知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

26 records (took 0.023 seconds)

    Tracking semantic objects in vector image sequences
    11.
    发明授权
    Tracking semantic objects in vector image sequences 有权
    跟踪矢量图像序列中的语义对象

    公开(公告)号：US07162055B2

    公开(公告)日：2007-01-09

    申请号：US11171448

    申请日：2005-06-29

    Applicant: Chuang Gu ,  Ming-Chieh Lee

    Inventor： Chuang Gu ,  Ming-Chieh Lee

    IPC: G06K9/00 ,  G06K9/34 ,  H04N5/225

    CPC classification number: G06K9/32 ,  G06T7/11 ,  G06T7/174 ,  G06T7/215 ,  G06T7/246 ,  H04N19/543 ,  H04N19/80

    Abstract: A semantic object tracking method tracks general semantic objects with multiple non-rigid motion, disconnected components and multiple colors throughout a vector image sequence. The method accurately tracks these general semantic objects by spatially segmenting image regions from a current frame and then classifying these regions as to which semantic object they originated from in the previous frame. To classify each region, the method performs a region based motion estimation between each spatially segmented region and the previous frame to compute the position of a predicted region in the previous frame. The method then classifies each region in the current frame as being part of a semantic object based on which semantic object in the previous frame contains the most overlapping points of the predicted region. Using this method, each region in the current image is tracked to one semantic object from the previous frame, with no gaps or overlaps. The method propagates few or no errors because it projects regions into a frame where the semantic object boundaries are previously computed rather than trying to project and adjust a boundary in a frame where the object's boundary is unknown.

    Abstract translation: 语义对象跟踪方法在整个矢量图像序列中跟踪具有多个非刚性运动，断开组件和多种颜色的一般语义对象。 该方法通过对来自当前帧的图像区域进行空间分割，然后对这些区域进行分类，从而准确地跟踪这些一般语义对象，以便它们在前一帧中源自哪个语义对象。 为了对每个区域进行分类，该方法在每个空间分段区域和前一帧之间执行基于区域的运动估计，以计算前一帧中的预测区域的位置。 该方法然后根据前一帧中的哪个语义对象包含预测区域的最重叠点将当前帧中的每个区域分类为语义对象的一部分。 使用该方法，当前图像中的每个区域被跟踪到来自前一帧的一个语义对象，没有间隙或重叠。 该方法传播很少或没有错误，因为它将区域投影到预先计算语义对象边界的框架中，而不是尝试在对象边界未知的框架中投影和调整边界。

    Semantic video object segmentation and tracking
    12.
    发明授权
    Semantic video object segmentation and tracking 失效

    公开(公告)号：US06400831B1

    公开(公告)日：2002-06-04

    申请号：US09054280

    申请日：1998-04-02

    Applicant: Ming-Chieh Lee ,  Chuang Gu

    Inventor： Ming-Chieh Lee ,  Chuang Gu

    IPC: G06K900

    Abstract: A semantic video object extraction system using mathematical morphology and perspective motion modeling. A user indicates a rough outline around an image feature of interest for a first frame in a video sequence. Without further user assistance, the rough outline is processed by a morphological segmentation tool to snap the rough outline into a precise boundary surrounding the image feature. Motion modeling is performed on the image feature to track its movement into a subsequent video frame. The motion model is applied to the precise boundary to warp the precise outline into a new rough outline for the image feature in the subsequent video frame. This new rough outline is then snapped to locate a new precise boundary. Automatic processing is repeated for subsequent video frames.

    Staged element classification
    13.
    发明授权
    Staged element classification 有权
    分期元素分类

    公开(公告)号：US08588534B2

    公开(公告)日：2013-11-19

    申请号：US13102740

    申请日：2011-05-06

    Applicant: Yaming He ,  Chuang Gu

    Inventor： Yaming He ,  Chuang Gu

    IPC: G06K9/68

    CPC classification number: G06K9/00288 ,  G06K9/00677 ,  G06K9/6807

    Abstract: Various examples are disclosed herein that relate to staged element classification. For example, one disclosed example provides a method of classifying elements by forming elements for classification into a plurality of first-level sets in a first stage, generating primary groups within the first-level sets based on element similarity, forming a plurality of second-level sets from the first-level sets in a second stage, generating secondary groups within the second-level sets based on element similarity, and merging a plurality of the primary and/or secondary groups based on element similarity.

    Abstract translation: 本文公开了与分段元素分类相关的各种示例。 例如，一个公开的示例提供了一种通过在第一阶段中形成用于分类为多个第一级集合的元素来对元素进行分类的方法，基于元素相似性在第一级集合内生成主组，形成多个第二级组， 基于元素相似度在第二级集合内生成二级组，并且基于元素相似度合并多个主组和/或辅助组。

    Tracking semantic objects in vector image sequences
    17.
    发明申请
    Tracking semantic objects in vector image sequences 有权
    跟踪矢量图像序列中的语义对象

    公开(公告)号：US20050240629A1

    公开(公告)日：2005-10-27

    申请号：US11171448

    申请日：2005-06-29

    Applicant: Chuang Gu ,  Ming-Chieh Lee

    Inventor： Chuang Gu ,  Ming-Chieh Lee

    IPC: H04N7/18 ,  G06F7/00 ,  G06T3/00 ,  G06T7/20 ,  H04N7/26 ,  H04N7/32

    CPC classification number: G06K9/32 ,  G06T7/11 ,  G06T7/174 ,  G06T7/215 ,  G06T7/246 ,  H04N19/543 ,  H04N19/80

    Abstract: A semantic object tracking method tracks general semantic objects with multiple non-rigid motion, disconnected components and multiple colors throughout a vector image sequence. The method accurately tracks these general semantic objects by spatially segmenting image regions from a current frame and then classifying these regions as to which semantic object they originated from in the previous frame. To classify each region, the method perform a region based motion estimation between each spatially segmented region and the previous frame to computed the position of a predicted region in the previous frame. The method then classifies each region in the current frame as being part of a semantic object based on which semantic object in the previous frame contains the most overlapping points of the predicted region. Using this method, each region in the current image is tracked to one semantic object from the previous frame, with no gaps or overlaps. The method propagates few or no errors because it projects regions into a frame where the semantic object boundaries are previously computed rather than trying to project and adjust a boundary in a frame where the object's boundary is unknown.

    Abstract translation: 语义对象跟踪方法在整个矢量图像序列中跟踪具有多个非刚性运动，断开组件和多种颜色的一般语义对象。 该方法通过对来自当前帧的图像区域进行空间分割，然后对这些区域进行分类，从而准确地跟踪这些一般语义对象，以便它们在前一帧中源自哪个语义对象。 为了对每个区域进行分类，该方法在每个空间分段区域和前一帧之间执行基于区域的运动估计，以计算先前帧中的预测区域的位置。 该方法然后根据前一帧中的哪个语义对象包含预测区域的最重叠点将当前帧中的每个区域分类为语义对象的一部分。 使用该方法，当前图像中的每个区域被跟踪到来自前一帧的一个语义对象，没有间隙或重叠。 该方法传播很少或没有错误，因为它将区域投影到预先计算语义对象边界的框架中，而不是尝试在对象边界未知的框架中投影和调整边界。

    Segmentation of image features using hierarchical analysis of multi-valued image data and weighted averaging of segmentation results
    18.
    发明授权
    Segmentation of image features using hierarchical analysis of multi-valued image data and weighted averaging of segmentation results 失效
    使用多值图像数据的分层分析和分割结果的加权平均来分割图像特征

    公开(公告)号：US6075875A

    公开(公告)日：2000-06-13

    申请号：US722981

    申请日：1996-09-30

    Applicant: Chuang Gu

    Inventor： Chuang Gu

    IPC: G06T5/00 ,  G06T7/20 ,  H04N7/26 ,  H04N7/36 ,  G06K9/00

    CPC classification number: G06T7/2006 ,  G06T7/0081 ,  G06T7/0091 ,  G06T9/001 ,  G06T9/20 ,  H04N19/162 ,  H04N19/20 ,  H04N19/51 ,  H04N19/54 ,  H04N19/63 ,  G06T2207/10016 ,  G06T2207/20016 ,  G06T2207/20152

    Abstract: Homogeneous moving objects of arbitrary shapes are segmented and tracked with respect to the motion of the objects. In an intraframe mode of operation, a segmentation method includes obtaining a motion representation of corresponding pixels in the selected video image frame and a preceding video image frame to form motion-segmented video image features. Video image features are also segmented according to their spatial image characteristics (e.g., color) to form spatially-segmented video image features. Finally, the video image features are jointly segmented as a weighted combination of the motion-segmented video image features and the spatially-segmented video image features. The joint motion and spatial segmentation of image features provides enhanced accuracy in representing moving image features. This enhanced accuracy is particularly beneficial because the motion of image features is a significant display characteristic for human observers.

    Abstract translation: 任意形状的均匀移动物体相对于物体的运动被分段和跟踪。 在帧内操作模式中，分割方法包括获得所选择的视频图像帧中的相应像素的运动表示和先前的视频图像帧，以形成运动分割的视频图像特征。 视频图像特征也根据其空间图像特征（例如，颜色）被分割以形成空间分割的视频图像特征。 最后，视频图像特征被联合分割为运动分割的视频图像特征和空间分割的视频图像特征的加权组合。 图像特征的联合运动和空间分割提供了表示运动图像特征的增强的准确度。 这种增强的精度是特别有益的，因为图像特征的运动是人类观察者的显着特征。

    Video encoding using previously calculated motion information
    20.
    发明授权
    Video encoding using previously calculated motion information 有权
    使用先前计算的运动信息的视频编码

    公开(公告)号：US08311115B2

    公开(公告)日：2012-11-13

    申请号：US12362427

    申请日：2009-01-29

    Applicant: Chuang Gu ,  Chun-Wei Chan ,  William Chen ,  Stacey Spears ,  Thomas W. Holcomb

    Inventor： Chuang Gu ,  Chun-Wei Chan ,  William Chen ,  Stacey Spears ,  Thomas W. Holcomb

    IPC: H04N7/12

    CPC classification number: H04N19/436 ,  H04N19/105 ,  H04N19/157 ,  H04N19/176 ,  H04N19/187 ,  H04N19/33 ,  H04N19/43 ,  H04N19/51

    Abstract: A video encoder uses previously calculated motion information for inter frame coding to achieve faster computation speed for video compression. In a multi bit rate application, motion information produced by motion estimation for inter frame coding of a compressed video bit stream at one bit rate is passed on to a subsequent encoding of the video at a lower bit rate. The video encoder chooses to use the previously calculated motion information for inter frame coding at the lower bit rate if the video resolution is unchanged. A multi core motion information pre-calculation produces motion information prior to encoding by dividing motion estimation of each inter frame to separate CPU cores.

    Abstract translation: 视频编码器使用先前计算的帧间编码运动信息来实现视频压缩的更快的计算速度。 在多比特率应用中，通过用于以一个比特率的压缩视频比特流的帧间编码的运动估计产生的运动信息被传递到较低比特率的视频的后续编码。 如果视频分辨率不变，则视频编码器选择使用先前计算的运动信息用于较低比特率的帧间编码。 多核心运动信息预计算在编码之前通过将每个帧间的运动估计划分成分离的CPU核心来产生运动信息。

Patent Agency Ranking