theory. The modifications are then rendered in an output 3D picture either automatically and/or according to user inputs. In various embodiments, corrections made to the selected one of the at least two image streams can be automatically applied to the other of the image streams.
摘要翻译： 包括为相同场景捕获的至少两个分开的图像流的3D图像的颜色校正的系统和方法包括确定所选图像流的至少一部分的三维特性，包括光和表面反射特性 ，表面颜色，反射性，场景几何等。 然后通过改变所确定的三维属性中的至少一个的值，并且在一个实施例中应用图像形成理论来修改所选图像流的部分的外观。 然后，这些修改自动地和/或根据用户输入在输出3D图像中呈现。 在各种实施例中，对所选择的至少两个图像流中的一个图像流进行的校正可被自动地应用于另一个图像流。
-
公开(公告)号：US20100208994A1
公开(公告)日：2010-08-19
申请号：US12658464
申请日：2010-02-09
申请人： Ning Yao , Izzat Izzat , Tao Zhang , Dong-Qing Zhang
发明人： Ning Yao , Izzat Izzat , Tao Zhang , Dong-Qing Zhang
IPC分类号： G06K9/34
CPC分类号： G06T5/005 , G06T7/11 , G06T7/162 , G06T2207/10024 , G06T2207/10028
摘要： Various implementations relate to improving depth maps. This may be done, for example, by identifying bad depth values and modifying those values. The values may represent, for example, holes and/or noise. According to a general aspect, a segmentation is determined based on an intensity image. The intensity image is associated with a corresponding depth image that includes depth values for corresponding locations in the intensity image. The segmentation is applied to the depth image to segment the depth image into multiple regions. A depth value is modified in the depth image based on the segmentation. A two-stage iterative procedure may be used to improve the segmentation and then modify bad depth values in the improved segmentation, and iterating until a desired level of smoothness is achieved. Both stages may be based, for example, on average depth values in a segment.
摘要翻译： 各种实现涉及改进深度图。 这可以通过例如识别不良深度值和修改这些值来完成。 这些值可以表示例如孔和/或噪声。 根据一般方面，基于强度图像来确定分割。 强度图像与包括强度图像中相应位置的深度值的对应深度图像相关联。 分割应用于深度图像，将深度图像分割成多个区域。 基于分割，在深度图像中修改深度值。 可以使用两阶段迭代程序来改进分割，然后在改进的分割中修改不良深度值，并且迭代直到实现所需的平滑度。 这两个阶段可以基于例如一段中的平均深度值。
-
-
-
-
-
-
-
-
-
搜索结果
82 条记录 (耗时 0.029 秒)
