利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

178 条记录 (耗时 0.055 秒)

    Image processing device and method, and imaging device
    73.
    发明授权
    Image processing device and method, and imaging device 失效
    图像处理装置及方法及成像装置

    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。

    Image processing apparatus and method, and image pickup apparatus
    77.
    发明授权
    Image processing apparatus and method, and image pickup apparatus 失效
    图像处理装置和方法以及图像拾取装置

    公开(公告)号：US08134613B2

    公开(公告)日：2012-03-13

    申请号：US10297632

    申请日：2002-04-01

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

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

    IPC分类号： H04N5/262 ,  H04N5/228 ,  G06K9/40 ,  G06K9/00

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

    摘要： The present invention particularly relates to an image processing apparatus in which motion blur contained in a blurred image can be eliminated. An area specifying unit 103 specifies a non-mixed area formed of a foreground area consisting of foreground object components which form a foreground object and a background area consisting of background object components which form a background object, or a mixed area in which the foreground object components and the background object components are mixed. A separating/blur-eliminating unit 1503 simultaneously performs processing for separating the foreground object components and the background object components from the pixel data of the mixed area and processing for eliminating motion blur from the separated foreground object components based on a result obtained by specifying the area. The present invention is applicable to an image processing apparatus in which a difference between a signal detected by an image-capturing device and the real world is considered.

    摘要翻译： 本发明特别涉及可以消除包含在模糊图像中的运动模糊的图像处理装置。 区域指定单元103指定由前景区域组成的前景区域形成的非混合区域，前景区域由形成前景对象的前景对象分量和由形成背景对象的背景对象分量组成的背景区域，或者前景对象 组件和背景对象组件混合。 分离/模糊消除单元1503同时执行用于从混合区域的像素数据中分离前景对象分量和背景对象分量的处理以及用于从分离的前景对象分量消除运动模糊的处理，该处理基于通过指定 区。 本发明可应用于其中考虑了由图像捕获装置检测到的信号与现实世界之间的差异的图像处理装置。

    Image processing device, learning device, and coefficient generating device and method
    78.
    发明授权
    Image processing device, learning device, and coefficient generating device and method 失效
    图像处理装置，学习装置和系数产生装置及方法

    公开(公告)号：US07903890B2

    公开(公告)日：2011-03-08

    申请号：US11722450

    申请日：2005-12-21

    申请人： Takahiro Nagano ,  Tetsujiro Kondo ,  Tsutomu Watanabe ,  Junichi Ishibashi ,  Hisakazu Shiraki ,  Naoki Fujiwara ,  Masanori Kanemaru ,  Shinichiro Kaneko ,  Yasuhiro Suto

    发明人： Takahiro Nagano ,  Tetsujiro Kondo ,  Tsutomu Watanabe ,  Junichi Ishibashi ,  Hisakazu Shiraki ,  Naoki Fujiwara ,  Masanori Kanemaru ,  Shinichiro Kaneko ,  Yasuhiro Suto

    IPC分类号： G06K9/46 ,  G06K9/62 ,  G06K9/40 ,  H04N11/04

    CPC分类号： H04N5/23248 ,  G06T5/003 ,  G06T5/50 ,  G06T7/20 ,  G06T2207/20081 ,  G06T2207/20201 ,  H04N5/144 ,  H04N5/23254 ,  H04N5/23267

    摘要： A target-pixel-setting section (31) sets a target pixel in a target image to be predicted. A motion-direction-detecting section (32) detects a motion direction corresponding to the target pixel. A pixel-value-extracting section (36) extracts from peripheral images corresponding to the target image, in order to extract a main term that mainly contains component of the target pixel in a moving object that encounters a motion blur in the peripheral images, at least pixel values of pixels in the peripheral images whose space position roughly agree with space position of the target pixel. A processing-coefficient-setting section (37a) sets a specific motion-blur-removing-processing coefficient. A pixel-value-generating section (38a) newly generates pixel values for processing from the pixel values extracted by the pixel-value-extracting section (36) corresponding to the motion direction and generates pixel values corresponding to the target pixel based on the pixel values for processing and the specific motion-blur-removing-processing coefficients. It is possible to perform a robust motion-blur-removing processing on any shifts of motion vector.

    摘要翻译： 目标像素设置部分（31）设置要预测的目标图像中的目标像素。 运动方向检测部（32）检测与目标像素对应的运动方向。 像素值提取部分（36）从与目标图像相对应的外围图像中提取，以便提取主要包含在外围图像中遇到运动模糊的移动物体中的目标像素的分量的主项， 其空间位置与目标像素的空间位置大致一致的周边图像中的像素的最小像素值。 处理系数设定部（37a）设定特定的运动模糊去除处理系数。 像素值生成部（38a）根据与运动方向对应的像素值提取部（36）提取的像素值新生成用于处理的像素值，并且基于像素生成与像素值对应的像素值 处理值和具体的运动模糊去除处理系数。 可以对运动矢量的任何移动执行鲁棒的运动模糊去除处理。

    Image processing device that removes motion blur from an image and method of removing motion blur from an image
    79.
    发明授权
    Image processing device that removes motion blur from an image and method of removing motion blur from an image 有权
    从图像中去除运动模糊的图像处理装置和从图像中去除运动模糊的方法

    公开(公告)号：US07750943B2

    公开(公告)日：2010-07-06

    申请号：US11793701

    申请日：2005-12-21

    申请人： Takahiro Nagano ,  Tetsujiro Kondo ,  Tsutomu Watanabe ,  Junichi Ishibashi ,  Hisakazu Shiraki ,  Naoki Fujiwara ,  Masanori Kanemaru ,  Shinichiro Kaneko ,  Yasuhiro Suto

    发明人： Takahiro Nagano ,  Tetsujiro Kondo ,  Tsutomu Watanabe ,  Junichi Ishibashi ,  Hisakazu Shiraki ,  Naoki Fujiwara ,  Masanori Kanemaru ,  Shinichiro Kaneko ,  Yasuhiro Suto

    IPC分类号： H04N5/232

    CPC分类号： H04N5/23248 ,  H04N5/23254 ,  H04N5/23258 ,  H04N5/23277

    摘要： A shooting-information-detecting section detects shooting information from an image pick-up section. A motion-detecting section detects a motion direction of an image on an overall screen based on a motion direction of the image pick-up section contained in the shooting information. A processing-region-setting section sets a processing region in at least any one of a predicted target image and a peripheral image thereof, which correspond to a target pixel in the predicted target image. A processing-coefficient-setting section sets a motion-blur-removing-processing coefficient that corresponds to the motion direction detected in the motion-detecting section. A pixel-value-generating section generates a pixel value that corresponds to the target pixel based on a pixel value of a pixel in the processing region set in the processing-region-setting section and the processing coefficient set in the processing-coefficient-setting section. Motion-blur-removing processing can be accurately performed.

    摘要翻译： 拍摄信息检测部分从图像拾取部分检测拍摄信息。 运动检测部分基于包含在拍摄信息中的图像拾取部分的运动方向来检测整个屏幕上的图像的运动方向。 处理区域设定部设置与预测对象图像中的目标像素对应的预测对象图像和周边图像中的至少任一个中的处理区域。 处理系数设定部设定与运动检测部中检测到的运动方向对应的运动模糊去除处理系数。 像素值生成部基于处理区域设定部中设定的处理区域中的像素的像素值和处理系数设定中设定的处理系数，生成与目标像素对应的像素值 部分。 可以精确地进行运动模糊去除处理。

    Learning device, learning method, and learning program
    80.
    发明授权
    Learning device, learning method, and learning program 失效
    学习设备，学习方法和学习方案

    公开(公告)号：US07940993B2

    公开(公告)日：2011-05-10

    申请号：US11722141

    申请日：2005-12-21

    申请人： Takahiro Nagano ,  Tetsujiro Kondo ,  Tsutomu Watanabe ,  Junichi Ishibashi ,  Hisakazu Shiraki ,  Naoki Fujiwara ,  Masanori Kanemaru ,  Shinichiro Kaneko ,  Yasuhiro Suto

    发明人： Takahiro Nagano ,  Tetsujiro Kondo ,  Tsutomu Watanabe ,  Junichi Ishibashi ,  Hisakazu Shiraki ,  Naoki Fujiwara ,  Masanori Kanemaru ,  Shinichiro Kaneko ,  Yasuhiro Suto

    IPC分类号： G06K9/40 ,  G06K9/00 ,  H04N5/228

    CPC分类号： H04N5/21 ,  H04N5/142 ,  H04N5/144

    摘要： A motion-setting section (61) sets a motion amount and a motion direction for obtaining processing coefficients. A student-image-generating section (62) generates student images obtained by adding a motion blur to a teacher image not only based on the set motion amount and the set motion direction but also by changing at least one of the motion amount and motion direction in a specific ratio and student images obtained by adding no motion blur to the teacher image. A prediction-tap-extracting section (64) extracts, in order to extract a main term that mainly contains component of the target pixel, at least a pixel value of pixel in the student image whose space position roughly agrees with space position of the target pixel in the teacher image. A processing-coefficient-generating section (65) generates processing coefficients for predicting the target pixels in the teacher images from the pixel values of extracted pixels based on a relationship between the pixels thus extracted and the target pixels in the teacher images. The processing coefficients that are suitable for any motion blur removing which is robust against any shift of the motion vector can be generated through learning.

    摘要翻译： 运动设定部（61）设定用于获得处理系数的运动量和运动方向。 学生图像生成部（62）生成不仅基于设定的运动量和设定的运动方向而将运动模糊添加到教师图像而获得的学生图像，而且通过改变运动量和运动方向中的至少一个 以特定比例和学生图像通过添加没有运动模糊获得的教师图像。 预测抽头部（64）为了提取主要包含目标像素的成分的主项，提取学生图像中的空间位置大致与目标的空间位置一致的像素的像素值 像素在老师的形象。 处理系数生成部（65）基于所提取的像素与教师图像中的目标像素之间的关系，从提取的像素的像素值生成用于预测教师图像中的目标像素的处理系数。 可以通过学习来产生适用于对运动矢量的任何移动而鲁棒的任何运动模糊去除的处理系数。