专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

EP2697777A1 IMAGE PROCESSING 审中-公开
标题翻译：图像处理
公开(公告)号：EP2697777A1
公开(公告)日：2014-02-19
申请号：EP12712888.2
申请日：2012-04-02
申请人： LiberoVision AG
发明人： NIEDERBERGER, Christoph , WÜRMLIN STADLER, Stephan , ZIEGLER, Remo , FERIENCIK, Marco , BURCH, Andreas , DÖNNI, Urs , KEISER, Richard , VOGEL WENZIN, Julia
IPC分类号： G06T11/00
CPC分类号： G06K9/00624 , G06T11/00 , G06T2200/04 , G06T2207/10016 , G06T2207/30228 , G06T2219/004
摘要： A method of processing image data comprises the steps of: • providing an image sequence such as a video sequence, or a camera transition, • identifying a region-of-interest (1) in at least one image of the image sequence, • defining a transition region around the region-of-interest (1) and defining a remaining portion of the image to be a default region or background region, • applying different image effects to the region-of-interest (1), the transition region and the background region.
摘要翻译：一种处理图像数据的方法包括以下步骤：提供诸如视频序列或相机转变的图像序列;识别图像序列的至少一个图像中的感兴趣区域（1）;定义（1）周围的过渡区域并将图像的剩余部分定义为默认区域或背景区域;·将不同的图像效果应用于感兴趣区域（1），过渡区域和背景区域。

2. 发明公开

EP2707834A2 SILHOUETTE-BASED POSE ESTIMATION 有权转让
标题翻译： SILHOUETTENBASIERTEPOSENSCHÄTZUNG
公开(公告)号：EP2707834A2
公开(公告)日：2014-03-19
申请号：EP12720395.8
申请日：2012-05-08
申请人： LiberoVision AG
发明人： POPA, Tiberiu , GERMANN, Marcel , KEISER, Richard , GROSS, Markus , ZIEGLER, Remo
IPC分类号： G06K9/00 , G06T7/00
摘要： Estimating a pose of an articulated 3D object model (4) by a computer is done by •obtaining a sequence of source images (10) and therefrom corresponding source image segments (13) with objects (14) separated from the image background; •matching such a sequence (51) with sequences (52) of reference silhouettes (13′), determining one or more selected sequences of reference silhouettes (13′) forming a best match; •for each of these selected sequences of reference silhouettes (13′), retrieving a reference pose that is associated with one of the reference silhouettes (13′); and •computing an estimate of the pose of the articulated object model (4) from the retrieved reference pose or poses. The result of these steps is an initial pose estimate, which then can be used in further steps, for example, for maintaining local consistency between pose estimates from consecutive frames, and global consistency over a longer sequence of frames.
摘要翻译：通过计算机估计关节式3D对象模型（4）的姿态是通过以下步骤完成的：通过从图像背景分离的对象（14）获得源图像序列（10）及其对应的源图像片段（13）; 将这样的序列（51）与参考轮廓（13'）的序列（52）匹配，确定形成最佳匹配的一个或多个所选择的参考轮廓序列（13'）; •对于这些所选择的参考轮廓序列（13'）中的每一个，检索与所述参考轮廓（13'）之一相关联的参考姿势; 以及•从检索到的参考姿势或姿势计算所述铰接对象模型（4）的姿态的估计。这些步骤的结果是初始姿态估计，其然后可以用于进一步的步骤，例如，用于维持来自连续帧的姿态估计之间的局部一致性，以及在更长的帧序列上的全局一致性。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式