公开(公告)号：WO2014110954A1

公开(公告)日：2014-07-24

申请号：PCT/CN2013/089703

申请日：2013-12-17

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： XU, Kun ,  WANG, Jianyu ,  LI, Baoli ,  DENG, Haifeng ,  ZHU, Zhe

IPC: G06F9/45

CPC classification number: G06T3/0062 ,  A61B6/025 ,  G02B13/06 ,  G06T3/0087 ,  G06T3/4038 ,  G06T5/005 ,  G06T2200/32 ,  G06T2207/20016 ,  H04N5/23238 ,  H04N5/3415 ,  H04N2013/0088

Abstract: A method for panoramic image completion is disclosed. The method includes: acquiring a panoramic image; obtaining a projected image by mapping pixels of the panoramic image onto a polar coordinate system, wherein a long side component of the pixel coordinate of the pixels is corresponding to the polar angle of the polar coordinate system and a short side component of the pixel coordinate of the pixels is corresponding to a radial coordinate of the polar coordinate system; acquiring an incomplete region of the projected image, and obtaining a completed image by completing the incomplete region; and obtaining a completed panoramic image by inverse mapping the pixels of the completed image according to the polar coordinate system. Furthermore, a device for panoramic image completion is also disclosed. The above method and device for panoramic image completion take account of the perspective curvature of the panoramic image, to improve the degree of restoration.

Abstract translation: 公开了一种用于全景图像完成的方法。 该方法包括：获取全景图像; 通过将全景图像的像素映射到极坐标系上来获得投影图像，其中像素的像素坐标的长边分量对应于极坐标系的极角和像素坐标的短边分量 像素对应于极坐标系的径向坐标; 获取投影图像的不完整区域，并通过完成不完整区域来获得完成图像; 以及通过根据极坐标系对映像完成的图像的像素来获得完整的全景图像。 此外，还公开了一种用于全景图像完成的装置。 上述用于全景图像完成的方法和装置考虑了全景图像的透视曲率，以提高恢复的程度。

公开(公告)号：WO2007057893A2

公开(公告)日：2007-05-24

申请号：PCT/IL2006/001320

申请日：2006-11-15

Applicant: YISSUM RESEARCH DEVELOPMENT COMPANY OF THE HEBREW UNIVERSITY OF JERUSALEM ,  PELEG, Shmuel ,  RAV-ACHA, Alexander

Inventor： PELEG, Shmuel ,  RAV-ACHA, Alexander

CPC classification number: G06F17/30843 ,  G06K9/00711 ,  G06T3/0087 ,  G11B27/034 ,  G11B27/28 ,  H04N5/2625

Abstract: A computer-implemented method and system transforms a first sequence of video frames of a first dynamic scene to a second sequence of at least two video frames depicting a second dynamic scene. A subset of video frames in the first sequence is obtained that show movement of at least one object having a plurality of pixels located at respective x, y coordinates and portions from the subset are selected that show non-spatially overlapping appearances of the at least one object in the first dynamic scene. The portions are copied from at least three different input frames to at least two successive frames of the second sequence without changing the respective x, y coordinates of the pixels in the object and such that at least one of the frames of the second sequence contains at least two portions that appear at different frames in the first sequence.

Abstract translation: 计算机实现的方法和系统将第一动态场景的第一视频帧序列变换为描绘第二动态场景的至少两个视频帧的第二序列。 获得第一序列中的视频帧的子集，其显示具有位于各自的x，y坐标处的多个像素的至少一个对象的移动，并且选择非空间示出的部分 在第一动态场景中重叠出现至少一个对象。 将这些部分从至少三个不同的输入帧复制到第二序列的至少两个连续帧，而不改变对象中像素的相应的x，y坐标，并且使得至少一个 第二个序列的帧包含至少两个出现在第一个序列中不同帧的部分。

公开(公告)号：WO2006048875A2

公开(公告)日：2006-05-11

申请号：PCT/IL2005001150

申请日：2005-11-02

Applicant: UNIV JERUSALEM YISSUM RES DEV ,  PELEG SHMUEL ,  RAV-ACHA ALEXANDER ,  LISCHINSKI DANIEL

Inventor： PELEG SHMUEL ,  RAV-ACHA ALEXANDER ,  LISCHINSKI DANIEL

IPC: G06T3/00

CPC classification number: G06T3/0087 ,  G06T13/80 ,  G06T2210/44 ,  H04N5/2625 ,  H04N5/2628

Abstract: A computer-implemented method and system for transforming a first sequence of video frames of a first dynamic scene captured at regular time intervals to a second sequence of video frames depicting a second dynamic scene wherein for at least two successive frames of the second sequence, there are selected from at least three different frames of the first sequence portions that are spatially contiguous in the first dynamic scene and copied to a corresponding frame of the second sequence so as to maintain their spatial continuity in the first sequence. In a second aspect, for at least one feature in the first dynamic scene respective portions of the first sequence of video frames are sampled at a different rate than surrounding portions of the first sequence of video frames; and the sampled portions are copied to a corresponding frame of the second sequence.

Abstract translation: 一种计算机实现的方法和系统，用于将以规则的时间间隔捕获的第一动态场景的第一视频帧序列变换为描述第二动态场景的第二视频帧序列，其中对于第二序列的至少两个连续帧， 是从在第一动态场景中在空间上连续的第一序列部分的至少三个不同帧中选择的并且被复制到第二序列的对应帧中以便保持它们在第一序列中的空间连续性。 在第二方面，对于第一动态场景中的至少一个特征，以与第一视频帧序列的周围部分不同的速率对第一视频帧序列的相应部分进行采样; 并且采样的部分被复制到第二序列的对应帧。

公开(公告)号：WO00008858A1

公开(公告)日：2000-02-17

申请号：PCT/EP1999/005511

申请日：1999-07-29

IPC: H04N5/262 ,  G06T3/00 ,  H04N1/387 ,  H04N7/26 ,  H04N7/32

CPC classification number: G06K9/32 ,  G06K2009/2045 ,  G06T3/0087 ,  H04N19/23

Abstract: The invention relates to a method and device for generating a large static image M(n), such as a sprite or a mosaic, from a video sequence including successive video objects. This method comprises a first step for estimating motion parameters related to the current video object V0(n) of the sequence with respect to the previously generated static image M(n-1), a second step for warping this video object on the basis of the estimated motion parameters, and a third step for blending the warped video object WV0(n) thus obtained with the previously generated static image M(n-1). According to the invention, an additional step for computing, for each picture element of the current video object, a weighting coefficient WWF(n)[x,y] correlated to the error between the warped video object and the static image M(n-1) is provided, and the blending formula now takes into account said weighting coefficients.

Abstract translation: 本发明涉及一种用于从包括连续视频对象的视频序列生成诸如子画面或马赛克的大静态图像M（n）的方法和装置。 该方法包括：第一步骤，用于相对于先前产生的静态图像M（n-1）估计与序列的当前视频对象V0（n）相关的运动参数;第二步骤，用于基于 估计运动参数，以及用于将由此获得的翘曲视频对象WV0（n）与先前产生的静态图像M（n-1）进行混合的第三步骤。 根据本发明，对于当前视频对象的每个图像元素，计算与翘曲视频对象与静态图像M（n-1）之间的误差相关的加权系数WWF（n）[x，y] 1），并且混合公式现在考虑到所述加权系数。

公开(公告)号：WO2017187821A1

公开(公告)日：2017-11-02

申请号：PCT/JP2017/010034

申请日：2017-03-13

Applicant: ソニー株式会社

Inventor： 笠原　俊一 ,  右田　隆仁 ,  高橋　慧 ,  角田　智弘

IPC: H04N21/2343 ,  G06T3/00 ,  G06T19/00 ,  H04N21/218

CPC classification number: H04N13/194 ,  G06T3/00 ,  G06T3/0087 ,  G06T19/00 ,  H04N5/23238 ,  H04N13/111 ,  H04N13/167 ,  H04N13/172 ,  H04N21/218 ,  H04N21/2187 ,  H04N21/2343 ,  H04N21/42201 ,  H04N21/4223 ,  H04N21/816

Abstract: 全天周映像のマッピング処理を行なう情報処理装置及び情報処理方法を提供する。　全天周映像を撮像する映像提供装置側の状況、全天周映像を視聴する映像再生装置側の状況、被写体となる空間の状況、配信先が複数になる場合の状況、伝送路の状況などに基づいて、要求されるデータ削減量や画質の保存状態を割り出し、適合するマッピング方法に適応的に切り替えて、全天周映像の伝送を行なう。また、受信側で元の全天周映像を復元できるようにするために、マッピング方法を示す情報を含んだ伝送フォーマットで、全天周映像の伝送を行なう。

Abstract translation:

以提供充分天守信息处理装置和用于视频的映射处理的信息处理方法。 该图像用于成像整个天守视频情况提供装置，所有天守的图像再现装置的侧视图照片状态，受试者，情况，其中传送目的地是多重的，空间的状态，例如信道条件 基于，索引数据缩减和图像质量的所请求的量的所存储的状态，自适应地在一个兼容的映射方法切换，以发送整个天守图像。 此外，为了能够恢复在接收侧的原始总天守视频，包括指示所述映射方法的信息的传输格式，发送整个天守图像。

公开(公告)号：WO2015050795A1

公开(公告)日：2015-04-09

申请号：PCT/US2014/057860

申请日：2014-09-26

Applicant: REALD INC. ,  KARAFIN, Jon ,  KUMAR, Mrityunjay

Inventor： KARAFIN, Jon ,  KUMAR, Mrityunjay

IPC: H04N5/76 ,  G06T5/00

CPC classification number: G06K9/4609 ,  G06T3/0087 ,  G06T3/4038 ,  G06T5/002 ,  G06T5/007 ,  G06T5/50 ,  G06T2207/10016 ,  G06T2207/20076 ,  G06T2207/20182 ,  G06T2207/20208 ,  H04N5/76 ,  H04N5/911

Abstract: Systems, devices, and methods disclosed herein may apply a computational spatial-temporal analysis to assess pixels between temporal and/or perspective view imagery to determine imaging details that may be used to generate image data with increased signal-to-noise ratio.

Abstract translation: 本文公开的系统，装置和方法可以应用计算空间 - 时间分析来评估时间和/或透视图像之间的像素，以确定可用于生成具有增加的信噪比的图像数据的成像细节。

公开(公告)号：WO2015048048A1

公开(公告)日：2015-04-02

申请号：PCT/US2014/057086

申请日：2014-09-24

Applicant: FARO TECHNOLOGIES, INC.

Inventor： BECKER, Reinhard ,  OSSIG, Martin

IPC: G01S17/89 ,  G01C3/06 ,  G01C15/00 ,  G01S17/36 ,  G06T7/00 ,  G06T19/00 ,  G01S7/51

CPC classification number: G06T3/0087 ,  G01B11/24 ,  G01C3/06 ,  G01C15/002 ,  G01S7/51 ,  G01S17/023 ,  G01S17/89 ,  G06T7/38 ,  G06T7/521 ,  G06T7/579 ,  G06T19/003 ,  G06T2207/10016 ,  G06T2207/10021 ,  H04N5/147 ,  H04N5/23238 ,  H04N13/257 ,  H04N13/324

Abstract: A method interactively displays panoramic images of a scene. The method includes measuring 3D coordinates of the scene with a 3D measuring instrument at a first position and a second position. The 3D coordinates are registering into a common frame of reference. Within the scene, a trajectory includes a plurality of trajectory points. Along the trajectory, 2D images are generated from the commonly registered 3D coordinates. A user interface provides a trajectory display mode that sequentially displays a collection of 2D images at the trajectory points. The user interface also provides a rotational display mode that allows a user to select a desired view direction at a given trajectory point. The user selects the trajectory display mode or the rotational display mode and sees the result shown on the display device.

Abstract translation: 一种交互式显示场景全景图像的方法。 该方法包括使用3D测量仪器在第一位置和第二位置处测量场景的3D坐标。 3D坐标正在注册到公共参考系。 在场景内，轨迹包括多个轨迹点。 沿着轨迹，从共同注册的3D坐标生成2D图像。 用户界面提供轨迹显示模式，其在轨迹点处依次显示2D图像的集合。 用户界面还提供旋转显示模式，其允许用户在给定的轨迹点处选择期望的视图方向。 用户选择轨迹显示模式或旋转显示模式，并看到显示设备上显示的结果。

公开(公告)号：WO2013106652A1

公开(公告)日：2013-07-18

申请号：PCT/US2013/021149

申请日：2013-01-11

Applicant: GOOGLE INC.

Inventor： JONES, Jonah ,  SIMPSON, Matthew, Robert

IPC: G06T15/00

CPC classification number: G06T3/0087 ,  G06F17/30241 ,  G06T15/20 ,  G06T17/05 ,  H04N5/23238

Abstract: Methods and systems for navigating panoramic imagery are provided. If a user rotates panoramic imagery to a view having a view angle that deviates beyond a threshold view angle, the view of the panoramic imagery will be adjusted to the threshold view angle. In a particular implementation, the view is drifted to the threshold view angle so that a user can at least temporarily view the imagery that deviates beyond the threshold view angle. A variety of transition animations can be used as the imagery is drifted to the threshold view angle. For instance, the view can be elastically snapped back to the threshold view angle to provide a visually appealing transition to a user.

Abstract translation: 提供了导航全景图像的方法和系统。 如果使用者将全景图像转换为具有偏离超过阈值视角的视角的视图，则全景图像的视图将被调整到阈值视角。 在特定实现中，视图被漂移到阈值视角，使得用户可以至少临时观看偏离超过阈值视角的图像。 当图像漂移到阈值视角时，可以使用各种转换动画。 例如，视图可以被弹性地卡扣回到阈值视角，以向用户提供视觉吸引人的过渡。

公开(公告)号：WO2008017051A2

公开(公告)日：2008-02-07

申请号：PCT/US2007/075122

申请日：2007-08-02

Applicant: INNEROPTIC TECHNOLOGY INC.

Inventor： RAZZAQUE, Sharif, A. ,  KELLER, Kurtis, P. ,  STATE, Andrei ,  GREEN, Caroline, K. ,  ACKERMAN, Jeremy, D.

IPC: H04N7/18

CPC classification number: G06T3/0087 ,  A61B1/0005 ,  A61B1/042 ,  A61B1/313 ,  A61B8/12 ,  A61B8/463 ,  A61B8/5238 ,  H04N7/181

Abstract: A system and method of providing composite real-time dynamic imagery of a medical procedure site from multiple modalities which continuously and immediately depicts the current state and condition of the medical procedure site synchronously with respect to each modality and without undue latency is disclosed. The composite real-time dynamic imagery may be provided by spatially registering multiple real-time dynamic video streams from the multiple modalities to each other. Spatially registering the multiple real-time dynamic video streams to each other may provide a continuous and immediate depiction of the medical procedure site with an unobstructed and detailed view of a region of interest at the medical procedure site at multiple depths. As such, a surgeon, or other medical practitioner, may view a single, accurate, and current composite real-time dynamic imagery of a region of interest at the medical procedure site as he/she performs a medical procedure, and thereby, may properly and effectively implement the medical procedure.

Abstract translation: 公开了一种从多种模式提供医疗程序现场的复合实时动态图像的系统和方法，其连续并立即描绘了相对于每个模态并且没有不适当延迟的医疗程序现场的当前状态和状况。 复合实时动态图像可以通过将来自多个模态的多个实时动态视频流空间注册到彼此来提供。 将多个实时动态视频流空间注册到彼此可以提供医疗程序站点的连续且立即的描述，其中在医疗程序站点的多个深度处，不受阻碍地和详细地观察感兴趣的区域。 因此，外科医生或其他医生可以在执行医疗程序时在医疗程序现场查看感兴趣区域的单一，准确和当前的复合实时动态图像，从而可以适当地 有效实施医疗程序。

公开(公告)号：WO2012015563A1

公开(公告)日：2012-02-02

申请号：PCT/US2011/042904

申请日：2011-07-03

Applicant: HARRIS CORPORATION

Inventor： HACKETT, Jay ,  BAKIR, Tariq ,  JACKSON, Jeremy ,  CANNATA, Richard ,  RILEY, Ronald Alan

IPC: G06T3/00 ,  G06F17/30

CPC classification number: G06T3/0087 ,  G06F17/30784 ,  G06F17/30843 ,  G06T7/33 ,  G06T2207/10032 ,  G06T2207/30181

Abstract: The video summarization system and method supports a moving sensor or multiple sensors by mapping imagery back to a common ortho-rectified geometry. The video summarization system includes at least one video sensor to acquire video data, of at least one area of interest (AOI), including video frames having a plurality of different perspectives. The video sensor may be a moving sensor or a plurality of sensors to acquire video data, of the at least one AOI, from respective different perspectives. A memory stores the video data, and a processor is configured to cooperate with the memory to register video frames from the AOI, ortho-rectify registered video frames based upon a common geometry, identify events within the ortho-rectified registered video frames, and generate a video summary of selected events shifted in time within a selected AOI based upon identified events within the ortho-rectified registered video frames.

Abstract translation: 视频摘要系统和方法通过将图像映射到普通的正交校正几何形状来支持移动传感器或多个传感器。 视频摘要系统包括至少一个视频传感器，以获取至少一个感兴趣区域（AOI）的视频数据，包括具有多个不同视角的视频帧。 视频传感器可以是移动传感器或多个传感器，以从各个不同的角度获取至少一个AOI的视频数据。 存储器存储视频数据，并且处理器被配置为与存储器协作以从AOI注册视频帧，基于公共几何对邻接校正注册的视频帧进行校正，识别经正射校正的已注册视频帧内的事件，并生成 基于在经矫正的已注册视频帧内的已识别事件，所选事件在所选AOI内在时间上移动的视频摘要。