公开(公告)号：US20060018539A1

公开(公告)日：2006-01-26

申请号：US11141308

申请日：2005-05-31

申请人： Satoshi Sato ,  Kunio Nobori ,  Kazutoyo Takata

发明人： Satoshi Sato ,  Kunio Nobori ,  Kazutoyo Takata

IPC分类号： G06K9/34

CPC分类号： G06K9/36 ,  G06T5/008 ,  G06T5/20 ,  G06T5/50 ,  G06T2207/20021

摘要： An image region dividing section (105) partitions each of input images into a small regions, and a small region synthesized image generation section (106) generates a base image of each small region, which is an image including only diffuse reflection, from each input image. An image interpolation section (107) generates by interpolation a base image of a small region of which base image cannot be generated. A linearized image generation section (103) generates a linearized image, which is an image in an ideal state under given lighting condition, using the base image of each small region.

摘要翻译： 图像区域分割部（105）将输入图像分割为小区域，小区域合成图像生成部（106）从每个输入生成作为仅包括漫反射的图像的每个小区域的基础图像 图片。 图像插值部（107）通过插值生成不能生成基本图像的小区域的基本图像。 线性化图像生成部（103）使用各小区域的基础图像，生成作为在给定照明条件下的理想状态下的图像的线性化图像。

公开(公告)号：US07764397B2

公开(公告)日：2010-07-27

申请号：US11785699

申请日：2007-04-19

申请人： Kunio Nobori ,  Satoshi Sato ,  Kazutoyo Takata

发明人： Kunio Nobori ,  Satoshi Sato ,  Kazutoyo Takata

IPC分类号： G06F15/00 ,  H04N5/262

CPC分类号： H04N1/3871 ,  G06T11/60 ,  H04N5/2354 ,  H04N5/2625

摘要： An image synthesizing apparatus which generates, from plural images with differing resolutions and lighting conditions, a synthesized image in which the resolution of the original image is improved and the lighting conditions match those of the original image. The image synthesizing apparatus includes: a camera which acquires an original image and plural reference images; a reference image conversion unit; a coefficient calculation unit which calculates a conversion coefficient used in performing linear combination on the plural converted reference images and generating an original image; and an image synthesizing unit.

摘要翻译： 一种图像合成装置，其从具有不同分辨率和照明条件的多个图像生成其中改善了原始图像的分辨率并且照明条件与原始图像的照明条件匹配的合成图像。 该图像合成装置包括：获取原始图像和多个参考图像的相机; 参考图像转换单元; 系数计算单元，计算在多个转换的参考图像上执行线性组合所使用的转换系数并生成原始图像; 和图像合成单元。

公开(公告)号：US07236630B2

公开(公告)日：2007-06-26

申请号：US11591778

申请日：2006-11-02

申请人： Satoshi Sato ,  Kunio Nobori ,  Kazutoyo Takata

发明人： Satoshi Sato ,  Kunio Nobori ,  Kazutoyo Takata

IPC分类号： G06K9/34

CPC分类号： G06K9/36 ,  G06T5/008 ,  G06T5/20 ,  G06T5/50 ,  G06T2207/20021

摘要： An image region dividing section (105) partitions each of input images into a small regions, and a small region synthesized image generation section (106) generates a base image of each small region, which is an image including only diffuse reflection, from each input image. An image interpolation section (107) generates by interpolation a base image of a small region of which base image cannot be generated. A linearized image generation section (103) generates a linearized image, which is an image in an ideal state under given lighting condition, using the base image of each small region.

摘要翻译： 图像区域分割部（105）将输入图像分割为小区域，小区域合成图像生成部（106）从每个输入生成作为仅包括漫反射的图像的每个小区域的基础图像 图片。 图像插值部（107）通过插值生成不能生成基本图像的小区域的基本图像。 线性化图像生成部（103）使用各小区域的基础图像，生成作为在给定照明条件下的理想状态下的图像的线性化图像。

公开(公告)号：US20070092132A1

公开(公告)日：2007-04-26

申请号：US11591778

申请日：2006-11-02

申请人： Satoshi Sato ,  Kunio Nobori ,  Kazutoyo Takata

发明人： Satoshi Sato ,  Kunio Nobori ,  Kazutoyo Takata

IPC分类号： G06K9/00

CPC分类号： G06K9/36 ,  G06T5/008 ,  G06T5/20 ,  G06T5/50 ,  G06T2207/20021

摘要： An image region dividing section (105) partitions each of input images into a small regions, and a small region synthesized image generation section (106) generates a base image of each small region, which is an image including only diffuse reflection, from each input image. An image interpolation section (107) generates by interpolation a base image of a small region of which base image cannot be generated. A linearized image generation section (103) generates a linearized image, which is an image in an ideal state under given lighting condition, using the base image of each small region.

公开(公告)号：US20060023090A1

公开(公告)日：2006-02-02

申请号：US11132654

申请日：2005-05-19

申请人： Kazutoyo Takata ,  Kunio Nobori ,  Satoshi Sato

发明人： Kazutoyo Takata ,  Kunio Nobori ,  Satoshi Sato

IPC分类号： H04N5/262

CPC分类号： H04N5/2624

摘要： An overlap image group each having a first overlap region is selected (S11). The overlap image group is composed of N images including a second overlap region other than the first overlap region and a to-be-expanded image not including the second overlap region. A linearization coefficient of the to-be-expanded image is calculated using the images of the overlap image group in the first overlap region (S12), and the to-be-expanded image is expanded in size up to the second overlap region, using the thus calculated linearization coefficient and the N images in the second overlap region (S14). This processing is repeated to generate a panorama image.

摘要翻译： 选择每个具有第一重叠区域的重叠图像组（S11）。 重叠图像组由包括除了第一重叠区域之外的第二重叠区域和不包括第二重叠区域的待扩展图像的N个图像组成。 使用第一重叠区域中的重叠图像组的图像计算待扩展图像的线性化系数（S12），并且待扩展图像的尺寸扩大到第二重叠区域， 使用如此计算的线性化系数和第二重叠区域中的N个图像（S14）。 重复该处理以产生全景图像。

公开(公告)号：US07535499B2

公开(公告)日：2009-05-19

申请号：US11132654

申请日：2005-05-19

申请人： Kazutoyo Takata ,  Kunio Nobori ,  Satoshi Sato

发明人： Kazutoyo Takata ,  Kunio Nobori ,  Satoshi Sato

IPC分类号： H04N5/262 ,  H04N5/225 ,  G06K9/34

CPC分类号： H04N5/2624

摘要： An overlap image group each having a first overlap region is selected (S11). The overlap image group is composed of N images including a second overlap region other than the first overlap region and a to-be-expanded image not including the second overlap region. A linearization coefficient of the to-be-expanded image is calculated using the images of the overlap image group in the first overlap region (S12), and the to-be-expanded image is expanded in size up to the second overlap region, using the thus calculated linearization coefficient and the N images in the second overlap region (S14). This processing is repeated to generate a panorama image.

摘要翻译： 选择每个具有第一重叠区域的重叠图像组（S11）。 重叠图像组由包括除了第一重叠区域之外的第二重叠区域和不包括第二重叠区域的待扩展图像的N个图像组成。 使用第一重叠区域中的重叠图像组的图像来计算待扩展图像的线性化系数（S12），并且将待扩展图像的尺寸扩大到第二重叠区域，使用 这样计算的线性化系数和第二重叠区域中的N个图像（S14）。 重复该处理以产生全景图像。

公开(公告)号：US20070188613A1

公开(公告)日：2007-08-16

申请号：US11785699

申请日：2007-04-19

申请人： Kunio Nobori ,  Satoshi Sato ,  Kazutoyo Takata

发明人： Kunio Nobori ,  Satoshi Sato ,  Kazutoyo Takata

IPC分类号： H04N5/225

CPC分类号： H04N1/3871 ,  G06T11/60 ,  H04N5/2354 ,  H04N5/2625

摘要： An image synthesizing apparatus which generates, from plural images with differing resolutions and lighting conditions, a synthesized image in which the resolution of the original image is improved and the lighting conditions match those of the original image. The image synthesizing apparatus includes: a camera which acquires an original image and plural reference images, the reference images being obtained by capturing the same object shown in the original image under differing lighting conditions; a reference image conversion unit which converts the resolution of the acquired plural reference images to the same resolution as the original image; a coefficient calculation unit which calculates, based on the original image and plural reference images, which now have the same resolution, a conversion coefficient used in performing linear combination on the plural converted reference images and generating an original image; and an image synthesizing unit which generates plural converted reference images by converting the plural reference images to a target resolution, generates a linear-converted image by performing linear combination on the generated plural converted reference images using the conversion coefficient, and outputs, as a synthesized image, the generated linear-converted image or an image in which the adjusted linear-converted image has been adjusted.

摘要翻译： 一种图像合成装置，其从具有不同分辨率和照明条件的多个图像生成其中改善了原始图像的分辨率并且照明条件与原始图像的照明条件匹配的合成图像。 该图像合成装置包括：获取原始图像和多个参考图像的相机，通过在不同的照明条件下捕获原始图像中所示的相同对象获得参考图像; 参考图像转换单元，其将所获取的多个参考图像的分辨率转换为与原始图像相同的分辨率; 系数计算单元，其基于原始图像和现在具有相同分辨率的多个参考图像，对在多个转换的参考图像上执行线性组合而使用的转换系数和生成原始图像; 以及图像合成单元，其通过将多个参考图像转换为目标分辨率来生成多个转换参考图像，通过使用转换系数对所生成的多个转换参考图像进行线性组合来生成线性转换图像，并将其作为合成 图像，生成的线性转换图像或调整后的经过调整的线性转换图像的图像。

公开(公告)号：US07203362B2

公开(公告)日：2007-04-10

申请号：US11141308

申请日：2005-05-31

申请人： Satoshi Sato ,  Kunio Nobori ,  Kazutoyo Takata

发明人： Satoshi Sato ,  Kunio Nobori ,  Kazutoyo Takata

IPC分类号： G06K9/34

CPC分类号： G06K9/36 ,  G06T5/008 ,  G06T5/20 ,  G06T5/50 ,  G06T2207/20021

摘要： An image region dividing section (105) partitions each of input images into a small regions, and a small region synthesized image generation section (106) generates a base image of each small region, which is an image including only diffuse reflection, from each input image. An image interpolation section (107) generates by interpolation a base image of a small region of which base image cannot be generated. A linearized image generation section (103) generates a linearized image, which is an image in an ideal state under given lighting condition, using the base image of each small region.

公开(公告)号：US20100027879A1

公开(公告)日：2010-02-04

申请号：US12557555

申请日：2009-09-11

申请人： Satoshi Sato ,  Kunio Nobori ,  Katsuhiro Kanamori

发明人： Satoshi Sato ,  Kunio Nobori ,  Katsuhiro Kanamori

IPC分类号： G06K9/00

CPC分类号： H04N5/235 ,  G06T5/007 ,  G06T7/11 ,  G06T7/174 ,  G06T7/42 ,  G06T2207/10152 ,  G06T2207/20056

摘要： The process captures a plurality of images under a light source whose luminance varies over time, such as a fluorescent lamp, under such an imaging condition that a plurality of images that are different from one another in terms of light source conditions can be captured (S11). The process detects a temporal luminance variation from the plurality of captured images (S12), estimates a shadow area by using the temporal luminance variation (S13), and performs an image process such as a process of synthesizing a linearized image or an image segmentation based on optical characteristics (S14).

摘要翻译： 在能够捕获在光源条件方面彼此不同的多个图像的成像条件下，该处理捕获亮度随时间变化的光源（例如荧光灯）下的多个图像（S11 ）。 该过程检测来自多个拍摄图像的时间亮度变化（S12），通过使用时间亮度变化来估计阴影区域（S13），并且执行诸如合成线性化图像或图像分割的处理的图像处理 关于光学特性（S14）。

公开(公告)号：US07176959B2

公开(公告)日：2007-02-13

申请号：US10237514

申请日：2002-09-09

申请人： Satoshi Sato ,  Masamichi Nakagawa ,  Shusaku Okamoto ,  Atsushi Morimura ,  Yoshihiko Matsukawa ,  Kunio Nobori

发明人： Satoshi Sato ,  Masamichi Nakagawa ,  Shusaku Okamoto ,  Atsushi Morimura ,  Yoshihiko Matsukawa ,  Kunio Nobori

IPC分类号： H04N7/18

CPC分类号： G01S11/12 ,  G01S17/936

摘要： In the vehicle surroundings display device of the invention, an image processor generates an image showing the situation around a vehicle. When an obstacle is detected by an obstacle detection means, the image processor determines an image missing region using the position of the border of the obstacle on the vehicle side detected by an obstacle position detection means and fills the image missing region with substitute image data. This eliminates unnaturalness of a display image the user may feel and enables the user to accurately recognize the position of a neighboring obstacle that is important in driving operation.

摘要翻译： 在本发明的车辆周边显示装置中，图像处理器生成表示车辆周围的情况的图像。 当障碍物检测装置检测到障碍物时，图像处理器使用由障碍物位置检测装置检测到的车辆侧的障碍物的边界的位置来确定图像丢失区域，并用替代图像数据填充图像丢失区域。 这消除了用户可能感觉到的显示图像的不自然，并且使用户能够准确地识别在驾驶操作中重要的相邻障碍物的位置。