专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

71. 发明申请

WO2013056311A1 KEYPOINT BASED KEYFRAME SELECTION 审中-公开
标题翻译：基于键盘的键盘选择
公开(公告)号：WO2013056311A1
公开(公告)日：2013-04-25
申请号：PCT/AU2012/001272
申请日：2012-10-18
申请人： THE UNIVERSITY OF SYDNEY , WANG, Zhiyong , FENG, Dagan
发明人： WANG, Zhiyong , FENG, Dagan
IPC分类号： G06K9/72 , G06T7/40
CPC分类号： G06K9/72 , G06K9/00751 , G06K9/4671
摘要： Disclosed herein are a keypoint based keyframe selection (KBKS) video compression system and method. The disclosed method of compressing a video sequence identifies unique keypoints in each frame in a video sequence (110) and forms a global keypoint pool, based on the identified unique keypoints. The method then associates each frame with a selection value based on a number of unique keypoints identified in that frame (115, 120) and selects keyframes of the video sequence, based upon the selection values (125). The selection values include a coverage value and an optional redundancy value.
摘要翻译：这里公开了一种基于关键点的关键帧选择（KBKS）视频压缩系统和方法。所公开的压缩视频序列的方法在视频序列（110）中识别每个帧中的唯一关键点，并且基于所识别的唯一关键点形成全局关键点池。该方法然后基于在该帧（115,120）中识别的唯一关键点的数量将每个帧与选择值相关联，并且基于选择值（125）选择视频序列的关键帧。选择值包括覆盖值和可选冗余值。

72. 发明申请

WO2012019417A8 DEVICE, SYSTEM AND METHOD FOR ONLINE VIDEO CONDENSATION 审中-公开
标题翻译：用于在线视频缩合的装置，系统和方法
公开(公告)号：WO2012019417A8
公开(公告)日：2012-12-06
申请号：PCT/CN2010080607
申请日：2010-12-31
申请人： CHINESE ACAD INST AUTOMATION , AUTHENMETRIC CO LTD , LI ZIQING , FENG SHIKUN , WANG RUI , LEI ZHEN
发明人： LI ZIQING , FENG SHIKUN , WANG RUI , LEI ZHEN
IPC分类号： G06F17/30
CPC分类号： H04N21/234318 , G06F17/30843 , G06K9/00711 , G06K9/00751 , G06T7/11 , G06T7/194 , G06T7/215 , H04N19/137 , H04N19/20
摘要： A device, system and method for online video condensation are provided. The method comprises: step 1, obtaining a frame of image; step 2, segmenting a foreground image and a background image from the image, and carrying out step 3 on the segmented foreground image, and carrying out step 5 on the segmented background image; step 3, extracting moving objects from the foreground image; step 4, circularly executing step 1 to step 3, and cumulating the moving objects respectively extracted from each frame of foreground image to form a moving object sequence until the number of cycles reaching a predetermined value; step 5, circularly executing step 1 to step 2, and cumulating the background image of each frame of image and extracting n frames of specific background images as a main background sequence until the number of cycles reaching a predetermined value; step 6, mosaicking the main background sequence and the moving object sequence to form a condensation video. The method utilizes an online condensation mode, and shortens the length of the condensation video and retains the information of the moving objects of the video as much as possible.
摘要翻译：提供了一种用于在线视频缩合的装置，系统和方法。该方法包括：步骤1，获取图像帧; 步骤2，从图像中分割出前景图像和背景图像，对分割后的前景图像进行步骤3，对分割后的背景图像进行步骤5; 步骤3，从前景图像中提取移动物体; 步骤4，循环执行步骤1至步骤3，累积分别从前景图像的各帧中提取的运动物体，形成运动物体序列，直至达到预定值的周期数; 步骤5，循环执行步骤1至步骤2，累积每帧图像的背景图像并提取n帧特定背景图像作为主背景序列，直至达到预定值的周期数; 步骤6，镶嵌主背景序列和运动对象序列以形成凝结视频。该方法利用在线凝结模式，缩短凝结视频的长度，尽可能保留视频运动物体的信息。

73. 发明申请

WO2012139228A1 VIDEO-BASED DETECTION OF MULTIPLE OBJECT TYPES UNDER VARYING POSES 审中-公开
标题翻译：基于视频检测的多个对象类型在不同的位置
公开(公告)号：WO2012139228A1
公开(公告)日：2012-10-18
申请号：PCT/CA2012/050239
申请日：2012-04-13
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION , IBM CANADA LIMITED-IBM CANADA LIMITEE
发明人： DATTA, Ankur , FERIS, Rogerio S. , PANKANTI, Sharathchandra , SIDDIQUIE, Behjat , ZHAI, Yun
IPC分类号： G01V8/10 , G01B11/04 , G06T7/20
CPC分类号： G06K9/4604 , G06K9/00751
摘要： Training data object images are clustered as a function of motion direction attributes and resized from respective original into same aspect ratios. Motionlet detectors are learned for each of the sets from features extracted from the resized object blobs. A deformable sliding window is applied to detect an object blob in input by varying window size, shape or aspect ratio to conform to a shape of the detected input video object blob. A motion direction of an underlying image patch of the detected input video object blob is extracted and motionlet detectors selected and applied that have similar motion directions. An object is thus detected within the detected blob and semantic attributes of an underlying image patch extracted if a motionlet detectors fires, the extracted semantic attributes available for use for searching for the detected object.
摘要翻译：训练数据对象图像作为运动方向属性的函数进行聚类，并从相应的原始尺寸变为相同的宽高比。通过从调整大小的对象斑点中提取的特征，为每个集合学习运动检测器。应用可变形滑动窗口通过改变窗口尺寸，形状或宽高比来检测输入中的对象斑点，以符合检测到的输入视频对象斑点的形状。提取检测到的输入视频对象斑点的底层图像块的运动方向，并选择并应用具有相似运动方向的运动检测器。因此，如果移动检测器触发，则所提取的底层图像块的检测到的blob和语义属性中的对象被检测到，所提取的语义属性可用于搜索检测到的对象。

74. 发明申请

WO2012138491A2 VIDEO SIGNATURE 审中-公开
标题翻译：视频签名
公开(公告)号：WO2012138491A2
公开(公告)日：2012-10-11
申请号：PCT/US2012/030396
申请日：2012-03-23
申请人： MICROSOFT CORPORATION
发明人： HENDRICKSON, Seth , DONG, George Randell , MANDAL, Saswata , ZITNICK III, Charles Lawrence
IPC分类号： H04N7/16 , H04N7/26
CPC分类号： H04N21/8352 , G06F17/30781 , G06K9/00751
摘要： Video signatures are generated when a small change in video information between consecutive frames N-1 and N is followed by a large change in video information between consecutive frames N and N+1. Information from frames N and/or N+1 is used to form a video signature.
摘要翻译：当在连续帧N-1和N之间的视频信息的小变化后跟随连续帧N和N + 1之间的视频信息的大的变化时，产生视频签名。来自帧N和/或N + 1的信息用于形成视频签名。

75. 发明申请

WO2012068154A1 METHOD AND SYSTEM FOR VIDEO SUMMARIZATION 审中-公开
标题翻译：视频总结方法与系统
公开(公告)号：WO2012068154A1
公开(公告)日：2012-05-24
申请号：PCT/US2011/060847
申请日：2011-11-15
申请人： GAO, Jizhou , HUANG, Yu , YU, Hong Heather , HUAWEI TECHNOLOGIES CO., LTD.
发明人： GAO, Jizhou , HUANG, Yu , YU, Hong Heather
IPC分类号： H04N9/73
CPC分类号： G10L15/02 , G06K9/00744 , G06K9/00751 , G06K9/00765 , G10L15/08 , H04N21/4358 , H04N21/44008 , H04N21/44016 , H04N21/44029 , H04N21/8549
摘要： A video summary method comprises dividing a video (202) into a plurality of video shots (206), analyzing each frame in a video shot (206) from the plurality of video shots (206), determining a saliency of each frame of the video shot, determining a key frame (210) of the video shot (206) based on the saliency of each frame of the video shot (206), extracting visual features from the key frame (210) and performing shot clustering of the plurality of video shots (206) to determine concept patterns based on the visual features. The method further comprises fusing different concept patterns using a saliency tuning method and generating a summary of the video based upon a global optimization method.
摘要翻译：视频摘要方法包括将视频（202）划分成多个视频镜头（206），分析来自多个视频镜头（206）的视频镜头（206）中的每个帧，确定视频的每个帧的显着性拍摄，基于视频镜头（206）的每个帧的显着性确定视频镜头（206）的关键帧（210），从关键帧（210）提取视觉特征并执行多个视频的拍摄聚类拍摄（206）以基于视觉特征来确定概念模式。该方法还包括使用显着性调整方法来融合不同的概念模式，并且基于全局优化方法生成视频的摘要。

76. 发明申请

WO2010000163A1 提取视频摘要的方法、系统及设备审中-公开
公开(公告)号：WO2010000163A1
公开(公告)日：2010-01-07
申请号：PCT/CN2009/071953
申请日：2009-05-25
申请人：腾讯科技(深圳)有限公司 , 李世平
发明人：李世平
IPC分类号： G11B27/00
CPC分类号： G06K9/00751

77. 发明申请

WO2009009697A1 COGNITIVE MODEL FOR A MACHINE-LEARNING ENGINE IN A VIDEO ANALYSIS SYSTEM 审中-公开
标题翻译：视频分析系统中机器学习引擎的认知模型
公开(公告)号：WO2009009697A1
公开(公告)日：2009-01-15
申请号：PCT/US2008/069700
申请日：2008-07-10
申请人： BEHAVIORAL RECOGNITION SYSTEMS, INC. , 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
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.
摘要翻译：公开了一种机器学习引擎，其被配置为通过分析移动和/或活动（或不存在）来识别和学习行为，以及识别和区分场景内的正常和异常行为）随着时间的推移。机器学习引擎可以被配置为评估针对在视频帧序列中描绘的对象和相关矢量表示的原始事件序列和相关联的运动学数据。矢量表示从原始事件符号流和相空间符号流生成，并且流描述了在视频帧序列中描绘的对象的动作。

78. 发明申请

WO2008049851A3 METHOD FOR COMPARING GROUPS OF IMAGES 审中-公开
标题翻译：比较图像组的方法
公开(公告)号：WO2008049851A3
公开(公告)日：2008-11-27
申请号：PCT/EP2007061385
申请日：2007-10-24
申请人： THOMSON LICENSING , LEFEBVRE FREDERIC , MASSOUDI AYOUB
发明人： LEFEBVRE FREDERIC , MASSOUDI AYOUB
IPC分类号： G06K9/00 , G06K9/68
CPC分类号： G06K9/00751 , G06F17/30799 , G06K9/6857
摘要： The invention relates to a method for comparing a group of images, called candidate group, with reference groups of images, said reference groups being stored in a database with their representing key frames to which are associated local features and global features. The method comprises the following steps: - detecting an image within said candidate group, called key frame; - computing a global feature of said key frame; - comparing said computed global feature with the global feature of each key frame of the reference group; - if the differences between said computed global feature and each stored global feature are above a predefined threshold then: computing a local feature of said key frame; comparing said computed local feature with the local feature of each key frame of the reference group.
摘要翻译：本发明涉及一种用于将称为候选组的图像组与参考图像组进行比较的方法，所述参考组被存储在具有与其相关联的局部特征和全局特征的关键帧的数据库中。该方法包括以下步骤： - 检测所述候选组内的称为关键帧的图像; - 计算所述关键帧的全局特征; - 将所述计算的全局特征与所述参考组的每个关键帧的全局特征进行比较; - 如果所述计算的全局特征与每个存储的全局特征之间的差异高于预定阈值，则：计算所述关键帧的局部特征; 将所述计算的局部特征与参考组的每个关键帧的本地特征进行比较。

79. 发明申请

WO2004040479A1 METHOD FOR MINING CONTENT OF VIDEO 审中-公开
标题翻译：采矿视频内容的方法
公开(公告)号：WO2004040479A1
公开(公告)日：2004-05-13
申请号：PCT/JP2003/013202
申请日：2003-10-15
申请人： MITSUBISHI DENKI KABUSHIKI KAISHA
发明人： DIVAKARAN, Ajay , PEKER, Kadir, A.
IPC分类号： G06F17/30
CPC分类号： G06K9/00751 , G06F17/30787 , G06F17/30802 , G06F17/30808 , G06F17/30811 , G06F17/30843
摘要： A method for mining unknown content of a video by first selecting one or more low-level features of the video. For each selected feature, or combination of features, time series data is generated. The time series data is then self-correlated to identify similar segments of the video according to the low-level features. The similar segments are grouped into clusters to discover high-level patterns in the unknown content of video.
摘要翻译：通过首先选择视频的一个或多个低级特征来挖掘视频的未知内容的方法。对于每个选定的特征或特征的组合，生成时间序列数据。然后，时间序列数据被自相关，以根据低级特征来识别视频的类似片段。类似的段被分组成群集以发现视频的未知内容中的高级模式。

80. 发明申请

WO00040011A1 METHOD FOR EDITING VIDEO INFORMATION AND EDITING DEVICE 审中-公开
标题翻译：编辑视频信息和编辑设备的方法
公开(公告)号：WO00040011A1
公开(公告)日：2000-07-06
申请号：PCT/JP1999/007419
申请日：1999-12-28
IPC分类号： G11B27/024 , G11B27/026 , G11B27/031 , G11B27/032 , G11B27/034 , G11B27/11 , H04N5/262 , H04N9/804 , H04N5/91
CPC分类号： H04N5/262 , G06K9/00751 , G11B27/024 , G11B27/026 , G11B27/031 , G11B27/032 , G11B27/034 , G11B27/11 , G11B2220/216 , G11B2220/2575 , G11B2220/90 , H04N9/8045
摘要： The full video of a video title is divided into shot or scene units with time codes. Given condition information, which is semantic evaluation of a story, is added to each scene unit to produce a scene score, scenes necessary for each use and object are extracted according to the scene score and a threshold (process Pr14), evaluation information on video characteristic is added to each shot constituting each extracted scene to produce a shot score (process Pr16), optimum shots for each extracted scene are selected according to predetermined rules adapted to the use and object (process Pr16), the optimum shots are extracted from the full video (process Pr21), and preview video adapted to the use and object is automatically produced (process Pr22).
摘要翻译：视频标题的完整视频分为具有时间码的拍摄或场景单位。将每个场景单元的给定状况信息添加到每个场景单元以产生场景分数，根据场景得分和阈值（处理Pr14）提取每个使用和对象所需的场景，视频评估信息将特征添加到构成每个提取的场景的每个镜头以产生拍摄分数（处理Pr16），根据适合于使用和对象的预定规则（处理Pr16）来选择针对每个提取场景的最佳拍摄，从最佳拍摄完整视频（进程Pr21）和自动生成适合使用和对象的预览视频（进程Pr22）。

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