利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

320 条记录 (耗时 0.021 秒)

    ACTION RECOGNITION IN A VIDEO SEQUENCE
    5.
    发明公开
    ACTION RECOGNITION IN A VIDEO SEQUENCE 审中-公开
    视频序列中的行动识别

    公开(公告)号：EP3321844A1

    公开(公告)日：2018-05-16

    申请号：EP16198678.1

    申请日：2016-11-14

    申请人： Axis AB

    发明人： Danielsson, Niclas ,  Molin, Simon

    IPC分类号： G06K9/00 ,  G06K9/68

    CPC分类号： G06K9/00718 ,  G06K9/00335 ,  G06K9/00744 ,  G06K9/00979 ,  G06K9/3233 ,  G06K9/685 ,  G06K2009/00738

    摘要： The present disclosure relates to a system for action recognition in a video sequence. The system comprises a camera (100) configured to capture the video sequence and a server (200) configured to perform action recognition. The camera comprises an object identifier (124) configured to identify an object of interest in an object image frame of the video sequence; an action candidate recognizer (126) configured to apply a first action recognition algorithm to the object image frame and thereby detecting presence of an action candidate; an video extractor (127) configured to produce action image frames of an action video sequence by extracting video data pertaining to a plurality of image frames from the video sequence, wherein one or more of the plurality of image frames from which the video data is extracted comprises the object of interest; and a network interface (130) configured to transfer the action video sequence to the server. The server comprises an action verifier (210) configured to apply a second action recognition algorithm to the action video sequence and thereby verify or reject that the action candidate is an action. Also a method for action recognition in a video sequence is presented.

    摘要翻译： 本公开涉及用于视频序列中的动作识别的系统。 该系统包括配置成捕捉视频序列的相机（​​100）和配置成执行动作识别的服务器（200）。 该相机包括被配置为识别视频序列的对象图像帧中的感兴趣对象的对象标识符（124） 动作候选识别器（126），被配置为将第一动作识别算法应用于所述对象图像帧并由此检测动作候选者的存在; 视频提取器（127），被配置为通过从视频序列中提取与多个图像帧有关的视频数据来产生动作视频序列的动作图像帧，其中提取视频数据的多个图像帧中的一个或多个 包括感兴趣的对象; 以及配置成将动作视频序列传送到服务器的网络接口（130）。 该服务器包括动作验证器（210），动作验证器（210）被配置为将第二动作识别算法应用于动作视频序列，从而验证或拒绝动作候选者是动作。 还提出了一种用于视频序列中的动作识别的方法。

    WATERMARK DETECTION USING A MULTIPLICITY OF PREDICTED PATTERNS
    7.
    发明公开
    WATERMARK DETECTION USING A MULTIPLICITY OF PREDICTED PATTERNS 审中-公开

    公开(公告)号：EP3183883A4

    公开(公告)日：2018-03-28

    申请号：EP15833741

    申请日：2015-08-19

    申请人： VERANCE CORP

    发明人： PETROVIC RADE ,  ZHAO JIAN ,  WINOGRAD JOSEPH M

    IPC分类号： H04N21/2389 ,  H04N21/8358

    CPC分类号： G06T1/0028 ,  G06F21/16 ,  G06K9/00744 ,  G06T1/005 ,  G06T1/0085 ,  G06T2201/005 ,  G06T2201/0065 ,  H04N5/08 ,  H04N19/467 ,  H04N21/00 ,  H04N21/4307 ,  H04N21/4627 ,  H04N21/8358

    摘要： Methods, devices and computer program products allow embedding and detection of watermarks into and from a multimedia content. One watermark embedding method includes selecting a content segment that lacks inherent features for embedding of watermarks without producing perceptible artifacts, and obtaining a first dither pattern corresponding to a first watermark symbol of a watermark symbol alphabet, where each symbol is associated with a particular dither pattern. Further, each particular dither pattern, upon combination with the multimedia content segment that lacks inherent features, produces a composite content segment without perceptible artifacts. By combining the first dither pattern with the multimedia content segment that lacks inherent features, a first composite content segment with the first embedded watermark symbol is produced. The detection of watermarks messages can be carried out quickly by examining a small portions of the multimedia because even the featureless content segments include embedded watermarks.

    STORING AND RETRIEVAL HEURISTICS
    9.
    发明公开
    STORING AND RETRIEVAL HEURISTICS 审中-公开
    存储和检索启发式

    公开(公告)号：EP3274868A1

    公开(公告)日：2018-01-31

    申请号：EP16706907.9

    申请日：2016-02-18

    申请人： Cisco Technology, Inc.

    发明人： MAOZ, Tal ,  MOSHITCH, Gal ,  ITZKOWITZ, Aliza ,  GEYZEL, Zeev ,  WACHTFOGEL, Reuven

    IPC分类号： G06F17/30 ,  G06K9/00

    CPC分类号： G06F17/30858 ,  G06F17/30802 ,  G06K9/00744 ,  G06K9/00758

    摘要： In one embodiment, a system comprises a processor to retrieve a first data element including a value X0 and Y0, provide a hash function for use with a hash table having buckets, the hash function having a first and second input that in combination map to one of the buckets wherein the first input is in a range of X- values having X-value sub-ranges, the second input is in a range of Y-values having Y-value sub-ranges, different combinations of the X-value sub-ranges and the Y- value sub-ranges map using the hash function to different buckets, and input the value X0 and Y0 into the hash function yielding an output which is indicative of a first bucket of the hash-table. Related apparatus and methods are also described.

    INFORMATION PROCESSING APPARATUS, METHOD AND COMPUTER PROGRAM PRODUCT
    10.
    发明公开
    INFORMATION PROCESSING APPARATUS, METHOD AND COMPUTER PROGRAM PRODUCT 审中-公开
    信息处理装置，方法和计算机程序产品

    公开(公告)号：EP3270327A1

    公开(公告)日：2018-01-17

    申请号：EP17172556.7

    申请日：2017-05-23

    申请人： Sony Corporation

    发明人： Williams, Michael John ,  Leathers-Smith, William Jack ,  Prayle, Paul Edward

    IPC分类号： G06K9/00 ,  G11B27/10 ,  G06T7/38

    CPC分类号： G06K9/00348 ,  G06K9/00744 ,  G06K9/6215 ,  G06T7/248 ,  G06T7/38 ,  G06T2207/10016 ,  G06T2207/30196 ,  G06T2207/30224 ,  G06T2207/30228 ,  G11B27/031 ,  G11B27/10 ,  G11B27/34 ,  H04N5/23296

    摘要： An information processing apparatus, comprising: receiver circuitry configured to receive i) a video stream comprising a plurality of images, each image containing at least one object located at a position in a plane and the image having associated image timing information indicating its temporal position in the video stream and ii) a stream of object tracking information each having associated object timing information indicating its temporal position in the stream of object tracking information wherein the stream of object tracking information corresponds to the video stream and separately defines the position of the object in the plane captured in each image in the video stream; and controller circuitry configured to perform pattern matching on the position of each of the objects in the video stream and the object tracking information, and when there is a closest matching position, synchronising the image timing information and the object timing information.

    摘要翻译： 1。一种信息处理装置，包括：接收器电路，被配置为接收i）包括多个图像的视频流，每个图像包含位于平面中的位置处的至少一个对象，并且所述图像具有指示其在 视频流和ii）对象跟踪信息流，每个对象跟踪信息具有指示其在对象跟踪信息流中的其时间位置的关联对象定时信息，其中对象跟踪信息流对应于视频流并且分别定义对象在 在视频流中的每个图像中捕获的飞机; 以及控制器电路，被配置为对视频流中的每个对象的位置和对象跟踪信息执行模式匹配，并且当存在最接近的匹配位置时，使图像定时信息和对象定时信息同步。