公开(公告)号：EP3311334A1

公开(公告)日：2018-04-25

申请号：EP15895256.4

申请日：2015-06-18

申请人： WIZR ,  Cao, Song ,  Duan, Genquan

发明人： CAO, Song ,  DUAN, Genquan

IPC分类号： G06K9/60

CPC分类号： G06K9/00771 ,  G06K9/00711 ,  G06K9/00751 ,  G06K2009/00738

摘要： The current invention discloses a method comprising: determining a first feature description of an event in a first video; determining a first location of the event in the first video; determining a first time stamp of the first video; determining a second feature description of an event in a second video; determining a second location of the event in the second video; determining a second time stamp of the second video; and determining a correlation value based on the first location, the second location, the first time stamp, the second time stamp, the first feature description, and the second feature description.

公开(公告)号：EP3211596A1

公开(公告)日：2017-08-30

申请号：EP17156383.6

申请日：2017-02-15

申请人： Xerox Corporation

发明人： WANG, Qiao ,  GAIDON, Adrien ,  VIG, Eleonora

IPC分类号： G06T7/20 ,  G06T19/00

CPC分类号： G06K9/6262 ,  G06K9/00711 ,  G06K9/00751 ,  G06T7/20 ,  G06T19/00 ,  G06T2207/10016 ,  G06T2207/30236

摘要： A system and method are suited for assessing video performance analysis. A computer graphics engine clones real-world data in a virtual world by decomposing the real-world data into visual components and objects in one or more object categories and populates the virtual world with virtual visual components and virtual objects. A scripting component controls the virtual visual components and the virtual objects in the virtual world based on the set of real-world data. A synthetic clone of the video sequence is generated based on the script controlling the virtual visual components and the virtual objects. The real-world data is compared with the synthetic clone of the video sequence and a transferability of conclusions from the virtual world to the real-world is assessed based on this comparison.

摘要翻译： 系统和方法适用于评估视频性能分析。 计算机图形引擎通过将真实世界的数据分解为一个或多个对象类别中的可视化组件和对象，并利用虚拟可视化组件和虚拟对象填充虚拟世界，从而克服虚拟世界中的实际数据。 脚本组件基于真实世界数据集来控制虚拟世界中的虚拟可视组件和虚拟对象。 基于控制虚拟可视组件和虚拟对象的脚本来生成视频序列的合成克隆。 将真实世界的数据与视频序列的合成克隆进行比较，并根据此比较评估从虚拟世界到现实世界的结论的可转移性。

公开(公告)号：EP3163473A1

公开(公告)日：2017-05-03

申请号：EP16160483

申请日：2016-03-15

申请人： XIAOMI INC

发明人： ZHANG TAO ,  CHEN ZHIJUN ,  LONG FEI

IPC分类号： G06F17/30 ,  H04N21/482

CPC分类号： G11B27/10 ,  G06F17/30 ,  G06F17/3002 ,  G06K9/00751 ,  G06K9/00765 ,  G06K9/00771 ,  G06K2209/21 ,  H04L65/60 ,  H04N7/183 ,  H04N21/278 ,  H04N21/4828

摘要： Described is a video playing method and device, which belongs to the technical field of Internet. The method includes: a playing request is received (201), the playing request carrying target object information and the target object information including a target image where a target object is located or a target keyword of the target object; a video segment where the target object is located in a monitoring video is determined (202) on the basis of the target object information; and the video segment is sent (203) to a terminal to enable the terminal to play the video segment.

摘要翻译： 所描述的是一种视频播放方法及装置，属于互联网技术领域。 该方法包括：接收播放请求（201），该播放请求中携带有目标物信息和目标物信息，目标物信息包括目标物所在的目标图像或目标物的目标关键词; 基于目标对象信息来确定（202）目标对象位于监视视频中的视频片段; 并将视频片段发送（203）给终端，使终端能够播放视频片段。

公开(公告)号：EP3021258A2

公开(公告)日：2016-05-18

申请号：EP15194373.5

申请日：2015-11-12

申请人： Sony Corporation

发明人： Gurbuz, Sabri

IPC分类号： G06K9/46 ,  G06K9/00 ,  G06T7/20 ,  G06K9/52

CPC分类号： H04N19/527 ,  G06K9/00751 ,  G06K9/4652 ,  G06K9/52 ,  G06T7/00 ,  G06T7/20 ,  G06T7/90 ,  G06T2207/10016 ,  G11B27/28 ,  H04N5/147 ,  H04N19/105 ,  H04N19/139 ,  H04N19/142 ,  H04N19/172 ,  H04N19/87

摘要： Various aspects of a method and system to process video content are disclosed herein. The method includes determination of a first frame identification value associated with a video content. The first frame identification value corresponds to an average color value of a frame of the video content. The method further includes determination of a second frame identification value associated with the video content. The second frame identification value corresponds to a global motion vector (GMV) value of the frame of the video content. The method further includes determination of a first intermediate frame based on one or both of the first frame identification value and the second frame identification value.

摘要翻译： 这里公开了处理视频内容的方法和系统的各个方面。 该方法包括确定与视频内容相关联的第一帧识别值。 第一帧识别值对应于视频内容的帧的平均色彩值。 该方法还包括确定与视频内容相关联的第二帧识别值。 第二帧识别值对应于视频内容的帧的全局运动矢量（GMV）值。 该方法还包括基于第一帧识别值和第二帧识别值中的一个或两个确定第一中间帧。

公开(公告)号：EP2996067A1

公开(公告)日：2016-03-16

申请号：EP14794946.5

申请日：2014-05-05

申请人： Li, Dongge

发明人： Li, Dongge

IPC分类号： G06K9/00

CPC分类号： G06K9/00335 ,  G06K9/00751 ,  H04N7/18

摘要： Disclosed are a method and device for generating a motion signature on the basis of motion signature information. A detection is made on whether or not an activation-triggering criterion or generating the motion signature on the basis of the motion signature information is satisfied; when the activation-triggering criterion is satisfied, the motion feature information corresponding to a motion is determined on the basis of a detection of the motion that corresponds to the activation-triggering criterion; the motion signature information is encoded, and, the motion signature corresponding to the motion signature information is generated.

公开(公告)号：EP2960811A1

公开(公告)日：2015-12-30

申请号：EP14306009.3

申请日：2014-06-26

申请人： Thomson Licensing

发明人： Sharma, Gaurav ,  Perez, Patrick

IPC分类号： G06F17/30 ,  G06K9/00

CPC分类号： G06F17/3079 ,  G06F17/30837 ,  G06K9/00751

摘要： The present disclosure relates to a method for analyzing a database comprising a plurality of video images, characterized in that the method comprises the steps of:
- sampling (S1) each video image of at least a part of the plurality of video images of the database in order to get a plurality of image patches for said video image, each image patch being a portion of said video image;
- filtering (S2) said plurality of image patches based on at least one predetermined criterion in order to remove image patches having redundant visual content and to keep a limited group of visually non-similar image patches and/or visually non-similar image patches representative of said plurality of image patches ; and
- clustering (S2) image patches of said limited group of image patches into a plurality of clusters according to a visual similarity criterion, each cluster including image patches including visually and/or semantically similar visual motifs.

摘要翻译： 本发明涉及用于分析一个数据库，其包括视频图像，在DASS模方法，其特征的多个A方法包括以下步骤： - 采样（S1）的至少所述数据库的视频图像的多个部分的每个视频图像 为了得到用于所述视频图像的图像补丁复数，每个图像补丁是所述视频图像的至少一部分; - 过滤（S2）图像块，所述多个基于为了去除图像块具有冗余的视觉内容，并保持在视觉上不相似的图像块和/或视觉上不相似的图像块的代表的一组有限的至少一个预定准则 所述多个图像块; 以及 - 所述有限图像块组的聚类（S2）图像块为簇的多元性gemäß于视觉相似性准则，每个集群包括图像块包括视觉和/或语义上相似的视觉图案。

公开(公告)号：EP2176811A4

公开(公告)日：2015-09-30

申请号：EP08781639

申请日：2008-07-10

申请人： BEHAVIORAL RECOGNITION SYS INC

发明人： EATON JOHN ERIC ,  COBB WESLEY KENNETH ,  URECH DENNIS G ,  FRIEDLANDER DAVID S ,  XU GANG ,  SEOW MING-JUNG ,  RISINGER LON W ,  SOLUM DAVID M ,  YANG TAO ,  GOTTUMUKKAL RAJKIRAN K ,  SAITWAL KISHOR ADINATH

IPC分类号： G06K9/00

CPC分类号： G06K9/00718 ,  G06F17/30598 ,  G06K9/00335 ,  G06K9/00751 ,  G06K9/00771 ,  G06K9/6215 ,  G06K9/66 ,  G06K2009/00738 ,  G06N99/005

摘要： A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.

公开(公告)号：EP2754098A4

公开(公告)日：2015-09-02

申请号：EP12830794

申请日：2012-09-10

申请人： SAMSUNG ELECTRONICS CO LTD

发明人： SAXENA ANKUR ,  FERNANDES FELIX CARLOS ,  VADIVEL KARTHIKEYAN S ,  LAI WANG LIN ,  MA ZHAN

IPC分类号： G06K9/46 ,  G06F17/30 ,  G06K9/20

CPC分类号： G06F17/30784 ,  G06K9/00751

公开(公告)号：EP2902961A1

公开(公告)日：2015-08-05

申请号：EP13840346.4

申请日：2013-09-18

申请人： Olympus Corporation

发明人： YAGUCHI, Yoichi

IPC分类号： G06T1/00 ,  A61B1/00 ,  H04N5/91

CPC分类号： G06T5/50 ,  G06F17/30843 ,  G06K9/00751 ,  G06K9/6203 ,  G06K2209/05 ,  G06T7/0014 ,  G06T7/254 ,  G06T2207/10016 ,  G06T2207/10068 ,  G06T2207/30028 ,  G06T2207/30096 ,  H04N5/76

摘要： An image processing device includes an image sequence acquisition section (200) that acquires an image sequence that includes a plurality of constituent images, and a processing section (100) that performs an image summarization process that deletes some of the plurality of constituent images included in the image sequence to generate a summary image sequence, the processing section (100) selecting a reference image and a determination target image from the plurality of constituent images, detecting an unnecessary area from the determination target image, calculating a loss area based on deformation information about the reference image and the determination target image, and the unnecessary area, the loss area being an area that is lost when the determination target image is deleted, and determining whether or not the determination target image can be deleted based on the calculated loss area.

摘要翻译： 一种图像处理设备，包括：图像序列获取部分（200），其获取包括多个构成图像的图像序列;以及处理部分（100），其执行图像概要处理，该图像概要处理删除包括在图像序列中的多个构成图像中的一些 （100）从多个构成图像中选择参考图像和判定对象图像，根据判定对象图像检测不需要区域，根据变形信息计算出损失区域 关于参考图像和确定目标图像以及不必要区域，丢失区域是当确定目标图像被删除时丢失的区域，并且基于计算出的损失区域确定是否可以删除确定目标图像 。

公开(公告)号：EP2823754A1

公开(公告)日：2015-01-14

申请号：EP13757814.2

申请日：2013-03-07

申请人： OLYMPUS CORPORATION

发明人： YAGUCHI, Yoichi

IPC分类号： A61B5/00 ,  A61B1/00

CPC分类号： G06T7/30 ,  A61B1/00009 ,  F04C2270/0421 ,  G06F19/00 ,  G06F19/321 ,  G06K9/00751 ,  G06K9/68

摘要： An image processing device includes an image sequence acquisition section (200) that acquires an image sequence that includes a plurality of images, and a processing section (100) that performs an image summarization process that deletes some of the plurality of images included in the acquired image sequence to acquire a summary image sequence, the processing section (100) selecting a reference image and a determination target image from the plurality of images, calculating a coverage ratio of the determination target image by the reference image based on deformation information about the reference image and the determination target image, and determining whether or not the determination target image can be deleted based on the coverage ratio.

摘要翻译： 一种图像处理设备，包括：图像序列获取部分（200），其获取包括多个图像的图像序列;以及处理部分（100），其执行图像精简处理，所述图像精简处理删除包括在所获取的多个图像中的一些图像 图像序列以获取概要图像序列，处理部分（100）从多个图像中选择参考图像和确定目标图像，基于关于参考的变形信息来计算参考图像的确定目标图像的覆盖率 图像和确定目标图像，并且基于覆盖率确定是否可以删除确定目标图像。