公开(公告)号：US09467682B2

公开(公告)日：2016-10-11

申请号：US13976200

申请日：2011-12-22

申请人： Daisuke Watanabe ,  Shinji Uchiyama ,  Daisuke Kotake

发明人： Daisuke Watanabe ,  Shinji Uchiyama ,  Daisuke Kotake

IPC分类号： G06T15/00 ,  H04N13/02 ,  G06T7/00

CPC分类号： H04N13/275 ,  G06T7/75 ,  G06T2207/10004 ,  G06T2207/10028

摘要： An information processing apparatus includes a model storing unit configured to store a three-dimensional form model for acquiring the position and posture of a measurement target object, an image acquiring unit configured to acquire an image of the measurement target object, a first position and posture acquiring unit configured to acquire a first position and posture of the three-dimensional form model in a first coordinate system on the basis of a first geometric feature of the three-dimensional form model and a first geometric feature within the image, and a second position and posture acquiring unit configured to acquire a second position and posture of the three-dimensional form model in a second coordinate system that is different from the first coordinate system on the basis of a second geometric feature of the three-dimensional form model and a second geometric feature within the image and the first position and posture.

摘要翻译： 一种信息处理设备，包括：模型存储单元，被配置为存储用于获取测量目标对象的位置和姿势的三维形式模型;图像获取单元，被配置为获取测量目标对象的图像，第一位置和姿势 获取单元，被配置为基于所述三维形式模型的第一几何特征和所述图像内的第一几何特征获取第一坐标系中的所述三维形式模型的第一位置和姿势，以及第二位置 以及姿势获取单元，被配置为基于所述三维形式模型的第二几何特征，在与所述第一坐标系不同的第二坐标系中获取所述三维形式模型的第二位置和姿势;以及第二 图像内的几何特征和第一位置和姿势。

公开(公告)号：US20130271577A1

公开(公告)日：2013-10-17

申请号：US13976200

申请日：2011-12-22

申请人： Daisuke Watanabe ,  Shinji Uchiyama ,  Daisuke Kotake

发明人： Daisuke Watanabe ,  Shinji Uchiyama ,  Daisuke Kotake

IPC分类号： H04N13/02

CPC分类号： H04N13/275 ,  G06T7/75 ,  G06T2207/10004 ,  G06T2207/10028

摘要： An information processing apparatus includes a model storing unit configured to store a three-dimensional form model for acquiring the position and posture of a measurement target object, an image acquiring unit configured to acquire an image of the measurement target object, a first position and posture acquiring unit configured to acquire a first position and posture of the three-dimensional form model in a first coordinate system on the basis of a first geometric feature of the three-dimensional form model and a first geometric feature within the image, and a second position and posture acquiring unit configured to acquire a second position and posture of the three-dimensional form model in a second coordinate system that is different from the first coordinate system on the basis of a second geometric feature of the three-dimensional form model and a second geometric feature within the image and the first position and posture.

摘要翻译： 一种信息处理设备，包括：模型存储单元，被配置为存储用于获取测量目标对象的位置和姿势的三维形式模型;图像获取单元，被配置为获取测量目标对象的图像，第一位置和姿势 获取单元，被配置为基于所述三维形式模型的第一几何特征和所述图像内的第一几何特征获取第一坐标系中的所述三维形式模型的第一位置和姿势，以及第二位置 以及姿势获取单元，被配置为基于所述三维形式模型的第二几何特征，在与所述第一坐标系不同的第二坐标系中获取所述三维形式模型的第二位置和姿势;以及第二 图像内的几何特征和第一位置和姿势。

公开(公告)号：US20130230235A1

公开(公告)日：2013-09-05

申请号：US13885965

申请日：2011-11-15

申请人： Keisuke Tateno ,  Daisuke Kotake ,  Shinji Uchiyama

发明人： Keisuke Tateno ,  Daisuke Kotake ,  Shinji Uchiyama

IPC分类号： G06T19/00

CPC分类号： G06T19/003 ,  G06T7/75 ,  G06T2207/10004 ,  G06T2207/10028 ,  G06T2207/30108

摘要： An information processing apparatus according to the present invention includes a three-dimensional model storage unit configured to store data of a three-dimensional model that describes a geometric feature of an object, a two-dimensional image input unit configured to input a two-dimensional image in which the object is imaged, a range image input unit configured to input a range image in which the object is imaged, an image feature detection unit configured to detect an image feature from the two-dimensional image input from the two-dimensional image input unit, an image feature three-dimensional information calculation unit configured to calculate three-dimensional coordinates corresponding to the image feature from the range image input from the range image input unit, and a model fitting unit configured to fit the three-dimensional model into the three-dimensional coordinates of the image feature.

摘要翻译： 根据本发明的信息处理装置包括：三维模型存储单元，被配置为存储描述对象的几何特征的三维模型的数据;二维图像输入单元，被配置为输入二维 对象被成像的图像，被配置为输入对象被成像的范围图像的范围图像输入单元，被配置为从从二维图像输入的二维图像中检测图像特征的图像特征检测单元 输入单元，图像特征三维信息计算单元，被配置为从所述范围图像输入单元输入的范围图像中计算与所述图像特征对应的三维坐标;以及模型拟合单元，被配置为将所述三维模型拟合为 图像特征的三维坐标。

公开(公告)号：US20060094955A1

公开(公告)日：2006-05-04

申请号：US11265981

申请日：2005-11-03

申请人： Kiyohide Satoh ,  Daisuke Kotake ,  Shinichi Aratani ,  Shinji Uchiyama

发明人： Kiyohide Satoh ,  Daisuke Kotake ,  Shinichi Aratani ,  Shinji Uchiyama

IPC分类号： A61B5/05

CPC分类号： G01S5/163

摘要： An objective viewpoint image of an object captured at an objective viewpoint position is obtained, a measurement value of a sensor is received, information about the image coordinates of calibrating indices is detected from an objective viewpoint image, and two kinds of arrangement information of the calibrating indices and the sensor both placed on and relative to the object are obtained on the basis of the measurement value and the information about the image coordinates of the calibrating indices. With this, the two kinds of arrangement information are easily and accurately obtained at the same time.

公开(公告)号：US20050253870A1

公开(公告)日：2005-11-17

申请号：US11126916

申请日：2005-05-11

申请人： Daisuke Kotake ,  Shinji Uchiyama ,  Kiyohide Satoh

发明人： Daisuke Kotake ,  Shinji Uchiyama ,  Kiyohide Satoh

IPC分类号： G06T1/00 ,  G06T7/00 ,  G06T7/60 ,  A61B5/05

CPC分类号： G06T7/73

摘要： A marker placement information estimating method includes a constraint condition setting step for setting a constraint condition that can be defined with a geometric condition regarding placement information of markers, a capturing step for capturing photographed images including a marker image, a marker detecting step for detecting markers from the photographed images, and an estimating step for estimating the placement information of the markers using the positions of the detected markers on the images and the constraint condition. Thus, even if a constraint condition regarding the placement of markers exists, the placement information can be obtained with precision so as to satisfy the constraint condition.

摘要翻译： 一种标记放置信息估计方法，包括：约束条件设定步骤，用于设定可以利用关于标记的放置信息的几何条件来定义的约束条件;捕获步骤，用于捕获包括标记图像的拍摄图像，用于检测标记的标记检测步骤 以及估计步骤，用于使用检测到的标记在图像上的位置和约束条件来估计标记的放置信息。 因此，即使存在关于标记的放置的约束条件，也可以精确地获得放置信息，以满足约束条件。

公开(公告)号：US08483424B2

公开(公告)日：2013-07-09

申请号：US12627279

申请日：2009-11-30

申请人： Daisuke Kotake ,  Shinji Uchiyama

发明人： Daisuke Kotake ,  Shinji Uchiyama

IPC分类号： G06K9/00

CPC分类号： G06T7/75 ,  G06T2207/30244

摘要： An information processing apparatus that calculates information on a position and an orientation of an image capture device relative to an object captured by the image capture device, holds three-dimensional information including a plurality of line segments that constitute the object, acquires an image of the object captured by the image capture device, detects an image feature indicating a line segment from the acquired image, calculates a position and orientation of the image capture device based on correspondence between the image feature indicating the detected line segment and the held line segment, and determines, for each of the held line segments, whether to use the line segment for the calculation of the position and orientation thereafter, based on at least one of a result of detection of the image feature, and information acquired in the calculation of the position and orientation.

公开(公告)号：US20130010070A1

公开(公告)日：2013-01-10

申请号：US13538437

申请日：2012-06-29

申请人： Keisuke Tateno ,  Daisuke Kotake ,  Shinji Uchiyama

发明人： Keisuke Tateno ,  Daisuke Kotake ,  Shinji Uchiyama

IPC分类号： G06K9/00 ,  H04N13/02

CPC分类号： B25J9/1697 ,  G01B11/002 ,  G05B2219/37425 ,  G05B2219/40548 ,  G06T7/75 ,  G06T2207/10021 ,  G06T2207/30108

摘要： An information processing apparatus configured to estimate a position and orientation of a measuring object using an imaging apparatus includes an approximate position and orientation input unit configured to input a relative approximate position and orientation between the imaging apparatus and the measuring object, a first position and orientation updating unit configured to update the approximate position and orientation by matching a three-dimensional shape model to a captured image, a position and orientation difference information input unit configured to calculate and acquire a position and orientation difference amount of the imaging apparatus relative to the measuring object having moved after the imaging apparatus has captured an image of the measuring object or after last position and orientation difference information has been acquired, and a second position and orientation updating unit configured to update the approximate position and orientation based on the position and orientation difference amount.

摘要翻译： 一种被配置为使用成像装置估计测量对象的位置和姿态的信息处理装置，包括近似位置和方向输入单元，被配置为输入成像装置和测量对象之间的相对近似位置和取向，第一位置和方向 更新单元，被配置为通过将三维形状模型与拍摄图像相匹配来更新近似位置和取向;位置和方位差信息输入单元，被配置为计算并获取所述成像装置相对于所述测量的位置和方位差量 已经在成像装置捕获了测量对象的图像之后或者在获取了最后位置和方位差异信息之后已经移动的对象，以及被配置为基于位置和方向来更新大致位置和取向的第二位置和方位更新单元， 取向差值。

公开(公告)号：US20100289797A1

公开(公告)日：2010-11-18

申请号：US12778385

申请日：2010-05-12

申请人： Keisuke Tateno ,  Daisuke Kotake ,  Shinji Uchiyama

发明人： Keisuke Tateno ,  Daisuke Kotake ,  Shinji Uchiyama

IPC分类号： G06T15/00

CPC分类号： G06T17/00 ,  G06T7/13 ,  G06T7/75 ,  G06T2207/30164

摘要： A position and orientation estimation apparatus detects correspondence between a real image obtained by an imaging apparatus by imaging a target object to be observed and a rendered image. The rendered image is generated by projecting a three dimensional model onto an image plane based on three dimensional model data expressing the shape and surface information of the target object, and position and orientation information of the imaging apparatus. The position and orientation estimation apparatus then calculates a relative position and orientation of the imaging apparatus and the target object to be observed based on the correspondence. Then, the surface information of the three dimensional model data is updated by associating image information of the target object to be observed in the real image with the surface information of the three dimensional model data, based on the calculated positions and orientations.

摘要翻译： 位置和姿态估计装置通过对要观察的目标对象进行成像和渲染图像来检测由成像装置获得的实际图像之间的对应关系。 基于表示目标对象的形状和表面信息的三维模型数据以及成像装置的位置和取向信息，将三维模型投影到图像平面上来生成渲染图像。 然后，位置和姿势估计装置基于对应来计算成像装置和要观察的目标对象的相对位置和取向。 然后，基于计算出的位置和方向，通过将实际图像中要观察的目标对象的图像信息与三维模型数据的表面信息相关联来更新三维模型数据的表面信息。

公开(公告)号：US07671875B2

公开(公告)日：2010-03-02

申请号：US11235556

申请日：2005-09-26

申请人： Mahoro Anabuki ,  Daisuke Kotake ,  Shinji Uchiyama

发明人： Mahoro Anabuki ,  Daisuke Kotake ,  Shinji Uchiyama

IPC分类号： G09G5/00

CPC分类号： G06F3/0325 ,  G06F3/0346 ,  G06K9/3216 ,  G06K2009/3225 ,  G06T7/246 ,  G06T7/73 ,  G06T19/006

摘要： In a case where a position and/or orientation of a shooting viewpoint is calculated by using information about image coordinates of markers placed in a scene, the present invention enables a user to easily determine positions of the markers so that the position and orientation can be calculated more accurately. Information about markers placed in a physical space is obtained and area information about mixing accuracy between a physical space image and a virtual space image is obtained based on the information about the markers, so that a virtual space image is generated in accordance with the obtained area information.

摘要翻译： 在通过使用关于放置在场景中的标记的图像坐标的信息来计算拍摄视点的位置和/或取向的情况下，本发明使得用户能够容易地确定标记的位置，使得位置和取向可以 计算更准确。 获得关于放置在物理空间中的标记的信息，并且基于关于标记的信息获得关于物理空间图像和虚拟空间图像之间的混合精度的区域信息，从而根据获得的区域生成虚拟空间图像 信息。

公开(公告)号：US20090262113A1

公开(公告)日：2009-10-22

申请号：US12418082

申请日：2009-04-03

申请人： Daisuke Kotake ,  Shinji Uchiyama

发明人： Daisuke Kotake ,  Shinji Uchiyama

IPC分类号： G06T15/20

CPC分类号： G06F3/011 ,  G02B27/017 ,  G02B2027/0138 ,  G02B2027/014 ,  G02B2027/0187 ,  G06T7/12 ,  G06T7/73 ,  G06T19/006 ,  G06T2207/10016

摘要： A unit (110) acquires an image, sensed by an image sensing device (100), of a physical object having an outer appearance that can be expressed by line segments. A unit (120) stores defining data used to classify line segments configuring a 3D virtual object that simulates the outer appearance of the physical object into a plurality of groups and to define respective line segments belonging to the groups. A unit (130) selects one group from the groups one by one without any repetition. The unit (130) projects line segments which belong to the selected group onto a physical space using the defining data used to define that line segments, and the image of the physical space. The unit (130) then updates a position and orientation of the image sensing unit based on the line segments projected onto the physical space and a feature in the image of the physical object.

摘要翻译： 单元（110）获取由图像感测装置（100）感测到的具有可以由线段表示的外观的物理对象的图像。 单元（120）存储定义用于将配置3D虚拟对象的线段分类的数据，所述3D虚拟对象将物理对象的外观模拟成多个组，并且定义属于组的各个线段。 一个单元（130）从一个接一个地选择一个组而不重复。 单元（130）使用用于定义该线段的定义数据和物理空间的图像将属于所选择的组的线段投射到物理空间上。 然后，单元（130）基于投影到物理空间上的线段和物理对象的图像中的特征来更新图像感测单元的位置和方位。