利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

812 条记录 (耗时 0.028 秒)

    SMOKE DETECTION METHOD AND APPARATUS
    91.
    发明公开
    SMOKE DETECTION METHOD AND APPARATUS 有权
    方法和设备烟雾探测

    公开(公告)号：EP1994502A2

    公开(公告)日：2008-11-26

    申请号：EP07750488.4

    申请日：2007-02-13

    申请人： Axonx, L.L.C.

    发明人： PRIVALOV, George

    IPC分类号： G06T7/20 ,  G08B13/194

    CPC分类号： G08B17/125 ,  G06K9/00771 ,  G06T7/254

    摘要： An apparatus for detecting smoke in a monitored area includes: (a) a means for capturing a series of successive video images of the monitored area as a series of two-dimensional bitmaps having a specified number of pixels, (b) a means for examining this series of bitmaps to identify areas in successive bitmaps of adjacent pixels that have the potential for being used as indicators for the existence of smoke in the monitored area, (c) a means for storing these identified areas from the bitmaps, (d) a means for associating, on the basis of the likelihood of the existence of smoke in the monitored area, the identified areas from successive bitmaps so as to form a cluster of overlapping regions within those bitmaps, and (d) a means for analyzing the identified areas so as to identify the temporal changes in these areas which are indicative of the presence of smoke.

    INTER-MODE REGION-OF-INTEREST VIDEO OBJECT SEGMENTATION
    92.
    发明公开
    INTER-MODE REGION-OF-INTEREST VIDEO OBJECT SEGMENTATION 审中-公开
    ZWISCHENMODUS-VIDEOOBJEKTSEGMENTIERUNG区域

    公开(公告)号：EP1982529A2

    公开(公告)日：2008-10-22

    申请号：EP07763153.9

    申请日：2007-02-07

    申请人： QUALCOMM Incorporated

    发明人： WANG, Haohong ,  EL-MALEH, Khaled, Helmi

    IPC分类号： H04N7/26 ,  H04N7/32 ,  G06K9/00 ,  G06T5/00

    CPC分类号： G06K9/00248 ,  G06K9/00261 ,  G06K9/00281 ,  G06K9/00604 ,  G06K9/3233 ,  G06T7/11 ,  G06T7/174 ,  G06T7/194 ,  G06T7/215 ,  G06T7/251 ,  G06T7/254 ,  G06T2207/20132 ,  G06T2207/30201 ,  H04N19/17 ,  H04N19/20 ,  H04N19/503

    摘要： The disclosure is directed to techniques for automatic segmentation of a region-of-interest (ROI) video object from a video sequence. ROI object segmentation enables selected ROI or “foreground” objects of a video sequence that may be of interest to a viewer to be extracted from non-ROI or “background” areas of the video sequence. Examples of a ROI object are a human face or a head and shoulder area of a human body. The disclosed techniques include a hybrid technique that combines ROI feature detection, region segmentation, and background subtraction. In this way, the disclosed techniques may provide accurate foreground object generation and low-complexity extraction of the foreground object from the video sequence. A ROI object segmentation system may implement the techniques described herein. In addition, ROI object segmentation may be useful in a wide range of multimedia applications that utilize video sequences, such as video telephony applications and video surveillance applications.

    摘要翻译： 本公开涉及用于从视频序列自动分割感兴趣区域（ROI）视频对象的技术。 ROI对象分割使得可以从视频序列的非ROI或“背景”区域中提取观看者感兴趣的视频序列的所选ROI或“前景”对象。 ROI对象的示例是人体的人脸或头肩部区域。 所公开的技术包括组合ROI特征检测，区域分割和背景减除的混合技术。 以这种方式，所公开的技术可以从视频序列提供前景对象生成和前景对象的低复杂度提取的准确性。 ROI对象分割系统可以实现本文描述的技术。 此外，ROI对象分割可能在使用诸如视频电话应用和视频监控应用之类的视频序列的多种多媒体应用中是有用的。

    EVENT DETECTION METHOD AND VIDEO SURVEILLANCE SYSTEM USING SAID METHOD
    93.
    发明公开
    EVENT DETECTION METHOD AND VIDEO SURVEILLANCE SYSTEM USING SAID METHOD 有权
    VERFAHREN ZUR EREIGNISERKENNUNG UNDVIDEOÜBERWACHUNGSSYSTEMMIT DIESEM VERFAHREN

    公开(公告)号：EP1908016A1

    公开(公告)日：2008-04-09

    申请号：EP07789499.6

    申请日：2007-07-20

    申请人： VIDEOTEC S.P.A.

    发明人： GENNARI, Giambattista ,  RACCANELLI, Giorgio ,  FREZZA, Ruggero ,  CENEDESE, Angelo ,  CAMPANA, Enrico

    IPC分类号： G06T7/20

    CPC分类号： G06K9/00771 ,  G06T7/254

    摘要： An event detection method for video surveillance systems and a related video surveillance system are described. The method comprises a learning phase, wherein learning images of a supervised area are acquired at different time instants in the absence of any detectable events, and an operating detection phase wherein current images of said area are acquired. The method detects an event by comparing a current image with an image corresponding to a linear combination of a plurality of reference images approximating, or coinciding with, respective learning images.

    摘要翻译： 描述了用于视频监控系统和相关视频监控系统的事件检测方法。 该方法包括学习阶段，其中在不存在任何可检测事件的情况下在不同时刻获取监督区域的学习图像，以及其中获取所述区域的当前图像的操作检测阶段。 该方法通过将当前图像与对应于与各个学习图像近似或一致的多个参考图像的线性组合的图像进行比较来检测事件。

    IMAGE ENHANCEMENT IN SPORT RECORDINGS
    94.
    发明公开
    IMAGE ENHANCEMENT IN SPORT RECORDINGS 有权
    运动录像中的图像增强

    公开(公告)号：EP1899025A1

    公开(公告)日：2008-03-19

    申请号：EP06748053.3

    申请日：2006-06-22

    申请人： Forsgren, Daniel

    发明人： Forsgren, Daniel

    IPC分类号： A63B69/36 ,  G06T7/20 ,  H04N7/08

    CPC分类号： G01N15/1484 ,  A63B24/0021 ,  A63B2024/0034 ,  G01N15/1475 ,  G01N21/03 ,  G01N21/11 ,  G01N2015/1486 ,  G01N2021/0321 ,  G01N2021/0325 ,  G01N2021/0346 ,  G06T7/136 ,  G06T7/194 ,  G06T7/254 ,  G06T2207/20224 ,  G06T2207/30224 ,  G06T2207/30241

    摘要： The present invention relates to production of a video signal representing a sports scene involving a rapid ball movement in front of an essentially static background. A series of source images (IMG) of the scene is registered. An initial image position (p1) for the moving ball is identified automatically by, for each image (IMG) in said series, producing a difference image between the image (IMG) and an image subsequent thereto. In the difference image, all image elements representing a contents alteration below a threshold level are allocated a first value, and all image elements representing a contents alteration above or equal to the threshold level are allocated a second value. A set of ball candidates is then identified in which each candidate is represented by a group of neighboring image elements that all contain the second value. The group must also fulfil a ball size criterion. The initial image position (p1) is selected from the set of ball candidates based on a ball selection algorithm. Thereafter, the ball is tracked, and a composite image sequence is generated wherein a synthetic trace (ΠB) representing the path of the moving ball is shown as successively added image data (p1, p2, p3, p4).

    摘要翻译： 本发明涉及代表涉及在基本上静止的背景之前的快速球运动的运动场景的视频信号的产生。 场景的一系列源图像（IMG）被注册。 通过对于所述系列中的每个图像（IMG），自动地识别移动球的初始图像位置（p1），从而在图像（IMG）和其之后的图像之间产生差异图像。 在差分图像中，表示低于阈值水平的内容改变的所有图像元素被分配第一值，并且表示高于或等于阈值水平的内容改变的所有图像元素被分配第二值。 然后识别一组球候选者，其中每个候选者由一组全部包含第二值的相邻图像元素表示。 该组还必须符合球尺寸标准。 基于球选择算法从候选球组中选择初始图像位置（p1）。 之后，跟踪球，并且产生合成图像序列，其中表示移动球的路径的合成轨迹（IIB）被显示为连续添加的图像数据（p1，p2，p3，p4）。

    OBJECT TRACKING SYSTEM
    95.
    发明公开
    OBJECT TRACKING SYSTEM 审中-公开
    OBJEKTVERFOLGUNGSSYSTEM

    公开(公告)号：EP1891601A1

    公开(公告)日：2008-02-27

    申请号：EP06773331.1

    申请日：2006-06-15

    申请人： Honeywell International Inc.

    发明人： MORELLAS, Vassillos ,  ANDREW, Johnson ,  MA, Yunqian ,  BAZAKOS, Michael, E.

    IPC分类号： G06T7/20

    CPC分类号： G06K9/32 ,  G06K9/00369 ,  G06K9/00771 ,  G06T7/246 ,  G06T7/254 ,  G06T7/292

    摘要： A system for tracking objects across an area having a network of cameras with overlapping and non-overlapping fields of view. The system may use a combination of color, shape, texture and/or multi-resolution histograms for object representation or target modeling for the tacking of an object from one camera to another. The system may include user and output interfacing.

    摘要翻译： 一种用于在具有重叠和非重叠视场的摄像机网络的区域上跟踪对象的系统。 系统可以使用颜色，形状，纹理和/或多分辨率直方图的组合来进行对象表示或目标建模，用于将对象从一个摄像机固定到另一个摄像机。 该系统可以包括用户和输出接口。

    CLASSIFYING AN OBJECT IN A VIDEO FRAME
    97.
    发明公开
    CLASSIFYING AN OBJECT IN A VIDEO FRAME 有权
    爱立信VIDEORAHMEN中的KLASSIFIZIERUNG EINES OBJEKTS

    公开(公告)号：EP1844443A1

    公开(公告)日：2007-10-17

    申请号：EP06709638.8

    申请日：2006-02-06

    申请人： BRITISH TELECOMMUNICATIONS public limited company

    发明人： LEI, Banjun ,  XU, Li-qun

    IPC分类号： G06T7/20

    CPC分类号： G06T7/20 ,  G06K9/00369 ,  G06T7/254 ,  G06T2207/30241

    摘要： In a digital video surveillance system, a number of processing stages are employed to identify foreground regions representing moving objects in a video sequence. An object tracking stage (5) is also provided in order to identify a correspondence between candidate objects in a current frame and those that have already been identified in one or more previous frames. In this way, it is possible to calculate the path taken by the or each foreground object and to record this path information in a trajectory database. In order to improve tracking performance, the object tracking stage (5) employs a state transitional object management scheme which determines whether or not a particular object is tracked. The path information generated by the object tracking stage (5) can be displayed on a video monitor (15) of the surveillance system and/or made available to high level applications (7).

    摘要翻译： 在数字视频监控系统中，采用多个处理阶段来识别表示视频序列中移动物体的前景区域。 还提供对象跟踪阶段（5），以便识别当前帧中的候选对象与在一个或多个先前帧中已被识别的对象之间的对应关系。 以这种方式，可以计算由每个前景对象采取的路径并将该路径信息记录在轨迹数据库中。 为了提高跟踪性能，对象跟踪阶段（5）采用状态过渡对象管理方案来确定特定对象是否被跟踪。 由对象跟踪阶段（5）生成的路径信息可以显示在监视系统的视频监视器（15）上和/或可用于高级应用（7）。