Background removal in a live video
    81.
    发明授权
    Background removal in a live video 有权
    在实时视频中进行后台删除

    公开(公告)号:US07720283B2

    公开(公告)日:2010-05-18

    申请号:US11469371

    申请日:2006-08-31

    IPC分类号: G06K9/34

    摘要: Exemplary systems and methods segment a foreground from a background image in a video sequence. In one implementation, a system refines a segmentation boundary between the foreground and the background image by attenuating background contrast while preserving contrast of the segmentation boundary itself, providing an accurate background cut of live video in real time. A substitute background may then be merged with the segmented foreground within the live video. The system can apply an adaptive background color mixture model to improve segmentation of foreground from background under various background changes, such as camera movement, illumination change, and movement of small objects in the background.

    摘要翻译: 示例性系统和方法从视频序列中的背景图像分割前景。 在一个实现中,系统通过衰减背景对比度同时保留分割边界本身的对比度来优化前景和背景图像之间的分割边界,从而实时提供实况视频的精确背景切割。 然后可以将替代背景与实时视频中的分段前景合并。 该系统可以应用自适应背景颜色混合模型,从而在各种背景变化(例如相机移动,照明变化和背景中的小物体的移动)下改进背景的前景分割。

    ALIGNMENT OF SHARP AND BLURRED IMAGES BASED ON BLUR KERNEL SPARSENESS
    82.
    发明申请
    ALIGNMENT OF SHARP AND BLURRED IMAGES BASED ON BLUR KERNEL SPARSENESS 有权
    基于BLER KERNEL SPARSENESS的SHARP和BLEDI图像的对齐

    公开(公告)号:US20100086232A1

    公开(公告)日:2010-04-08

    申请号:US12245339

    申请日:2008-10-03

    IPC分类号: G06K9/32

    CPC分类号: G06T7/35

    摘要: The alignment of a sharp image of a subject and a blurred image of the same subject is disclosed. For example, one disclosed embodiment provides a method of determining a series of trial images. The method comprises applying a corresponding series of coordinate transforms to the sharp image, the series of coordinate transforms differing with respect to one or more of a rotational operation and a scaling operation. The method further comprises computing a series blur kernels corresponding to the series of trial images, each blur kernel mapping a trial image from the series of trial images to the blurred image. The method further includes locating a sparsest blur kernel in the series of blur kernels, and identifying one or more of the rotational operation and the scaling operation of the coordinate transform mapping the trial image corresponding to the sparsest blur kernel to the blurred image.

    摘要翻译: 公开了对象的清晰图像与相同被摄体的模糊图像的对准。 例如,一个公开的实施例提供了确定一系列试验图像的方法。 该方法包括将相应的一系列坐标变换应用于锐利图像,所述一系列坐标变换相对于旋转操作和缩放操作中的一个或多个而不同。 该方法还包括计算与该系列试验图像相对应的一系列模糊粒子,每个模糊核心将来自一系列试验图像的试验图像映射到模糊图像。 该方法还包括将稀疏模糊核心定位在一系列模糊核心中,以及将映射与稀疏模糊核心的试用图像映射到模糊图像的坐标变换的旋转操作和缩放操作中的一个或多个。

    IMAGE SUPER-RESOLUTION USING GRADIENT PROFILE PRIOR
    83.
    发明申请
    IMAGE SUPER-RESOLUTION USING GRADIENT PROFILE PRIOR 有权
    使用梯度轮廓的图像超分辨率

    公开(公告)号:US20100086227A1

    公开(公告)日:2010-04-08

    申请号:US12245712

    申请日:2008-10-04

    IPC分类号: G06K9/36

    摘要: Described is a technology by which a low-resolution image is processed into a high-resolution image, including by performing processing in the gradient domain. A gradient profile corresponding to the lower-resolution image is transform into a sharpened image gradient. A high-resolution gradient profile is estimated from a low-resolution gradient profile, e.g., by multiplying the low-resolution gradient profile by a transform ratio that is based upon learned shape parameters, learned sharpness values and a curve distance to an edge pixel along the gradient profile. The transform ratio is used to transform a low-resolution gradient field to a high-resolution gradient field. Reconstructing the higher-resolution image is performed by using the high-resolution gradient field as a gradient domain constraint, e.g., in along with a reconstruction constraint obtained from image domain data. An energy function is minimized by enforcing the gradient domain constraint and the reconstruction constraint, e.g., by performing a gradient descent algorithm.

    摘要翻译: 描述了将低分辨率图像处理成高分辨率图像的技术,包括通过在梯度域中执行处理。 对应于较低分辨率图像的渐变曲线被转换成锐化的图像梯度。 从低分辨率梯度轮廓估计高分辨率梯度轮廓,例如,通过将低分辨率梯度轮廓乘以基于学习的形状参数,学习的锐度值和到边缘像素的曲线距离的变换比, 梯度轮廓。 变换比用于将低分辨率梯度场转换为高分辨率梯度场。 通过使用高分辨率梯度场作为梯度域约束,例如与从图像域数据获得的重建约束一起,进行重建高分辨率图像。 通过执行梯度域约束和重构约束,例如通过执行梯度下降算法来最小化能量函数。

    Submersible hollow shaft motor and submersible floating aerator comprising the same
    84.
    发明授权
    Submersible hollow shaft motor and submersible floating aerator comprising the same 有权
    潜水空心轴电动机和包括该潜水器的潜水式浮动曝气器

    公开(公告)号:US07661658B2

    公开(公告)日:2010-02-16

    申请号:US11953093

    申请日:2007-12-10

    申请人: Shulin Sun Jian Sun

    发明人: Shulin Sun Jian Sun

    IPC分类号: B01F3/04

    摘要: Provided is a submersible floating aerator, including a submersible hollow shaft motor (1) including a hollow shaft (2), a bottom shaft extension (4), a first motor flange (15), a second motor flange (16), a first flange (24) and a second flange (25), a gas-ring compressor (17), a base (21) having a gas inlet hole (22), a gas inlet tube (23), a dome (26), a propeller assembly (60) and an air outlet opening (18); wherein the base (21) is fixed on the top of the gas inlet tube (23), the gas-ring compressor (17) is fixed on the base (21) via a bracket (19); the air outlet opening (18) is connected to the gas-inlet hole (22) via a pipe (20); the gas inlet tube (23) is fixed to the first motor flange (15) via a first flange (24); the second motor flange (16) is fixed to the dome (26) via the second flange (25); the bottom shaft extension (4) is coaxially connected to the propeller assembly (60); and the hollow shaft (2) rotates along with the propeller assembly (60). The submersible floating aerator features large aeration depth, high utilization of oxygen, and uniform gas distribution.

    摘要翻译: 提供一种潜水式浮动曝气器,包括一个包括中空轴(2),底部轴延伸部(4),第一马达凸缘(15),第二马达凸缘(16),第一 凸缘(24)和第二凸缘(25),气环式压缩机(17),具有气体入口孔(22)的基座(21),气体入口管(23),圆顶(26), 螺旋桨组件(60)和空气出口开口(18); 其特征在于,所述基座(21)固定在所述气体导入管(23)的顶部,所述气环式压缩机(17)经由支架(19)固定在所述基座(21)上。 空气出口开口(18)经由管道(20)连接到气体入口孔(22)。 气体入口管(23)经由第一凸缘(24)固定到第一马达凸缘(15); 所述第二马达凸缘(16)经由所述第二凸缘(25)固定到所述圆顶(26)。 底轴延伸部(4)同轴连接到螺旋桨组件(60)上; 空心轴(2)与螺旋桨组件(60)一起旋转。 潜水浮式曝气机具有曝气深度大,氧气利用率高,气体分布均匀的特点。

    Vertical winding structures for planar magnetic switched-mode power converters
    85.
    发明授权
    Vertical winding structures for planar magnetic switched-mode power converters 有权
    平面磁开关电源转换器的垂直绕组结构

    公开(公告)号:US07554430B2

    公开(公告)日:2009-06-30

    申请号:US12015234

    申请日:2008-01-16

    IPC分类号: H01F5/00

    摘要: A vertical winding structure for planar integrated magnetics used in switched-mode power converters maintains close coupling between the different windings but reduces the eddy current losses, lowers the DC winding resistance and reduces the number of layers of the PCB. Vertical and horizontal windings can be used together without sacrificing these performance advantages and further minimizing the capacitive coupling between the outer-leg windings and the center-leg winding. This winding structure can be used in a wide range of magnetic structures including isolated and non-isolated CDRs, interleaved CDRs, and buck and boost converters.

    摘要翻译: 用于开关模式功率转换器的平面集成磁体的垂直绕组结构保持不同绕组之间的紧密耦合,但是减小了涡流损耗,降低了直流绕组电阻并减少了PCB的层数。 垂直和水平绕组可以一起使用,而不会牺牲这些性能优势,并进一步最小化外腿绕组和中心腿绕组之间的电容耦合。 该绕组结构可用于宽范围的磁结构,包括隔离和非隔离CDR,交错CDR,降压和升压转换器。

    Image completion with structure propagation
    86.
    发明授权
    Image completion with structure propagation 失效
    图像完成与结构传播

    公开(公告)号:US07502521B2

    公开(公告)日:2009-03-10

    申请号:US11158113

    申请日:2005-06-21

    IPC分类号: G06T3/00

    CPC分类号: G06T5/005

    摘要: Image completion with structure propagation is described. In one aspect, synthesized patches for an unknown region in an input image are automatically generated. The synthesized patches are generated from a known region in the input image based on information from one or more curves. The one or more curves were generated to provide missing structure to the unknown region. Structure is propagated to the unknown region with the synthesized patches.

    摘要翻译: 描述了具有结构传播的图像完成。 在一个方面,自动生成输入图像中未知区域的合成补丁。 基于来自一个或多个曲线的信息,从输入图像中的已知区域生成合成的补丁。 生成一条或多条曲线以向未知区域提供缺失的结构。 结构用合成的斑块传播到未知区域。

    Creating optimized gradient mesh of a vector-based image from a raster-based image
    87.
    发明申请
    Creating optimized gradient mesh of a vector-based image from a raster-based image 有权
    从基于光栅的图像创建基于矢量的图像的优化梯度网格

    公开(公告)号:US20080278479A1

    公开(公告)日:2008-11-13

    申请号:US11800680

    申请日:2007-05-07

    IPC分类号: G06T15/00

    CPC分类号: G06T17/20

    摘要: A method for creating an optimized gradient mesh of a vector-based image from a raster-based image. In one implementation, a set of boundaries for an object on a raster-based image may be received. An initial gradient mesh of the object may be created. A residual energy between the object on the raster-based image and a rendered initial gradient mesh may be minimized to generate an optimized gradient mesh.

    摘要翻译: 一种用于从基于光栅的图像创建基于矢量的图像的优化梯度网格的方法。 在一个实现中,可以接收基于光栅的图像上的对象的一组边界。 可以创建对象的初始渐变网格。 基于光栅的图像上的对象与渲染的初始梯度网格之间的剩余能量可以被最小化以生成优化的梯度网格。

    Picture Collage Systems And Methods
    88.
    发明申请
    Picture Collage Systems And Methods 失效
    图片拼贴系统和方法

    公开(公告)号:US20080193048A1

    公开(公告)日:2008-08-14

    申请号:US11674243

    申请日:2007-02-13

    IPC分类号: G06K9/36

    CPC分类号: G06T11/60

    摘要: Systems and methods provide picture collage systems and methods. In one implementation, a system determines a salient region in each of multiple images and develops a Bayesian model to maximize visibility of the salient regions in a collage that overlaps the images. The Bayesian model can also minimize blank spaces in the collage and normalize the percentage of each salient region that can be visibly displayed in the collage. Images are placed with diversified rotational orientation to provide a natural artistic collage appearance. A Markov Chain Monte Carlo technique is applied to the parameters of the Bayesian model to obtain image placement, orientation, and layering. The MCMC technique can combine optimization proposals that include local, global, and pairwise samplings from a distribution of state variables.

    摘要翻译: 系统和方法提供图片拼贴系统和方法。 在一个实现中,系统确定多个图像中的每一个中的显着区域,并且开发贝叶斯模型以最大化与图像重叠的拼贴中的显着区域的可见性。 贝叶斯模型还可以将拼贴中的空白空间最小化,并将每个显着区域的百分比归一化,可以在拼贴画中显示。 图像以多样化的旋转方向放置,以提供自然的艺术拼贴外观。 将马尔科夫链蒙特卡罗技术应用于贝叶斯模型的参数,以获得图像放置,取向和分层。 MCMC技术可以结合来自状态变量分布的本地,全局和成对采样的优化提议。

    Generic image hallucination
    89.
    发明授权
    Generic image hallucination 有权
    通用图像幻象

    公开(公告)号:US07379611B2

    公开(公告)日:2008-05-27

    申请号:US10817471

    申请日:2004-04-01

    IPC分类号: G06K9/32 G06K9/40

    CPC分类号: G06T3/4007

    摘要: Techniques are disclosed to enable generation of a high-resolution image from any generic low-resolution image. In one described implementation, a method includes extracting, at a training phase, a plurality of primal sketch priors from training data. At a synthesis phase, the plurality of primal sketch priors are utilized to improve a low-resolution image by replacing one or more low-frequency primitives extracted from the low-resolution image with corresponding ones of the plurality of primal sketch priors.

    摘要翻译: 公开了技术以使得能够从任何通用的低分辨率图像生成高分辨率图像。 在一个描述的实现中,一种方法包括在训练阶段从训练数据中提取多个原始草图先验。 在合成阶段,利用多个原始草图优先级,通过将从低分辨率图像提取的一个或多个低频原语替换为多个原始素描先验中的相应图像,来利用低分辨率图像来改善低分辨率图像。

    Vertically packaged switched-mode power converter
    90.
    发明授权
    Vertically packaged switched-mode power converter 有权
    垂直封装的开关模式电源转换器

    公开(公告)号:US07012414B1

    公开(公告)日:2006-03-14

    申请号:US10922062

    申请日:2004-08-19

    IPC分类号: G05F3/06

    摘要: A vertically packaged cellular power converter solves the problems associated with conventional designs and paves the way for a cellular circuit architecture with ultra-low interconnect resistance and inductance. The vertical packaging results in a power flow in the vertical direction (from the bottom to the top) with very short internal interconnects, thereby minimizing the associated conduction losses and permitting high conversion efficiency at high currents. The cellular architecture is ideally suited for generating multiple supply voltages.

    摘要翻译: 垂直封装的蜂窝功率转换器解决了与常规设计相关的问题,为具有超低互连电阻和电感的蜂窝电路架构铺平了道路。 垂直封装导致垂直方向(从底部到顶部)的功率流具有非常短的内部互连,从而最小化相关联的传导损耗并且在高电流下允许高的转换效率。 蜂窝结构非常适合产生多个电源电压。