专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明公开

EP1450275A2 Intelligent video information management system 失效
标题翻译：智能系统zur Verwaltung von Videoinformationen
公开(公告)号：EP1450275A2
公开(公告)日：2004-08-25
申请号：EP04004123.8
申请日：1997-10-01
申请人： Sensormatic Electronics Corporation
发明人： The designation of the inventor has not yet been filed
IPC分类号： G06F17/30
CPC分类号： G08B13/1968 , G06F17/30017 , G06F17/30784 , G06T7/20 , G08B13/19604 , G08B13/19634 , G08B13/19645 , G08B13/19667 , G08B13/19671 , G08B13/19673 , G08B13/19682 , H04N5/445 , H04N5/76 , H04N5/781 , H04N5/782 , H04N5/783 , H04N7/181 , H04N9/8042 , H04N9/8205 , H04N9/8227 , H04N19/103 , H04N19/107 , H04N19/12 , H04N19/136 , H04N19/162 , H04N19/172 , H04N19/42 , H04N19/423 , H04N19/46 , H04N19/59 , H04N19/60
摘要： A flexible video information storage and analysis apparatus stores a video information data base and a plurality of moving image content analysis algorithms for analyzing the video information in the data base. A user can manipulate a mouse to select one of the analysis algorithms. The selected algorithm is used to analyze video information in the data base. The apparatus records and displays plural streams of video information. Content analysis algorithms may be downloaded from a remote location. The apparatus takes appropriate actions in response to detected features in incoming video streams. Tile-based conditional-refresh video data compression is employed.
摘要翻译：灵活的视频信息存储和分析装置存储用于分析数据库中的视频信息的视频信息数据库和多个运动图像内容分析算法。用户可以操纵鼠标来选择一个分析算法。所选算法用于分析数据库中的视频信息。该装置记录和显示多个视频信息流。内容分析算法可以从远程位置下载。该装置响应于输入视频流中的检测到的特征而采取适当的动作。采用基于瓦片的条件刷新视频数据压缩。

52. 发明公开

EP1405214A2 CONTEXT AND CONTENT BASED INFORMATION PROCESSING FOR MULTIMEDIA SEGMENTATION AND INDEXING 审中-公开
标题翻译：在上下文和内容为基础的信息处理FOR多媒体分割和索引
公开(公告)号：EP1405214A2
公开(公告)日：2004-04-07
申请号：EP01967208.8
申请日：2001-07-18
申请人： Koninklijke Philips Electronics N.V.
发明人： JASINSCHI, Radu, S.
IPC分类号： G06F17/30
CPC分类号： G06K9/00711 , G06F17/30784 , G06F17/30787 , G06F17/30796 , G06F17/30858
摘要： Method and system are disclosed for information processing, for example, for multimedia segmentation, indexing and retrieval. The method and system includes multimedia, for example audio/visual/text (A/V/T), integration using a probabilistic framework. Both, multimedia content and context information are represented and processed via the probabilistic framework. This framework is represented, for example, by a Bayesian network and hierarchical priors, which is graphically described by stages, each having a set of layers with each layer including a number of nodes representing content or context information. At least the first layer of the first stage is processes multimedia content information such as objects in the A/V/T domains, or combinations of thereof. The other layers of the various stages describe multimedia context information, as further described below. Each layer is a Bayesian network, wherein nodes of each layer explain certain characteristics of the next 'lower' layer and/or 'lower' stages. Together, the nodes and connections there between form an augmented Bayesian network. Multimedia context is the circumstance, situation, underlying structure of the multimedia information (audio, visual, text) being processed. The multimedia information (both content and context) is combined at different levels of granularity and level of abstraction within the layers and stages.

53. 发明授权

EP3185577B1 CONTENT IDENTIFICATION APPARATUS AND CONTENT IDENTIFICATION METHOD 有权
公开(公告)号：EP3185577B1
公开(公告)日：2018-10-24
申请号：EP15832982.1
申请日：2015-08-19
申请人： Panasonic Intellectual Property Management Co., Ltd.
发明人： YABU, Hiroshi
IPC分类号： H04N21/8352 , H04N21/8358
CPC分类号： H04N21/8352 , G06F17/30743 , G06F17/30784 , G06F17/3079 , G06K9/00744 , G06K9/00758 , H04N21/8358
摘要： Provided is a recognition data creation device capable of reducing processing required for recognizing video content while increasing recognition accuracy of the video content. This recognition data creation device includes: a fingerprint creator; a sorter; and a collator. The fingerprint creator creates fingerprints for each of a plurality of acquired video content candidates. The sorter sorts the video content candidates by using attached information included in recognition data input from an outside. The collator collates the fingerprints of the video content candidates which are sorted by the sorter with fingerprints included in the recognition data, and specifies video content which corresponds to the fingerprints included in the recognition data from among the video content candidates.

54. 发明授权

EP2191400B1 DETECTION AND CLASSIFICATION OF MATCHES BETWEEN TIME-BASED MEDIA 有权转让
公开(公告)号：EP2191400B1
公开(公告)日：2018-10-03
申请号：EP08798558.6
申请日：2008-08-22
申请人： Google LLC
发明人： COVELL, Michele , YAGNIK, Jay , FAUST, Jeff , BALUJA, Shumeet
IPC分类号： G06F17/30 , G06K9/00
CPC分类号： G06K9/00758 , G06F17/30784
摘要： A system and method detects matches between portions of video content. A matching module receives an input video fingerprint representing an input video and a set of reference fingerprints representing reference videos in a reference database. The matching module compares the reference fingerprints and input fingerprints to generate a list of candidate segments from the reference video set. Each candidate segment comprises a time-localized portion of a reference video that potentially matches the input video. A classifier is applied to each of the candidate segments to classify the segment as a matching segment or a non-matching segment. A result is then outputted identifying a matching portion of a reference video from the reference video set based on the segments classified as matches.

55. 发明公开

EP3376402A1 DIGIT STRING BASED REAL TIME INFORMATION DISTRIBUTION SYSTEM USING SMART TERMINAL AND INFORMATION DISTRIBUTION METHOD 审中-公开
公开(公告)号：EP3376402A1
公开(公告)日：2018-09-19
申请号：EP16864477.1
申请日：2016-10-21
申请人： The SYG Institute Co., Ltd.
发明人： SHIN, Yong-Gyun
IPC分类号： G06F17/30 , G06Q50/10 , G06Q30/02
CPC分类号： H04N21/84 , G06F17/30038 , G06F17/30784 , H04N21/4828 , H04N21/812
摘要： The present disclosure discloses an information distribution system and an information distribution method that supports digit string-based information distribution using a smart terminal. The information distribution system according to the present disclosure includes a theme digit string registration unit which receives a registration request of a theme digit string by a theme of the content and stores and registers the received theme string in a digit string DB, a content registration unit which receives a registration request of theme digit string and content matched to the theme digit string, matches the received theme digit string and content and stores the same in a content DB, and an information distribution management unit which receives a provision request of the content including the digit string, retrieves the content matched to the theme digit string from the content DB, and transmits the retrieved content to the smart terminal, to manage provision of the information distribution service. According to the present disclosure, it fully supports improved identifiability and accesability of information using a digit string, and increased sales of products for content matched to the digit string through promotion of the content.

56. 发明授权

EP2657884B1 Identifying multimedia objects based on multimedia fingerprint 有权转让
公开(公告)号：EP2657884B1
公开(公告)日：2018-09-12
申请号：EP13164040.1
申请日：2013-04-17
申请人： Dolby Laboratories Licensing Corporation
发明人： Bauer, Claus , Lu, Lie , Hu, Mingqing
IPC分类号： G06K9/00 , G06F17/30 , G06K9/62 , G06T1/00
CPC分类号： G06T1/0021 , G06F17/30023 , G06F17/30247 , G06F17/30345 , G06F17/30598 , G06F17/30743 , G06F17/30784 , G06K9/00744 , G06K9/6292
摘要： Embodiments of identifying multimedia objects based on multimedia fingerprints are provided. Query fingerprints are derived from a multimedia object according to differing fingerprint algorithms. For each fingerprint algorithm, decisions are calculated through at least one classifier corresponding to the fingerprint algorithm based on the query fingerprint and reference fingerprints, the reference fingerprints being derived from reference multimedia objects according to the same fingerprint algorithm. Each of the decisions indicates a possibility that the query fingerprint and the reference fingerprint are not derived from the same multimedia content. For each of the reference multimedia objects, a distance is calculated as a weighted sum of the decisions relating to the reference fingerprints. The multimedia object is identified as matching the reference multimedia object with the smallest distance less than a threshold.

57. 发明授权

EP2471026B1 RELEVANCE-BASED IMAGE SELECTION 有权转让
标题翻译：基于相关的图像选择
公开(公告)号：EP2471026B1
公开(公告)日：2018-04-11
申请号：EP10812505.5
申请日：2010-08-18
申请人： Google LLC
发明人： CHECHIK, Gal , BENGIO, Samy
IPC分类号： G06K9/62 , G06F17/30
CPC分类号： G06F17/3082 , G06F17/30781 , G06F17/30784 , G06F17/30817 , G06F17/30837 , G06F17/30849
摘要： A system, computer readable storage medium, and computer-implemented method presents video search results responsive to a user keyword query. The video hosting system uses a machine learning process to learn a feature-keyword model associating features of media content from a labeled training dataset with keywords descriptive of their content. The system uses the learned model to provide video search results relevant to a keyword query based on features found in the videos. Furthermore, the system determines and presents one or more thumbnail images representative of the video using the learned model.

58. 发明公开

EP3239896A1 DATA STRUCTURE FOR DESCRIBING AN IMAGE SEQUENCE IMAGE, AND METHODS FOR EXTRACTING AND MATCHING THESE DATA STRUCTURES 有权
标题翻译：用于描述图像序列图像的数据结构以及用于提取和匹配这些数据结构的方法
公开(公告)号：EP3239896A1
公开(公告)日：2017-11-01
申请号：EP16167518.6
申请日：2016-04-28
申请人： Joanneum Research Forschungsgesellschaft mbH
发明人： Bailer, Werner , Wechtitsch, Stefanie
IPC分类号： G06K9/00 , G06K9/46
CPC分类号： G06K9/00744 , G06F17/30784 , G06F17/30858 , G06K9/00751 , G06K9/00758 , G06K9/00765 , G06K9/4671 , G06K9/6215
摘要： A compact image sequence descriptor (101), used for describing an image sequence, comprises a segment global descriptor (113) for at least one segment within the sequence, which includes global descriptor information for respective images, relating to interest points within the video content of the images. The segment global descriptor (113) includes a base descriptor (121), which is a global descriptor associated with a representative frame (120) of the image sequence, and a number of relative descriptors (125). The relative descriptors contain information of a respective global descriptor relative to the base descriptor allowing to reconstruct an exact or approximated global descriptor associated with a respective image of the image sequence. The image sequence descriptor (101) may further include a segment local descriptor (114) for a segment, comprising a set of encoded local feature descriptors.
摘要翻译：用于描述图像序列的紧凑图像序列描述符（101）包括用于该序列内的至少一个分段的分段全局描述符（113），该分段全局描述符包括与视频内容内的兴趣点有关的各个图像的全局描述符信息的图像。段全局描述符（113）包括基本描述符（121）和多个相对描述符（125），该基本描述符是与图像序列的代表性帧（120）相关联的全局描述符。相对描述符包含相对于基本描述符的相应全局描述符的信息，从而允许重建与图像序列的相应图像相关联的精确或近似全局描述符。图像序列描述符（101）可以进一步包括用于片段的片段局部描述符（114），其包括一组编码的局部特征描述符。

59. 发明公开

EP3207469A1 SUBTITLING METHOD AND SYSTEM 审中-公开
标题翻译：转码方法和系统
公开(公告)号：EP3207469A1
公开(公告)日：2017-08-23
申请号：EP15784109.9
申请日：2015-10-14
申请人： British Broadcasting Corporation
发明人： HUGHES, Chris , ARMSTRONG, Mike
IPC分类号： G06F17/30
CPC分类号： G06F17/30038 , G06F17/30026 , G06F17/30743 , G06F17/30784
摘要： A method of retrieving supplementary data related to audio-video content with reference to a reference version of that content involves deriving an audio signature from audio-video content. The audio signature is searched against reference audio signatures of reference versions of the audio-video content. If a match is found, supplementary data related to the reference audio-video content is retrieved. The search is a directed search using data extracted from the transmission route by which the audio-video content is to be delivered to a consumer. The search process is thereby more efficient as the search may be started at an appropriate location or conducted in an appropriate direction, rather than searching blindly.
摘要翻译：参照该内容的参考版本检索与音频 - 视频内容相关的补充数据的方法涉及从音频 - 视频内容导出音频签名。将音频签名与音频 - 视频内容的参考版本的参考音频签名进行搜索。如果找到匹配，则检索与参考音频 - 视频内容有关的补充数据。该搜索是使用从传输路径提取的数据的定向搜索，通过该传输路径将音频 - 视频内容传送给消费者。因此搜索过程更有效，因为搜索可以在适当的位置开始或以适当的方向进行，而不是盲目搜索。

60. 发明公开

EP3191989A1 VIDEO PROCESSING FOR MOTOR TASK ANALYSIS 有权转让
标题翻译：视频处理的电机任务分析
公开(公告)号：EP3191989A1
公开(公告)日：2017-07-19
申请号：EP15770696.1
申请日：2015-09-07
申请人： Microsoft Technology Licensing, LLC
发明人： KONTSCHIEDER, Peter , DORN, Jonas , ZIKIC, Darko , CRIMINISI, Antonio
IPC分类号： G06F19/00 , G06F17/30 , G06T7/20
CPC分类号： G06K9/00744 , G06F17/30784 , G06F17/30887 , G06F19/00 , G06F19/3481 , G06K9/00342 , G06K9/6267 , G06K9/6278 , G06K2009/00738 , G06N5/00 , G06N5/025 , G06N99/005 , G06T7/0012 , G06T7/20 , G06T2207/10016 , G06T2207/20081 , G16H50/20
摘要： Video processing for motor task analysis is described. In various examples, a video of at least part of a person or animal carrying out a motor task, such as placing the forefinger on the nose, is input to a trained machine learning system to classify the motor task into one of a plurality of classes. In an example, motion descriptors such as optical flow are computed from pairs of frames of the video and the motion descriptors are input to the machine learning system. For example, during training the machine learning system identifies time-dependent and/or location-dependent acceleration or velocity features which discriminate between the classes of the motor task. In examples, the trained machine learning system computes, from the motion descriptors, the location dependent acceleration or velocity features which it has learned as being good discriminators. In various examples, a feature is computed using sub-volumes of the video.
摘要翻译：描述了用于电动机任务分析的视频处理。在各种示例中，执行运动任务的人或动物的至少一部分（诸如将食指放置在鼻子上）的视频被输入到经训练的机器学习系统以将运动任务分类为多个类别之一。在一个示例中，诸如光流的运动描述符是从视频帧对中计算的，并且运动描述符被输入到机器学习系统。例如，在训练期间，机器学习系统识别区分运动任务的类别的依赖于时间和/或位置的加速度或速度特征。在示例中，训练的机器学习系统根据运动描述符来计算它已经学习为良好鉴别器的位置相关加速度或速度特征。在各种示例中，使用视频的子卷来计算特征。

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