Hardware-constrained transforms for video stabilization processes
    31.
    发明授权
    Hardware-constrained transforms for video stabilization processes 有权
    用于视频稳定处理的硬件约束转换

    公开(公告)号:US08659679B2

    公开(公告)日:2014-02-25

    申请号:US13586031

    申请日:2012-08-15

    CPC分类号: H04N5/23248

    摘要: The video stabilization method can generate output data for an output frame from input data of an input frame according to a perspective transform of a transform matrix. The input data used for the perspective transform can be obtained from a buffer of a predetermined depth. The transform matrix can be altered when the input data required for the transform exceeds the depth of the buffer.

    摘要翻译: 视频稳定方法可以根据变换矩阵的透视变换从输入帧的输入数据生成输出帧的输出数据。 用于透视变换的输入数据可以从预定深度的缓冲器获得。 当变换所需的输入数据超过缓冲区的深度时,可以改变变换矩阵。

    AUTOMATED TRIPOD DETECTION AND HANDLING IN VIDEO STABILIZATION
    32.
    发明申请
    AUTOMATED TRIPOD DETECTION AND HANDLING IN VIDEO STABILIZATION 有权
    自动三体检测和处理在视频稳定

    公开(公告)号:US20130342714A1

    公开(公告)日:2013-12-26

    申请号:US13530500

    申请日:2012-06-22

    IPC分类号: H04N5/228

    CPC分类号: H04N5/23258 H04N5/23267

    摘要: An apparatus, method, and computer-readable medium for motion sensor-based video stabilization. A motion sensor may capture motion data of a video sequence. A controller may compute instantaneous motion of the camera for a current frame of the video sequence. The controller may compare the instantaneous motion to a threshold value representing a still condition and reduce a video stabilization strength parameter for the current frame if the instantaneous motion is less than the threshold value. A video stabilization unit may perform video stabilization on the current frame according to the frame's strength parameter.

    摘要翻译: 一种用于基于运动传感器的视频稳定的装置,方法和计算机可读介质。 运动传感器可以捕获视频序列的运动数据。 控制器可以计算摄像机对视频序列的当前帧的瞬时运动。 如果瞬时运动小于阈值,则控制器可以将瞬时运动与表示静止状态的阈值进行比较,并且减小当前帧的视频稳定强度参数。 视频稳定单元可以根据帧的强度参数在当前帧上执行视频稳定。

    Motion-Based Image Stitching
    33.
    发明申请
    Motion-Based Image Stitching 有权
    基于运动的图像拼接

    公开(公告)号:US20130329072A1

    公开(公告)日:2013-12-12

    申请号:US13490326

    申请日:2012-06-06

    IPC分类号: H04N5/225

    摘要: Systems, methods, and computer readable media for stitching or aligning multiple images (or portions of images) to generate a panoramic image are described. In general, techniques are disclosed for using motion data (captured at substantially the same time as image data) to align images rather than performing image analysis and/or registration operations. More particularly, motion data may be used to identify the rotational change between successive images. The identified rotational change, in turn, may be used to calculate a motion vector that describes the change in position between a point in a first image and a corresponding point in a subsequent image. The motion vector may be utilized to align successive images in an image sequence based on the motion data associated with the images.

    摘要翻译: 描述用于拼接或对准多个图像(或图像的部分)以产生全景图像的系统,方法和计算机可读介质。 通常,公开了使用运动数据(在与图像数据基本上相同的时间捕获)来对准图像而不是执行图像分析和/或注册操作的技术。 更具体地,运动数据可用于识别连续图像之间的旋转变化。 识别的旋转变化又可以用于计算描述第一图像中的点与随后图像中的对应点之间的位置变化的运动矢量。 运动矢量可以用于基于与图像相关联的运动数据来对齐图像序列中的连续图像。

    ROLLING SHUTTER REDUCTION BASED ON MOTION SENSORS
    34.
    发明申请
    ROLLING SHUTTER REDUCTION BASED ON MOTION SENSORS 有权
    基于运动传感器的滚动快门减速

    公开(公告)号:US20130044230A1

    公开(公告)日:2013-02-21

    申请号:US13598268

    申请日:2012-08-29

    申请人: Jianping Zhou

    发明人: Jianping Zhou

    IPC分类号: G06K9/40 H04N5/228

    摘要: This disclosure pertains to devices, methods, and computer readable media for reducing rolling shutter distortion effects in captured video frames based on timestamped positional information obtained from positional sensors in communication with an image capture device. In general, rolling shutter reduction techniques are described for generating and applying image segment-specific perspective transforms to already-captured segments of a single image or images in a video sequence, to compensate for unwanted distortions that occurred during the read out of the image sensor. Such distortions may be due to, for example, the use of CMOS sensors combined with the movement of the image capture device. In contrast to the prior art, rolling shutter reduction techniques described herein may be applied to captured images or videos in real-time or near real-time using positional sensor information and without intensive image processing that would require an analysis of the content of the underlying image data.

    摘要翻译: 本公开涉及用于基于从与图像捕获装置通信的位置传感器获得的时间戳位置信息来减少捕获的视频帧中的滚动快门失真效应的装置,方法和计算机可读介质。 通常,描述了滚动快门缩减技术,用于将图像段特定的透视变换应用于单个图像或视频序列中的图像的已经捕获的段,以补偿在图像传感器的读出期间发生的不期望的失真 。 这种失真可能是由于例如使用结合图像捕获装置的移动的CMOS传感器。 与现有技术相反,本文描述的滚动快门缩减技术可以使用位置传感器信息实时或接近实时地应用于捕获的图像或视频,并且不需要对需要分析底层的内容的强化图像处理 图像数据。

    ADAPTIVE LIGHT METHOD AND SYSTEM FOR LOW POWER ARCHITECTURES
    35.
    发明申请
    ADAPTIVE LIGHT METHOD AND SYSTEM FOR LOW POWER ARCHITECTURES 有权
    自适应光学方法和低功率结构的系统

    公开(公告)号:US20110243440A1

    公开(公告)日:2011-10-06

    申请号:US12752952

    申请日:2010-04-01

    申请人: Jianping Zhou

    发明人: Jianping Zhou

    IPC分类号: G06K9/00

    CPC分类号: G06T5/009 G06T5/40

    摘要: Embodiments of an apparatus, system and method are described for an adaptive light method for low power architecture. A histogram with a plurality of bins may be determined based on luminance for an image. A tone differential may be decreased based on a sum of pixel counts from adjacent bins. The image may be displayed based at least in part on a tone differential of a bin. Other embodiments are described and claimed.

    摘要翻译: 对于低功率架构的自适应光法描述了装置,系统和方法的实施例。 可以基于图像的亮度来确定具有多个箱的直方图。 可以基于来自相邻箱的像素数的总和来减小色差。 该图像可以至少部分地基于纸盒的色差来显示。 描述和要求保护其他实施例。

    SYSTEM, METHOD AND APPARATUS FOR AN EDGE-PRESERVING SMOOTH FILTER FOR LOW POWER ARCHITECTURE
    36.
    发明申请
    SYSTEM, METHOD AND APPARATUS FOR AN EDGE-PRESERVING SMOOTH FILTER FOR LOW POWER ARCHITECTURE 有权
    用于低功率结构的边缘保护滤波器的系统,方法和装置

    公开(公告)号:US20110242129A1

    公开(公告)日:2011-10-06

    申请号:US12753350

    申请日:2010-04-02

    IPC分类号: G09G5/00

    CPC分类号: G09G3/2059 G06T5/002 G06T5/20

    摘要: Embodiments of an apparatus, system and method are described for an edge-preserving smooth filter for low power architecture. A weighted pixel sum may be determined based on a weight of a central pixel and a weight of one or more neighboring pixels. The weight sum for the central pixel may be set to a power of two. An output of the central pixel may be displayed based on the weight sum and the weighted pixel sum. Other embodiments are described and claimed.

    摘要翻译: 描述了用于低功率架构的边缘保持平滑滤波器的装置,系统和方法的实施例。 可以基于中心像素的权重和一个或多个相邻像素的权重来确定加权像素和。 中心像素的权重和可以设为2的幂。 可以基于加权和和加权像素和来显示中心像素的输出。 描述和要求保护其他实施例。

    DIGITAL CAMERA AND METHOD
    37.
    发明申请
    DIGITAL CAMERA AND METHOD 审中-公开
    数码相机和方法

    公开(公告)号:US20100321520A1

    公开(公告)日:2010-12-23

    申请号:US12862458

    申请日:2010-08-24

    申请人: Jianping Zhou

    发明人: Jianping Zhou

    IPC分类号: H04N5/228 G06K9/00

    摘要: Digital camera contrast enhancement with piecewise-linear transform with lower and upper cutoffs for the transform determined from histogram analysis with a green color conversion approximation for images and IIR parameter filtering for videos.

    摘要翻译: 数字相机对比度增强与分段线性变换,具有用于图像的灰度转换近似和视频的IIR参数滤波的直方图分析确定的变换的下限和上限截止值。

    Universal visualization platform
    38.
    发明授权
    Universal visualization platform 有权
    通用可视化平台

    公开(公告)号:US07734607B2

    公开(公告)日:2010-06-08

    申请号:US11346609

    申请日:2006-02-01

    IPC分类号: G06F17/30

    摘要: The invention relates to a framework system and methods for connecting a plurality of tools. The system comprises a plug-in mechanism configured to dynamically load the plurality of tools, a data pool having storage space configured to store data sets associated with the plurality of tools, a linking mechanism configured to establish communications links between the loaded plurality of tools to enable coordinated operation of the loaded plurality of tools, a session component configured to record the process history of the operations of the loaded plurality of tool and the system states corresponding to the process history of the operations and an annotation module configured to associate user-provided data corresponding to one or more of the stored data sets.

    摘要翻译: 本发明涉及一种用于连接多个工具的框架系统和方法。 所述系统包括被配置为动态加载所述多个工具的插件机构,具有被配置为存储与所述多个工具相关联的数据集的存储空间的数据池,被配置为在所加载的多个工具之间建立通信链接的链接机构, 启用所加载的多个工具的协调操作,被配置为记录所加载的多个工具的操作的处理历史和对应于操作的处理历史的系统状态的会话组件以及被配置为将用户提供的关联的注释模块 对应于一个或多个所存储的数据集的数据。

    METHOD AND APPARATUS FOR DETERMINING IMAGE ORIENTATION
    39.
    发明申请
    METHOD AND APPARATUS FOR DETERMINING IMAGE ORIENTATION 有权
    用于确定图像方位的方法和装置

    公开(公告)号:US20100110107A1

    公开(公告)日:2010-05-06

    申请号:US12610801

    申请日:2009-11-02

    申请人: Jianping Zhou

    发明人: Jianping Zhou

    IPC分类号: G09G5/00

    摘要: A method and apparatus for automatically deciding on the orientation of image. The method includes computing average and standard deviation of luminance of the top region of a portion of the image, of the bottom region of a portion of the image, of the left region of a portion of the image, and of the right region of a portion of the image, computing average luminance of the image, computing, in the digital signal processor, consolidated luminance difference and uniformity of top and bottom regions, and left and right regions, utilizing the computed average and standard deviation of at least one of the bottom region, the left region or the right region andutilizing portrait orientation if difLR−difTB>t1 && stdTB−stdLR>t2 or if difLR−difTB>t3 && stdTB−stdLR>t4, otherwise, utilizing landscape orientation.

    摘要翻译: 一种用于自动决定图像方向的方法和装置。 该方法包括计算图像的一部分的底部区域,图像的一部分的左侧区域的底部区域和图像的一部分的右侧区域的顶部区域的亮度的平均和标准偏差 图像的部分,图像的计算平均亮度,数字信号处理器中的计算,顶部和底部区域以及左侧和右侧区域的整合亮度差和均匀性的计算,利用计算的平均和标准偏差 如果difLR-difTB> t1 && stdTB-stdLR> t2或者difLR-difTB> t3 && stdTB-stdLR> t4,则使用横向方向。