公开(公告)号：US07120124B2

公开(公告)日：2006-10-10

申请号：US09991384

申请日：2001-11-21

申请人： Takeshi Kawasaki ,  Hitoshi Yamada

发明人： Takeshi Kawasaki ,  Hitoshi Yamada

IPC分类号： G01R31/08

CPC分类号： H04L67/1008 ,  H04L45/00 ,  H04L47/125 ,  H04L67/1002

摘要： A load-distribution method that transmits packets received from a network to two or more transmission destinations to distribute a load, comprising storing a weight value of distribution and an accumulated value according to actual transmission for every transmission destination, and transmitting the received packets, upon occurrence of a distribution event, to a transmission destination that has a smallest accumulated value.

公开(公告)号：US09092875B2

公开(公告)日：2015-07-28

申请号：US13699811

申请日：2012-04-10

申请人： Hitoshi Yamada ,  Pongsak Lasang ,  Sheng Mei Shen

发明人： Hitoshi Yamada ,  Pongsak Lasang ,  Sheng Mei Shen

IPC分类号： G06T7/00 ,  G06T7/20

CPC分类号： G06T7/2006 ,  G06T7/246 ,  G06T7/571 ,  G06T2207/10016 ,  G06T2207/10148 ,  G06T2207/20201

摘要： A motion estimation apparatus according to an aspect of the present invention is a motion estimation apparatus for estimating, using a set of multi-focus images which correspond to a single scene and have different focuses, motion for each of the first regions included in the scene, including: a cost value computing unit configured to compute, using the set of multi-focus images, for each of the first regions, a cost value indicating a difference between a blur amount of the first region and a standard blur amount determined for each of distances in a depth direction; and a motion estimation unit configured to estimate, using the cost value, the motion of the first region corresponding to the cost value.

摘要翻译： 根据本发明的一个方面的运动估计装置是一种运动估计装置，用于使用与单个场景相对应且具有不同焦点的一组多焦点图像来估计包括在场景中的每个第一区域的运动 包括：成本值计算单元，被配置为针对所述第一区域中的每个区域计算使用所述一组多焦点图像，所述成本值指示所述第一区域的模糊量与为每个所述第一区域确定的标准模糊量之间的差异 深度方向的距离; 以及运动估计单元，被配置为使用所述成本值来估计与所述成本值对应的所述第一区域的运动。

公开(公告)号：US09070042B2

公开(公告)日：2015-06-30

申请号：US13583646

申请日：2012-01-11

申请人： Hitoshi Yamada ,  Sheng Mei Shen ,  Bo Li ,  Chin Phek Ong

发明人： Hitoshi Yamada ,  Sheng Mei Shen ,  Bo Li ,  Chin Phek Ong

IPC分类号： G06K9/46 ,  G06K9/00 ,  G06T7/00

CPC分类号： G06K9/4642 ,  G06K9/4671 ,  G06T7/33 ,  G06T2207/10012 ,  G06T2207/20021

摘要： To enhance the accuracy of image alignment performed to reduce a vertical disparity between a first image and a second image that are images of the same object captured from different viewpoints, an image processing apparatus according to an aspect of the present invention includes: a division unit which divides each of the first image and the second image into a plurality of sub-regions; and an extraction unit which performs feature point extraction on each of the sub-regions, wherein the extraction unit performs the feature point extraction in such a manner that a value indicating a degree of variation among the sub-regions in total number of extracted feature points is less than or equal to a predetermined value.

摘要翻译： 为了提高图像对准的准确性，为了减少作为从不同视点拍摄的同一物体的图像的第一图像和第二图像之间的垂直视差，本发明的图像处理装置包括：分割单元 其将所述第一图像和所述第二图像中的每一个划分为多个子区域; 以及提取单元，其对每个子区域执行特征点提取，其中提取单元以指示提取的特征点的总数中的子区域之间的变化程度的值来执行特征点提取 小于或等于预定值。

公开(公告)号：US09068831B2

公开(公告)日：2015-06-30

申请号：US13812038

申请日：2012-05-24

申请人： Yusuke Monobe ,  Hitoshi Yamada

发明人： Yusuke Monobe ,  Hitoshi Yamada

IPC分类号： G06K9/00 ,  G01C11/06 ,  H04N5/232 ,  H04N5/235 ,  G01C3/32 ,  G06T5/00 ,  G06T5/50 ,  G06T7/20 ,  G02B7/38

CPC分类号： G01C11/06 ,  G01C3/32 ,  G02B7/38 ,  G06T5/003 ,  G06T5/50 ,  G06T7/20 ,  G06T2207/20201 ,  H04N5/23254 ,  H04N5/23267 ,  H04N5/2355

摘要： An image processing apparatus measures a subject distance using a plurality of captured images acquired by capturing the same subject in a plurality of imaging states in succession of time. The image processing apparatus includes a target motion amount estimation unit that estimates a target motion amount representing an amount of shift in subject position between first and second images among the captured images. The first image is captured in a first imaging state and a second image is captured in a second imaging state different from the first imaging state. A corrected image generation unit generates a corrected image by performing motion compensation on the second image based on the target motion amount, and an image processing unit performs image processing such as measuring a subject distance or generating an HDR image, using the first image and the corrected image.

摘要翻译： 图像处理装置使用通过在多个成像状态中连续地捕获同一被摄体而获取的多个拍摄图像来测量被摄体距离。 图像处理装置包括目标运动量估计单元，其估计表示拍摄图像中的第一图像和第二图像之间的被摄体位置的偏移量的目标运动量。 以第一成像状态捕获第一图像，并且以与第一成像状态不同的第二成像状态捕获第二图像。 校正图像生成单元通过基于目标运动量对第二图像执行运动补偿来生成校正图像，并且图像处理单元使用第一图像和/或图像处理单元来执行诸如测量被摄体距离或生成HDR图像的图像处理， 校正图像。

公开(公告)号：US09001222B2

公开(公告)日：2015-04-07

申请号：US13521133

申请日：2011-11-08

申请人： Hitoshi Yamada ,  Jun Ohmiya

发明人： Hitoshi Yamada ,  Jun Ohmiya

IPC分类号： H04N5/232 ,  G06T7/20

CPC分类号： H04N5/23254 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/20164 ,  H04N5/23248 ,  H04N5/23267

摘要： An image processing device of the present invention includes: a motion amount estimating unit which estimates, using feature points extracted from each of a first picture and a second picture, a motion amount indicating an amount of displacement of the second picture with respect to the first picture, the second picture being captured temporally after the first picture; a determining unit which determines, using the feature points, whether or not correction is made using the motion amount estimated by the motion amount estimating unit; and a picture correcting unit which corrects the displacement of the second picture with respect to the first picture using the motion amount so as to correct the displacement between the pictures, in the case where the determining unit determines that the correction is made using the motion amount.

摘要翻译： 本发明的图像处理装置包括：运动量估计单元，其使用从第一图像和第二图像中的每一个提取的特征点来估计指示第二图像相对于第一图像的位移量的运动量 图片，第二张照片在第一张照片之后被暂时捕获; 确定单元，其使用所述特征点来确定是否使用由所述运动量估计单元估计的运动量进行校正; 以及图像校正单元，其使用所述运动量来校正所述第二图像相对于所述第一图像的位移，以便校正图像之间的位移，在所述确定单元确定使用所述运动量进行所述校正的情况下 。

公开(公告)号：US08798387B2

公开(公告)日：2014-08-05

申请号：US13521169

申请日：2011-11-08

申请人： Hitoshi Yamada ,  Jun Ohmiya

发明人： Hitoshi Yamada ,  Jun Ohmiya

IPC分类号： G06K9/40 ,  G06K9/20 ,  G06K9/32 ,  H04N5/232 ,  G06T7/20 ,  G06T7/00 ,  H04N5/14 ,  G06T5/00

CPC分类号： H04N5/23254 ,  G06T5/006 ,  G06T7/246 ,  G06T7/33 ,  G06T2207/10016 ,  G06T2207/20164 ,  G06T2207/20201 ,  H04N5/145 ,  H04N5/23248 ,  H04N5/23258

摘要： An image processing device including: a motion amount estimating unit estimating a first motion amount indicating a displacement amount of a second picture with respect to a first picture; an area setting unit setting an area to be used for post-processing for each of the first picture and a first corrected picture, using feature points extracted from the first picture and the second picture; a post-processing unit generating a first cutout picture from the first picture and a second cutout picture from the first corrected picture and estimating a second motion amount indicating a displacement amount of the second cutout picture with respect to the first cutout picture; and a motion amount obtaining unit obtaining a motion amount indicating a displacement amount between the first picture and the second picture, from the estimated first motion amount and the estimated second motion amount.

摘要翻译： 一种图像处理装置，包括：运动量估计单元，估计指示第二图像相对于第一图像的位移量的第一运动量; 区域设置单元，使用从第一图像和第二图像提取的特征点，设置用于第一图像和第一校正图像中的每一个的后处理的区域; 后处理单元，从第一图像生成第一切割图像，从第一修正图像生成第二切割图像，并且估计指示第二切出图像相对于第一切除图像的位移量的第二运动量; 以及运动量获取单元，根据估计的第一运动量和估计的第二运动量，获得指示第一图像和第二图像之间的位移量的运动量。

公开(公告)号：US08681230B2

公开(公告)日：2014-03-25

申请号：US13521083

申请日：2011-11-08

申请人： Jun Ohmiya ,  Hitoshi Yamada

发明人： Jun Ohmiya ,  Hitoshi Yamada

IPC分类号： H04N5/228

CPC分类号： G06T7/33 ,  G06T7/248 ,  G06T2207/10016 ,  G06T2207/20164 ,  G06T2207/30244

摘要： The picture processing device of the present invention includes: a rotational motion distance calculating unit which calculates a rotational motion distance of a second picture with respect to a first picture; a cutout picture generating unit which (i) generates a first cutout picture from the first picture, and (ii) and generates a second cutout picture from a first corrected picture, the first corrected picture being generated from the second picture whose rotational displacement amount, in a combination of directions in three axes, is corrected; a parallel motion amount calculating unit which calculates a parallel motion amount of a second cutout picture with respect to the first cutout picture; and a motion amount determining unit which determines a motion amount of the second picture with respect to the first picture.

摘要翻译： 本发明的图像处理装置包括：旋转运动距离计算单元，其计算第二图像相对于第一图像的旋转运动距离; 切割图像生成单元，其从（i）从第一图像生成第一切割图像，和（ii）从第一修正图像生成第二切割图像，从第二图像生成第一修正图像，其旋转位移量， 在三轴方向的组合中进行校正; 平行运动量计算单元，其计算相对于所述第一剪切图像的第二切割图像的平行运动量; 以及运动量确定单元，其确定第二图像相对于第一图片的运动量。

公开(公告)号：US20140049614A1

公开(公告)日：2014-02-20

申请号：US14110210

申请日：2013-01-21

申请人： Hitoshi Yamada

发明人： Hitoshi Yamada

IPC分类号： G06T7/00 ,  H04N13/02

CPC分类号： G06T7/0075 ,  G06T7/174 ,  G06T7/55 ,  G06T11/60 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/10148 ,  H04N5/2226 ,  H04N5/23293 ,  H04N13/156 ,  H04N13/183 ,  H04N13/239 ,  H04N13/271 ,  H04N13/296

摘要： An image processing apparatus includes: an image obtainment unit that obtains an image; an information obtainment unit that obtains embedment information that is to be embedded into a region within the image obtained by the image obtainment unit; a depth information obtainment unit that obtains depth information indicating a depth value of each pixel in the image obtained by the image obtainment unit; and an embedment region determination unit that determines, using the depth information, an embedment region into which the embedment information is to be embedded.

摘要翻译： 一种图像处理装置，包括：获取图像的图像获得单元; 获取嵌入信息的信息获取单元，所述嵌入信息被嵌入到由所述图像获取单元获得的图像内的区域中; 深度信息获取单元，获取指示由图像获取单元获得的图像中的每个像素的深度值的深度信息; 以及嵌入区域确定单元，其使用所述深度信息来确定要嵌入所述嵌入信息的嵌入区域。

公开(公告)号：US08417059B2

公开(公告)日：2013-04-09

申请号：US12375726

申请日：2008-06-03

申请人： Hitoshi Yamada

发明人： Hitoshi Yamada

IPC分类号： G06K9/20

CPC分类号： H04N5/23248 ,  G06T7/215 ,  G06T7/73 ,  G06T2207/30196 ,  H04N19/103 ,  H04N19/117 ,  H04N19/139 ,  H04N19/14 ,  H04N19/17 ,  H04N19/51

摘要： A motion vector calculation unit calculates inter-frame movement amounts. A masked region specification unit separates the entire edge image of frame feature data into (i) an edge image showing relatively large movement amounts and (ii) an edge image showing relatively small movement amounts. The masked region specification unit then specifies the edge image showing relatively large movement amounts as a region to be masked. This way, a correction parameter is detected from a region other than the masked region. When the correction parameter is a slang angle, a slant correction unit performs slant correction on a frame picture obtained by an image sensor.

摘要翻译： 运动矢量计算单元计算帧间移动量。 掩蔽区域指定单元将帧特征数据的整个边缘图像分离成（i）显示相对大的移动量的边缘图像和（ii）显示相对较小移动量的边缘图像。 掩蔽区域指定单元然后将显示相对大的移动量的边缘图像指定为要被屏蔽的区域。 这样，从掩蔽区域​​以外的区域检测出校正参数。 当校正参数为俚语角时，倾斜校正单元对由图像传感器获得的帧图像执行倾斜校正。

公开(公告)号：US07949755B2

公开(公告)日：2011-05-24

申请号：US11753604

申请日：2007-05-25

申请人： Masafumi Katoh ,  Tsuguo Kato ,  Ryuichi Takechi ,  Yoichiro Igarashi ,  Hitoshi Yamada

发明人： Masafumi Katoh ,  Tsuguo Kato ,  Ryuichi Takechi ,  Yoichiro Igarashi ,  Hitoshi Yamada

IPC分类号： G06F15/16

CPC分类号： H04L67/306 ,  H04L29/12018 ,  H04L29/12047 ,  H04L41/0856 ,  H04L41/0866 ,  H04L41/0893 ,  H04L41/5067 ,  H04L47/15 ,  H04L47/70 ,  H04L47/808 ,  H04L61/10 ,  H04L61/15

摘要： A network/service control method comprises a step of acquiring, when providing a communication service to a user, a user context defined as knowledge information about the user associated with an environment surrounding the user and a past behavior pattern of the user, a step of acquiring a user profile defined as information about a user's favorite registered previously by the user at arbitrary timing, and a service control step of determining network requirements for providing the communication service on the basis of the user context and the user profile.

摘要翻译： 网络/服务控制方法包括以下步骤：当向用户提供通信服务时，将被定义为关于与所述用户周围的环境相关联的用户的知识信息和所述用户的过去行为模式定义的用户上下文的步骤， 获取被定义为用户以任意时间先前登录的用户喜好的信息的用户简档;以及服务控制步骤，用于基于用户上下文和用户简档来确定提供通信服务的网络需求。