公开(公告)号：US20100214444A1

公开(公告)日：2010-08-26

申请号：US12709639

申请日：2010-02-22

申请人： Yoshihiro TESHIMA ,  Kouichi Nakagomi

发明人： Yoshihiro TESHIMA ,  Kouichi Nakagomi

IPC分类号： H04N5/228

CPC分类号： H04N5/23212 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/10148 ,  H04N5/23293 ,  H04N5/23296

摘要： In a digital camera 1, a storing means stores feature quantities of a subject area in an image, and a search point setting means sets a plurality of search points in the subject area. Next, an updating means updates coordinates of the set plurality of search points using random numbers. Then, a weight setting means compares feature quantities of the updated search points with the stored feature quantities, and sets a weight for each search point based on similarity. Next, a sorting means sorts the search points depend on those weight, and a variance acquiring means calculates the variance of the sorted search points. Then, an angle-of-view adjusting means determines the amount of adjustment for the angle-of-view based on the calculated variance.

摘要翻译： 在数字照相机1中，存储装置存储图像中的被摄体区域的特征量，并且搜索点设定装置在对象区域中设定多个搜索点。 接下来，更新装置使用随机数来更新所设置的多个搜索点的坐标。 然后，权重设定装置将更新的搜索点的特征量与存储的特征量进行比较，并且基于相似度设置每个搜索点的权重。 接下来，排序装置根据这些权重对搜索点进行排序，并且方差获取装置计算排序的搜索点的方差。 然后，视角调整装置基于所计算的方差确定视角的调整量。

公开(公告)号：US08189056B2

公开(公告)日：2012-05-29

申请号：US12709639

申请日：2010-02-22

申请人： Yoshihiro Teshima ,  Kouichi Nakagomi

发明人： Yoshihiro Teshima ,  Kouichi Nakagomi

IPC分类号： H04N5/228 ,  H04N5/262 ,  H04N5/232 ,  H04N5/225 ,  G06K9/00 ,  G06K9/62 ,  G06K9/64

CPC分类号： H04N5/23212 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/10148 ,  H04N5/23293 ,  H04N5/23296

摘要： In a digital camera 1, a storing means stores feature quantities of a subject area in an image, and a search point setting means sets a plurality of search points in the subject area. Next, an updating means updates coordinates of the set plurality of search points using random numbers. Then, a weight setting means compares feature quantities of the updated search points with the stored feature quantities, and sets a weight for each search point based on similarity. Next, a sorting means sorts the search points depend on those weight, and a variance acquiring means calculates the variance of the sorted search points. Then, an angle-of-view adjusting means determines the amount of adjustment for the angle-of-view based on the calculated variance.

摘要翻译： 在数字照相机1中，存储装置存储图像中的被摄体区域的特征量，并且搜索点设定装置在对象区域中设定多个搜索点。 接下来，更新装置使用随机数来更新所设置的多个搜索点的坐标。 然后，权重设定装置将更新的搜索点的特征量与存储的特征量进行比较，并且基于相似度设置每个搜索点的权重。 接下来，排序装置根据这些权重对搜索点进行排序，并且方差获取装置计算排序的搜索点的方差。 然后，视角调整装置基于所计算的方差确定视角的调整量。

公开(公告)号：US08345986B2

公开(公告)日：2013-01-01

申请号：US12874705

申请日：2010-09-02

申请人： Kouichi Nakagomi

发明人： Kouichi Nakagomi

IPC分类号： G06K9/46 ,  G06K9/66

CPC分类号： G06K9/629 ,  G06K9/46 ,  H04N5/23219 ,  H04N5/23245

摘要： There is provided an image processing apparatus. The image processing apparatus includes: an obtaining unit configured to obtain an image; a generating unit configured to generate a plurality of feature maps for a plurality of features of the image, wherein each of the feature maps corresponds to one of the features of the image; an imaging situation determining unit configured to determine an imaging situation of the image; a weighting unit configured to weight the feature maps in accordance with the imaging situation; and a detector configured to detect a region of interest from the image based on feature distributions of the weighted feature maps.

摘要翻译： 提供了一种图像处理装置。 图像处理装置包括：获取单元，被配置为获得图像; 生成单元，被配置为生成图像的多个特征的多个特征图，其中每个特征图对应于图像的特征之一; 被配置为确定图像的成像状况的成像状况确定单元; 配置为根据成像情况对所述特征图进行加权的加权单元; 以及检测器，被配置为基于所述加权特征图的特征分布来从所述图像检测感兴趣区域。

公开(公告)号：US07542666B2

公开(公告)日：2009-06-02

申请号：US11500750

申请日：2006-08-08

申请人： Kouichi Nakagomi

发明人： Kouichi Nakagomi

IPC分类号： G03B17/00

CPC分类号： G03B17/00 ,  G03B2217/005 ,  H04N5/23248 ,  H04N5/23254 ,  H04N5/23267

摘要： An image-capturing apparatus includes a first image pickup element which picks up an actual image of a subject, a second image pickup element which detects a displacement and has sensitivity that is higher than that of the first image pickup element, an image pickup unit for picking up an image of the subject by driving the first image pickup element and the second image pickup element simultaneously, a displacement detecting unit for computing an amount of displacement between images due to a camera shake using image data obtained from the second image pickup element when the image of the subject is picked up by the image pickup unit, and a position correcting unit for correcting a position of image data obtained from the first image pickup element, based on the amount of displacement computed by the displacement detecting unit.

摘要翻译： 一种图像拍摄装置包括拾取被摄体的实际图像的第一图像拾取元件，检测位移并具有高于第一图像拾取元件的灵敏度的第二图像拾取元件，用于 通过同时驱动第一图像拾取元件和第二图像拾取元件来拾取对象的图像;位移检测单元，用于使用从第二图像拾取元件获得的图像数据计算由于相机抖动引起的图像之间的位移量， 由图像拾取单元拾取被摄体的图像，以及位置校正单元，用于基于由位移检测单元计算的位移量来校正从第一图像拾取元件获得的图像数据的位置。

公开(公告)号：US08411911B2

公开(公告)日：2013-04-02

申请号：US12624743

申请日：2009-11-24

申请人： Kouichi Nakagomi

发明人： Kouichi Nakagomi

IPC分类号： G06K9/00 ,  G06K9/40 ,  G06K9/36

CPC分类号： G06T5/006 ,  G06K9/00248 ,  G06T3/0093 ,  G06T2207/30201

摘要： An image processing apparatus comprises an image capture unit configured to capture an image, a characteristic part detector configured to detect a characteristic part of a face from the image captured by the image capture unit, an outline generator configured to generate a pseudo outline of the face based on positions of the characteristic part detected by the characteristic part detector and a correction unit configured to correct the image based on the pseudo outline generated by the outline generator.

摘要翻译： 图像处理装置包括被配置为拍摄图像的图像捕获单元，被配置为从由图像捕获单元捕获的图像检测面部的特征部分的特征部分检测器，被配置为生成面部的伪轮廓的轮廓生成器 基于由特征部分检测器检测到的特征部分的位置和基于由轮廓生成器生成的伪轮廓来校正图像的校正单元。

公开(公告)号：US08248480B2

公开(公告)日：2012-08-21

申请号：US12392322

申请日：2009-02-25

申请人： Kazuhisa Matsunaga ,  Kouichi Nakagomi ,  Tetsuji Makino

发明人： Kazuhisa Matsunaga ,  Kouichi Nakagomi ,  Tetsuji Makino

IPC分类号： H04N5/225 ,  H04N5/228

CPC分类号： H04N5/272 ,  H04N5/23232 ,  H04N5/2621 ,  H04N5/345

摘要： An imaging apparatus includes: an imaging section configured to acquire a plurality of images that are consecutively taken in time series by an imaging device; a reference region setting section configured to employ one of the images acquired by the imaging section as a reference image and to set a region of the reference image as reference region, the region having high-frequency components; and an image processing section configured to combine the images including the reference image by positioning the images so as to overlap subject portions in each images, the subject portions being defined in the reference region set by the reference region setting section.

摘要翻译： 一种成像装置，包括：成像部，被配置为获取由成像装置按时间序列连续拍摄的多个图像; 参考区域设置部分，被配置为使用由成像部分获取​​的图像之一作为参考图像，并且将参考图像的区域设置为参考区域，所述区域具有高频分量; 以及图像处理部，被配置为通过定位图像来组合包括参考图像的图像，以便重叠每个图像中的对象部分，所述对象部分被限定在由参考区域设置部分设置的参考区域中。

公开(公告)号：US08121193B2

公开(公告)日：2012-02-21

申请号：US11504021

申请日：2006-08-14

申请人： Kouichi Nakagomi ,  Akira Hamada ,  Shinichi Matsui

发明人： Kouichi Nakagomi ,  Akira Hamada ,  Shinichi Matsui

IPC分类号： H04N11/04

CPC分类号： H04N19/00145 ,  H04N7/5086 ,  H04N19/103 ,  H04N19/109 ,  H04N19/11 ,  H04N19/137 ,  H04N19/176 ,  H04N19/192

摘要： The minimum Sum of Absolute Differences obtained by a motion vector search roughly judges the magnitude of quantization error by whether or not exceeding a predetermined threshold value. When the quantization error is lower, whether or not visually noticeable noise exists in some of the pixels of the current macroblock is judged based on the amount of flatness and noise detected in each of the 4x4 pixel blocks of the current macroblock partitioned into 16 sub-macroblocks. If there is visually noticeable noise, intra-frame coding is selected. When the quantization error is higher, whether or not visually noticeable noise exists in the current macroblock is judged while considering the magnitude of the motion vector. If there is visually noticeable noise, intra-frame coding is selected.

摘要翻译： 通过运动矢量搜索获得的最小绝对差值之和粗略地判断量化误差的大小是否超过预定阈值。 当量化误差较低时，根据分割为16个子像素的当前宏块的4×4个像素块中的每一个中检测到的平坦度和噪声量来判断存在当前宏块的一些像素中是否存在视觉上可见的噪声， 宏块。 如果存在视觉上明显的噪点，则选择帧内编码。 当量化误差较高时，在考虑运动矢量的大小的同时判断在当前宏块中是否存在视觉上可察觉的噪声。 如果存在视觉上明显的噪点，则选择帧内编码。

公开(公告)号：US08040947B2

公开(公告)日：2011-10-18

申请号：US12277677

申请日：2008-11-25

申请人： Kouichi Nakagomi ,  Kazuhisa Matsunaga

发明人： Kouichi Nakagomi ,  Kazuhisa Matsunaga

IPC分类号： H04N7/12 ,  H04N11/02

CPC分类号： H04N19/115 ,  H04N19/149 ,  H04N19/172

摘要： A bitrate control device controls bitrate of video data and includes: a setting module that sets, for each frame in the video data, a target code amount to be used in encoding the frame by an encoding module for maintaining a given bitrate; an adjusting module that adjusts the target code amount set by the setting module based on given information; and a managing module that is configured to perform: saving a code amount corresponding to an amount reduced in the target code amount by the adjusting module in a virtual storage management buffer having a given upper limit, when the adjusting module adjusts to reduce the target code amount; and withdrawing a code amount corresponding to an amount increased in the target code amount by the adjusting module from the virtual storage management buffer, when the adjusting module adjusts to increase the target code amount.

摘要翻译： 比特率控制装置控制视频数据的比特率，包括：设置模块，为视频数据中的每一帧设定用于由编码模块对帧进行编码的目标码量，用于维持给定的比特率; 调整模块，其基于给定的信息调整由所述设定模块设定的所述目标代码量; 以及管理模块，其被配置为：当所述调整模块调整以减少所述目标代码时，通过所述调整模块在具有给定上限的虚拟存储管理缓冲器中执行与所述目标代码量减少量相对应的代码量; 量; 以及当所述调整模块调整以增加所述目标代码量时，通过所述调整模块从所述虚拟存储管理缓冲器中取出与所述目标代码量增加的量相对应的代码量。

公开(公告)号：US08811472B2

公开(公告)日：2014-08-19

申请号：US12950731

申请日：2010-11-19

申请人： Kouichi Nakagomi ,  Kazuhisa Matsunaga

发明人： Kouichi Nakagomi ,  Kazuhisa Matsunaga

IPC分类号： H04N7/26 ,  G06K9/36

CPC分类号： H04N19/115 ,  H04N19/149 ,  H04N19/172

摘要： A bitrate control device controls bitrate of video data and includes: a setting module that sets, for each frame in the video data, a target code amount to be used in encoding the frame by an encoding module for maintaining a given bitrate; an adjusting module that adjusts the target code amount set by the setting module based on given information; and a managing module that is configured to perform: saving a code amount corresponding to an amount reduced in the target code amount by the adjusting module in a virtual storage management buffer having a given upper limit, when the adjusting module adjusts to reduce the target code amount; and withdrawing a code amount corresponding to an amount increased in the target code amount by the adjusting module from the virtual storage management buffer, when the adjusting module adjusts to increase the target code amount.

摘要翻译： 比特率控制装置控制视频数据的比特率，包括：设置模块，为视频数据中的每一帧设定用于由编码模块对帧进行编码的目标码量，用于维持给定的比特率; 调整模块，其基于给定的信息调整由所述设定模块设定的所述目标代码量; 以及管理模块，其被配置为：当所述调整模块调整以减少所述目标代码时，通过所述调整模块在具有给定上限的虚拟存储管理缓冲器中执行与所述目标代码量减少量相对应的代码量; 量; 以及当所述调整模块调整以增加所述目标代码量时，通过所述调整模块从所述虚拟存储管理缓冲器中取出与所述目标代码量增加的量相对应的代码量。

公开(公告)号：US08699569B2

公开(公告)日：2014-04-15

申请号：US11820155

申请日：2007-06-18

申请人： Jun Muraki ,  Yuji Kuriyama ,  Kouichi Nakagomi ,  Kimiyasu Mizuno ,  Kenichi Iwata ,  Seiji Mochizuki ,  Ren Imaoka

发明人： Jun Muraki ,  Yuji Kuriyama ,  Kouichi Nakagomi ,  Kimiyasu Mizuno ,  Kenichi Iwata ,  Seiji Mochizuki ,  Ren Imaoka

IPC分类号： H04N7/12 ,  H04N7/50 ,  H04N7/26

CPC分类号： H04N7/50 ,  H04N19/107 ,  H04N19/132 ,  H04N19/159 ,  H04N19/172 ,  H04N19/176 ,  H04N19/31 ,  H04N19/436 ,  H04N19/44 ,  H04N19/46 ,  H04N19/587 ,  H04N19/61 ,  H04N19/70

摘要： A CODEC compresses and encodes a motion picture captured at a high speed of 240 fps frame rate in MPEG format. The CODEC divides pictures in each frame into I pictures and the main frame P pictures and the other sub frame P pictures. In encoding P pictures of the main frame, the CODEC uses I pictures that are adjacent on the time axis or P pictures of other main frames as a reference picture. With a playback device, etc., of its motion picture playback performance of 60 fps, to perform an actual speed playback with the playback time being equal to the picture-capturing time, only the main frame alone is to be subjected to playback, in that case the decoding process of P pictures of the sub frames is not required.

摘要翻译： CODEC压缩并编码以MPEG格式以240fps帧速率高速捕获的动态图像。 CODEC将每帧中的图像分为I图像和主帧P图像和其他子帧P图像。 在编码主帧的P图像时，CODEC使用时间轴上相邻的I图像或其他主帧的P图像作为参考图像。 对于60 fps的动态影像播放性能的播放装置等，为了在播放时间等于拍摄时间的情况下进行实际的速度重放，仅仅主框架将被重放， 在这种情况下，不需要子帧的P画面的解码处理。