公开(公告)号：US07634111B2

公开(公告)日：2009-12-15

申请号：US10490855

申请日：2003-07-30

申请人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Kazushi Yoshikawa ,  Seiji Wada

发明人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Kazushi Yoshikawa ,  Seiji Wada

IPC分类号： G06K9/00 ,  G06K9/36

CPC分类号： H04N19/521 ,  H04N19/433 ,  H04N19/543 ,  H04N19/567

摘要： An image processing apparatus and an image processing method capable of performing matching processing with a small amount of calculation and highly accurately detecting a motion vector, etc., provided with a first feature extraction portion 13 for extracting a feature and spatial coordinates of a focused pixel from information of a current frame; a second feature extraction portion 14 for extracting from information of a reference frame a feature, a focused pixel, spatial coordinates of the focused pixel, spatial coordinates of vicinity region of the focused pixel, and distance information of the focused pixel with respect to the spatial coordinates; a database creation portion 15 for creating a database indicating relative relationship of the feature, the focused pixel, the spatial coordinates in the vicinity of the focused pixel and the distance information of the focused pixel with respect to the spatial coordinates; and a motion vector detection portion 16 for obtaining spatial coordinates of a shifted position by calculating by searching distance information linked to the feature from the database based on the feature extracted by the first feature extraction portion 13.

摘要翻译： 一种图像处理装置和图像处理方法，其能够以少量的计算进行匹配处理，并且高精度地检测运动矢量等，该运动矢量等设置有用于提取焦点像素的特征和空间坐标的第一特征提取部分13 从当前帧的信息; 第二特征提取部分14，用于从参考帧的信息中提取特征，聚焦像素，聚焦像素的空间坐标，聚焦像素的附近区域的空间坐标以及聚焦像素相对于空间的距离信息 坐标 数据库创建部分15，用于创建指示相对于空间坐标的特征，聚焦像素，聚焦像素附近的空间坐标和聚焦像素的距离信息的相对关系的数据库; 以及运动矢量检测部分16，用于基于由第一特征提取部分13提取的特征，通过从数据库搜索与特征相关联的距离信息来计算来获得移位位置的空间坐标。

公开(公告)号：US07602442B2

公开(公告)日：2009-10-13

申请号：US11044812

申请日：2005-01-26

申请人： Tetsujiro Kondo ,  Seiji Wada ,  Hideo Nakaya ,  Takashi Tago

发明人： Tetsujiro Kondo ,  Seiji Wada ,  Hideo Nakaya ,  Takashi Tago

IPC分类号： H04N7/00

CPC分类号： H04N21/440263 ,  H04N5/21 ,  H04N5/44504 ,  H04N5/45 ,  H04N7/012 ,  H04N7/0125 ,  H04N7/0137 ,  H04N7/0145 ,  H04N7/1675

摘要： A plurality of processing portions sequentially performs a plurality of processing operation on an information signal. In this case, the plurality of processing portions is provided with a control-command-added information signal to which control commands are added for controlling the processing piece to be performed by some or all of the plurality of processing portions, for each predetermined unit of the information signal. The processing portions respectively separate the control command and the information signal from the control-command-added information signal. The information signal thus separated is then processed on the basis of the separated control command for controlling the processing to be performed by this processing portion. The separated control command is added to the post-processing information signal for each predetermined unit thereof, thereby determining a control-command-added information signal to be output.

摘要翻译： 多个处理部分对信息信号顺序执行多个处理操作。 在这种情况下，多个处理部分设置有控制命令添加信息信号，对于每个预定单位，多个处理部分中的一些或全部添加有用于控制要执行的处理部件的控制命令 信息信号。 处理部分分别将控制命令和信息信号与控制命令添加信息信号分开。 然后，根据用于控制由该处理部分执行的处理的分离的控制命令来处理如此分离的信息信号。 对于其每个预定单元，分离的控制命令被添加到后处理信息信号，从而确定要输出的控制命令添加信息信号。

公开(公告)号：US07596268B2

公开(公告)日：2009-09-29

申请号：US11627195

申请日：2007-01-25

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

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

IPC分类号： G06K9/34

CPC分类号： G06T3/4023 ,  G06T1/00 ,  G06T7/12 ,  G06T2207/10016 ,  G06T2207/20192

摘要： An image processing device, method, and a program capable of obtaining processing results which are even more accurate and even more precise as to events in the real world, taking into consideration the real world where data has been acquired. The image processing device may include a computer configured to compute a product-sum coefficient and a recorder configured to record the product-sum operation coefficient. In another embodiment, the image processing device may include a data continuity detector, a recorder, and a difference computer.

摘要翻译： 考虑到已经获取数据的现实世界，能够获得对现实世界中的事件更准确甚至更精确的处理结果的图像处理装置，方法和程序。 图像处理装置可以包括被配置为计算乘积和系数的计算机和被配置为记录乘积和运算系数的记录器。 在另一个实施例中，图像处理设备可以包括数据连续性检测器，记录器和差分计算机。

公开(公告)号：US07595800B2

公开(公告)日：2009-09-29

申请号：US11670754

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： G06T15/50

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

摘要： A data processing apparatus and method, where the apparatus includes a region selecting unit configured to select a region corresponding to a pixel of interest, a frequency detector configured to detect a frequency corresponding to pixels belonging to the region, a continuity detector configured to detect data continuity of the image data, and a real world estimating unit configured to estimate the light signals by estimating the continuity of the real world light signals which have been lost.

摘要翻译： 一种数据处理装置和方法，其中所述装置包括：区域选择单元，被配置为选择与感兴趣像素对应的区域;频率检测器，被配置为检测对应于属于所述区域的像素的频率;连续性检测器，被配置为检测数据 图像数据的连续性，以及被配置为通过估计已经丢失的真实世界光信号的连续性来估计光信号的真实世界估计单元。

公开(公告)号：US07536049B2

公开(公告)日：2009-05-19

申请号：US10362580

申请日：2002-06-25

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

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

IPC分类号： G06K9/34 ,  H04N9/74 ,  G09G5/00

CPC分类号： G06T5/002 ,  G06T5/003 ,  G06T5/20 ,  G06T7/194 ,  G06T7/20 ,  G06T2207/10016 ,  G06T2207/20012 ,  G06T2207/20201

摘要： An object of the present invention is to enable the detection of a mixture ratio indicating the mixture state of a plurality of objects, such as a background image and a moving object image. A normal-equation adder 541 extracts mixed pixel data according to a motion, and also extracts background pixel data corresponding to the mixed pixel data so as to generate relational expressions for a designated pixel. A normal-equation calculator 542 detects the mixture ratio indicating the mixture state of the objects based on the relational expressions. The normal-equation adder 541 generates the plurality of relational expressions based on a first approximation in which foreground object components change substantially linearly, and a second approximation in which the mixture ratio changes substantially linearly. The present invention is applicable to a signal processing apparatus for processing images.

摘要翻译： 本发明的目的是能够检测指示诸如背景图像和移动物体图像的多个物体的混合状态的混合比率。 正方程加法器541根据运动提取混合像素数据，并且还提取与混合像素数据相对应的背景像素数据，以产生指定像素的关系表达式。 正态方程计算器542基于关系表达式检测指示对象的混合状态的混合比率。 正方程加法器541基于前景对象分量基本上线性地改变的第一近似以及混合比基本上线性地改变的第二近似来生成多个关系表达式。 本发明可应用于处理图像的信号处理装置。

公开(公告)号：US07483565B2

公开(公告)日：2009-01-27

申请号：US12044557

申请日：2008-03-07

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： G06K9/62 ,  G06K9/36 ,  G06K9/46

CPC分类号： H04N7/0137 ,  H04N7/0125 ,  H04N7/0145

摘要： With the present invention, data continuity is used at the time of converting an input image into high-quality image data with higher quality than the input image data, to obtain processing results which are more accurate and have higher precision. A class tap extracting unit (902) and prediction tap extracting unit (906) extract a class tap and prediction tap based on data continuity of multiple perimeter pixels corresponding to a pixel of interest in the input image, detected by a data continuity detecting unit (901). An image synthesizing unit (909) selectively outputs a prediction value of a first pixel of interest and a prediction value of a second pixel of interest, based on the relation between a prediction value, predicted by a pixel value predicting unit (907), of the first pixel of interest, and a second prediction value of the second pixel of interest temporally or spatially adjacent to the first pixel of interest, and the pixel value of a corresponding pixel in the input image situated at a position encompassing at least the first pixel of interest and the second pixel of interest in the temporal direction or spatial direction, which is detected by an integration property determining unit (908).

摘要翻译： 利用本发明，在将输入图像转换为具有比输入图像数据更高质量的高质量图像数据时，使用数据连续性，以获得更精确和更高精度的处理结果。 类别抽头提取单元（902）和预测抽头提取单元（906）基于由数据连续性检测单元检测到的输入图像中与感兴趣像素相对应的多个周边像素的数据连续性提取类别抽头和预测抽头（ 901）。 图像合成部（909）根据由像素值预测部（907）预测的预测值与关注像素的预测值的关系，选择性地输出感兴趣的第一像素的预测值和感兴趣的第二像素的预测值 感兴趣的第一像素以及与感兴趣的第一像素在时间上或空间上相关的第二像素的第二预测值，以及位于至少包含第一像素的位置的输入图像中的对应像素的像素值 和由时间方向或空间方向感兴趣的第二像素，其由积分特性确定单元（908）检测。

公开(公告)号：US07450764B2

公开(公告)日：2008-11-11

申请号：US10545074

申请日：2004-02-13

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： G06K9/46 ,  G06K9/56 ,  H04N5/21

CPC分类号： H04N7/0137 ,  H04N7/0125 ,  H04N7/0145

摘要： With the present invention, data continuity is used at the time of converting an input image into high-quality image data with higher quality than the input image data, to obtain processing results which are more accurate and have higher precision. A class tap extracting unit (902) and prediction tap extracting unit (906) extract a class tap and prediction tap based on data continuity of multiple perimeter pixels corresponding to a pixel of interest in the input image, detected by a data continuity detecting unit (901). An image synthesizing unit (909) selectively outputs a prediction value of a first pixel of interest and a prediction value of a second pixel of interest, based on the relation between a prediction value, predicted by a pixel value predicting unit (907), of the first pixel of interest, and a second prediction value of the second pixel of interest temporally or spatially adjacent to the first pixel of interest, and the pixel value of a corresponding pixel in the input image situated at a position encompassing at least the first pixel of interest and the second pixel of interest in the temporal direction or spatial direction, which is detected by an integration property determining unit (908).

摘要翻译： 利用本发明，在将输入图像转换为具有比输入图像数据更高质量的高质量图像数据时，使用数据连续性，以获得更精确和更高精度的处理结果。 类别抽头提取单元（902）和预测抽头提取单元（906）基于由数据连续性检测单元检测到的输入图像中与感兴趣像素相对应的多个周边像素的数据连续性提取类别抽头和预测抽头（ 901）。 图像合成部（909）根据由像素值预测部（907）预测的预测值与关注像素的预测值的关系，选择性地输出感兴趣的第一像素的预测值和感兴趣的第二像素的预测值 感兴趣的第一像素以及与感兴趣的第一像素在时间上或空间上相关的第二像素的第二预测值，以及位于至少包含第一像素的位置的输入图像中的对应像素的像素值 和由时间方向或空间方向感兴趣的第二像素，其由积分特性确定单元（908）检测。

公开(公告)号：US20080199072A1

公开(公告)日：2008-08-21

申请号：US12044557

申请日：2008-03-07

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： G06K9/62 ,  G06K9/36

CPC分类号： H04N7/0137 ,  H04N7/0125 ,  H04N7/0145

摘要： With the present invention, data continuity is used at the time of converting an input image into high-quality image data with higher quality than the input image data, to obtain processing results which are more accurate and have higher precision. A class tap extracting unit (902) and prediction tap extracting unit (906) extract a class tap and prediction tap based on data continuity of multiple perimeter pixels corresponding to a pixel of interest in the input image, detected by a data continuity detecting unit (901). An image synthesizing unit (909) selectively outputs a prediction value of a first pixel of interest and a prediction value of a second pixel of interest, based on the relation between a prediction value, predicted by a pixel value predicting unit (907), of the first pixel of interest, and a second prediction value of the second pixel of interest temporally or spatially adjacent to the first pixel of interest, and the pixel value of a corresponding pixel in the input image situated at a position encompassing at least the first pixel of interest and the second pixel of interest in the temporal direction or spatial direction, which is detected by an integration property determining unit (908).

摘要翻译： 利用本发明，在将输入图像转换为具有比输入图像数据更高质量的高质量图像数据时，使用数据连续性，以获得更精确和更高精度的处理结果。 类别抽头提取单元（902）和预测抽头提取单元（906）基于由数据连续性检测单元检测到的输入图像中与感兴趣像素相对应的多个周边像素的数据连续性提取类别抽头和预测抽头（ 901）。 图像合成部（909）根据由像素值预测部（907）预测的预测值与关注像素的预测值的关系，选择性地输出感兴趣的第一像素的预测值和感兴趣的第二像素的预测值 感兴趣的第一像素以及与感兴趣的第一像素在时间上或空间上相关的第二像素的第二预测值，以及位于至少包含第一像素的位置的输入图像中的对应像素的像素值 和由时间方向或空间方向感兴趣的第二像素，其由积分特性确定单元（908）检测。

公开(公告)号：US07340106B2

公开(公告)日：2008-03-04

申请号：US10362579

申请日：2002-06-25

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

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

IPC分类号： G06K9/40

CPC分类号： H04N5/2622 ,  G06T7/254 ,  H04N5/145 ,  H04N19/17 ,  H04N19/23

摘要： The present invention allows the amount of movement indicating the movement of an object within an exposure period to be obtained. An estimated-mixture-ratio processor 401 calculates an estimated mixture ratio for each pixel and an estimated motion vector by a calculation corresponding to a model of a covered background area, and sends the calculated estimated mixture ratio and the calculated estimated motion vector to a mixture-ratio determining portion 403. An estimated-mixture-ratio processor 402 calculates an estimated mixture ratio for each pixel and an estimated motion vector by a calculation corresponding to a model of an uncovered background area, and sends the calculated estimated mixture ratio and the calculated estimated motion vector to the mixture-ratio determining portion 403. The mixture-ratio determining portion 403 sets a mixture ratio and a motion vector according to area information indicating to which of a foreground area, a background area, the covered background area, or the uncovered background area a designated pixel belongs. The present invention can be applied to image processing apparatuses.

摘要翻译： 本发明允许获得指示曝光期间内物体的移动的移动量。 估计混合比处理器401通过与覆盖背景区域的模型相对应的计算来计算每个像素的估计混合比和估计的运动矢量，并将计算的估计混合比和计算出的估计运动矢量发送到混合物 比例判定部403。 估计混合比处理器402通过与未覆盖的背景区域的模型相对应的计算来计算每个像素的估计混合比和估计的运动矢量，并将所计算的估计混合比和所计算的估计运动矢量发送到混合物 比例判定部403。 混合比确定部分403根据指示前景区域，背景区域，覆盖背景区域或指定像素所属的未覆盖背景区域中哪一个的区域信息来设置混合比率和运动矢量。 本发明可以应用于图像处理装置。

公开(公告)号：US20070189634A1

公开(公告)日：2007-08-16

申请号：US11627230

申请日：2007-01-25

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

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

IPC分类号： G06K9/40

CPC分类号： G06T3/4023 ,  G06T1/00 ,  G06T7/12 ,  G06T2207/10016 ,  G06T2207/20192

摘要： An image processing device, method, and program are capable of obtaining processing results which are even more accurate and even more precise as to events in the real world, taking into consideration the real world where data has been acquired. The image processing device includes a data continuity detector and a real world estimating unit.

摘要翻译： 图像处理装置，方法和程序能够获得与现实世界中的事件相比更加准确和更精确的处理结果，同时考虑到已经获取数据的现实世界。 图像处理装置包括数据连续性检测器和真实世界估计单元。