-
公开(公告)号：US08553780B2
公开(公告)日：2013-10-08
申请号：US13851470
申请日：2013-03-27
Applicant: Fujitsu Limited
Inventor： Akira Nakagawa , Taizo Anan , Eishi Morimatsu , Takashi Itoh
IPC: H04N7/12
CPC classification number: H04N19/00587 , H04N19/105 , H04N19/12 , H04N19/13 , H04N19/137 , H04N19/15 , H04N19/176 , H04N19/51 , H04N19/513 , H04N19/52 , H04N19/61
Abstract: A prediction error generating unit generates a predictive vector from the motion vectors of a plurality of adjacent blocks, and obtains a difference from a target vector. A plurality of variable-length coding units respectively encode the output of the prediction error generating unit with different encoding methods. A determining unit estimates the accuracy of the predictive vector generated by the prediction error generating unit based on the degrees of non-uniformity of the motion vectors of the plurality of adjacent blocks. A selecting unit selects one of the encoding results obtained by the plurality of variable-length coding units.
-
公开(公告)号：US20130208803A1
公开(公告)日：2013-08-15
申请号：US13851474
申请日：2013-03-27
Applicant: Fujitsu Limited
Inventor： Akira NAKAGAWA , Taizo Anan , Eishi Morimatsu , Takashi Itoh
IPC: H04N7/26
CPC classification number: H04N19/00587 , H04N19/105 , H04N19/12 , H04N19/13 , H04N19/137 , H04N19/15 , H04N19/176 , H04N19/51 , H04N19/513 , H04N19/52 , H04N19/61
Abstract: A prediction error generating unit generates a predictive vector from the motion vectors of a plurality of adjacent blocks, and obtains a difference from a target vector. A plurality of variable-length coding units respectively encode the output of the prediction error generating unit with different encoding methods. A determining unit estimates the accuracy of the predictive vector generated by the prediction error generating unit based on the degrees of non-uniformity of the motion vectors of the plurality of adjacent blocks. A selecting unit selects one of the encoding results obtained by the plurality of variable-length coding units.
-
13.发明申请VIDEO IMAGE FEATURE GENERATION SYSTEM AND VIDEO IMAGE FEATURE GENERATION METHOD 有权视频图像特征生成系统和视频图像特征生成方法公开(公告)号：US20140270531A1
公开(公告)日：2014-09-18
申请号：US14075268
申请日：2013-11-08
Applicant: FUJITSU LIMITED
Inventor： Shohei NAKAGATA , Taizo Anan
IPC: G06K9/00
CPC classification number: G06K9/00758 , G06F17/30784 , G06K9/00744
Abstract: A video image feature generation system includes a processor; and a memory which stores a plurality of instructions, which when executed by the processor, cause the processor to execute, extracting a frame feature value featuring a frame, which is a unit of an input video image, based on a pixel value of the frame; and generating a phase of each frequency as a video image feature based on at least two frequencies, the frame feature value obtained in the extracting, and generation information for generating phases of the frequencies according to the frequencies and the frame feature value.
Abstract translation: 视频图像特征生成系统包括处理器; 以及存储器，其存储多个指令，当所述处理器执行时，使所述处理器执行，基于所述帧的像素值提取作为输入视频图像的单位的特征帧的帧特征值 ; 以及基于至少两个频率，在提取中获得的帧特征值和根据频率和帧特征值产生频率相位的生成信息，生成每个频率的相位作为视频图像特征。
-
公开(公告)号：US08654856B2
公开(公告)日：2014-02-18
申请号：US13851419
申请日：2013-03-27
Applicant: Fujitsu Limited
Inventor： Akira Nakagawa , Taizo Anan , Eishi Morimatsu , Takashi Itoh
IPC: H04N7/12
CPC classification number: H04N19/00587 , H04N19/105 , H04N19/12 , H04N19/13 , H04N19/137 , H04N19/15 , H04N19/176 , H04N19/51 , H04N19/513 , H04N19/52 , H04N19/61
Abstract: A prediction error generating unit generates a predictive vector from the motion vectors of a plurality of adjacent blocks, and obtains a difference from a target vector. A plurality of variable-length coding units respectively encode the output of the prediction error generating unit with different encoding methods. A determining unit estimates the accuracy of the predictive vector generated by the prediction error generating unit based on the degrees of non-uniformity of the motion vectors of the plurality of adjacent blocks. A selecting unit selects one of the encoding results obtained by the plurality of variable-length coding units.
Abstract translation: 预测误差生成单元从多个相邻块的运动矢量生成预测矢量，并且从目标矢量获得差。 多个可变长度编码单元分别以不同的编码方式编码预测误差生成单元的输出。 确定单元基于多个相邻块的运动矢量的不均匀度来估计由预测误差生成单元生成的预测矢量的精度。 选择单元选择由多个可变长度编码单元获得的编码结果之一。
-
Patent Agency Ranking
公开(公告)号：US08599923B2
公开(公告)日：2013-12-03
申请号：US13851474
申请日：2013-03-27
Applicant: Fujitsu Limited
Inventor： Akira Nakagawa , Taizo Anan , Eishi Morimatsu , Takashi Itoh
IPC: H04N7/12
CPC classification number: H04N19/00587 , H04N19/105 , H04N19/12 , H04N19/13 , H04N19/137 , H04N19/15 , H04N19/176 , H04N19/51 , H04N19/513 , H04N19/52 , H04N19/61
Abstract: A prediction error generating unit generates a predictive vector from the motion vectors of a plurality of adjacent blocks, and obtains a difference from a target vector. A plurality of variable-length coding units respectively encode the output of the prediction error generating unit with different encoding methods. A determining unit estimates the accuracy of the predictive vector generated by the prediction error generating unit based on the degrees of non-uniformity of the motion vectors of the plurality of adjacent blocks. A selecting unit selects one of the encoding results obtained by the plurality of variable-length coding units.
-
公开(公告)号：US11449770B2
公开(公告)日：2022-09-20
申请号：US16575465
申请日：2019-09-19
Applicant: FUJITSU LIMITED
Inventor： Takuro Ikeda , Taizo Anan , Eiji Kitagawa , Vishal Sharma
Abstract: An action selection learning device includes a memory; and a processor coupled to the memory and configured to generate a reference model that is a set of model parameter vectors that indicate an influence level of each factor that influences selection of an action alternative, calculate a selection probability for each action alternative, for each of the model parameter vectors, calculate a model parameter vector for each user using a subset of model parameter vectors extracted from the reference model, based on the selection probability for each action alternative and a selection history of the action alternative by each user, generate the action alternatives based on the model parameter vector for each user, and transmit the generated action alternatives to a terminal device.
-
公开(公告)号：US09037871B2
公开(公告)日：2015-05-19
申请号：US14030629
申请日：2013-09-18
Applicant: FUJITSU LIMITED
Inventor： Jun Takahashi , Shohei Nakagata , Kensuke Kuraki , Taizo Anan
CPC classification number: H04L9/28 , G09C5/00 , H04N1/32224 , H04N1/32229 , H04N1/32309 , H04N1/448
Abstract: An image processing apparatus includes: a dividing unit dividing at least one region on a digitalized image into multiple blocks; a scrambling unit producing an encrypted image by rearranging each block; a pixel value judging unit judging, for each block on the encrypted image, whether a difference between a statistically representative value of a pixel value of a first region included in the block and a statistically representative value of a pixel value of a second region is no smaller than a predetermined value, the second region being included in a block adjacent to the block and being adjacent to the first region; and a pixel value converting unit converting the pixel value of the first region in each block having the difference smaller than the predetermined value, while not converting the pixel value of the first region in each block having the difference no smaller than the predetermined value.
Abstract translation: 一种图像处理装置包括：分割单元，将数字化图像上的至少一个区域划分成多个块; 加扰单元，通过重新排列每个块来产生加密图像; 像素值判定单元，对加密图像上的每个块判断包含在块中的第一区域的像素值的统计学上代表值与第二区域的像素值的统计学上代表值之间的差为否 小于预定值，所述第二区域被包括在与所述块相邻并且与所述第一区域相邻的块中; 以及像素值转换单元，其将不同于预定值的差异的每个块中的第一区域的像素值转换为不具有不同于预定值的差异的块中的第一区域的像素值。
-
公开(公告)号：US08760722B2
公开(公告)日：2014-06-24
申请号：US13719549
申请日：2012-12-19
Applicant: Fujitsu Limited
Inventor： Jun Takahashi , Shohei Nakagata , Kensuke Kuraki , Taizo Anan
CPC classification number: G06K15/1848 , H04N1/3871 , H04N1/4486
Abstract: An area designation unit designates a processing area within an input image. An image processing unit performs predetermined processing on the processing area. A marker area detection unit detects a marker area in the input image, the marker area being capable of accommodating a marker that demarcates the processing area. A marking unit determines a position in the marker area for placing the marker, based on priority conditions.
Abstract translation: 区域指定单元指定输入图像内的处理区域。 图像处理单元对处理区域执行预定处理。 标记区域检测单元检测输入图像中的标记区域，标记区域能够容纳划分处理区域的标记。 基于优先级条件，标记单元确定用于放置标记的标记区域中的位置。
-
公开(公告)号：US20130100502A1
公开(公告)日：2013-04-25
申请号：US13719549
申请日：2012-12-19
Applicant: Fujitsu Limited
Inventor： Jun TAKAHASHI , Shohei Nakagata , Kensuke Kuraki , Taizo Anan
IPC: G06K15/02
CPC classification number: G06K15/1848 , H04N1/3871 , H04N1/4486
Abstract: An area designation unit designates a processing area within an input image. An image processing unit performs predetermined processing on the processing area. A marker area detection unit detects a marker area in the input image, the marker area being capable of accommodating a marker that demarcates the processing area. A marking unit determines a position in the marker area for placing the marker, based on priority conditions.
Abstract translation: 区域指定单元指定输入图像内的处理区域。 图像处理单元对处理区域执行预定处理。 标记区域检测单元检测输入图像中的标记区域，标记区域能够容纳划分处理区域的标记。 基于优先级条件，标记单元确定用于放置标记的标记区域中的位置。
-
-
-
-
-
-
-
-
Search Results
19
records
(took 0.017 seconds)
