知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

149 条记录 (耗时 0.019 秒)

    Camera calibration using feature identification
    71.
    发明授权
    Camera calibration using feature identification 有权
    相机校准使用功能标识

    公开(公告)号：US09286678B2

    公开(公告)日：2016-03-15

    申请号：US13338555

    申请日：2011-12-28

    申请人： Hongwei Zhu ,  Farzin Aghdasi ,  Greg Millar

    发明人： Hongwei Zhu ,  Farzin Aghdasi ,  Greg Millar

    IPC分类号： G06T7/00 ,  G06T19/00 ,  H04N7/18

    CPC分类号： G06T7/0018 ,  G06T7/80 ,  G06T2207/10016 ,  G06T2207/20076 ,  G06T2207/30196 ,  G06T2207/30232 ,  G06T2207/30236

    摘要： Disclosed are methods, systems, computer readable media and other implementations, including a method to calibrate a camera that includes capturing by the camera a frame of a scene, identifying features appearing in the captured frame, the features associated with pre-determined values representative of physical attributes of one or more objects, and determining parameters of the camera based on the identified features appearing in the captured frame and the pre-determined values associated with the identified features.

    摘要翻译： 公开了方法，系统，计算机可读介质和其他实施方式，包括校准相机的方法，其包括由相机拍摄场景的帧，识别出现在所捕获的帧中的特征，与代表 一个或多个对象的物理属性，以及基于所捕获的帧中出现的所识别的特征以及与所识别的特征相关联的预定值来确定摄像机的参数。

    Dynamic Media Transcoding for P2P Communications
    72.
    发明申请
    Dynamic Media Transcoding for P2P Communications 有权
    P2P通信的动态媒体转码

    公开(公告)号：US20150281301A1

    公开(公告)日：2015-10-01

    申请号：US14228848

    申请日：2014-03-28

    申请人： Pelco, Inc.

    发明人： Bryan K. Neff

    IPC分类号： H04L29/06 ,  H04L29/08 ,  H04N21/44

    CPC分类号： H04L65/60 ,  H04L65/4084 ,  H04L65/605 ,  H04L65/80 ,  H04L67/104 ,  H04N21/2187 ,  H04N21/234363 ,  H04N21/2402 ,  H04N21/41407 ,  H04N21/44

    摘要： An apparatus for distributing video content includes one or more video input modules each adapted to receive a video signal from a video source, and a video combiner for receiving the video signals from the one or more video inputs and generating a video packet data stream. The apparatus also includes at least one video output module adapted to transmit the video packet data stream, and a processor coupled to the video combiner and the at least one video output. The processor cooperates with one or both of the video combiner and the at least one video output to transcode at least a portion of the video packet data stream.

    摘要翻译： 用于分配视频内容的装置包括一个或多个视频输入模块，每个视频输入模块适于从视频源接收视频信号，以及视频组合器，用于从一个或多个视频输入端接收视频信号，并产生视频分组数据流。 该装置还包括适于发送视频分组数据流的至少一个视频输出模块，以及耦合到视频组合器和至少一个视频输出的处理器。 处理器与视频组合器和至少一个视频输出中的一个或两个协作以对视频分组数据流的至少一部分进行转码。

    OBJECT REMOVAL DETECTION USING 3-D DEPTH INFORMATION
    75.
    发明申请
    OBJECT REMOVAL DETECTION USING 3-D DEPTH INFORMATION 审中-公开
    使用三维深度信息的对象去除检测

    公开(公告)号：US20140147011A1

    公开(公告)日：2014-05-29

    申请号：US13689158

    申请日：2012-11-29

    申请人： PELCO, INC.

    发明人： Shu Yang

    IPC分类号： G06T7/20

    CPC分类号： G06T7/254 ,  G06T7/285 ,  G06T2207/10028 ,  G06T2207/30232 ,  G08B13/19602

    摘要： A novel object removal detection method and corresponding apparatus is described. The method employs a combination of detecting a change in a scene pattern and a change in the depth of field. The method significantly reduced false alarms caused by occlusion or rearrangement of the monitored objects.

    摘要翻译： 描述了一种新颖的物体去除检测方法和相应的装置。 该方法采用检测场景图案的变化和景深变化的组合。 该方法显着减少了被监视对象的遮挡或重新排列引起的误报。

    Method and system for displaying a timeline
    76.
    发明授权
    Method and system for displaying a timeline 有权
    显示时间轴的方法和系统

    公开(公告)号：US08705932B2

    公开(公告)日：2014-04-22

    申请号：US13332768

    申请日：2011-12-21

    申请人： Kirsten A. Medhurst ,  Adrianus A. de Klerk

    发明人： Kirsten A. Medhurst ,  Adrianus A. de Klerk

    IPC分类号： H04N9/80 ,  H04N5/93 ,  G11B27/00 ,  H04N5/76 ,  H04N5/783

    CPC分类号： G11B27/34 ,  G06F17/30064 ,  G06F17/30846 ,  G11B27/031 ,  G11B27/105 ,  H04N21/47205 ,  H04N21/8455 ,  H04N21/8456 ,  H04N21/8547

    摘要： A method of displaying a timeline of recorded video comprising the steps of dividing the recorded video into timespans, providing a thumbnail and a timestamp for each timespan that has recorded video, providing a gap and a timestamp between thumbnails for each timespan in which there is no recorded video, displaying a first timeline containing the provided thumbnails and timestamps and the provided gaps and timestamps having an uncompressed format, receiving user input requesting that the first timeline be compressed, removing the gaps and their respective timestamps from the first timeline and moving the thumbnails and their timestamps located on either side of the gaps so that the thumbnails on either side of the gaps are adjacent to provide a compressed timeline, and displaying the compressed timeline.

    摘要翻译： 一种显示记录视频的时间线的方法，包括以下步骤：将记录的视频划分成时间段，为每个记录视频的每个时段提供一个缩略图和一个时间戳，在每个不存在视频的每个时间段的缩略图之间提供间隙和时间戳 显示包含所提供的缩略图和时间戳的第一时间线，以及所提供的具有未压缩格式的间隙和时间戳，接收请求压缩第一时间线的用户输入，从第一时间线移除间隙及其各自的时间戳并移动缩略图 并且其时间戳位于间隙的任一侧，使得间隙任一侧上的缩略图相邻以提供压缩的时间线，并显示压缩的时间线。

    CLUSTERING-BASED OBJECT CLASSIFICATION
    77.
    发明申请
    CLUSTERING-BASED OBJECT CLASSIFICATION 有权
    基于聚类的对象分类

    公开(公告)号：US20130170696A1

    公开(公告)日：2013-07-04

    申请号：US13338617

    申请日：2011-12-28

    申请人： Hongwei Zhu ,  Farzin Aghdasi ,  Greg Millar

    发明人： Hongwei Zhu ,  Farzin Aghdasi ,  Greg Millar

    IPC分类号： G06K9/46

    CPC分类号： G06K9/68

    摘要： An example of a method for identifying objects in video content according to the disclosure includes receiving video content of a scene captured by a video camera, detecting an object in the video content, identifying a track that the object follows over a series of frames of the video content, extracting object features for the object from the video content, and classifying the object based on the object features. Classifying the object further comprises: determining a track-level classification for the object using spatially invariant object features, determining a global-clustering classification for the object using spatially variant features, and determining an object type for the object based on the track-level classification and the global-clustering classification for the object.

    摘要翻译： 根据本公开的用于识别视频内容中的对象的方法的示例包括：接收由摄像机捕获的场景的视频内容，检测视频内容中的对象，识别该对象在一系列帧上跟随的轨迹 视频内容，从视频内容提取对象的对象特征，以及基于对象特征对对象进行分类。 分类对象还包括：使用空间不变对象特征来确定对象的轨道级分类，使用空间变异特征确定对象的全局聚类分类，以及基于轨道级分类确定对象的对象类型 和对象的全局聚类分类。

    SEARCHING RECORDED VIDEO
    78.
    发明申请
    SEARCHING RECORDED VIDEO 有权
    搜索录制的视频

    公开(公告)号：US20130028467A9

    公开(公告)日：2013-01-31

    申请号：US12982601

    申请日：2010-12-30

    申请人： Greg Millar ,  Farzin Aghdasi ,  Lei Wang

    发明人： Greg Millar ,  Farzin Aghdasi ,  Lei Wang

    IPC分类号： G06K9/34

    CPC分类号： G06F17/30784 ,  G06F17/3079 ,  G06K9/00771 ,  G06K9/346

    摘要： Embodiments of the disclosure provide for systems and methods for creating metadata associated with a video data. The metadata can include data about objects viewed within a video scene and/or events that occur within the video scene. Some embodiments allow users to search for specific objects and/or events by searching the recorded metadata. In some embodiments, metadata is created by receiving a video frame and developing a background model for the video frame. Foreground object(s) can then be identified in the video frame using the background model. Once these objects are identified they can be classified and/or an event associated with the foreground object may be detected. The event and the classification of the foreground object can then be recorded as metadata.

    摘要翻译： 本公开的实施例提供了用于创建与视频数据相关联的元数据的系统和方法。 元数据可以包括关于在视频场景内观看的对象的数据和/或在视频场景内发生的事件。 一些实施例允许用户通过搜索记录的元数据来搜索特定对象和/或事件。 在一些实施例中，通过接收视频帧并开发视频帧的背景模型来创建元数据。 然后可以使用背景模型在视频帧中识别前景对象。 一旦识别出这些对象，就可以对它们进行分类和/或可以检测与前景对象相关联的事件。 然后可以将事件和前景对象的分类记录为元数据。

    Method of improving video images by removing the effects of camera vibration
    79.
    发明授权
    Method of improving video images by removing the effects of camera vibration 有权
    通过消除摄像机振动的影响来改善视频图像的方法

    公开(公告)号：US08269844B2

    公开(公告)日：2012-09-18

    申请号：US12527619

    申请日：2008-03-26

    申请人： Chien-Min Huang ,  Farzin Aghdasi

    发明人： Chien-Min Huang ,  Farzin Aghdasi

    IPC分类号： H04N5/228 ,  H04N7/18

    CPC分类号： H04N5/23248 ,  G06T5/003 ,  G06T2207/10016 ,  G06T2207/20201 ,  G06T2207/30232

    摘要： A method of improving a video image by removing the effects of camera vibration comprising the steps of, obtaining a reference frame, receiving an incoming frame, determining the frame translation vector for the incoming frame, translating the incoming frame to generate a realigned frame, performing low pass filtering in the spatial domain on pixels in the realigned frame, performing low pass filtering in the spatial domain on pixels in the reference frame, determining the absolute difference between the filtered pixels in the reference frame and the filtered pixels in the realigned frame, performing low pass filtering in the temporal domain on the pixels in the realigned frame to generate the output frame if the absolute difference is less than a predetermined threshold, and providing the realigned frame as the output frame if the absolute difference is greater than the predetermined threshold.

    摘要翻译： 通过消除摄像机振动的影响来改善视频图像的方法包括以下步骤：获得参考帧，接收输入帧，确定输入帧的帧转换向量，翻译输入帧以产生重新排列的帧，执行 在重新排列的帧中的像素上的空间域中进行低通滤波，对参考帧中的像素执行空间域中的低通滤波，确定参考帧中的滤波像素与重新排列的帧中的滤波像素之间的绝对差， 在所述重新排列的帧中的所述像素上执行所述时域上的低通滤波以在所述绝对差小于预定阈值时产生所述输出帧，并且如果所述绝对差大于所述预定阈值，则将所述重新排列的帧提供为所述输出帧 。

    OPTICAL COMPENSATION IN SURVEILLANCE DOMES
    80.
    发明申请
    OPTICAL COMPENSATION IN SURVEILLANCE DOMES 有权
    监察院的光学补偿

    公开(公告)号：US20120169870A1

    公开(公告)日：2012-07-05

    申请号：US12981659

    申请日：2010-12-30

    申请人： Prateek Jain ,  David Campbell

    发明人： Prateek Jain ,  David Campbell

    IPC分类号： H04N7/18 ,  G02B27/42

    CPC分类号： G02B27/0025 ,  G02B27/0037 ,  G02B27/4216

    摘要： Techniques are discussed for correcting optical aberrations that exist in surveillance domes that have spherical and non-spherical parts. For example, the image quality of a surveillance camera is reduced when it focuses on an object through a non-spherical base of a surveillance dome. This image quality reduction could potentially compromise the security of the area monitored by the surveillance camera by failing to provide enough detail to identify individuals or other objects of interest. Utilizing a corrective optical element to provide curvature to a wavefront that travels through the non-spherical base, however, helps preserve the image quality of the camera and thereby helps maintain the integrity of the surveillance system.

    摘要翻译： 讨论了用于校正存在于具有球形和非球形部分的监视穹顶中的光学像差的技术。 例如，当监视摄像机通过监视穹顶的非球形基座对焦在物体上时，图像质量被降低。 这种图像质量降低可能潜在地损害由监控摄像机监视的区域的安全性，因为未能提供足够的细节来识别个人或其他感兴趣的对象。 然而，利用校正光学元件来提供穿过非球形基座的波前的曲率，有助于保持相机的图像质量，从而有助于维持监视系统的完整性。