公开(公告)号：US20170041543A1

公开(公告)日：2017-02-09

申请号：US15226119

申请日：2016-08-02

申请人： Taro KIKUCHI

发明人： Taro KIKUCHI

IPC分类号： H04N5/232 ,  G06T5/40

CPC分类号： H04N5/23258 ,  G06T5/001 ,  G06T5/40 ,  G06T5/50 ,  G06T2207/20012 ,  G06T2207/20021 ,  G06T2207/20201 ,  H04N5/23274

摘要： An image processing device includes an image input unit, a shake-amount measuring unit, a shake correcting unit, a dividing unit, a feature-value calculating unit, and an enhancement processing unit. The image input unit receives an input of an image in chronological order. The shake-amount measuring unit measures an amount of shake of an image. The shake correcting unit corrects shake of the image in accordance with the amount of shake measured. The dividing unit divides the image corrected into multiple areas. The feature-value calculating unit calculates a histogram indicating a feature value of an image, for each of the divided areas. The enhancement processing unit determines processing details of enhancement processing to change a form of the histogram for each of the areas in accordance with the measured amount of shake of the image, and conducts enhancement processing on the area based on the histogram calculated for each area.

摘要翻译： 图像处理装置包括图像输入单元，抖动量测量单元，抖动校正单元，分割单元，特征值计算单元和增强处理单元。 图像输入单元以时间顺序接收图像的输入。 抖动量测量单元测量图像的抖动量。 抖动校正单元根据测量的抖动量校正图像的抖动。 分割单元将校正的图像划分为多个区域。 特征值计算单元针对每个分割区域计算指示图像的特征值的直方图。 增强处理单元根据所测量的图像的抖动量来确定增强处理的处理细节以改变每个区域的直方图的形式，并且基于为每个区域计算的直方图对该区域进行增强处理。

公开(公告)号：US20170019612A1

公开(公告)日：2017-01-19

申请号：US15086790

申请日：2016-03-31

申请人： Olympus Corporation

发明人： Tatsuya KINO

IPC分类号： H04N5/265 ,  G06T5/00 ,  G06T7/00 ,  H04N5/232

CPC分类号： G06T5/003 ,  G06T5/50 ,  G06T2207/20201 ,  H04N5/23254 ,  H04N5/23287 ,  H04N5/23293 ,  H04N5/2356

摘要： An image pickup apparatus includes: an IS unit that corrects blurring during exposure by driving a lens or an image pickup device based on a blur amount detected by a blur detecting unit; an alignment processing section that calculates a correlation value for arbitrary two images among image data of a plural images obtained by consecutive photographing; a combination processing section that aligns and combines image data of the two images based on the correlation value; and a microcomputer that is capable of setting a consecutive photographing combination mode. In a case where the consecutive photographing combination mode is set, the IS unit restricts an image stabilization range during live view.

摘要翻译： 图像拾取装置包括：IS单元，其基于由模糊检测单元检测到的模糊量，通过驱动透镜或图像拾取装置来校正曝光期间的模糊; 对准处理部，其计算通过连续拍摄获得的多个图像的图像数据中的任意两个图像的相关值; 组合处理部，其基于所述相关值对准并组合所述两个图像的图像数据; 以及能够设置连续拍摄组合模式的微型计算机。 在设置了连续拍摄组合模式的情况下，IS单元在实时取景期间限制图像稳定范围。

公开(公告)号：US09542754B2

公开(公告)日：2017-01-10

申请号：US14167651

申请日：2014-01-29

申请人： FUJIFILM Corporation

发明人： Hisashi Endo

IPC分类号： G06K9/00 ,  H04N5/232 ,  G06T7/20

CPC分类号： G06T7/20 ,  G06K9/00624 ,  G06T7/246 ,  G06T7/254 ,  G06T2207/10016 ,  G06T2207/10144 ,  G06T2207/20201 ,  G06T2207/20212 ,  H04N5/23212 ,  H04N5/23254 ,  H04N5/23261

摘要： A moving object detection apparatus comprising: an image acquisition device; a first moving object detection device; a difference image generation device; a second moving object detection device for detecting existence/nonexistence of the moving object based on the difference image generated by the difference image generation device; and an integration device for integrating a detection result by the first moving object detection device and a detection result by the second moving object detection device and determining that the moving object is detected in a case where the moving object is not detected by at least the first moving object detection device and the moving object is detected by the second moving object detection device.

摘要翻译： 一种移动物体检测装置，包括：图像获取装置; 第一移动物体检测装置; 差分图像生成装置; 第二移动物体检测装置，用于基于由差分图像生成装置生成的差分图像来检测移动物体的存在/不存在; 以及集成装置，用于将第一移动物体检测装置的检测结果和第二移动物体检测装置的检测结果进行积分，并且在至少第一移动物体检测装置未检测到移动物体的情况下，确定检测到移动物体 移动物体检测装置和移动物体由第二移动物体检测装置检测。

公开(公告)号：US09538069B2

公开(公告)日：2017-01-03

申请号：US14807419

申请日：2015-07-23

申请人： RICOH COMPANY, LTD.

发明人： Seiji Nagao

IPC分类号： H04N5/232 ,  G06T5/00 ,  G06T5/50 ,  G06T7/00

CPC分类号： H04N5/23212 ,  G06T5/002 ,  G06T5/003 ,  G06T5/004 ,  G06T5/50 ,  G06T7/11 ,  G06T7/571 ,  G06T2207/10004 ,  G06T2207/10028 ,  G06T2207/10148 ,  G06T2207/20201 ,  G06T2207/20224 ,  H04N5/2254 ,  H04N5/23216 ,  H04N5/23219 ,  H04N5/23222 ,  H04N5/23264 ,  H04N5/23293 ,  H04N5/369

摘要： An imaging device includes: an optical system which obtains an optical image of a photographic subject; an image sensor which converts the optical image to an electric signal; a digital signal processor which produces image data based on the electric signal; a display section which displays a photographic subject image expressed by the image data; and an operating section which performs a necessary setting regarding imaging, the digital signal processor including: an autofocus operation section which performs an autofocus operation based on data of an autofocus area set in the photographic subject image; a main area setting section which sets a main area in the photographic subject image; and a blurring operation section which performs a blurring operation on an area other than the main area in the photographic subject image, wherein the autofocus area is set automatically to overlap with at least a part of the main area.

摘要翻译： 一种成像装置，包括：获得被摄体的光学图像的光学系统; 将光学图像转换成电信号的图像传感器; 数字信号处理器，其基于所述电信号产生图像数据; 显示部，其显示由所述图像数据表示的拍摄对象图像; 所述数字信号处理器包括：自动对焦操作部，其基于在所述摄影对象图像中设置的自动聚焦区域的数据进行自动聚焦操作; 主区域设定部，其设置摄影对象图像中的主区域; 以及对摄影对象图像中的主区域以外的区域进行模糊操作的模糊操作部，其中自动对焦区域被自动设置为与主区域的至少一部分重叠。

公开(公告)号：US09530079B2

公开(公告)日：2016-12-27

申请号：US14437953

申请日：2013-03-07

申请人： NIKON CORPORATION

发明人： Gazi Ali ,  Li Hong ,  Radka Tezaur ,  Mark Takita

IPC分类号： G06K9/00 ,  G06K9/62 ,  G06K9/40 ,  G06K9/52 ,  G06T5/00 ,  G06T7/20

CPC分类号： G06K9/626 ,  G06K9/40 ,  G06K9/52 ,  G06K9/525 ,  G06K9/6201 ,  G06K9/6256 ,  G06K9/6286 ,  G06T5/003 ,  G06T7/20 ,  G06T2207/20201

摘要： A method for classifying a test image (16) includes the steps of building a classifier (300), and classifying the test image (16) with the classifier (300). After the test image (16) is classified, the test image (16) can be subsequently processed (e.g. deblurred) with improved accuracy. The classifier (300) can classify and distinguish between PSF features associated with motion blurred images, and PSF features associate with defocus blurred images. The classifier (300) can be built using a plurality of training images (304), and extracting one or more training features from each the training images (304). The PSF features can include image moments of the point spread function, and/or geometric features of the point spread function.

摘要翻译： 用于分类测试图像（16）的方法包括以下步骤：建立分类器（300），并且用分类器（300）对测试图像（16）进行分类。 在测试图像（16）被分类之后，测试图像（16）可以随后以改进的精度进行处理（例如去毛刺）。 分类器（300）可以对与运动模糊图像相关联的PSF特征进行分类和区分，并且PSF特征与散焦模糊图像相关联。 分类器（300）可以使用多个训练图像（304）构建，并且从每个训练图像（304）提取一个或多个训练特征。 PSF特征可以包括点扩散函数的图像矩，和/或点扩散函数的几何特征。

公开(公告)号：US20160358334A1

公开(公告)日：2016-12-08

申请号：US15174130

申请日：2016-06-06

申请人： University of Tennessee Research Foundation

发明人： Dustin R. Osborne ,  Dongming Hu ,  Sang Hyeb Lee

IPC分类号： G06T7/00 ,  G06T5/40

CPC分类号： G06T7/246 ,  A61B6/032 ,  A61B6/037 ,  A61B6/5205 ,  A61B6/5217 ,  A61B6/5264 ,  A61B6/5288 ,  A61B6/5294 ,  G06T5/003 ,  G06T11/005 ,  G06T2207/10104 ,  G06T2207/20201 ,  G06T2207/30016 ,  G06T2207/30096 ,  G06T2211/412

摘要： Systems and methods for correcting motion during medical imaging involve using a detector to track annihilation photons produced by one of (i) external emitting sources placed onto a body of a person being imaged or (ii) an object of interest in the body. Motion information is generated based on the tracking. A motion-corrected image is formed from recorded image data, using the motion information.

摘要翻译： 用于在医学成像期间校正运动的系统和方法涉及使用检测器来跟踪由（i）放置在被成像的人的身体上的外部发射源产生的湮灭光子，或（ii）身体中的感兴趣对象。 基于跟踪生成运动信息。 使用运动信息由记录图像数据形成运动校正图像。

公开(公告)号：US09514525B2

公开(公告)日：2016-12-06

申请号：US14449011

申请日：2014-07-31

申请人： Apple Inc.

发明人： Suk Hwan Lim ,  D. Amnon Silverstein

IPC分类号： H04N5/217 ,  G06T5/20

CPC分类号： G06T5/20 ,  G06T5/002 ,  G06T5/50 ,  G06T2207/20024 ,  G06T2207/20182 ,  G06T2207/20201 ,  H04N5/217

摘要： A temporal filter in an image processing pipeline may perform filtering using spatial filtering and noise history. A given pixel of a current image frame may be received for filtering at a temporal filter. A filtering weight may be determined for blending the given pixel with a corresponding pixel of a reference image frame that was previously filtered at the temporal filter. The filtering weight may be determined based on neighboring pixels of the given pixel in the current image frame and corresponding pixels in the reference image frame. The filtering weight may be adjusted according to a quality score indicating noise history for the corresponding pixel in the reference image frame. Based on the filtering weight, a filtered version of the given pixel may be generated, blending the given pixel and the corresponding pixel to store as part of a filtered version of the current image frame.

摘要翻译： 图像处理流水线中的时间滤波器可以使用空间滤波和噪声历史来执行滤波。 可以接收当前图像帧的给定像素以在时间滤波器处进行滤波。 可以确定用于将给定像素与先前在时间滤波器处被滤波的参考图像帧的对应像素混合的滤波权重。 可以基于当前图像帧中的给定像素和参考图像帧中的相应像素的相邻像素来确定滤波权重。 可以根据指示参考图像帧中的相应像素的噪声历史的质量得分来调整滤波权重。 基于过滤权重，可以生成给定像素的滤波版本，将给定像素和相应像素混合存储为当前图像帧的滤波版本的一部分。

公开(公告)号：US20160350901A1

公开(公告)日：2016-12-01

申请号：US15237527

申请日：2016-08-15

申请人： Gary SHUSTER ,  Brian SHUSTER

发明人： Gary SHUSTER ,  Brian SHUSTER

IPC分类号： G06T5/50 ,  G06K9/00 ,  G06T11/60 ,  G06T7/00 ,  G06T5/00

CPC分类号： G06T5/50 ,  G06K9/00677 ,  G06K9/62 ,  G06T5/003 ,  G06T7/0002 ,  G06T11/60 ,  G06T2207/10004 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20201 ,  G06T2207/20221 ,  G06T2207/30168 ,  G06T2207/30196 ,  H04N5/225

摘要： Aspects are disclosed for enhancing digital media. In an aspect, a target object in a primary image is identified, and reference images that include the target object are located. The target object is then modified within the primary image according to data derived from analyzing the reference image. In another aspect, a primary file is received, and at least one reference file is referenced to generate enhancement data that facilitates enhancing the primary file from an extrapolation of the reference file. In yet another aspect, media files corresponding to a common event are aggregated, and a desired enhancement of a primary file is identified. Here, the desired enhancement corresponds to a modification of an obstruction included in the primary file. A reference file which includes data associated with the desired enhancement is then referenced, and the obstructed data is modified based on replacement data extrapolated from the reference file.

公开(公告)号：US09507170B2

公开(公告)日：2016-11-29

申请号：US14302294

申请日：2014-06-11

申请人： CANON KABUSHIKI KAISHA

发明人： Shinji Imada

IPC分类号： H04N5/232 ,  G02B27/64 ,  G06T7/20 ,  G06T5/00

CPC分类号： G02B27/646 ,  G06T5/003 ,  G06T7/223 ,  G06T2207/20201 ,  H04N5/23209 ,  H04N5/23245 ,  H04N5/23254 ,  H04N5/23258 ,  H04N5/23287

摘要： An optical apparatus includes a blurring detection unit configured to detect image blurring applied to the optical apparatus; and a motion vector calculation unit configured to calculate a motion vector among a plurality of images shot by the optical apparatus. Image blurring is corrected in accordance with a signal obtained from blurring detected by the blurring detection unit; the motion vector is calculated using a correction result of the image blurring; and the image blurring is further corrected using the calculated motion vector.

摘要翻译： 光学装置包括：模糊检测单元，被配置为检测施加到所述光学装置的图像模糊; 以及运动矢量计算单元，被配置为计算由所述光学装置拍摄的多个图像中的运动矢量。 根据由模糊检测单元检测到的模糊获得的信号校正图像模糊; 使用图像模糊的校正结果计算运动矢量; 并且使用所计算的运动矢量进一步校正图像模糊。

公开(公告)号：US20160328852A1

公开(公告)日：2016-11-10

申请号：US15149824

申请日：2016-05-09

申请人： THE CLEVELAND CLINIC FOUNDATION

发明人： Erik B. Beall ,  Mark J. Lowe

IPC分类号： G06T7/00 ,  G06T7/20 ,  G06N7/00

CPC分类号： G06T7/38 ,  G06N7/005 ,  G06T5/001 ,  G06T7/0012 ,  G06T7/20 ,  G06T7/215 ,  G06T2207/10088 ,  G06T2207/20182 ,  G06T2207/20201 ,  G06T2207/30016

摘要： Systems and methods are provided for detecting motion in an imaging system. A time series of volumetric images of a region of interest are captured at the imaging system. Each volumetric image of the time series of volumetric images is captured as a series of two-dimensional slices of the region of interest. A representative value is calculated for each voxel to create a representative volumetric dataset representing the region of interest. For each slice of the series of two-dimensional slices, a simulated volumetric time series is generated, including time series data for the slice and the calculated representative value at all times for the other slices of the series of two-dimensional slices. A volumetric registration is performed on each of the simulated volumetric time series to provide a set of estimated motion parameters for the slice associated with the simulated volumetric time series.

摘要翻译： 提供了用于检测成像系统中的运动的系统和方法。 在成像系统中捕获感兴趣区域的体积图像的时间序列。 体积图像的时间序列的每个体积图像被捕获为感兴趣区域的一系列二维切片。 为每个体素计算代表性值以创建代表感兴趣区域的代表性体积数据集。 对于一系列二维切片的每个切片，产生模拟体积时间序列，包括切片的时间序列数据和所有二维切片系列的其他切片的计算代表值。 对每个模拟体积时间序列进行体积配准，以提供与模拟体积时间序列相关联的切片的估计运动参数的集合。