-
Patent Agency Ranking
公开(公告)号：US20170163892A1
公开(公告)日：2017-06-08
申请号：US14957435
申请日：2015-12-02
Applicant: Intel Corporation
Inventor： Bosko Mihic , Stojan Rakic , Dusan Zoric , Zdravko Pantic
CPC classification number: H04N5/23254 , G06T5/003 , G06T5/50 , G06T7/246 , G06T2207/10016 , G06T2207/20021 , G06T2207/30196 , G06T2207/30221 , H04N5/145 , H04N5/23267
Abstract: Video stabilization is described using content-aware camera motion estimation. In some versions a luminance target frame and a luminance source frame of a sequence of video frames of a scene are received. Motion is extracted from the received luminance target and source frames and the motion is represented as a motion vector field and weights. The weights are divided into a first set of zeros weights for motion in the motion vector field that is near zero motion and a second set of peak weights for motion in the motion field that is not near zero. The zeros weights are compared to a threshold to determine whether there is motion in the scene and if the zeros weights exceed the threshold then selecting a zero motion motion model. A frame of the video sequence is adjusted corresponding to the target frame based on the selected motion model.
-
公开(公告)号：US09275468B2
公开(公告)日：2016-03-01
申请号：US14252944
申请日：2014-04-15
Applicant: Intel Corporation
Inventor： Vladimir Kovacevic , Zdravko Pantic , Aleksandar Beric , Milos Markovic , Vladimir Ilic
CPC classification number: G06T7/20 , G06K9/46 , G06K9/52 , G06K9/6215 , G06K2009/4666 , G06T7/262 , G06T2207/10016 , G06T2207/20021 , G06T2207/20056
Abstract: Techniques related to managing the use of motion estimation in video processing are discussed. Such techniques may include determining dividing two video frames each into corresponding regions, generating phase plane correlations for the corresponding regions, determining whether the video frames are motion estimation correlated based on the phase plane correlations, and providing a video frame prediction mode indicator based on the determination.
Abstract translation: 讨论了与视频处理中运动估计的使用有关的技术。 这样的技术可以包括确定将两个视频帧分成对应的区域，产生相应区域的相位平面相关性，基于相位平面相关性确定视频帧是否是运动估计相关的，以及基于 决心。
-
公开(公告)号：US09674439B1
公开(公告)日：2017-06-06
申请号：US14957435
申请日：2015-12-02
Applicant: Intel Corporation
Inventor： Bosko Mihic , Stojan Rakic , Dusan Zoric , Zdravko Pantic
CPC classification number: H04N5/23254 , G06T5/003 , G06T5/50 , G06T7/246 , G06T2207/10016 , G06T2207/20021 , G06T2207/30196 , G06T2207/30221 , H04N5/145 , H04N5/23267
Abstract: Video stabilization is described using content-aware camera motion estimation. In some versions a luminance target frame and a luminance source frame of a sequence of video frames of a scene are received. Motion is extracted from the received luminance target and source frames and the motion is represented as a motion vector field and weights. The weights are divided into a first set of zeros weights for motion in the motion vector field that is near zero motion and a second set of peak weights for motion in the motion field that is not near zero. The zeros weights are compared to a threshold to determine whether there is motion in the scene and if the zeros weights exceed the threshold then selecting a zero motion motion model. A frame of the video sequence is adjusted corresponding to the target frame based on the selected motion model.
-
公开(公告)号：US09407926B2
公开(公告)日：2016-08-02
申请号：US14287967
申请日：2014-05-27
Applicant: Intel Corporation
Inventor： Vladimir Kovacevic , Zdravko Pantic , Aleksandar Beric , Ramanathan Sethuraman , Jean-Pierre Giacalone , Anton Igorevich Veselov , Marat Ravilevich Gilmutdinov
IPC: G06K9/34 , H04N19/503 , G06T7/20 , H04N19/176 , H04N19/102 , H04N19/14 , H04N19/137 , H04N19/85 , H04N19/587
CPC classification number: H04N19/503 , H04N19/102 , H04N19/137 , H04N19/14 , H04N19/176 , H04N19/587 , H04N19/85
Abstract: Methods, apparatus, systems and articles of manufacture to perform block-based static region detection for video processing are disclosed. Disclosed example video processing methods include segmenting pixels in a first frame of a video sequence into a first plurality of pixel blocks. Such example methods can also include processing the first plurality of pixel blocks and a second plurality of pixel blocks corresponding to a prior second frame of the video sequence to create, based on a first criterion, a map identifying one or more static pixel blocks in the first plurality of pixel blocks. Such example methods can further include identifying, based on the map, a static region in the first frame of the video sequence.
Abstract translation: 公开了用于执行视频处理的基于块的静态区域检测的方法，装置，系统和制品。 公开的示例视频处理方法包括将视频序列的第一帧中的像素分割为第一多个像素块。 这样的示例性方法还可以包括处理第一多个像素块和与视频序列的先前第二帧相对应的第二多个像素块，以基于第一准则创建标识一个或多个静态像素块中的一个或多个静态像素块的映射 第一多个像素块。 这样的示例方法还可以包括基于该图来识别视频序列的第一帧中的静态区域。
-
公开(公告)号：US10007990B2
公开(公告)日：2018-06-26
申请号：US14757899
申请日：2015-12-24
Applicant: Intel Corporation
Inventor： Bosko Mihic , Zdravko Pantic
CPC classification number: G06T7/80 , G06T5/009 , G06T5/50 , G06T7/0002 , G06T2207/10016 , G06T2207/10144 , G06T2207/20221 , G06T2207/30168 , H04N5/265
Abstract: An example apparatus includes a kernel size estimator to estimate a blur kernel size of a captured image. The example apparatus also further includes a frame checker to discard the captured image if the estimated blur kernel size of the captured images exceeds a threshold kernel size. The captured image is to be used in a set if the estimated blur kernel size does not exceed the threshold kernel size. The example apparatus further includes a composite generator to generate a composite image based on the set of images.
-
-
-
-
Search Results
5
records
(took 0.009 seconds)
