-
公开(公告)号：US20120263437A1
公开(公告)日：2012-10-18
申请号：US13516228
申请日：2010-12-10
IPC分类号： H04N9/80
CPC分类号： G06K9/00711 , G06K9/00335 , G06K9/00724 , G06K9/033 , G06T7/246 , G06T2207/10016 , G06T2207/30228 , G06T2207/30241
摘要： A method and associated apparatus for using a trajectory-based technique to detect a moving object in a video sequence at incorporates human interaction through a user interface. The method comprises steps of identifying and evaluating sets of connected components in a video frame, filtering the list of connected components by comparing features of the connected components to predetermined criteria, identifying candidate trajectories across multiple frames, evaluating the candidate trajectories to determine a selected trajectory, eliminating incorrect trajectories through use of the interface and processing images in said video sequence responsive to the evaluating and eliminating steps.
摘要翻译： 一种用于使用基于轨迹的技术来检测视频序列中的移动对象的方法和相关联的装置，其通过用户界面并入人类交互。 该方法包括以下步骤：识别和评估视频帧中的连接分量集合，通过将所连接分量的特征与预定标准进行比较来过滤所连接分量的列表，识别跨多个帧的候选轨迹，评估候选轨迹以确定所选择的轨迹 通过使用界面消除不正确的轨迹，并响应于评估和消除步骤来处理所述视频序列中的图像。
-
公开(公告)号：US09118912B2
公开(公告)日：2015-08-25
申请号：US13508562
申请日：2010-12-08
IPC分类号： H04N7/26 , H04N19/103 , H04N19/172 , H04N19/115 , H04N19/14 , H04N19/154 , H04N19/20 , H04N19/176 , H04N19/147 , H04N19/46 , H04N19/124 , H04N19/137 , H04N19/167 , H04N19/85 , H04N19/177
CPC分类号： H04N19/103 , H04N19/115 , H04N19/124 , H04N19/137 , H04N19/14 , H04N19/147 , H04N19/154 , H04N19/167 , H04N19/172 , H04N19/176 , H04N19/177 , H04N19/20 , H04N19/46 , H04N19/85
摘要： A method of object-aware video coding is provided that comprises the steps of: receiving a video sequence having a plurality of frames; selecting at least two frames; determing total area of at least one object of interest in each of the at least two frames; comparing the total area to a threshold area; classifying each of the at least two frames as being a low object weighted frame or a high object weighted frame, low object weighted frames being frames having the total area exceeding the threshold area and high object weighted frames being frame having the total area not exceeding the threshold area; and encoding each low object weighted frame according to one encoding mode and encoding each high object weighted frame according to a different encoding mode.
摘要翻译： 提供了一种对象感知视频编码方法，包括以下步骤：接收具有多个帧的视频序列; 选择至少两个帧; 确定所述至少两个帧中的每一个中的至少一个感兴趣对象的总面积; 将总面积与阈值区域进行比较; 将至少两个帧中的每一个分类为低对象加权帧或高对象加权帧，低对象加权帧是具有超过阈值区域的总区域的帧，并且高对象加权帧是具有不超过阈值区域的总区域的帧 阈值面积 并根据一个编码模式对每个低对象加权帧进行编码，并根据不同的编码模式对每个高对象加权帧进行编码。
-
公开(公告)号：US08977109B2
公开(公告)日：2015-03-10
申请号：US13516228
申请日：2010-12-10
CPC分类号： G06K9/00711 , G06K9/00335 , G06K9/00724 , G06K9/033 , G06T7/246 , G06T2207/10016 , G06T2207/30228 , G06T2207/30241
摘要： A method and associated apparatus for using a trajectory-based technique to detect a moving object in a video sequence at incorporates human interaction through a user interface. The method comprises steps of identifying and evaluating sets of connected components in a video frame, filtering the list of connected components by comparing features of the connected components to predetermined criteria, identifying candidate trajectories across multiple frames, evaluating the candidate trajectories to determine a selected trajectory, eliminating incorrect trajectories through use of the interface and processing images in said video sequence responsive to the evaluating and eliminating steps.
摘要翻译： 一种用于使用基于轨迹的技术来检测视频序列中的移动对象的方法和相关联的装置，其通过用户界面并入人类交互。 该方法包括以下步骤：识别和评估视频帧中的连接分量集合，通过将所连接分量的特征与预定标准进行比较来过滤所连接分量的列表，识别跨多个帧的候选轨迹，评估候选轨迹以确定所选择的轨迹 通过使用界面消除不正确的轨迹，并响应于评估和消除步骤来处理所述视频序列中的图像。
-
公开(公告)号：US20120224629A1
公开(公告)日：2012-09-06
申请号：US13508562
申请日：2010-12-08
IPC分类号： H04N7/26
CPC分类号： H04N19/103 , H04N19/115 , H04N19/124 , H04N19/137 , H04N19/14 , H04N19/147 , H04N19/154 , H04N19/167 , H04N19/172 , H04N19/176 , H04N19/177 , H04N19/20 , H04N19/46 , H04N19/85
摘要： A method of object-aware video coding is provided that comprises the steps of: receiving a video sequence having a plurality of frames; selecting at least two frames; determing total area of at least one object of interest in each of the at least two frames; comparing the total area to a threshold area; classifying each of the at least two frames as being a low object weighted frame or a high object weighted frame, low object weighted frames being frames having the total area exceeding the threshold area and high object weighted frames being frame having the total area not exceeding the threshold area; and encoding each low object weighted frame according to one encoding mode and encoding each high object weighted frame according to a different encoding mode.
摘要翻译： 提供了一种对象感知视频编码方法，包括以下步骤：接收具有多个帧的视频序列; 选择至少两个帧; 确定所述至少两个帧中的每一个中的至少一个感兴趣对象的总面积; 将总面积与阈值区域进行比较; 将至少两个帧中的每一个分类为低对象加权帧或高对象加权帧，低对象加权帧是具有超过阈值区域的总区域的帧，并且高对象加权帧是具有不超过阈值区域的总区域的帧 阈值面积 并根据一个编码模式对每个低对象加权帧进行编码，并根据不同的编码模式对每个高对象加权帧进行编码。
-
5.发明申请TRAJECTORY-BASED METHOD TO DETECT AND ENHANCE A MOVING OBJECT IN A VIDEO SEQUENCE 审中-公开基于TRAJECTORY的方法来检测和增强视频序列中的移动对象公开(公告)号：US20120114184A1
公开(公告)日：2012-05-10
申请号：US13386145
申请日：2010-07-20
IPC分类号： G06K9/68
CPC分类号： G06K9/00711 , G06T7/246 , G06T2207/10016 , G06T2207/30224 , G06T2207/30241
摘要： The present invention concerns a method and associated apparatus for using a trajectory-based technique to detect a moving object in a video sequence, such as the ball in a soccer game. In one embodiment, the method comprises steps of identifying and evaluating sets of connected components in a video frame, filtering the list of connected components by comparing features of the connected components to predetermined criteria, identifying candidate trajectories across multiple frames, evaluating the candidate trajectories to determine a selected trajectory, and processing images in the video sequence based at least in part upon the selected trajectory.
摘要翻译： 本发明涉及一种使用基于轨迹的技术来检测诸如足球游戏中的球的视频序列中的移动物体的方法和相关装置。 在一个实施例中，该方法包括以下步骤：识别和评估视频帧中的连接分量集合，通过将所连接分量的特征与预定标准进行比较来过滤所连接分量列表，识别跨多个帧的候选轨迹，评估候选轨迹 确定所选择的轨迹，以及至少部分地基于所选择的轨迹来处理视频序列中的图像。
-
公开(公告)号：US20120320153A1
公开(公告)日：2012-12-20
申请号：US13580757
申请日：2010-12-20
申请人： Jesus Barcons-Palau , Joan Llach
发明人： Jesus Barcons-Palau , Joan Llach
IPC分类号： H04N13/00
CPC分类号： G06T7/33 , G06T2207/10021 , H04N13/10 , H04N13/156 , H04N13/183 , H04N13/361
摘要： In various embodiment of the present invention, the difference of disparity between subtitles in stereoscopic content along time is restrained by a function of time and disparity. This guarantees that two consecutive subtitles will have similar disparity if they are close in time. More specifically, a method for the positioning of subtitles in stereoscopic content includes estimating a position for a subtitle in at least one frame of the stereoscopic content and restraining a difference in disparity between subtitles in at least two frames by a function of time and disparity. In such an embodiment, the estimating can include computing a disparity value for the subtitle using a disparity of an object in a region in the at least one frame in which the subtitle is to be inserted. The subtitle can then be adjusted to be in front of or behind the object.
摘要翻译： 在本发明的各种实施例中，随时间和视差的函数来限制立体内容中的字幕与时间的差异。 这确保了两个连续的字幕在时间上是接近的时候会有相似的差异。 更具体地说，用于在立体内容中定位字幕的方法包括估计立体内容的至少一帧中的字幕的位置，并且通过时间和视差的函数来抑制至少两帧中的字幕之间的差异的差异。 在这样的实施例中，估计可以包括使用要插入字幕的至少一个帧中的区域中的对象的视差来计算字幕的视差值。 然后可以将字幕调整为在对象的前面或后面。
-
7.发明申请Method and apparatus for synchronized workstation with two-dimensional and three-dimensional outputs 审中-公开用于具有二维和三维输出的同步工作站的方法和装置公开(公告)号：US20110211816A1
公开(公告)日：2011-09-01
申请号：US12932156
申请日：2011-02-18
IPC分类号： H04N5/93
CPC分类号： H04N5/76 , H04N5/765 , H04N9/7921 , H04N9/8227
摘要： A method and apparatus are disclosed and described for providing a synchronized workstation with two-dimensional and three-dimensional outputs. The apparatus includes a video decoder (315) for decoding picture data. The video decoder includes a data manager (320) for receiving video production commands and managing a video playback of the picture data in at least one of a two-dimensional video output mode and a three-dimensional video output mode responsive to the video production commands. The two-dimensional video output mode and the three-dimensional video output mode are capable of being used independently and simultaneously.
摘要翻译： 公开和描述了一种提供具有二维和三维输出的同步工作站的方法和装置。 该装置包括用于解码图像数据的视频解码器（315）。 视频解码器包括数据管理器（320），用于接收视频制作命令并且响应于视频制作命令以二维视频输出模式和三维视频输出模式中的至少一个来管理图像数据的视频回放 。 二维视频输出模式和三维视频输出模式能够独立且同时使用。
-
公开(公告)号：US20120314023A1
公开(公告)日：2012-12-13
申请号：US13580165
申请日：2010-10-08
申请人： Jesus Barcons-Palau , Joan Llach
发明人： Jesus Barcons-Palau , Joan Llach
IPC分类号： H04N13/00
CPC分类号： H04N13/139 , H04N5/2624 , H04N13/161 , H04N13/30
摘要： A method, apparatus and system are provided for the visual inspection of a three-dimensional video stream as it is being re-encoded into a second video format. A portion of a frame of a decoded three-dimensional video stream and a corresponding portion of a frame of the three-dimensional video stream having been re-encoded are arranged into a combined video frame such that the video frame portions appear together in the combined video frame. A boundary between the video frame portions in the combined video frame is manipulated such that a change of disparity on the boundary between the video frame portions, and any overlap between the combined video frame portions, are not visible.
摘要翻译： 提供了一种方法，装置和系统，用于在三维视频流被重新编码为第二视频格式时的目视检查。 解码的三维视频流的帧的一部分和已被重新编码的三维视频流的帧的对应部分被布置成组合视频帧，使得视频帧部分在组合中一起出现 视频帧。 操作组合视频帧中的视频帧部分之间的边界，使得视频帧部分之间的边界上的视差的变化以及组合的视频帧部分之间的任何重叠是不可见的。
-
9.发明申请METHODS AND APPARATUS FOR UPGRADING A PROJECTOR TO DISPLAY THREE-DIMENSIONAL CONTENT 审中-公开用于升级投影仪以显示三维内容的方法和装置公开(公告)号：US20130229500A1
公开(公告)日：2013-09-05
申请号：US13885523
申请日：2010-11-18
IPC分类号： H04N13/04
CPC分类号： H04N13/30 , G02B27/2264 , G02B27/26 , H04N13/341 , H04N13/363
摘要： An apparatus for upgrading a projector having a two-dimensional projector lens to display three-dimensional content includes a circular polarized filter having at least two polarized zones, and a motor having a shaft on which is mounted the filter. At least one light sensor is disposed in front of the two-dimensional projector lens for providing a spatial control output signal and a temporal control output signal. A processor controls a speed at which the filter is rotated around the shaft of the motor responsive to information determined from the spatial control output signal and the temporal control output signal, such that the filter is automatically adjusted to spin so as to respectively place an appropriate one of the at least two polarized zones of the filter in front of an applicable frame of the video sequence to obtain a polarization thereof representative of the three-dimensional content.
摘要翻译： 用于升级具有用于显示三维内容的二维投影仪透镜的投影仪的设备包括具有至少两个偏振区域的圆形偏振滤光器和具有轴的电机，其上安装有滤光器。 至少一个光传感器设置在二维投影透镜的前面，用于提供空间控制输出信号和时间控制输出信号。 处理器控制过滤器响应于从空间控制输出信号和时间控制输出信号确定的信息而围绕马达的轴线旋转的速度，使得滤波器被自动调整以旋转以便分别放置适当的 在视频序列的适用帧前面的滤波器的至少两个偏振区域中的一个，以获得代表三维内容的极化。
-
公开(公告)号：US20150294470A1
公开(公告)日：2015-10-15
申请号：US14443087
申请日：2012-11-27
申请人： Anton TE , Pierrer Hughes ROUTHIER , Jesus BARCONS -PALAU , Richard Edwin GOEDEKEN , Richard W. KROON , THOMSON LICENSING
CPC分类号： H04N13/128 , G06T7/50 , G06T7/593 , G06T2207/10016 , G06T2207/20228
摘要： A method and system to generate and visualize the distribution of disparities in a stereo sequence and the way they change through time. The data representing the disparities are generated using the disparity and confidence maps of the stereo sequence. For each frame, a histogram of disparity-confidence pairs is generated. These data are later visualized on the screen, presenting the disparity for the full sequence in one graph.
摘要翻译： 一种用于生成和可视化立体声序列中的差异分布的方法和系统及其随时间变化的方式。 使用立体声序列的视差和置信度图来生成表示差异的数据。 对于每个帧，生成视差置信对的直方图。 这些数据随后在屏幕上可视化，呈现一个图中完整序列的差异。
-
-
-
-
-
-
-
-
-
搜索结果
10 条记录 (耗时 0.023 秒)