专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20180137605A1 IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, COMPUTER PROGRAM PRODUCT 审中-公开
公开(公告)号：US20180137605A1
公开(公告)日：2018-05-17
申请号：US15677344
申请日：2017-08-15
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Junji OTSUKA , Takuma YAMAMOTO , Nao MISHIMA
IPC分类号： G06T5/00 , G06T5/50 , G06T7/11
CPC分类号： G06T5/002 , G06T5/50 , G06T7/11 , G06T2207/10028 , G06T2207/20084 , G06T2207/20182 , G06T2207/20221
摘要： According to one embodiment, an image processing device includes a storage and an image processor. The storage stores therein an input image. The image processor segments the input image into a plurality of regions by using a first convolutional neural network (CNN), generates a first image by converting pixel values of pixels in a first region included in the regions into a first value, and performs image processing on the first image by using a second CNN to generate a second image.

2. 发明申请

US20150264334A1 PARALLAX IMAGE GENERATION DEVICE 审中-公开
标题翻译： PARALLAX图像生成装置
公开(公告)号：US20150264334A1
公开(公告)日：2015-09-17
申请号：US14474303
申请日：2014-09-02
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Soichiro HOSODA , Takuma YAMAMOTO
IPC分类号： H04N13/02 , G06K9/46
CPC分类号： H04N13/225 , H04N19/53 , H04N2013/0085
摘要： A parallax image generation device generates motion vectors of a first image with respect to a second image, the first image including a blank region that does not contain any image information and an effective region that contains image information. The parallax image generation device includes a motion vector search circuit configured to generate motion vectors of blocks of the effective region and blocks of the blank region, at least one of the blocks of the blank region being generated from a motion vector of a block of the effective region, and an output control circuit connected to the motion vector search circuit and configured to output the motion vectors of the blocks of the effective region and the blank region that have been generated by the motion vector search circuit in a raster scan order.
摘要翻译：视差图像生成装置生成相对于第二图像的第一图像的运动矢量，第一图像包括不包含任何图像信息的空白区域和包含图像信息的有效区域。视差图像生成装置具有：运动矢量搜索电路，被配置为生成有效区域的块的运动矢量和空白区域的块，空白区域的块中的至少一个是从块的块的运动矢量生成的连接到运动矢量搜索电路并且被配置为以光栅扫描顺序输出由运动矢量搜索电路产生的有效区域和空白区域的块的运动矢量。

3. 发明申请

US20160165126A1 IMAGE PROCESSING DEVICE, IMAGING DEVICE, IMAGE PROCESSING METHOD, AND COMPUTER PROGRAM PRODUCT 审中-公开
标题翻译：图像处理装置，成像装置，图像处理方法和计算机程序产品
公开(公告)号：US20160165126A1
公开(公告)日：2016-06-09
申请号：US14950445
申请日：2015-11-24
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Nao MISHIMA , Takuma YAMAMOTO , Nobuyuki MATSUMOTO
IPC分类号： H04N5/232 , G06T5/20 , G06T7/00 , G06T5/00
CPC分类号： H04N5/23212 , G06T7/571 , G06T2207/10016
摘要： According to an embodiment, an image processing device includes a processing circuit configured to implement a first acquirer, a second acquirer, a first calculator, and a second calculator. The first acquirer acquires an all-in-focus image. The second acquirer acquires a first captured image taken at a first focus distance. The first calculator calculates, with respect to a pixel included in the first captured image, a first blur circle radius using the all-in-focus image and the first captured image. The second calculator calculates a first depth representing a distance to an object included in at least one of the first captured image and the all-in-focus image using the first blur circle radius.
摘要翻译：根据实施例，图像处理装置包括：处理电路，被配置为实现第一获取器，第二获取器，第一计算器和第二计算器。第一个收购方获得全焦点图像。第二获取器获取在第一焦点距离拍摄的第一拍摄图像。第一计算器使用全焦点图像和第一拍摄图像来计算关于包括在第一拍摄图像中的像素的第一模糊圆半径。第二计算器使用第一模糊圆半径计算表示到包括在第一拍摄图像和全焦点图像中的至少一个中的对象的距离的第一深度。

4. 发明申请

US20150310626A1 MOTION VECTOR DETECTOR, DISTANCE DETECTOR, MOTION VECTOR DETECTION METHOD AND COMPUTER PROGRAM PRODUCT 有权
标题翻译：运动矢量检测器，距离检测器，运动矢量检测方法和计算机程序产品
公开(公告)号：US20150310626A1
公开(公告)日：2015-10-29
申请号：US14689568
申请日：2015-04-17
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Takuma YAMAMOTO , Nao MISHIMA
IPC分类号： G06T7/20 , G06K9/52 , G06K9/62
CPC分类号： G06T7/269 , G06T7/223 , G06T2207/10012 , G06T2207/10016 , G06T2207/20016 , G06T2207/20021 , H04N5/145
摘要： According to an embodiment, a motion vector detector includes a searcher, a converter, a synthesizer, and a corrector. The searcher is configured to search for, in each block in a first image having a resolution of interest, an area having a high degree of correlation with a second image having the resolution of interest, and generate a first flow representing a set of motion vectors having the resolution of interest. The converter is configured to generate a second flow representing a set of motion vectors having the resolution of interest from a set of motion vectors having a higher resolution. The synthesizer is configured to generate a third flow representing a set of motion vectors having the resolution of interest. The corrector is configured to generate a set of motion vectors having the resolution of interest by optimizing gradient objective function having initial value set to the third flow.
摘要翻译：根据实施例，运动矢量检测器包括搜索器，转换器，合成器和校正器。搜索器被配置为在具有感兴趣分辨率的第一图像中的每个块中搜索与具有感兴趣分辨率的第二图像具有高度相关性的区域，并且生成表示一组运动矢量的第一流程有兴趣的决议。转换器被配置为从具有较高分辨率的一组运动矢量生成表示具有感兴趣分辨率的一组运动矢量的第二流。合成器被配置为生成表示具有感兴趣分辨率的一组运动矢量的第三流。校正器被配置为通过优化具有设置为第三流的初始值的梯度目标函数来生成具有感兴趣分辨率的运动矢量的集合。

5. 发明申请

US20150110416A1 IMAGE PROCESSING DEVICE AND IMAGE PROCESSING METHOD 有权
标题翻译：图像处理装置和图像处理方法
公开(公告)号：US20150110416A1
公开(公告)日：2015-04-23
申请号：US14459990
申请日：2014-08-14
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Takuma YAMAMOTO , Nao MISHIMA
IPC分类号： G06T5/00
CPC分类号： G06T5/003 , G06T5/50 , G06T2207/10028
摘要： An image processing device includes a processor and a memory storing instructions causing the processor to: generate a first intermediate image by applying, to an input image, inverse conversion being inverse of conversion corresponding to degrading process of imaging the input image; generating a second intermediate image by adding a frequency component to the input image; generate a weighting factor so that a second residual error between a second image and the input image becomes smaller than a first residual error between a first image and the input image, the first image being obtained by applying the conversion to the second intermediate image, and the second image being obtained by applying the conversion to a composite image obtained by the weighted addition of the first and second intermediate images; and generate the composite image by performing the weighted addition of the first and second intermediate images using the weighting factor.
摘要翻译：一种图像处理装置，包括：处理器和存储器，存储指令，使得处理器：通过向输入图像应用与对输入图像成像的劣化处理对应的转换相反的逆变换来产生第一中间图像; 通过向所述输入图像添加频率分量来生成第二中间图像; 生成加权因子，使得第二图像和输入图像之间的第二残差误差小于第一图像和输入图像之间的第一残差，第一图像是通过将转换应用于第二中间图像获得的，以及通过将转换应用于通过加权相加第一和第二中间图像获得的合成图像而获得的第二图像; 并且通过使用加权因子执行第一和第二中间图像的加权相加来生成合成图像。

6. 发明申请

US20140016827A1 IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, AND COMPUTER PROGRAM PRODUCT 审中-公开
标题翻译：图像处理装置，图像处理方法和计算机程序产品
公开(公告)号：US20140016827A1
公开(公告)日：2014-01-16
申请号：US13937495
申请日：2013-07-09
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Takuma YAMAMOTO , Yasunori TAGUCHI , Toshiyuki ONO , Nobuyuki MATSUMOTO
IPC分类号： G06T5/00
CPC分类号： G06T5/003 , G06T3/4053 , G06T2200/21 , G06T2207/10052
摘要： According to an embodiment, an image processing device includes a generator, a determinator, and a processor. The generator is configured to generate a refocused image focused at a predetermined distance from a plurality of unit images for which points on an object are imaged at different positions according to distances between an imaging unit and the positions of the points on the object by the imaging unit. The determinator is configured to determine sampling information including pairs of positions of pixels of the plurality of unit images in the refocused image and pixel values of the pixels. The processor is configured to perform resolution enhancement on a predetermined region including a first position indicated by the sampling information of the refocused image according to an intensity corresponding to a focusing degree of a pixel corresponding to the first position.
摘要翻译：根据实施例，图像处理装置包括发生器，确定器和处理器。发生器被配置为产生聚焦在预定距离处的预聚焦图像，所述多重单位图像根据成像单元与物体上的点的位置之间的距离在不同位置成像在物体上的点单元。确定器被配置为确定包括重新聚焦图像中的多个单位图像的像素的位置对和像素的像素值的采样信息。处理器被配置为根据与对应于第一位置的像素的聚焦度对应的强度，在包括由重聚焦图像的采样信息指示的第一位置的预定区域上执行分辨率增强。

7. 发明申请

US20190007670A1 ESTIMATION SYSTEM AND AUTOMOBILE 审中-公开
公开(公告)号：US20190007670A1
公开(公告)日：2019-01-03
申请号：US15908771
申请日：2018-02-28
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Tatsuma Sakurai , Takuma YAMAMOTO , Nao MISHIMA
IPC分类号： H04N13/00 , G06T7/73 , G05D1/02
摘要： According to one embodiment, an estimation system includes a monocular imaging unit and processing circuitry. The monocular imaging unit acquires, at a time of capturing, an image and first data relating to an actual distance to an object captured in the image. The processing circuitry estimates a position of the imaging unit by using the image and the first data.

8. 发明申请

US20160295232A1 IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND IMAGE PROCESSING PROGRAM 审中-公开
标题翻译：图像处理设备，图像处理方法和图像处理程序
公开(公告)号：US20160295232A1
公开(公告)日：2016-10-06
申请号：US14943374
申请日：2015-11-17
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Takuma YAMAMOTO , Nao MISHIMA
IPC分类号： H04N19/55 , H04N19/513
CPC分类号： H04N19/521 , H04N19/553 , H04N19/587
摘要： One embodiment discloses an image processing apparatus which generates an interpolation frame from consecutive first and second frames, including: a motion estimation section which assigns, to the interpolation frame, motion vectors from the first frame to the second frame; a first degree-of-difference calculation section which extracts calculates a first degree of difference in terms of pixel values; a second degree-of-difference calculation section which calculates a second degree of difference in terms of vectors; and an interpolation frame generation section which generates the interpolation frame by determining a motion vector that should be assigned to a pixel of attention on the basis of combined weights obtained by combining the first degrees of difference and the second degrees of difference, respectively.
摘要翻译：一个实施例公开了一种图像处理装置，其从连续的第一和第二帧生成内插帧，包括：运动估计部，其向内插帧分配从第一帧到第二帧的运动矢量; 提取的第一差异度计算部计算像素值的第一差分度; 第二差分计算部，计算向量的第二差分度; 以及内插帧生成部，其通过基于通过组合所述第一差异和所述第二差异度而获得的组合权重来确定应分配给注意的像素的运动矢量来生成所述插值帧。

9. 发明申请

US20150055874A1 IMAGE ANALYZING APPARATUS AND METHOD 审中-公开
标题翻译：图像分析装置和方法
公开(公告)号：US20150055874A1
公开(公告)日：2015-02-26
申请号：US14244012
申请日：2014-04-03
申请人： KABUSHIKI KAISHA TOSHIBA
发明人： Takuma YAMAMOTO , Yasunori Taguchi , Toshimitsu Kaneko
IPC分类号： G06T5/00
CPC分类号： G06T5/003 , G06T2207/20012 , G06T2207/20201
摘要： An image analyzing apparatus includes computer. The computer is programmed to obtain a motion vector from a first image toward a second image and calculate an evaluation value depending on a magnitude of frequency components. The frequency components have a higher frequency than a first frequency determined based on the motion vector. The computer is also programmed to detect a particular area from the first image based on the evaluation value.
摘要翻译：图像分析装置包括计算机。计算机被编程为从第一图像到第二图像获得运动矢量，并且根据频率分量的大小来计算评估值。频率分量具有比基于运动矢量确定的第一频率更高的频率。计算机还被编程为基于评估值从第一图像检测特定区域。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式