公开(公告)号：US08284252B2

公开(公告)日：2012-10-09

申请号：US12643018

申请日：2009-12-21

申请人： Takahiro Ishikawa

发明人： Takahiro Ishikawa

IPC分类号： H04N21/414

CPC分类号： G06K9/00335 ,  G06K9/00832

摘要： A detection unit obtains a position of a feature point of an occupant. A storage unit stores a model of all specific actions in each of physical feature classifications. The model defines a position or a locus of the feature point in each specific action, which an occupant may perform. A determining unit compares an in-action feature point with each model of a specific action, which is being performed, to determine a classification conformity weight indicating a possibility that the occupant belongs to the physical feature classification. An estimating unit compares the position of the feature point with each model to obtain a comparison result and generate a conformity value by incorporating the classification conformity weight into the comparison result. The estimating unit detects an estimated action, which is a specific action corresponding to the model, which has a highest conformity value.

摘要翻译： 检测单元获取乘员的特征点的位置。 存储单元在物理特征分类的每一个中存储所有特定动作的模型。 该模型定义了每个特定动作中的特征点的位置或轨迹，乘员可以执行该位置或轨迹。 确定单元将正在执行的特定动作的每个模型的动作特征点进行比较，以确定指示乘客属于物理特征分类的可能性的分类合格权重。 估计单元将特征点的位置与每个模型进行比较以获得比较结果，并通过将分类一致性权重并入到比较结果中来生成一致性值。 估计单元检测到具有最高一致性值的与模型对应的特定动作的估计动作。

公开(公告)号：US08098892B2

公开(公告)日：2012-01-17

申请号：US12285579

申请日：2008-10-09

申请人： Junya Inada ,  Takahiro Ishikawa

发明人： Junya Inada ,  Takahiro Ishikawa

IPC分类号： G06K9/00

CPC分类号： G06K9/00369 ,  G06K9/00832 ,  G06K2209/23

摘要： In a body position detecting apparatus, a controller repeatedly acquires image data that includes an object and an operator in a place where the operator is capable of operating the object. When the controller detects that the operator is in an operating position where the operator operates the object, the controller detects a position of a body part of the operator in the image data and the controller sets the position of the body part to an initial position. The controller detects a position of the body part of the operator in the image data that is acquired after the initial position is set, by detecting a displacement from a position of the body part detected last time and accumulating the displacement to the initial position.

摘要翻译： 在身体位置检测装置中，控制器在操作者能够操作对象的地方反复地获取包括对象和操作者的图像数据。 当控制器检测到操作者处于操作者操作对象的操作位置时，控制器检测操作者的身体部位在图像数据中的位置，并且控制器将身体部位的位置设置为初始位置。 控制器通过检测从上次检测到的身体部位的位置到累积位置到初始位置的位移，检测操作者的身体部位在初始位置设定后获取的图像数据中的位置。

公开(公告)号：US08077970B2

公开(公告)日：2011-12-13

申请号：US11987800

申请日：2007-12-04

申请人： Takahiro Ishikawa

发明人： Takahiro Ishikawa

IPC分类号： G06K9/00

CPC分类号： G06K9/00369 ,  G06K2009/3225

摘要： An operation estimating apparatus includes an image obtaining unit, a human body feature point specifying unit, and an operation estimating unit. The image obtaining unit repeatedly obtains images. The human body feature point specifying unit specifies a predetermined human body feature point of an operator in each of the images. The operation estimating unit estimates one of operations based on the human body feature points. The operation estimating unit compares an actual posture locus of the operator with a transitional estimation model for each of the operations by the operator to obtain a degree of approximation of the transitional estimation model to the actual posture locus. The operation estimating unit estimates that the operator is going to perform the one of the operations that corresponds to an estimated posture locus of the transitional estimation model having the degree of approximation that satisfies a predetermined threshold.

摘要翻译： 操作估计装置包括图像获取单元，人体特征点指定单元和操作估计单元。 图像获取单元重复获得图像。 人体特征点指定单元指定每个图像中的操作者的预定人体特征点。 操作估计单元基于人体特征点估计操作之一。 操作估计单元将操作者的实际姿势轨迹与操作者的每个操作的过渡估计模型进行比较，以获得与实际姿势轨迹的过渡估计模型的近似度。 操作估计单元估计操作者将执行与具有满足预定阈值的近似程度的过渡估计模型的估计姿势轨迹相对应的操作之一。

公开(公告)号：US08036424B2

公开(公告)日：2011-10-11

申请号：US11786152

申请日：2007-04-11

申请人： Takahiro Ishikawa ,  Takanori Fukao

发明人： Takahiro Ishikawa ,  Takanori Fukao

IPC分类号： G06K9/00

CPC分类号： G06K9/00805 ,  G06T7/269 ,  G06T7/70

摘要： A field recognition apparatus includes a first camera for imaging a forward field and a second camera for imaging a road surface. The second camera has a light axis tilted toward a downward direction for accurately tracking a characteristic point in consecutively captured images to calculate an optical flow and for accurately recognizing road structure information. In this manner, three dimensional information of obstacles in a field is accurately processed and detected.

摘要翻译： 场识别装置包括用于对前场成像的第一相机和用于对路面成像的第二相机。 第二相机具有朝向下方向倾斜的光轴，用于精确地跟踪连续拍摄图像中的特征点，以计算光流并准确地识别道路结构信息。 以这种方式，对场中的障碍物的三维信息进行精确的处理和检测。

公开(公告)号：US20100158316A1

公开(公告)日：2010-06-24

申请号：US12654476

申请日：2009-12-22

申请人： Takahiro Ishikawa

发明人： Takahiro Ishikawa

IPC分类号： G06K9/62

CPC分类号： G06K9/00771 ,  G06K9/00832

摘要： A storage unit stores a model defining a position or a locus of a feature point of an occupant in each specific action. An action estimation unit compares the feature point with each of the models to detect an estimated action. A detecting unit detects that a specific action is being performed as a definite action. A first generating unit generates a new definite model corresponding to the definite action by modifying a position or a locus of the feature point according to an in-action feature point when the definite action is being performed. A second generating unit generates a new non-definite model using the in-action feature point according to a correspondence between the feature point in the definite action and the feature point of a non-definite model other than the definite model. An update unit updates the definite action model and the non-definite action model.

摘要翻译： 存储单元存储在每个特定动作中定义乘客的特征点的位置或轨迹的模型。 动作估计单元将特征点与每个模型进行比较以检测估计的动作。 检测单元检测到正在执行特定动作作为确定的动作。 第一生成单元通过在执行确定动作时根据动作特征点修改特征点的位置或轨迹来生成与确定动作对应的新的确定模型。 第二生成单元根据确定动作中的特征点与除了确定模型以外的非确定模型的特征点的对应关系，使用动作特征点生成新的非确定模型。 更新单元更新确定动作模型和非确定动作模型。

公开(公告)号：US06993753B2

公开(公告)日：2006-01-31

申请号：US09774685

申请日：2001-02-01

申请人： Yutaka Yamanaka ,  Takahiro Ishikawa

发明人： Yutaka Yamanaka ,  Takahiro Ishikawa

IPC分类号： G06F9/45

CPC分类号： G06F8/456

摘要： The object of the present invention is to provided a compiler for parallel computers that enable rapid processing by introducing a new data structure. A compiler 20 which compiles a source program 10, which includes a parallelization directive, executes a step of detecting a parallelization directive in the source program; and if the parallelization directive is detected, generating a front-end intermediate language for the parallelization directive by positioning on a storage region, each processing code of at least part of the parallelization directive with a hierarchical structure in accordance with an internal structure of the parallelization directive. In addition, the compiler 20 may execute a step of: adding to the front-end intermediate language of a statement to which the parallelization directive is applied, reference information from the front-end intermediate language of the statement to which the parallelization directive is applied, to the front-end intermediate language for the parallelization directive.

摘要翻译： 本发明的目的是提供一种用于并行计算机的编译器，其通过引入新的数据结构来实现快速处理。 编译包含并行化指令的源程序10的编译器20执行检测源程序中的并行化指令的步骤; 并且如果检测到并行化指令，则通过在存储区域上定位来产生用于并行化指令的前端中间语言，根据并行化的内部结构，根据层次结构的至少一部分并行化指令的每个处理代码 指示。 此外，编译器20可以执行以下步骤：向应用了并行化指令的语句的前端中间语言添加来自应用并行化指令的语句的前端中间语言的引用信息 ，到并行化指令的前端中间语言。

公开(公告)号：US20050119475A1

公开(公告)日：2005-06-02

申请号：US10825210

申请日：2004-04-16

申请人： Takahiro Ishikawa ,  Akira Yamaguchi ,  Kyoko Suzuki ,  Kayoko Katsuyama

发明人： Takahiro Ishikawa ,  Akira Yamaguchi ,  Kyoko Suzuki ,  Kayoko Katsuyama

IPC分类号： C08B37/00 ,  C07H13/06 ,  C11B1/00 ,  C11B1/10 ,  C11B3/16 ,  C11B11/00 ,  C11C3/00 ,  G01N1/34

CPC分类号： C11B11/00 ,  C07H13/06 ,  C11B1/00 ,  G01N2001/4016 ,  Y02W30/74

摘要： With the object of providing a method for separating glycolipids (particularly gangliosides) capable of processing a large number of samples easily and at low cost, and capable of recovering multiple types of glycolipids with high recovery, in the method for separating glycolipids of the present invention (a) a sample solution obtained by hydrolysis of an extract derived from a biological sample with a mixture of a nonpolar solvent and a polar solvent is first brought into contact via a semipermeable membrane with a solution having lower osmotic pressure than the sample solution, and (b) the contact is continued until the sample solution divides into two or three layers, and the middle layer and/or bottom layer are/is separated.

摘要翻译： 本发明的目的是提供一种能够容易且低成本地分离加工大量样品的糖脂（特别是神经节苷脂）的方法，并且能够回收多种具有高回收率的糖脂，本发明的糖脂分离方法 （a）通过用非极性溶剂和极性溶剂的混合物将来自生物样品的提取物水解获得的样品溶液首先通过半透膜与具有比样品溶液更低的渗透压的溶液接触，以及 （b）继续进行接触，直到样品溶液分成两层或三层，中间层和/或底层被分离。