公开(公告)号：US09082183B2

公开(公告)日：2015-07-14

申请号：US13814259

申请日：2012-06-05

申请人： Kuniaki Isogai ,  Masayuki Misaki ,  Junichi Tagawa ,  Takashi Kawamura ,  Takashi Fujii

发明人： Kuniaki Isogai ,  Masayuki Misaki ,  Junichi Tagawa ,  Takashi Kawamura ,  Takashi Fujii

IPC分类号： G06K9/00 ,  G06T7/00 ,  G06T15/20 ,  G06T3/00 ,  H04N13/00

CPC分类号： G06T3/00 ,  G06K9/00 ,  G06T7/50 ,  G06T15/205 ,  H04N13/111 ,  H04N13/128

摘要： A data input unit is configured to receive an input image, depth data and a shooting parameter. A parameter input unit receives a transformation parameter as a parameter on projective transformation of a three-dimensional model, a transformed image generating unit that generate a transformed image by performing projective transformation based on the transformation parameter in the three-dimensional model obtained from the input image, the depth data, and the shooting parameter. A blank area detecting unit detects a blank area in the transformed image, the blank area being a group of blank pixels having no corresponding pixel in the input image, and an output unit is configured to output the transformed image in the case where a blank value indicating size of the blank area is smaller than or equal to a threshold value.

摘要翻译： 数据输入单元被配置为接收输入图像，深度数据和拍摄参数。 参数输入单元接收作为三维模型的投影变换的参数的变换参数，变换图像生成单元，其通过基于从输入获得的三维模型中的变换参数进行投影变换来生成变换后的图像 图像，深度数据和拍摄参数。 空白区域检测单元检测变换图像中的空白区域，空白区域是输入图像中没有对应像素的一组空白像素，并且输出单元被配置为在变形图像的空白值 指示空白区域的大小小于或等于阈值。

公开(公告)号：US08890995B2

公开(公告)日：2014-11-18

申请号：US13809951

申请日：2012-04-12

申请人： Takeshi Shimamoto ,  Takashi Kawamura ,  Yusuke Monobe

发明人： Takeshi Shimamoto ,  Takashi Kawamura ,  Yusuke Monobe

IPC分类号： G03B13/00 ,  H04N5/232 ,  H04N5/228 ,  G03B17/00 ,  G02B27/00 ,  G03B13/32 ,  G03B7/08 ,  G03B15/00 ,  G02B7/28

CPC分类号： G03B13/32 ,  G02B7/28 ,  G02B27/0075 ,  G03B7/08 ,  G03B15/00 ,  H04N5/23212

摘要： An image pickup device includes an image pickup element; a lens optical system including a focus lens; a driving section for driving one of the image pickup element and the focus lens so as to change a distance between the image pickup element and the focus lens; a displacement control section configured to output an instruction to the driving section to control displacement of the image pickup element or the focus lens which is driven, based on a prescribed displacement pattern; and a synchronization section configured to control the displacement control section based on timing for exposing the image pickup element.

摘要翻译： 图像拾取装置包括图像拾取元件; 包括聚焦透镜的透镜光学系统; 用于驱动图像拾取元件和聚焦透镜中的一个以便改变图像拾取元件和聚焦透镜之间的距离的驱动部分; 位移控制部，被配置为基于规定的位移图案，将指示输出到所述驱动部，以控制被驱动的图像拾取元件或聚焦透镜的位移; 以及同步部，被配置为基于用于曝光所述图像拾取元件的定时来控制所述位移控制部。

公开(公告)号：US08682085B2

公开(公告)日：2014-03-25

申请号：US12743284

申请日：2009-09-10

申请人： Kuniaki Isogai ,  Takashi Kawamura

发明人： Kuniaki Isogai ,  Takashi Kawamura

IPC分类号： G06K9/62 ,  G06F7/00 ,  G06K9/00

CPC分类号： G06F17/30247

摘要： A person cluster selection part selects one or more person clusters as representative person clusters in order of largest number of facial images included therein. A unit selection part selects, from each representative person cluster, (i) a unit having the highest likelihood as a first representative unit, and (ii) units in order of lowest likelihood as a second representative unit onward. A representative facial image selection part selects, from each representative unit, (i) a facial image having the highest likelihood as a first representative facial image, and (ii) facial images in order of lowest likelihood as a second representative facial image onward.

摘要翻译： 人群聚类选择部按照其中包含的最大数量的面部图像的顺序选择一个或多个人群作为代表人群。 单位选择部从每个代表人群中选择（i）具有最高可能性的单位作为第一代表单元，以及（ii）以最低可能性的顺序的单位作为第二代表单元。 代表性面部图像选择部分从每个代表单元中选择（i）具有最高可能性的面部图像作为第一代表性面部图像，以及（ii）作为第二代表性面部图像的最低似然次序的面部图像。

公开(公告)号：US08595233B2

公开(公告)日：2013-11-26

申请号：US13000083

申请日：2010-04-23

申请人： Takashi Kawamura ,  Kuniaki Isogai ,  Yazhou Liu

发明人： Takashi Kawamura ,  Kuniaki Isogai ,  Yazhou Liu

IPC分类号： G06F17/30

CPC分类号： G06K9/6218 ,  G06K9/6254

摘要： A data processing apparatus includes: a temporary storage unit storing a cluster-element correspondence table showing correspondence between a cluster ID for identifying each of clusters classified by the data processing apparatus and an element ID of element data belonging to the cluster identified by the cluster ID, and a group-cluster correspondence table showing correspondence between a group ID for identifying a group classified according to a user's subjective criterion and a cluster ID of a cluster belonging to the group identified by the group ID; a feature extraction unit extracting a feature value of newly added element data; and an automatic classification processing unit determining a belonging cluster from the clusters, and updating a classification boundary condition defining a boundary of the belonging cluster. The apparatus also includes a data management unit recording an element ID of the newly added element data and a cluster ID of the belonging cluster.

摘要翻译： 数据处理装置包括：临时存储单元，存储表示用于识别由数据处理装置分类的每个簇的集群ID与属于由集群ID识别的集群的元素数据的元素ID之间的对应关系的集群元素对应表 以及组群对应表，其表示用于识别根据用户的主观标准分类的组的组ID与属于由组ID识别的组的集群的集群ID之间的对应关系; 提取新添加的元素数据的特征量的特征提取单元; 以及自动分类处理单元，从所述群集中确定属性簇，并且更新定义所属簇的边界的分类边界条件。 该装置还包括记录新添加的元素数据的元素ID和所属簇的簇ID的数据管理单元。

公开(公告)号：US20130136342A1

公开(公告)日：2013-05-30

申请号：US13814259

申请日：2012-06-05

申请人： Kuniaki Isogai ,  Masayuki Misaki ,  Junichi Tagawa ,  Takashi Kawamura ,  Takashi Fujii

发明人： Kuniaki Isogai ,  Masayuki Misaki ,  Junichi Tagawa ,  Takashi Kawamura ,  Takashi Fujii

IPC分类号： G06T7/00

CPC分类号： G06T3/00 ,  G06K9/00 ,  G06T7/50 ,  G06T15/205 ,  H04N13/111 ,  H04N13/128

摘要： There are provided an data input unit configured to receive an input image, depth data, and a shooting parameter, a parameter input unit that receives a transformation parameter as a parameter on projective transformation of a three-dimensional model, a transformed image generating unit that generate a transformed image by performing projective transformation based on the transformation parameter in the three-dimensional model obtained from the input image, the depth data, and the shooting parameter, a blank area detecting unit that detects a blank area in the transformed image, the blank area being a group of blank pixels having no corresponding pixel in the input image, and an output unit configured to output the transformed image in the case where a blank value indicating size of the blank area is smaller than or equal to a threshold value.

摘要翻译： 提供了一种被配置为接收输入图像，深度数据和拍摄参数的数据输入单元，接收作为三维模型的投影变换的参数的变换参数的参数输入单元，变换图像生成单元， 通过基于从输入图像，深度数据和拍摄参数获得的三维模型中的变换参数进行投影变换来生成变换图像，检测变换图像中的空白区域的空白区域检测单元， 空白区域是在输入图像中没有对应像素的一组空白像素，以及输出单元，被配置为在空白区域的空白值小于或等于阈值的情况下输出变换图像。

公开(公告)号：US20130127846A1

公开(公告)日：2013-05-23

申请号：US13814514

申请日：2012-06-05

申请人： Kuniaki Isogai ,  Masayuki Misaki ,  Junichi Tagawa ,  Takashi Kawamura ,  Takashi Fujii

发明人： Kuniaki Isogai ,  Masayuki Misaki ,  Junichi Tagawa ,  Takashi Kawamura ,  Takashi Fujii

IPC分类号： G06T15/00

CPC分类号： G06T15/00 ,  H04N13/128 ,  H04N13/305 ,  H04N13/341 ,  H04N2013/0081

摘要： A parallax image generation device includes: a depth value correction unit which performs correction processing on a depth value, from among a plurality of depth values which define a depth image, to shift a position corresponding to the depth value to be closer to a display screen as the depth value is located closer to an end of the depth image, the display screen being for displaying a parallax image; and a parallax image generation unit which generates a first parallax image and a second parallax image having mutual parallax, using a two-dimensional image and the depth image corrected through the correction processing.

摘要翻译： 视差图像生成装置包括：深度值校正单元，对从定义深度图像的多个深度值中的深度值进行修正处理，使与深度值对应的位置移动到更接近显示画面 当深度值靠近深度图像的末端时，显示屏幕用于显示视差图像; 以及视差图像生成单元，其使用二维图像和通过校正处理校正的深度图像来生成具有互视差的第一视差图像和第二视差图像。

公开(公告)号：US08442268B2

公开(公告)日：2013-05-14

申请号：US12671101

申请日：2008-07-30

申请人： Kuniaki Isogai ,  Takashi Kawamura ,  Akihiro Kawabata

发明人： Kuniaki Isogai ,  Takashi Kawamura ,  Akihiro Kawabata

IPC分类号： G06K9/00

CPC分类号： H04N5/772 ,  G06F17/30793 ,  G06K9/00718 ,  G11B27/28 ,  H04N9/8233 ,  H04N21/4223 ,  H04N21/4334 ,  H04N21/84

摘要： An image analysis apparatus comprising: an identification unit operable to, in each of a plurality of scenes, identify one or more persons who appear in the scene; a scene evaluation value calculation unit operable to calculate a scene evaluation value for, among the plurality of scenes, each scene in which at least one person has been identified, the one person being included as one of persons identified by the identification unit; a scene selection unit operable to select, from among the plurality of scenes, one or more scenes that include the one person; and a person evaluation value calculation unit operable to calculate a person evaluation value for the one person by summating scene evaluation values of the scenes selected by the scene selection unit.

摘要翻译： 一种图像分析装置，包括：识别单元，用于在多个场景中的每一个场景中识别出现在场景中的一个或多个人; 场景评估值计算单元，用于计算多个场景中的至少一个人被识别的每个场景的场景评估值，所述一个人被包括为由所述识别单元识别的人员之一; 场景选择单元，其可操作以从所述多个场景中选择包括所述一个人的一个或多个场景; 以及个人评估值计算单元，用于通过对场景选择单元选择的场景的场景评估值进行求和来计算一个人的人评价值。

公开(公告)号：US20130010160A1

公开(公告)日：2013-01-10

申请号：US13636385

申请日：2012-01-30

申请人： Takashi Kawamura

发明人： Takashi Kawamura

IPC分类号： H04N5/76

CPC分类号： G06T5/003 ,  H04N5/23212 ,  H04N5/23229

摘要： An image restoration device according to the present invention includes: a point spread function storage unit which stores any two PSFs among a first range PSF for restoring a first sweep image serving as a sweep image when a sweep range is a first range; a second range PSF for restoring a second sweep image serving as the sweep image when the sweep range is a second range which excludes the first range; a third range PSF for restoring a third sweep image serving as the sweep image when the sweep range is a third range obtained by combining the first range and the second range; and a PSF calculation unit which performs addition or subtraction on the two PSFs to calculate a remaining one among the first, second, and third range PSFs.

摘要翻译： 根据本发明的图像恢复装置包括：点扩散功能存储单元，其在第一范围PSF中存储任何两个PSF，用于当扫描范围是第一范围时恢复用作扫描图像的第一扫描图像; 第二范围PSF，用于当所述扫描范围是排除所述第一范围的第二范围时，恢复用作所述扫描图像的第二扫描图像; 第三范围PSF，用于当所述扫描范围是通过组合所述第一范围和所述第二范围获得的第三范围时，恢复用作所述扫描图像的第三扫描图像; 以及PSF计算单元，其在两个PSF上执行加法或减法以计算第一，第二和第三范围PSF中的剩余的PSF。

公开(公告)号：US20120200673A1

公开(公告)日：2012-08-09

申请号：US13390139

申请日：2011-06-15

申请人： Junichi Tagawa ,  Yoshiaki Sugitani ,  Takashi Kawamura ,  Masayuki Kimura

发明人： Junichi Tagawa ,  Yoshiaki Sugitani ,  Takashi Kawamura ,  Masayuki Kimura

IPC分类号： H04N13/02

CPC分类号： G03B13/36 ,  G01C3/32 ,  G02B7/365 ,  G03B3/10 ,  G06T7/571 ,  H04N5/2226 ,  H04N5/23212

摘要： The present invention provides an imaging apparatus which generates, based on a captured image, a depth map of an object with a high degree of precision.A sensor drive unit (12) that shifts an image sensor (11) in an optical axis direction, along with a sensor drive control unit (13), capture images A and C which are focused on a near end side and a far end side of the object, respectively, and an image B by sweeping the image sensor (11) from the near end side to the far end side, an all-in-focus image generation unit (15) generates an all-in-focus image D from the sweep image B, a blur amount calculation unit (16) calculates an amount of blur in each of the partial regions of the images A and B through deconvolution processing in an image of a region corresponding to the all-in-focus image D, and a depth map generation unit (17) generates a distance between the imaging apparatus and the object in each of the image regions, in other words, a depth map, from an amount of blur in regions corresponding to the near end image A and the far end image C and from an optical coefficient value of the imaging apparatus including a focal length of a lens.

摘要翻译： 本发明提供一种成像装置，其基于拍摄图像以高精度生成对象的深度图。 传感器驱动单元（12），其与传感器驱动控制单元（13）一起沿光轴方向移动图像传感器（11），捕获聚焦在近端侧和远端侧的图像A和C 以及通过将图像传感器（11）从近端侧扫描到远端侧的图像B，全焦点图像生成单元（15）生成全焦点图像D 从扫描图像B，模糊量计算单元（16）通过对应于全焦点图像D的区域的图像中的去卷积处理来计算图像A和B的每个部分区域中的模糊量 ，并且深度图生成单元（17）根据与近端图像A对应的区域的模糊量，在每个图像区域中生成成像装置和对象之间的距离，换句话说，深度图 远端图像C和包括焦距o的成像设备的光学系数值 f镜头

公开(公告)号：US20120148109A1

公开(公告)日：2012-06-14

申请号：US13390849

申请日：2011-06-17

申请人： Takashi Kawamura ,  Pongsak Lasang

发明人： Takashi Kawamura ,  Pongsak Lasang

IPC分类号： G06K9/00

CPC分类号： G02B7/38 ,  G01C3/06 ,  G01C3/32 ,  G06T7/571 ,  H04N5/23212

摘要： A distance estimation device (1x) prevents the variation in distance estimation accuracy that has been a problem in distance estimation performed using an all-in-focus image and an arbitrary-focal-depth image. The distance estimation device can estimate a focal distance of any subject with a high degree of accuracy, and includes: a first generation unit (10w) generating a first distance map indicating a focal depth determined from an all-in-focus image and a first focal-depth image; a second generation unit (11w) generating a second distance map indicating a focal depth determined from the all-in-focus image and a second focal-depth image; and a distance map synthesis unit (14) synthesizing the generated first distance map and the generated second distance map to generate a synthetic distance map.

摘要翻译： 距离估计装置（1x）防止使用全焦点图像和任意焦点深度图像进行的距离估计中的问题的距离估计精度的变化。 距离估计装置可以高精度地估计任何被摄体的焦距，并且包括：第一生成单元（10w），生成表示从全焦点图像确定的焦点深度的第一距离图，以及第一 焦点深度图像; 产生指示从全焦点图像确定的焦点深度的第二距离图和第二焦深图像的第二生成单元（11w）; 以及合成所生成的第一距离图和所生成的第二距离图以产生合成距离图的距离图合成单元（14）。