-
公开(公告)号：US08744203B2
公开(公告)日：2014-06-03
申请号：US13458387
申请日：2012-04-27
IPC分类号： G06K9/00
CPC分类号： H04N21/4621 , H04N19/117 , H04N19/126 , H04N19/159 , H04N19/17 , H04N19/176 , H04N19/186 , H04N19/44 , H04N19/46 , H04N19/48 , H04N19/70 , H04N19/895 , H04N21/4728
摘要： The disclosure is directed to decoder-side region-of-interest (ROI) video processing. A video decoder determines whether ROI assistance information is available. If not, the decoder defaults to decoder-side ROI processing. The decoder-side ROI processing may estimate the reliability of ROI extraction in the bitstream domain. If ROI reliability is favorable, the decoder applies bitstream domain ROI extraction. If ROI reliability is unfavorable, the decoder applies pixel domain ROI extraction. The decoder may apply different ROI extraction processes for intra-coded (I) and inter-coded (P or B) data. The decoder may use color-based ROI generation for intra-coded data, and coded block pattern (CBP)-based ROI generation for inter-coded data. ROI refinement may involve shape-based refinement for intra-coded data, and motion- and color-based refinement for inter-coded data.
摘要翻译： 本公开涉及解码器侧感兴趣区域（ROI）视频处理。 视频解码器确定ROI辅助信息是否可用。 如果不是，则解码器默认为解码器侧ROI处理。 解码器侧ROI处理可以估计比特流域中的ROI提取的可靠性。 如果ROI可靠性较好，则解码器应用比特流域ROI提取。 如果ROI可靠性不利，则解码器应用像素域ROI提取。 解码器可以对帧内编码（I）和帧间编码（P或B）数据应用不同的ROI提取处理。 解码器可以使用用于帧内编码数据的基于颜色的ROI生成，以及用于帧间编码数据的基于编码块模式（CBP）的ROI生成。 ROI细化可能涉及帧内编码数据的基于形状的细化，以及帧间编码数据的基于运动和颜色的细化。
-
公开(公告)号：US08659592B2
公开(公告)日：2014-02-25
申请号：US12585784
申请日：2009-09-24
申请人： Haohong Wang , Glenn Adler
发明人： Haohong Wang , Glenn Adler
IPC分类号： G06T15/00
CPC分类号： G06T7/194 , G06T7/11 , G06T7/50 , G06T2207/10016 , G06T2207/10028 , G06T2207/20012 , H04N13/261
摘要： A method for real-time 2D to 3D video conversion includes receiving a decoded 2D video frame having an original resolution, downscaling the decoded 2D video frame into an associated 2D video frame having a lower resolution, and segmenting objects present in the downscaled 2D video frame into background objects and foreground objects. The method also includes generating a background depth map and a foreground depth map for the downscaled 2D video frame based on the segmented background and foreground objects, and deriving a frame depth map in the original resolution based on the background depth map and the foreground depth map. The method further includes providing a 3D video frame for display at a real-time playback rate. The 3D video frame is generated in the original resolution based on the frame depth map.
摘要翻译： 一种用于实时2D到3D视频转换的方法包括接收具有原始分辨率的解码的2D视频帧，将解码的2D视频帧缩小成具有较低分辨率的相关联的2D视频帧，以及分割存在于缩小的2D视频帧中的对象 进入背景对象和前景对象。 该方法还包括基于分割的背景和前景对象生成用于缩小的2D视频帧的背景深度图和前景深度图，并且基于背景深度图和前景深度图导出原始分辨率中的帧深度图 。 该方法还包括提供用于以实时重放速率显示的3D视频帧。 基于帧深度图以原始分辨率生成3D视频帧。
-
公开(公告)号：US08594180B2
公开(公告)日：2013-11-26
申请号：US11677335
申请日：2007-02-21
IPC分类号： G06F21/00
CPC分类号： H04N19/194 , H04N13/122 , H04N19/124 , H04N19/147 , H04N19/149 , H04N19/172 , H04N19/176 , H04N19/597 , H04N19/61
摘要： A stereo 3D video frame includes left and right components that are combined to produce a stereo image. For a given amount of distortion, the left and right components may have different impacts on perceptual visual quality of the stereo image due to asymmetry in the distortion response of the human eye. A 3D video encoder adjusts an allocation of coding bits between left and right components of the 3D video based on a frame-level bit budget and a weighting between the left and right components. The video encoder may generate the bit allocation in the rho (ρ) domain. The weighted bit allocation may be derived based on a quality metric that indicates overall quality produced by the left and right components. The weighted bit allocation compensates for the asymmetric distortion response to reduce overall perceptual distortion in the stereo image and thereby enhance or maintain visual quality.
摘要翻译： 立体3D视频帧包括组合以产生立体图像的左和右组件。 对于给定量的失真，由于人眼的失真响应的不对称，左和右分量可能对立体图像的感知视觉质量具有不同的影响。 3D视频编码器基于帧级比特预算和左右分量之间的加权来调整3D视频的左和右分量之间的编码比特的分配。 视频编码器可以在rho（rho）域中生成比特分配。 可以基于指示左组件和右组件产生的总体质量的质量度量来导出加权比特分配。 加权比特分配补偿非对称失真响应，以减少立体图像中的整体感知失真，从而增强或维持视觉质量。
-
公开(公告)号：US08208758B2
公开(公告)日：2012-06-26
申请号：US11363820
申请日：2006-02-28
IPC分类号： G06K9/20
CPC分类号： G06K9/00234 , H04N1/628 , H04N9/643
摘要： The disclosure is directed to techniques for region-of-interest (ROI) video processing based on low-complexity automatic ROI detection within video frames of video sequences. The low-complexity automatic ROI detection may be based on characteristics of video sensors within video communication devices. In other cases, the low-complexity automatic ROI detection may be based on motion information for a video frame and a different video frame of the video sequence. The disclosed techniques include a video processing technique capable of tuning and enhancing video sensor calibration, camera processing, ROI detection, and ROI video processing within a video communication device based on characteristics of a specific video sensor. The disclosed techniques also include a sensor-based ROI detection technique that uses video sensor statistics and camera processing side-information to improve ROI detection accuracy. The disclosed techniques also include a motion-based ROI detection technique that uses motion information obtained during motion estimation in video processing.
摘要翻译： 本公开涉及基于视频序列的视频帧内的低复杂度自动ROI检测的感兴趣区域（ROI）视频处理技术。 低复杂度的自动ROI检测可以基于视频通信设备内的视频传感器的特性。 在其他情况下，低复杂度自动ROI检测可以基于视频帧的运动信息和视频序列的不同视频帧。 所公开的技术包括基于特定视频传感器的特性，能够在视频通信设备内调整和增强视频传感器校准，相机处理，ROI检测和ROI视频处理的视频处理技术。 所公开的技术还包括基于传感器的ROI检测技术，其使用视频传感器统计和相机处理侧信息来提高ROI检测精度。 所公开的技术还包括基于运动的ROI检测技术，其使用在视频处理中的运动估计期间获得的运动信息。
-
公开(公告)号：US08019170B2
公开(公告)日：2011-09-13
申请号：US11364285
申请日：2006-02-28
CPC分类号： G06K9/00234 , H04N19/17 , H04N19/61
摘要： The disclosure is directed to techniques for region-of-interest (ROI) video processing based on low-complexity automatic ROI detection within video frames of video sequences. The low-complexity automatic ROI detection may be based on characteristics of video sensors within video communication devices. In other cases, the low-complexity automatic ROI detection may be based on motion information for a video frame and a different video frame of the video sequence. The disclosed techniques include a video processing technique capable of tuning and enhancing video sensor calibration, camera processing, ROI detection, and ROI video processing within a video communication device based on characteristics of a specific video sensor. The disclosed techniques also include a sensor-based ROI detection technique that uses video sensor statistics and camera processing side-information to improve ROI detection accuracy. The disclosed techniques also include a motion-based ROI detection technique that uses motion information obtained during motion estimation in video processing.
摘要翻译： 本公开涉及基于视频序列的视频帧内的低复杂度自动ROI检测的感兴趣区域（ROI）视频处理技术。 低复杂度的自动ROI检测可以基于视频通信设备内的视频传感器的特性。 在其他情况下，低复杂度自动ROI检测可以基于视频帧的运动信息和视频序列的不同视频帧。 所公开的技术包括基于特定视频传感器的特性，能够在视频通信设备内调整和增强视频传感器校准，相机处理，ROI检测和ROI视频处理的视频处理技术。 所公开的技术还包括基于传感器的ROI检测技术，其使用视频传感器统计和相机处理侧信息来提高ROI检测精度。 所公开的技术还包括基于运动的ROI检测技术，其使用在视频处理中的运动估计期间获得的运动信息。
-
公开(公告)号：US20070183661A1
公开(公告)日：2007-08-09
申请号：US11349659
申请日：2006-02-07
申请人： Khaled El-Maleh , Haohong Wang
发明人： Khaled El-Maleh , Haohong Wang
CPC分类号： G06K9/00234 , G06K9/00248 , G06T7/11 , G06T7/174 , G06T7/194 , G06T7/215 , G06T2207/10016 , G06T2207/20036 , G06T2207/20132 , G06T2207/30201
摘要： The disclosure is directed to techniques for automatic segmentation of a region-of-interest (ROI) video object from a video sequence. ROI object segmentation enables selected ROI or “foreground” objects of a video sequence that may be of interest to a viewer to be extracted from non-ROI or “background” areas of the video sequence. Examples of a ROI object are a human face or a head and shoulder area of a human body. The disclosed techniques include a hybrid technique that combines ROI feature detection, region segmentation, and background subtraction. In this way, the disclosed techniques may provide accurate foreground object generation and low-complexity extraction of the foreground object from the video sequence. A ROI object segmentation system may implement the techniques described herein. In addition, ROI object segmentation may be useful in a wide range of multimedia applications that utilize video sequences, such as video telephony applications and video surveillance applications.
摘要翻译： 本公开涉及从视频序列自动分割感兴趣区域（ROI）视频对象的技术。 ROI对象分割使得可以从视频序列的非ROI或“背景”区域中提取观看者感兴趣的视频序列的所选ROI或“前景”对象。 ROI对象的示例是人体的人脸或头肩部区域。 所公开的技术包括组合ROI特征检测，区域分割和背景减除的混合技术。 以这种方式，所公开的技术可以从视频序列提供前景对象生成和前景对象的低复杂度提取的准确性。 ROI对象分割系统可以实现本文描述的技术。 此外，ROI对象分割可能在使用诸如视频电话应用和视频监控应用之类的视频序列的多种多媒体应用中是有用的。
-
公开(公告)号：US20070076957A1
公开(公告)日：2007-04-05
申请号：US11364285
申请日：2006-02-28
申请人： Haohong Wang , Shuxue Quan , Khaled El-Maleh , Chlachuan Chiu , Xiaoyun Jiang
发明人： Haohong Wang , Shuxue Quan , Khaled El-Maleh , Chlachuan Chiu , Xiaoyun Jiang
CPC分类号： G06K9/00234 , H04N19/17 , H04N19/61
摘要： The disclosure is directed to techniques for region-of-interest (ROI) video processing based on low-complexity automatic ROI detection within video frames of video sequences. The low-complexity automatic ROI detection may be based on characteristics of video sensors within video communication devices. In other cases, the low-complexity automatic ROI detection may be based on motion information for a video frame and a different video frame of the video sequence. The disclosed techniques include a video processing technique capable of tuning and enhancing video sensor calibration, camera processing, ROI detection, and ROI video processing within a video communication device based on characteristics of a specific video sensor. The disclosed techniques also include a sensor-based ROI detection technique that uses video sensor statistics and camera processing side-information to improve ROI detection accuracy. The disclosed techniques also include a motion-based ROI detection technique that uses motion information obtained during motion estimation in video processing.
摘要翻译： 本公开涉及基于视频序列的视频帧内的低复杂度自动ROI检测的感兴趣区域（ROI）视频处理技术。 低复杂度的自动ROI检测可以基于视频通信设备内的视频传感器的特性。 在其他情况下，低复杂度自动ROI检测可以基于视频帧的运动信息和视频序列的不同视频帧。 所公开的技术包括基于特定视频传感器的特性，能够在视频通信设备内调整和增强视频传感器校准，相机处理，ROI检测和ROI视频处理的视频处理技术。 所公开的技术还包括基于传感器的ROI检测技术，其使用视频传感器统计和相机处理侧信息来提高ROI检测精度。 所公开的技术还包括基于运动的ROI检测技术，其使用在视频处理中的运动估计期间获得的运动信息。
-
公开(公告)号：US09667980B2
公开(公告)日：2017-05-30
申请号：US11200407
申请日：2005-08-09
申请人： Haohong Wang , Khaled Helmi El-Maleh , Yi Liang
发明人： Haohong Wang , Khaled Helmi El-Maleh , Yi Liang
IPC分类号： H04N7/18 , H04N19/196 , H04N19/147 , H04N19/172 , H04N19/115 , H04N19/126 , H04N19/132 , H04N19/14 , H04N19/137 , H04N19/154 , H04N19/162 , H04N19/177 , H04N19/17 , H04N19/587
CPC分类号： H04N19/198 , H04N19/115 , H04N19/126 , H04N19/132 , H04N19/137 , H04N19/14 , H04N19/147 , H04N19/154 , H04N19/162 , H04N19/17 , H04N19/172 , H04N19/177 , H04N19/196 , H04N19/587
摘要： The disclosure is directed to techniques for content-adaptive background skipping for region-of-interest (ROI) video coding. The techniques may be useful in video telephony (VT) applications such as video streaming and videoconferencing, and especially useful in low bit-rate wireless communication applications, such as mobile VT. The disclosed techniques analyze content information of a video frame to dynamically determine whether to skip a non-ROI area within the frame. For example, the skipping determination may be based on content activity, such as ROI shape deformation, ROI motion, non-ROI motion, non-ROI texture complexity, and accumulated distortion due to non-ROI skipping. The skip determination may operate in conjunction with either frame-level or macroblock-level bit allocation.
-
公开(公告)号：US08964127B2
公开(公告)日：2015-02-24
申请号：US13559595
申请日：2012-07-27
申请人： Haohong Wang
发明人： Haohong Wang
IPC分类号： H04N5/44
CPC分类号： H04N21/422 , H04N21/42204 , H04N21/44218
摘要： A method is provided for a user-sensing remote control system including a TV and a remote control. The method includes obtaining sensing data from a plurality of sensors in the remote control related to a user of the remote control, pre-processing the sensing data, and determining a user identity space containing a plurality of possible user identities of the user using a predetermined statistical algorithm. The method also includes determining whether there is a dominant possible user identity; when it is determined that there is no dominant possible user identity, selecting one or more possible user identities from the user identity space and updating the user identity space until there is a dominant possible user identity; and when it is determined that there is a dominant possible user identity, presenting the dominant possible user identity as the identity of the user to other applications.
摘要翻译： 提供了一种用于包括TV和遥控器的用户感测遥控系统的方法。 该方法包括从与遥控器的用户相关的遥控器中的多个传感器获得感测数据，预处理感测数据，以及使用预定的方式来确定包含用户的多个可能用户身份的用户身份空间 统计算法。 该方法还包括确定是否存在主导的可能的用户身份; 当确定不存在主导的可能的用户身份时，从用户身份空间中选择一个或多个可能的用户身份并更新用户身份空间，直到存在占主导地位的可能的用户身份; 并且当确定存在主导的可能的用户身份时，将主导的可能的用户身份呈现为用户的身份到其他应用。
-
公开(公告)号：US08595773B1
公开(公告)日：2013-11-26
申请号：US13559585
申请日：2012-07-26
申请人： Haohong Wang , Jim Xiao
发明人： Haohong Wang , Jim Xiao
CPC分类号： G06Q30/06 , H04N5/44543 , H04N21/422 , H04N21/43 , H04N21/44008 , H04N21/472 , H04N21/47815 , H04N21/6582 , H04N2005/44578
摘要： A method for an intelligent user-interaction control system includes generating a plurality of summary video frames for a certain time of incoming bit-stream of a video program to be shown on a display, and detecting a hold command from a user to stop the video program. The method also includes presenting the plurality of summary video frames to the user on the display after stopping the video program, obtaining a user selection on a selected summary frame from the plurality of the summary video frames, presenting a plurality of objects of interest from the selected summary frame to the user on the display, and determining a user-selected object of interest from the plurality of objects of interest. The method also includes searching the selected object in an online database to obtain searching results corresponding to the selected object, and prompting the user about the searching results.
摘要翻译： 一种用于智能用户交互控制系统的方法包括在显示器上显示的视频节目的输入比特流的特定时间生成多个摘要视频帧，以及检测来自用户的保持命令以停止视频 程序。 该方法还包括在停止视频节目之后在显示器上向用户呈现多个摘要视频帧，从多个摘要视频帧中获取用户对所选摘要帧的选择，从多个摘要视频帧中呈现多个感兴趣对象 在显示器上向用户选择的摘要帧，以及从多个感兴趣对象中确定用户选择的感兴趣对象。 该方法还包括在在线数据库中搜索所选择的对象以获得与所选对象相对应的搜索结果，并且向用户提示关于搜索结果。
-
-
-
-
-
-
-
-
-
搜索结果
58 条记录 (耗时 0.034 秒)
