公开(公告)号：US08391589B2

公开(公告)日：2013-03-05

申请号：US12013123

申请日：2008-01-11

申请人： Daisuke Kotake ,  Shinji Uchiyama ,  Hirokazu Kato

发明人： Daisuke Kotake ,  Shinji Uchiyama ,  Hirokazu Kato

IPC分类号： G06K9/00

CPC分类号： G01C11/00 ,  G01S5/16 ,  G06T7/20 ,  G06T7/73

摘要： Three pieces of candidate position information are calculated based on a plurality of pieces of sensing position information, and three pieces of candidate orientation information are calculated based on a plurality of pieces of sensing orientation information. Sets each of which combines one candidate position information and one candidate orientation information are prepared for all combinations. For each set, the candidate position information and candidate orientation information which configure that set are corrected. An evaluation value is calculated for each corrected set, and one of the sets is selected based on the calculated evaluation values. The candidate position information and candidate orientation information which configure the selected set are respectively recorded in a memory as sensing position information and sensing orientation information.

摘要翻译： 基于多条感测位置信息计算三条候选位置信息，并且基于多条感测取向信息来计算三条候选方向信息。 对于所有组合，为每个组合一个候选位置信息和一个候选方向信息。 对于每个集合，配置该组的候选位置信息和候选方向信息被校正。 针对每个校正组计算评估值，并且基于所计算的评估值来选择一组。 配置所选择的集合的候选位置信息和候选方向信息分别作为感测位置信息和感测取向信息记录在存储器中。

公开(公告)号：US20110206274A1

公开(公告)日：2011-08-25

申请号：US13030487

申请日：2011-02-18

申请人： Keisuke Tateno ,  Daisuke Kotake ,  Kazuhiko Kobayashi ,  Shinji Uchiyama

发明人： Keisuke Tateno ,  Daisuke Kotake ,  Kazuhiko Kobayashi ,  Shinji Uchiyama

IPC分类号： G06K9/00

CPC分类号： G06T7/75 ,  G06T2207/10028

摘要： A position and orientation estimation apparatus inputs an image capturing an object, inputs a distance image including three-dimensional coordinate data representing the object, extracts an image feature from the captured image, determines whether the image feature represents a shape of the object based on three-dimensional coordinate data at a position on the distance image corresponding to the image feature, correlates the image feature representing the shape of the object with a part of a three-dimensional model representing the shape of the object, and estimates the position and orientation of the object based on a correlation result.

摘要翻译： 位置和姿态估计装置输入拍摄对象的图像，输入包括表示对象的三维坐标数据的距离图像，从拍摄图像中提取图像特征，基于三个图像特征来确定图像特征是否表示对象的形状 在与图像特征相对应的距离图像上的位置处的三维坐标数据将表示对象的形状的图像特征与表示对象的形状的三维模型的一部分相关联，并且估计对象的位置和方向 该对象基于相关结果。

公开(公告)号：US07529387B2

公开(公告)日：2009-05-05

申请号：US11126436

申请日：2005-05-11

申请人： Daisuke Kotake ,  Shinji Uchiyama

发明人： Daisuke Kotake ,  Shinji Uchiyama

IPC分类号： G06K9/00

CPC分类号： G06K9/32 ,  G06K2009/3225 ,  G06T7/73

摘要： A method is provided for estimating the placement information of a plurality of types of markers of which the amounts of the placement information differ respectively, detects a plurality of types of markers from multiple images, calculates the position where the detected marker is projected on an image surface based on the approximate values of the positions and orientations of an imaging device when multiple images are photographed, obtains the correction value of the placement information of a marker so as to reduce a sum of error between the position of the detected marker on the image surface and the projected position of the marker calculated, corrects the placement information of the marker, and also calculates the placement information of a plurality of types of markers by repeating these processes.

摘要翻译： 提供了一种用于估计多个类型的标记的放置信息的放置信息的方法，其中放置信息的量分别不同，从多个图像中检测多种类型的标记，计算检测到的标记投影在图像上的位置 基于拍摄多个图像时的成像装置的位置和取向的近似值的表面，获得标记的放置信息的校正值，以减少图像上检测到的标记的位置之间的误差之和 计算出标记的投影位置，校正标记的放置信息，并且还通过重复这些处理来计算多种类型的标记的放置信息。

公开(公告)号：US20080285854A1

公开(公告)日：2008-11-20

申请号：US11836085

申请日：2007-08-08

申请人： Daisuke Kotake ,  Kazuki Takemoto ,  Kenji Morita ,  Sonoko Maeda

发明人： Daisuke Kotake ,  Kazuki Takemoto ,  Kenji Morita ,  Sonoko Maeda

IPC分类号： G06K9/66

CPC分类号： G06T7/73 ,  G06T2207/30208

摘要： A marker arrangement information measuring apparatus includes an image acquiring unit configured to acquire a captured image, a marker detecting unit configured to detect markers from the captured image, a marker identifying unit configured to identify the marker detected by the marker detecting unit, an arrangement information calculating unit configured to calculate arrangement information of the marker based on an identification result of the marker identifying unit, an analyzing unit configured to analyze the identification result of the marker identifying unit, and a display unit configured to display an image corresponding to an analysis result of the analyzing unit on the captured image in a combined manner, thus presenting the analysis result to a user.

摘要翻译： 标记装置信息测量装置包括：图像获取单元，被配置为获取拍摄图像;标记检测单元，被配置为从所述拍摄图像中检测标记;标记识别单元，被配置为识别由所述标记检测单元检测到的标记;布置信息 计算单元，被配置为基于标识识别单元的识别结果来计算标记的排列信息;分析单元，被配置为分析标记识别单元的识别结果;以及显示单元，被配置为显示与分析结果相对应的图像 的分析单元，从而将分析结果呈现给用户。

公开(公告)号：US20080172201A1

公开(公告)日：2008-07-17

申请号：US12013123

申请日：2008-01-11

申请人： Daisuke Kotake ,  Shinji Uchiyama ,  Hirokazu Kato

发明人： Daisuke Kotake ,  Shinji Uchiyama ,  Hirokazu Kato

IPC分类号： G01C11/00

CPC分类号： G01C11/00 ,  G01S5/16 ,  G06T7/20 ,  G06T7/73

摘要： Three pieces of candidate position information are calculated based on a plurality of pieces of sensing position information, and three pieces of candidate orientation information are calculated based on a plurality of pieces of sensing orientation information. Sets each of which combines one candidate position information and one candidate orientation information are prepared for all combinations. For each set, the candidate position information and candidate orientation information which configure that set are corrected. An evaluation value is calculated for each corrected set, and one of the sets is selected based on the calculated evaluation values. The candidate position information and candidate orientation information which configure the selected set are respectively recorded in a memory as sensing position information and sensing orientation information.

摘要翻译： 基于多条感测位置信息计算三条候选位置信息，并且基于多条感测取向信息来计算三条候选方向信息。 对于所有组合，为每个组合一个候选位置信息和一个候选方向信息。 对于每个集合，配置该组的候选位置信息和候选方向信息被校正。 针对每个校正组计算评估值，并且基于所计算的评估值来选择一组。 配置所选择的集合的候选位置信息和候选方向信息分别作为感测位置信息和感测取向信息记录在存储器中。

公开(公告)号：US07103232B2

公开(公告)日：2006-09-05

申请号：US09818627

申请日：2001-03-28

申请人： Daisuke Kotake ,  Akihiro Katayama

发明人： Daisuke Kotake ,  Akihiro Katayama

IPC分类号： G06K9/20

CPC分类号： G06T15/205

摘要： Each of the panoramic images corresponding to a plurality of positions of a viewpoint is compressed and stored as partial images obtained by dividing each panoramic image by a predetermined field of view. The panoramic image has a field of view wider than a display field of view of an image to be displayed on a display unit. A partial image containing an image to be reproduced is selected based on the information about the position and the direction of a viewpoint and the display field of view, and an image corresponding to the position and the direction of a viewpoint is generated and displayed from the selected partial image. Thus, when virtual space in the walk-through system is designed using the IBR technology, stored image data can be efficiently reproduced.

摘要翻译： 对应于视点的多个位置的每个全景图像被压缩并存储为通过将每个全景图像除以预定视场而获得的部分图像。 全景图像具有比要显示在显示单元上的图像的显示视野更宽的视野。 基于关于视点的位置和方向的信息以及显示视野来选择包含要再现的图像的部分图像，并且从视点的位置和方向生成并显示与视点的位置和方向对应的图像 选择部分图像。 因此，当使用IBR技术设计步行系统中的虚拟空间时，可以有效地再现存储的图像数据。

公开(公告)号：US06757441B1

公开(公告)日：2004-06-29

申请号：US09653002

申请日：2000-08-31

申请人： Akihiro Katayama ,  Daisuke Kotake ,  Yukio Sakagawa

发明人： Akihiro Katayama ,  Daisuke Kotake ,  Yukio Sakagawa

IPC分类号： G06K936

CPC分类号： G06T9/007

摘要： There is disclosed an image data encoding/decoding method and apparatus which can efficiently encode multi-viewpoint image data obtained by sensing a single object from many viewpoints, and can obtain decoded data in units of pixels at high speed. Reference images which are not encoded are set every predetermined number of images (S701), and encoding is done using only the relationship with this reference image. An orthogonal transform is used in encoding, and an inverse transform formula for each pixel in a block is expanded and stored upon computing the orthogonal transform (S704). The coefficients after the orthogonal transform are fixed-length encoded in units of pixels (S705). Upon decoding, fixed-length encoded data corresponding to desired pixels are decoded, and pixel data are decoded by substituting coefficients obtained by decoding in the expansions generated upon encoding.

摘要翻译： 公开了一种图像数据编码/解码方法和装置，其可以有效地编码通过从多个视点感测单个对象而获得的多视点图像数据，并且可以以高速度以像素为单位获得解码数据。 对每个预定数量的图像设置未编码的参考图像（S701），并且仅使用与该参考图像的关系来完成编码。 在编码中使用正交变换，并且在计算正交变换时扩展并存储块中的每个像素的逆变换公式（S704）。 正交变换后的系数以像素为单位进行固定长度编码（S705）。 在解码时，对应于期望像素的固定长度编码数据进行解码，并且通过将通过解码获得的系数代入在编码时生成的扩展中来对像素数据进行解码。

公开(公告)号：US06674922B1

公开(公告)日：2004-01-06

申请号：US09499300

申请日：2000-02-07

申请人： Daisuke Kotake ,  Yukio Sakagawa ,  Akihiro Katayama

发明人： Daisuke Kotake ,  Yukio Sakagawa ,  Akihiro Katayama

IPC分类号： G06K932

CPC分类号： G06T3/4007 ,  G06T15/04 ,  G06T15/205

摘要： An image processing apparatus includes recording unit which has recorded image information appended with quantized space information in units of pixels, setting unit for setting a resolution higher than that of the recorded image information, reconstruction unit for reconstructing an image by reading out image information from the recording unit at the recorded resolution irrespective of the resolution set by the setting unit, and interpolation unit for making pixel interpolation of the reconstructed image with the resolution of the reconstructed image matching the resolution set by the setting unit.

摘要翻译： 一种图像处理装置，包括以像素为单位记录附加有量化空间信息的图像信息的记录单元，用于设置分辨率高于记录图像信息的分辨率的设置单​​元，用于通过从图像信息中读出图像信息来重建图像的重建单元 记录单元以与设置单元设置的分辨率无关的记录分辨率，以及内插单元，用于对具有与设置单元设置的分辨率相匹配的重建图像的分辨率进行重构图像的像素插值。

公开(公告)号：US09025857B2

公开(公告)日：2015-05-05

申请号：US12818538

申请日：2010-06-18

申请人： Daisuke Kotake ,  Shinji Uchiyama

发明人： Daisuke Kotake ,  Shinji Uchiyama

IPC分类号： G06K9/00 ,  G01B11/25 ,  G06T7/00

CPC分类号： G01B11/25 ,  G06T7/521

摘要： A three-dimensional measurement apparatus includes a model holding unit configured to hold a three-dimensional shape model of a measurement object and a determination unit configured to determine a distance measurement region on the measurement object based on information indicating a three-dimensional shape of the measurement object. The measurement object is irradiated with a predetermined illumination pattern by an illumination unit. An image of the measurement object is sensed while the illumination unit irradiates the measurement object. Distance information indicating a distance from the image sensing unit to the measurement object is calculated based on region corresponding to the distance measurement region within the sensed image. A position and orientation of the measurement object is calculated based on the distance information and the three-dimensional shape model.

摘要翻译： 三维测量装置包括：模型保持单元，被配置为保持测量对象的三维形状模型;以及确定单元，被配置为基于指示测量对象的三维形状的信息来确定测量对象上的距离测量区域 测量对象。 通过照明单元以预定的照明图案照射测量对象。 当照明单元照射测量对象时，感测测量对象的图像。 基于与感测图像内的距离测量区域对应的区域来计算表示从摄像单元到测量对象的距离的距离信息。 基于距离信息和三维形状模型计算测量对象的位置和方位。

公开(公告)号：US20120288216A1

公开(公告)日：2012-11-15

申请号：US13561473

申请日：2012-07-30

申请人： Shinichi Aratani ,  Daisuke Kotake ,  Shinji Uchiyama

发明人： Shinichi Aratani ,  Daisuke Kotake ,  Shinji Uchiyama

IPC分类号： G06K9/60

CPC分类号： G06T7/74 ,  G06K9/3216 ,  G06K2009/3225 ,  G06T7/73 ,  G06T2207/30204

摘要： From a sequence of images captured by an image pickup unit, images necessary for measuring placement information regarding markers and/or a sensor are automatically determined and obtained. To this end, using position and orientation information regarding the image pickup unit at the time the image pickup unit has captured an obtained image and placement information regarding detected markers, whether to use the captured image corresponding to the position and orientation is determined. Using the captured image determined to be used, the marker placement information, placement information regarding a measurement target, or the position and orientation of the image pickup unit serving as an unknown parameter is obtained so as to minimize the error between the measured image coordinates and theoretical image coordinates of each marker, which are estimated on the basis of a rough value of the parameter.

摘要翻译： 从图像拾取单元拍摄的图像序列中，自动确定和获得关于测量关于标记和/或传感器的放置信息所需的图像。 为此，在图像拍摄单元拍摄获得的图像时使用关于图像拾取单元的位置和方向信息以及关于检测到的标记的放置信息，确定是否使用与位置和方位对应的拍摄图像。 使用确定使用的拍摄图像，获得标记放置信息，关于测量对象的放置信息，或者用作未知参数的图像拾取单元的位置和方向，以便使测量的图像坐标和 基于参数的粗略值估计的每个标记的理论图像坐标。