公开(公告)号：US20140098879A1

公开(公告)日：2014-04-10

申请号：US13901148

申请日：2013-05-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Seung-Gu KIM ,  Tae Gyoung AHN ,  Se-Hyeok PARK

IPC: H04N7/36

CPC classification number: H04N19/513 ,  H04N19/521 ,  H04N19/553

Abstract: The present invention relates to a method and apparatus for motion estimation (ME) of a video in a video system. The method includes estimating an occlusion area by using a pattern map; removing a motion vector which corresponds to the estimated occlusion area from a motion vector field, and outputting remaining motion vectors as first candidate motion vectors; collecting motion vectors which correspond to an area of interest in the input video, detecting a representative motion vector which represents the collected motion vectors, and comparing the first candidate motion vectors with the representative motion vector removing a first candidate motion vector having a difference in a weight value from the representative motion vector which is greater than a first threshold value and outputting the remaining first candidate motion vectors as second candidate motion vectors; and performing a motion estimation operation by using the second candidate motion vectors.

Abstract translation: 本发明涉及视频系统中视频的运动估计（ME）的方法和装置。 该方法包括通过使用模式图来估计遮挡区域; 从运动矢量场去除对应于估计的遮挡区域的运动矢量，并输出剩余运动矢量作为第一候选运动矢量; 收集对应于所述输入视频中的感兴趣区域的运动矢量，检测表示所收集的运动矢量的代表运动矢量，以及将所述第一候选运动矢量与所述代表运动矢量进行比较，从而去除具有差异的第一候选运动矢量 将所述剩余的第一候选运动矢量作为第二候选运动矢量输出， 以及通过使用所述第二候选运动矢量来执行运动估计操作。

公开(公告)号：US20140064567A1

公开(公告)日：2014-03-06

申请号：US14013650

申请日：2013-08-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seung-Gu KIM ,  Se-Hyeok PARK ,  Tae-Gyoung AHN

IPC: G06T7/20

CPC classification number: G06T7/223 ,  G06T2207/10016 ,  G06T2207/20021

Abstract: An apparatus and method for motion estimation apparatus in an image processing system are provided. A depth information detector detects depth information relating to an input image on the basis of a predetermined unit. An image reconfigurer separates objects included in the input image based on the detected depth information and generates an image corresponding to each of the objects. A motion estimator calculates a motion vector of an object in each of the generated images, combines the motion vectors of the objects calculated for the generated images, and outputs a combined motion vector as a final motion estimate of the input image.

Abstract translation: 提供了一种图像处理系统中的运动估计装置的装置和方法。 深度信息检测器基于预定单元检测与输入图像相关的深度信息。 图像重新配置器基于检测到的深度信息分离输入图像中包括的对象，并且生成与每个对象相对应的图像。 运动估计器计算每个生成的图像中的对象的运动矢量，组合为生成的图像计算的对象的运动矢量，并输出组合运动矢量作为输入图像的最终运动估计。