ESTIMATION OF IMAGE RELATIONS FROM POINT CORRESPONDENCES BETWEEN IMAGES
    1.
    发明申请
    ESTIMATION OF IMAGE RELATIONS FROM POINT CORRESPONDENCES BETWEEN IMAGES 失效
    从图像之间的点对应的图像关系的估计

    公开(公告)号:US20100232709A1

    公开(公告)日:2010-09-16

    申请号:US12633463

    申请日:2009-12-08

    IPC分类号: G06K9/46

    CPC分类号: G06T7/73 G06T7/77

    摘要: The invention relates to a method for estimating an image relation model for two or more related images based on a plurality of point correspondences. The method includes using a weighted random sampling algorithm to repeatedly draw subsets of point correspondences for generating model estimates, evaluating said model estimates for the full plurality of the point correspondences, and updating weights associated with each of the point correspondences in the random sampling algorithm based on information obtained in said evaluating.

    摘要翻译: 本发明涉及一种用于基于多个点对应度来估计两个或多个相关图像的图像关系模型的方法。 该方法包括使用加权随机抽样算法重复绘制点对应子集用于生成模型估计,评估所述多个点对应关系的所述模型估计,以及基于随机抽样算法中的每个点对应关系更新权重 对所述评估中获得的信息。

    Estimation of image relations from point correspondences between images
    2.
    发明授权
    Estimation of image relations from point correspondences between images 失效
    从图像之间的点对应度估计图像关系

    公开(公告)号:US08411966B2

    公开(公告)日:2013-04-02

    申请号:US12633463

    申请日:2009-12-08

    IPC分类号: G06K9/46 G06K9/32

    CPC分类号: G06T7/73 G06T7/77

    摘要: The invention relates to a method for estimating an image relation model for two or more related images based on a plurality of point correspondences. The method includes using a weighted random sampling algorithm to repeatedly draw subsets of point correspondences for generating model estimates, evaluating said model estimates for the full plurality of the point correspondences, and updating weights associated with each of the point correspondences in the random sampling algorithm based on information obtained in said evaluating.

    摘要翻译: 本发明涉及一种用于基于多个点对应度来估计两个或多个相关图像的图像关系模型的方法。 该方法包括使用加权随机抽样算法重复绘制点对应子集用于生成模型估计,评估所述多个点对应关系的所述模型估计,以及基于随机抽样算法中的每个点对应关系更新权重 对所述评估中获得的信息。

    Method for temporal interpolation of an image sequence using object-based image analysis
    3.
    发明授权
    Method for temporal interpolation of an image sequence using object-based image analysis 有权
    使用基于对象的图像分析的图像序列的时间插值方法

    公开(公告)号:US06625333B1

    公开(公告)日:2003-09-23

    申请号:US09369347

    申请日:1999-08-06

    IPC分类号: G06K932

    摘要: A method for temporal interpolation of an image sequence using object-based image analysis is disclosed. The method comprises the steps of image segmentation for partitioning a known image into objects, motion estimation, object-based motion field processing, determination of object depth order, detection of covered areas and newly exposed areas, adaptive interpolation using motion projection, and graceful degradation for alleviating remaining visible artifacts. The method produces interpolated images of high quality in real time for every type of image areas including fast moving objects, covered areas, and newly exposed areas.

    摘要翻译: 公开了一种基于对象的图像分析的图像序列的时间插值方法。 该方法包括以下步骤:将已知图像划分为对象,运动估计,基于对象的运动场处理,对象深度顺序的确定,覆盖区域和新曝光区域的检测,使用运动投影的自适应插值和优雅退化的步骤 以减轻剩余的可见伪影。 该方法为包括快速移动物体,覆盖区域和新曝光区域在内的每种图像区域实时生成高质量的内插图像。

    IMAGE AND VIDEO ENCODING AND DECODING
    4.
    发明申请
    IMAGE AND VIDEO ENCODING AND DECODING 审中-公开
    图像和视频编码和解码

    公开(公告)号:US20120294365A1

    公开(公告)日:2012-11-22

    申请号:US13435148

    申请日:2012-03-30

    IPC分类号: H04N7/34 G06K9/36 H04N7/26

    摘要: A method and system for image and video encoding and decoding is disclosed. A plurality of macro-blocks of pixels are defined in the image to be encoded, for subsequent block-by-block encoding and decoding. A node-cell structure of pixels is individually defined for each macro-block. The node pixels are encoded first. Then, the cell pixels are encoded using the decoded node pixels as a reference. This allows increasing macro-block size without a significant degradation of pixel encoding quality.

    摘要翻译: 公开了一种用于图像和视频编码和解码的方法和系统。 在要编码的图像中定义多个像素的宏块,用于随后的逐块编码和解码。 每个宏块分别定义像素的节点单元结构。 首先对节点像素进行编码。 然后,使用解码的节点像素作为参考来对单元像素进行编码。 这允许增加宏块大小而不会显着降低像素编码质量。

    Curved wavelet transform for image and video compression
    5.
    发明申请
    Curved wavelet transform for image and video compression 失效
    用于图像和视频压缩的弯曲小波变换

    公开(公告)号:US20050196060A1

    公开(公告)日:2005-09-08

    申请号:US11068160

    申请日:2005-03-01

    IPC分类号: G06K9/36 H04N7/26

    摘要: A curved wavelet transform and a related image/video compression system are disclosed. The curved wavelet transform (CWT) is carried out by applying one-dimensional (1-D) wavelet filters along curves, rather than along only horizontal and vertical directions. The image/video compression system includes a curve determination unit, a curved wavelet transform unit, a wavelet coefficient quantization unit, a wavelet coefficient coding unit, and a curve coding unit. The quantization and coding of the wavelet coefficients are related to the curves. In one embodiment, recursive wavelet filters are used for inverse wavelet decomposition. The system provides higher compression capability than conventional wavelet-based image compression systems.

    摘要翻译: 公开了一种弯曲小波变换和相关图像/视频压缩系统。 曲线小波变换(CWT)通过沿着曲线应用一维(1-D)小波滤波器而不是沿着水平和垂直方向进行。 图像/视频压缩系统包括曲线确定单元,弯曲小波变换单元,小波系数量化单元,小波系数编码单元和曲线编码单元。 小波系数的量化和编码与曲线相关。 在一个实施例中,递归小波滤波器用于逆小波分解。 该系统比传统的基于小波的图像压缩系统提供更高的压缩能力。

    Curved wavelet transform for image and video compression
    6.
    发明授权
    Curved wavelet transform for image and video compression 失效
    用于图像和视频压缩的弯曲小波变换

    公开(公告)号:US07418144B2

    公开(公告)日:2008-08-26

    申请号:US11068160

    申请日:2005-03-01

    IPC分类号: G06K9/36 G06K9/46

    摘要: A curved wavelet transform and a related image/video compression system are disclosed. The curved wavelet transform (CWT) is carried out by applying one-dimensional (1-D) wavelet filters along curves, rather than along only horizontal and vertical directions. The image/video compression system includes a curve determination unit, a curved wavelet transform unit, a wavelet coefficient quantization unit, a wavelet coefficient coding unit, and a curve coding unit. The quantization and coding of the wavelet coefficients are related to the curves. In one embodiment, recursive wavelet filters are used for inverse wavelet decomposition. The system provides higher compression capability than conventional wavelet-based image compression systems.

    摘要翻译: 公开了一种弯曲小波变换和相关图像/视频压缩系统。 曲线小波变换(CWT)通过沿着曲线应用一维(1-D)小波滤波器而不是沿着水平和垂直方向进行。 图像/视频压缩系统包括曲线确定单元,弯曲小波变换单元,小波系数量化单元,小波系数编码单元和曲线编码单元。 小波系数的量化和编码与曲线相关。 在一个实施例中,递归小波滤波器用于逆小波分解。 该系统比传统的基于小波的图像压缩系统提供更高的压缩能力。

    Learning filters for enhancing the quality of block coded still and video images
    7.
    发明授权
    Learning filters for enhancing the quality of block coded still and video images 失效
    学习过滤器,用于提高块编码静止图像和视频图像的质量

    公开(公告)号:US08204128B2

    公开(公告)日:2012-06-19

    申请号:US12184671

    申请日:2008-08-01

    IPC分类号: H04N7/12

    摘要: The invention relates to a method and an apparatus for reducing blocking artifacts in block-wise coding of still and video images. A learning filter generator is provided at the image encoder for generating a set of filters and associated filtering rules for filtering cross-boundary image patterns based on representative original and decoded training images using a supervised machine learning algorithm. An adaptive filter at the image decoder receives the generated filters and associated filtering rules and performs locally adaptive filtering in accordance with the received filtering rules.

    摘要翻译: 本发明涉及一种用于减少静止图像和视频图像的块状编码中的块伪影的方法和装置。 在图像编码器上设置学习滤波器发生器,用于使用监督机器学习算法基于代表性的原始和解码的训练图像来生成一组滤波器和相关联的滤波规则,用于过滤跨边界图像模式。 图像解码器处的自适应滤波器接收生成的滤波器和相关联的滤波规则,并根据接收到的滤波规则执行本地自适应滤波。

    Image Interpolation for motion/disparity compensation
    8.
    发明申请
    Image Interpolation for motion/disparity compensation 失效
    图像插值用于运动/视差补偿

    公开(公告)号:US20110069237A1

    公开(公告)日:2011-03-24

    申请号:US12923476

    申请日:2010-09-23

    IPC分类号: H04N5/14

    摘要: Methods of image interpolation disclosed herein include a method of irregular-grid expanded-block weighted motion compensation (IEWMC) and a method of block-wise directional hole interpolation (BDHI). The IEWMC can be used with unidirectional motion or disparity trajectories. The IEWMC can be applied in both forward and backward directions, and the interpolated images resulting from IEWMC application can be superimposed, or averaged, to reduce the blocking artifacts and handle the holes and overlaps. The BDHI takes into account the orientation of local edges and textures when filling the holes, which results in a sharper interpolated image.

    摘要翻译: 本文公开的图像插值方法包括不规则网格扩展块加权运动补偿(IEWMC)的方法和块定向孔插入(BDHI)的方法。 IEWMC可以用于单向运动或视差轨迹。 IEWMC可以在向前和向后两个方向上应用,并且由IEWMC应用产生的内插图像可以叠加或平均,以减少块伪影并处理孔和重叠。 BDHI在填充孔时考虑到局部边缘和纹理的方向,这导致更清晰的内插图像。

    Learning Filters For Enhancing The Quality Of Block Coded Still And Video Images
    9.
    发明申请
    Learning Filters For Enhancing The Quality Of Block Coded Still And Video Images 失效
    学习过滤器用于提高块编码静态图像和视频图像的质量

    公开(公告)号:US20090034622A1

    公开(公告)日:2009-02-05

    申请号:US12184671

    申请日:2008-08-01

    IPC分类号: H04N7/32 H04N7/26

    摘要: The invention relates to a method and an apparatus for reducing blocking artifacts in block-wise coding of still and video images. A learning filter generator is provided at the image encoder for generating a set of filters and associated filtering rules for filtering cross-boundary image patterns based on representative original and decoded training images using a supervised machine learning algorithm. An adaptive filter at the image decoder receives the generated filters and associated filtering rules and performs locally adaptive filtering in accordance with the received filtering rules.

    摘要翻译: 本发明涉及一种用于减少静止图像和视频图像的块状编码中的块伪影的方法和装置。 在图像编码器上设置学习滤波器发生器,用于使用监督机器学习算法基于代表性的原始和解码的训练图像来生成一组滤波器和相关联的滤波规则,用于过滤跨边界图像模式。 图像解码器处的自适应滤波器接收生成的滤波器和相关联的滤波规则,并根据接收到的滤波规则执行本地自适应滤波。