公开(公告)号：US07715643B2

公开(公告)日：2010-05-11

申请号：US10344568

申请日：2002-06-13

申请人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Takashi Sawao ,  Naoki Fujiwara ,  Takahiro Nagano ,  Seiji Wada ,  Toru Miyake

发明人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Takashi Sawao ,  Naoki Fujiwara ,  Takahiro Nagano ,  Seiji Wada ,  Toru Miyake

IPC分类号： G06K9/42

CPC分类号： G06T7/44 ,  G06T7/194 ,  G06T2207/10016

摘要： An image processing device for processing images of background images and moving objects. A region specifying unit specifies a mixed region made up of a mixture of a foreground object component and a background object component, and a non-mixed region made up of one or the other of a foreground object component and a background object component, and outputs region information corresponding to the specifying results. A foreground/background separation unit separates the input image into foreground component images and background component images, corresponding to the region information. A separated image processing unit processes the foreground component images and background component images individually, corresponding to the results of separation.

摘要翻译： 一种用于处理背景图像和移动物体的图像的图像处理装置。 区域指定单元指定由前景对象分量和背景对象分量的混合构成的混合区域和由前景对象分量和背景对象分量中的一个或多个构成的非混合区域，并且输出 对应于指定结果的区域信息。 前景/背景分离单元将输入图像分离成与区域信息对应的前景分量图像和背景分量图像。 分离的图像处理单元分别对应于分离结果处理前景分量图像和背景分量图像。

公开(公告)号：US07668393B2

公开(公告)日：2010-02-23

申请号：US10543839

申请日：2004-02-12

申请人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Takashi Sawao ,  Takahiro Nagano ,  Naoki Fujiwara ,  Toru Miyake ,  Seiji Wada

发明人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Takashi Sawao ,  Takahiro Nagano ,  Naoki Fujiwara ,  Toru Miyake ,  Seiji Wada

IPC分类号： G06K9/40 ,  G06K9/48

CPC分类号： G06K9/4609 ,  G06T3/4007 ,  G06T7/12 ,  G06T2207/10016 ,  G06T2207/20192

摘要： An apparatus and method which takes into consideration the real world where data was acquired, and enables obtaining of processing results which are more accurate and more precise as to phenomena in the real world. A data continuity detecting unit detects the continuity of data of second signals, having second dimensions that are fewer than first dimensions had by first signals which are real world signals and are projected whereby a part of the continuity of the real world signals is lost, wherein the continuity to be detected corresponds to the continuity of the real world signals that has been lost. An actual world estimating unit estimates a real world image by estimating the continuity of the real world image that has been lost, based on the continuity of the data detected by the data continuity detecting unit.

摘要翻译： 考虑到获取数据的真实世界的装置和方法，并且能够获得对于现实世界中的现象更准确和更准确的处理结果。 数据连续性检测单元检测第二信号的数据的连续性，其具有由第一信号小于第一尺寸的第二维度，该第一信号是真实世界信号的第一信号，并且被投影，从而一部分实际信号的连续性丢失，其中 要检测的连续性对应于已经丢失的真实世界信号的连续性。 基于由数据连续性检测单元检测到的数据的连续性，实际世界估计单元通过估计已丢失的真实世界图像的连续性来估计真实世界图像。

公开(公告)号：US07619655B2

公开(公告)日：2009-11-17

申请号：US10362725

申请日：2002-06-26

申请人： Tetsujiro Kondo ,  Takashi Sawao ,  Junichi Ishibashi ,  Takahiro Nagano ,  Naoki Fujiwara ,  Toru Miyake ,  Seiji Wada

发明人： Tetsujiro Kondo ,  Takashi Sawao ,  Junichi Ishibashi ,  Takahiro Nagano ,  Naoki Fujiwara ,  Toru Miyake ,  Seiji Wada

IPC分类号： H04N5/228

CPC分类号： H04N21/222 ,  G06T7/215 ,  H04N19/127 ,  H04N19/162 ,  H04N19/17 ,  H04N19/172 ,  H04N19/503 ,  H04N19/51 ,  H04N21/23473 ,  H04N21/23476 ,  H04N21/2541 ,  H04N21/25435 ,  H04N21/25875 ,  H04N21/26613 ,  H04N21/4542 ,  H04N21/45455 ,  H04N21/4627 ,  H04N21/4753 ,  H04N21/6125 ,  H04N21/6175 ,  H04N21/6332 ,  H04N21/6334 ,  H04N21/64322 ,  H04N21/654 ,  H04N21/835 ,  H04N21/8352 ,  H04N21/8586

摘要： The present invention enables the high speed processing of a foreground component image and a background component image associated with images received on a network platform. A client computer outputs information specifying image data to a separation server. The separation server then obtains the specified image data from a storage server and outputs it to a motion detecting server to perform motion detection processing. Thereafter, the image data, a motion vector, and positional information are output to an area specifying server. The area specifying server generates area information corresponding to the image data and outputs the area information to a mixture ratio calculating server in addition to the image data, the motion vector, and the positional information. The mixture ratio calculating server then calculates a mixture ratio on the basis of the image data, the motion vector, the positional information, and the area information, whereby a foreground/background image separation server separates the foreground and background of the input image on the basis this information.

摘要翻译： 本发明能够对与在网络平台上接收的图像相关联的前景分量图像和背景分量图像进行高速处理。 客户端计算机向分离服务器输出指定图像数据的信息。 然后，分离服务器从存储服务器获取指定的图像数据，并将其输出到运动检测服务器以执行运动检测处理。 此后，将图像数据，运动矢量和位置信息输出到区域指定服务器。 区域指定服务器生成与图像数据对应的区域信息，并且除了图像数据，运动矢量和位置信息之外，还将区域信息输出到混合比计算服务器。 混合比计算服务器然后根据图像数据，运动矢量，位置信息和区域信息计算混合比，由此前景/背景图像分离服务器将输入图像的前景和背景分离在 基础信息。

公开(公告)号：US07525574B2

公开(公告)日：2009-04-28

申请号：US11446905

申请日：2006-06-05

申请人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Takashi Sawao ,  Seiji Wada ,  Tohru Miyake ,  Takahiro Nagano ,  Naoki Fujiwara

发明人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Takashi Sawao ,  Seiji Wada ,  Tohru Miyake ,  Takahiro Nagano ,  Naoki Fujiwara

IPC分类号： H04N5/228

CPC分类号： G06T5/002 ,  G06T5/003 ,  G06T5/50 ,  G06T7/11 ,  G06T7/194 ,  G06T7/20 ,  G06T2207/10016 ,  G06T2207/20201

摘要： A signal processor 12 acquires a second signal obtained by detecting a first signal, as a signal of the real world, having a first dimension. The second signal is of a second dimension lower than the first dimension and has distortion relative to the first signal. The signal processor 12 performs signal processing which is based on the second signal to generate a third signal alleviated in distortion as compared to the second signal.

摘要翻译： 信号处理器12获取通过检测具有第一维度的作为现实世界的信号的第一信号而获得的第二信号。 第二信号具有比第一维小的第二维度，并且相对于第一信号具有失真。 信号处理器12执行基于第二信号的信号处理，以产生与第二信号相比在失真中减轻的第三信号。

公开(公告)号：US07477289B2

公开(公告)日：2009-01-13

申请号：US10362793

申请日：2002-06-26

申请人： Tetsujiro Kondo ,  Seiji Wada ,  Junichi Ishibashi ,  Takashi Sawao ,  Naoki Fujiwara ,  Takahiro Nagano ,  Toru Miyake

发明人： Tetsujiro Kondo ,  Seiji Wada ,  Junichi Ishibashi ,  Takashi Sawao ,  Naoki Fujiwara ,  Takahiro Nagano ,  Toru Miyake

IPC分类号： H04N5/228

CPC分类号： H04N5/272 ,  G06T7/194 ,  G06T7/215 ,  G06T2207/10016

摘要： An object of the present invention is to make it possible to detect the mixture state of an image. An area specifying unit 103 specifies, in correspondence with image data, a mixed area in which foreground object components forming a foreground object and background object components forming a background object are mixed and a non-mixed area formed of a foreground area consisting of only the foreground object components and a background area consisting of only the background object components. A mixture-ratio calculator 104 estimates, based on the ratio of the width of the mixed area in a predetermined direction with respect to the moving direction of the foreground object, the width of the mixed area being specified by the area information, to the distance from the position of a designated pixel to the edge of the mixed area in the predetermined direction, the mixture ratio indicating the ratio of the foreground object components and the background object components of the designated pixel. The present invention is applicable to an image processing apparatus.

摘要翻译： 本发明的目的是使得可以检测图像的混合状态。 区域指定单元103与图像​​数据对应地指定混合形成前景对象的前景对象分量和形成背景对象的背景对象分量的混合区域，以及由仅包含背景对象的前景区域构成的前景区域形成的非混合区域 前景对象组件和仅由背景对象组件组成的背景区域。 混合比率计算器104基于相对于前景物体的移动方向的预定方向上的混合区域的宽度与由区域信息指定的混合区域的宽度相对于距离 从指定像素的位置到预定方向上的混合区域的边缘，该混合比率指示指定像素的前景对象分量和背景对象分量的比率。 本发明可应用于图像处理装置。

公开(公告)号：US20080279267A1

公开(公告)日：2008-11-13

申请号：US11947423

申请日：2007-11-29

申请人： Takashi NAKANISHI ,  Shunsuke Mochizuki ,  Masahiro Yoshioka ,  Ryosuke Araki ,  Hiroto Kimura ,  Seiji Wada ,  Hiroshi Ichiki ,  Tetsujiro Kondo

发明人： Takashi NAKANISHI ,  Shunsuke Mochizuki ,  Masahiro Yoshioka ,  Ryosuke Araki ,  Hiroto Kimura ,  Seiji Wada ,  Hiroshi Ichiki ,  Tetsujiro Kondo

IPC分类号： H04B17/00

CPC分类号： H04L25/03133 ,  H04L2025/03375 ,  H04L2025/0377

摘要： A signal processing apparatus configured to process a signal transmitted via a transmission path where a waveform represented by a signal value of a particular symbol is stationarily distorted in accordance with values of symbols transmitted prior to the particular symbol, including the following elements: a receiving unit configured to receive a test signal which is the signal including symbols set to predetermined values via the transmission path; an obtaining unit configured to obtain the signal value of the particular symbol from the test signal received by the receiving unit; and a characteristic computing unit configured to compute a characteristic of distortion of the waveform represented by the signal value of the particular symbol in accordance with the values of the symbols transmitted prior to the particular symbol on the basis of waveforms represented by signal values obtained by the obtaining unit from a plurality of test signals.

摘要翻译： 一种信号处理装置，被配置为处理通过传输路径发送的信号，其中由特定符号的信号值表示的波形根据在特定符号之前发送的符号的值而静止失真，包括以下元件：接收单元 被配置为经由所述传输路径接收作为包括设置为预定值的符号的信号的测试信号; 获取单元，被配置为从所述接收单元接收的所述测试信号中获得所述特定符号的信号值; 以及特征计算单元，被配置为基于由所述特定符号的信号值表示的波形表示的波形的特性，根据由所述特定符号的信号值表示的波形，基于由所述特定符号获得的信号值所表示的波形， 从多个测试信号获取单元。

公开(公告)号：US07412075B2

公开(公告)日：2008-08-12

申请号：US10240377

申请日：2002-02-01

申请人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Takashi Sawao ,  Takahiro Nagano ,  Naoki Fujiwara ,  Toru Miyake ,  Seiji Wada

发明人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Takashi Sawao ,  Takahiro Nagano ,  Naoki Fujiwara ,  Toru Miyake ,  Seiji Wada

IPC分类号： G06K9/00 ,  G06K9/34 ,  G06K9/36

CPC分类号： H04N5/145 ,  H04N5/272

摘要： The present invention relates to a picture processing apparatus that allows detection of an area in which a plurality of objects, such as a background picture and a picture of a moving object, is mixed. A background picture generation unit 121 generates a background picture based on picture data. A binary object picture extraction unit 121 detects a correlation value between each pixel in picture data of a frame under consideration and a pixel in the background picture at a position corresponding to the pixel in the picture data of the frame under consideration. A temporal change detection unit 123 detects a mixed area in the frame under consideration, in which a plurality of real-world objects is mixed, based on a temporal change of the correlation value at each pixel position. The present invention can be applied to a picture processing apparatus that takes difference between a signal detected by a sensor and the real world into consideration.

摘要翻译： 本发明涉及一种图像处理装置，其能够检测混合了诸如背景图像和移动物体的图像的多个对象的区域。 背景图像生成单元121基于图像数据生成背景图像。 二值对象图像提取单元121检测所考虑的帧的图像数据中的每个像素与背景图像中的像素在与所考虑的帧的图像数据中的像素相对应的位置处的相关值。 时间变化检测单元123基于每个像素位置处的相关值的时间变化来检测其中混合了多个真实世界对象的所考虑的帧中的混合区域。 本发明可以应用于考虑传感器检测到的信号与现实世界之间的差异的图像处理装置。

公开(公告)号：US07260260B2

公开(公告)日：2007-08-21

申请号：US10362663

申请日：2002-06-26

申请人： Tetsujiro Kondo ,  Takahiro Nagano ,  Junichi Ishibashi ,  Takashi Sawao ,  Naoki Fujiwara ,  Seiji Wada ,  Toru Miyake

发明人： Tetsujiro Kondo ,  Takahiro Nagano ,  Junichi Ishibashi ,  Takashi Sawao ,  Naoki Fujiwara ,  Seiji Wada ,  Toru Miyake

IPC分类号： G06K9/34 ,  G06K9/36 ,  G06K9/54

CPC分类号： G06T7/20 ,  G06T5/002 ,  G06T5/003 ,  G06T5/50 ,  G06T7/194 ,  G06T2207/20201

摘要： An object of the present invention is to separate in real time a captured image into a foreground component image and a background component image. An image captured by an image-capturing unit 74 is separated into a foreground component image and a background component image, which are stored in an image storage unit 72. A billing processor 75 performs billing processing to charge fees for separating the image. A separating portion 91 performs motion-blur processing of the separated foreground component image and outputs the processed foreground component image and the background component image to a synthesizer 92. The synthesizer 92 combines the input motion-blur-processed foreground component image and the separated background component image to synthesize an image and displays the synthesized image on a display unit 73. The present invention is applicable to a camera terminal device.

摘要翻译： 本发明的目的是将拍摄图像实时地分离成前景分量图像和背景分量图像。 由图像拍摄单元74拍摄的图像被分离为前景分量图像和背景分量图像，其被存储在图像存储单元72中。 计费处理器75执行计费处理以对用于分离图像的费用收费。 分离部分91对分离的前景分量图像进行运动模糊处理，并将经处理的前景分量图像和背景分量图像输出到合成器92。 合成器92组合输入的运动模糊处理的前景分量图像和分离的背景分量图像以合成图像，并将合成图像显示在显示单元73上。 本发明可应用于相机终端装置。

公开(公告)号：US20070126882A1

公开(公告)日：2007-06-07

申请号：US11670776

申请日：2007-02-02

申请人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Takashi Sawao ,  Takahiro Nagano ,  Naoki Fujiwara ,  Toru Miyake ,  Seiji Wada

发明人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Takashi Sawao ,  Takahiro Nagano ,  Naoki Fujiwara ,  Toru Miyake ,  Seiji Wada

IPC分类号： H04N5/228

CPC分类号： G06K9/4609 ,  G06T3/4007 ,  G06T7/12 ,  G06T2207/10016 ,  G06T2207/20192

摘要： An image processing device and method, where the device includes a data continuity detector configured to detect data continuity of a first image data made up of a plurality of pixels acquired by light signals of a real world being cast upon a plurality of detecting elements each having spatio-temporal integration effects, a real world estimating unit configured to detect real world features which a first function representing the real world light signals has, and an image generator configured to predict and generate second image data having a higher quality than the first image data, based on the real world features detected by the real world estimating unit.

摘要翻译： 一种图像处理装置和方法，其中所述装置包括数据连续性检测器，所述数据连续性检测器被配置为检测由多个被施加的现实世界的光信号所获取的多个像素构成的第一图像数据的数据连续性，所述多个检测元件具有 时空整合效果，被配置为检测表示真实世界光信号的第一功能的真实世界特征的真实世界估计单元，以及被配置为预测和生成具有比第一图像数据更高质量的第二图像数据的图像生成器 ，基于真实世界估计单元检测到的真实世界特征。

公开(公告)号：US07218791B2

公开(公告)日：2007-05-15

申请号：US10276229

申请日：2002-03-12

申请人： Tetsujiro Kondo ,  Takahiro Nagano ,  Junichi Ishbashi ,  Takashi Sawao ,  Naoki Fujiwara ,  Seiji Wada ,  Toru Miyake

发明人： Tetsujiro Kondo ,  Takahiro Nagano ,  Junichi Ishbashi ,  Takashi Sawao ,  Naoki Fujiwara ,  Seiji Wada ,  Toru Miyake

IPC分类号： G06K9/40

CPC分类号： G06T13/80 ,  H04N7/01

摘要： The present invention relates to an image processing apparatus for generating an image having a high density in the direction of time and having a natural-looking motion blur. The correlation calculators 103 and 104 respectively calculate a correlation between pixel data of a target pixel in a target frame #n from among frames and pixel data of a corresponding pixel in a first frame #n−1 next to the target frame #n and a correlation between the pixel data of the target pixel in the target frame #n and pixel data of a corresponding pixel in a second frame #n+1 next to the target frame #n. The half-side pixel value generator 105 generates first pixel data in a first synthesis frame generated between the target frame #n and one of the first frame #n−1 and the second frame #n+1 containing the corresponding pixel having the pixel data with a larger correlation. The half-side pixel value generator 106 generates second pixel data in a second synthesis frame generated between the target frame #n and the other of the first frame and the second frame, based on the target pixel data and the first pixel data.

摘要翻译： 本发明涉及一种图像处理装置，用于产生在时间方向上具有高密度并且具有自然的运动模糊的图像。 相关计算器103和104分别计算来自帧之间的目标帧#n中的目标像素的像素数据与目标帧#n旁边的第一帧＃n-1中的对应像素的像素数据之间的相关性，以及 目标帧#n中的目标像素的像素数据与目标帧#n旁边的第二帧＃n + 1中的对应像素的像素数据之间的相关性。 半像素值生成器105在目标帧#n与包含具有像素数据的对应像素的第一帧＃n-1和第二帧＃n + 1中的一个之间生成的第一合成帧中生成第一像素数据 具有较大的相关性。 半像素值生成器106基于目标像素数据和第一像素数据，生成在目标帧#n与第一帧和第二帧中的另一个之间生成的第二合成帧中的第二像素数据。