公开(公告)号：US20160093058A1

公开(公告)日：2016-03-31

申请号：US14845493

申请日：2015-09-04

Applicant: FUJITSU LIMITED

Inventor： Atsunori Moteki ,  Nobuyasu YAMAGUCHI ,  Takahiro MATSUDA

IPC: G06T7/00 ,  G06K9/46

CPC classification number: G06T7/593 ,  G06K9/4604 ,  G06T7/579 ,  G06T7/73 ,  G06T2207/30208 ,  G06T2207/30244

Abstract: A three-dimensional coordinate computing apparatus includes an image selecting unit and a coordinate computing unit. The image selecting unit selects a first selected image from multiple captured images, and selects a second selected image from multiple subsequent images captured by the camera after the first selected image has been captured. The second selected image is selected based on a distance between a position of capture of the first selected image and a position of capture of each of the multiple subsequent images and the number of corresponding feature points, each of which corresponds to one of feature points extracted from the first selected image and one of feature points extracted from each of the multiple subsequent images. The coordinate computing unit computes three-dimensional coordinates of the multiple corresponding feature points based on two-dimensional coordinates of each corresponding feature point in the first and second selected images.

Abstract translation: 三维坐标计算装置包括图像选择单元和坐标计算单元。 图像选择单元从多个拍摄图像中选择第一选择图像，并且在捕获了第一选择图像之后，从由相机拍摄的多个后续图像中选择第二选择图像。 基于第一选择图像的拍摄位置与多个后续图像中的每一个的拍摄位置之间的距离和对应的特征点的数量来选择第二选择图像，每个相应特征点对应于提取的特征点之一 从所述第一选择图像和从所述多个后续图像中的每一个提取的特征点中的一个。 坐标计算单元基于第一和第二选择图像中的每个相应特征点的二维坐标来计算多个相应特征点的三维坐标。

公开(公告)号：US20140294233A1

公开(公告)日：2014-10-02

申请号：US14185106

申请日：2014-02-20

Applicant: FUJITSU LIMITED

Inventor： Kazuki OSAMURA ,  Taichi MURASE ,  Takahiro MATSUDA

IPC: G06T7/20

CPC classification number: G06T7/0075 ,  G06F3/0304 ,  G06F3/0425 ,  G06F3/0426 ,  G06T7/593 ,  G06T2207/10021

Abstract: An information processing device includes, a processor; and a memory which stores a plurality of instructions, which when executed by the processor, cause the processor to execute, acquiring images which includes a target object, and the images captured by a plurality of cameras on a time series basis; calculating a plurality of distance from the plurality of each cameras to a target object by using the images; and correcting, in a case where the target object has reached a predetermined x-y plane and a difference in an area of the target object between the images is equal to or less than a predetermined first threshold, the distance that has been calculated to a distance from the cameras to the x-y plane.

Abstract translation: 信息处理装置包括：处理器; 以及存储器，其存储多个指令，当由处理器执行时，使得处理器执行，基于时间序列获取包括目标对象的图像和由多个相机拍摄的图像; 通过使用所述图像计算从所述多个相机到目标对象的多个距离; 并且在目标对象已经达到预定的xy平面并且图像之间的目标对象的区域的差等于或小于预定的第一阈值的情况下，校正已经被计算出的距离 相机到xy平面。

公开(公告)号：US20140204018A1

公开(公告)日：2014-07-24

申请号：US14086535

申请日：2013-11-21

Applicant: FUJITSU LIMITED

Inventor： Taichi MURASE ,  Takahiro MATSUDA

IPC: G06F3/03

CPC classification number: G06F3/0425 ,  G06F3/0426

Abstract: An input method that is executed by a computer includes obtaining a first image of an object using an imaging device, detecting a first feature point of the object based on a shape of the object in the first image, calculating a first angle of the object with respect to a plane on which a pressing operation is performed based on the first feature point and information on a first area of the object in the first image, and selecting a first input item from a plurality of input items based on the first angle.

Abstract translation: 由计算机执行的输入方法包括使用成像装置获取对象的第一图像，基于第一图像中的对象的形状来检测对象的第一特征点，计算对象的第一角度， 相对于基于第一特征点执行按压操作的平面和关于第一图像中的对象的第一区域的信息，以及基于第一角度从多个输入项中选择第一输入项。

公开(公告)号：US20140056487A1

公开(公告)日：2014-02-27

申请号：US13903154

申请日：2013-05-28

Applicant: FUJITSU LIMITED

Inventor： Genta SUZUKI ,  Takahiro MATSUDA

IPC: G06K9/00

CPC classification number: G06K9/00892 ,  G06F21/32 ,  G06F21/36 ,  G06K9/00221 ,  G06K9/00288 ,  G06K9/00885

Abstract: An image processing device includes a processor; and a memory which stores a plurality of instructions, which when executed by the processor, cause the processor to execute, acquiring a captured image; extracting first feature data and second feature data of a first user included in the image; calculating a first authentication decision value, which indicates a probability that the first feature data of the first user resembles first feature data of a second user; and authenticating the first user by using the first feature data or both the first feature data and the second feature data according to the first authentication decision value.

Abstract translation: 图像处理装置包括处理器; 以及存储器，其存储多个指令，所述指令在由所述处理器执行时使所述处理器执行，获取捕获的图像; 提取包括在图像中的第一用户的第一特征数据和第二特征数据; 计算第一认证判定值，其指示第一用户的第一特征数据类似于第二用户的第一特征数据的概率; 以及根据所述第一认证判定值，通过使用所述第一特征数据或所述第一特征数据和所述第二特征数据来认证所述第一用户。

公开(公告)号：US20130342463A1

公开(公告)日：2013-12-26

申请号：US13892607

申请日：2013-05-13

Applicant: FUJITSU LIMITED

Inventor： Taichi MURASE ,  Nobuyuki HARA ,  Atsunori MOTEKI ,  Takahiro MATSUDA

IPC: G06F3/041

CPC classification number: G06F3/0418 ,  G06F3/0233 ,  G06F3/04886

Abstract: A method for inputting a character executed by a computer that inputs a character, the method includes: obtaining a first pressed position at which the pressing operation has been performed and a first key corresponding to the first pressed position; detecting deletion of a character input using the first key; obtaining, when the deletion is detected, a second pressed position at which a next pressing operation has been performed and a second key corresponding to the second pressed position; determining whether or not a distance between the first pressed position and the second key is smaller than or equal to a threshold; and correcting, when the distance is smaller than or equal to the threshold, a range that is recognized as the second key in the region on the basis of the first pressed position.

Abstract translation: 一种用于输入由输入字符的计算机执行的字符的方法，所述方法包括：获得已经执行了按压操作的第一按压位置和对应于第一按压位置的第一键; 使用所述第一键检测字符输入的删除; 当检测到删除时，获得已经执行下一个按压操作的第二按压位置和对应于第二按压位置的第二键; 确定所述第一按压位置和所述第二键之间的距离是否小于或等于阈值; 并且当所述距离小于或等于所述阈值时，基于所述第一按压位置来校正在所述区域中被识别为所述第二键的范围。

公开(公告)号：US20160274691A1

公开(公告)日：2016-09-22

申请号：US15075068

申请日：2016-03-18

Applicant: FUJITSU LIMITED

Inventor： Taichi Murase ,  Takahiro MATSUDA ,  Kazuki Osamura

IPC: G06F3/042 ,  G06K9/52 ,  G06K9/00 ,  G06T7/60 ,  G06T7/00 ,  G06K9/62

CPC classification number: G06F3/042 ,  G06K9/00375

Abstract: An input apparatus includes a processor which is configured to: detect a finger region containing a finger and a fingertip position in a first image captured by a first camera; set a template containing the finger region and generate a plurality of sub-templates by dividing the template along a longitudinal direction of the finger region; obtain a region that best matches the template on a second image generated by a second camera placed a prescribed distance away from the first camera and divide the region into search regions equal in number to the sub-templates along the longitudinal direction of the finger region; perform template matching between a sub-template containing the fingertip position and a corresponding search region to find a matching point corresponding to the fingertip position; and compute the fingertip position in real space based on the fingertip position and the matching point.

Abstract translation: 输入装置包括：处理器，被配置为：在由第一相机拍摄的第一图像中检测包含手指和指尖位置的手指区域; 设置包含所述手指区域的模板，并通过沿所述手指区域的纵向划分所述模板来生成多个子模板; 获得与由第一照相机放置规定距离的第二照相机生成的第二图像上最佳匹配的区域，并将该区域划分成沿着手指区域的纵向方向与子模板相等的搜索区域; 在包含指尖位置的子模板和相应的搜索区域之间执行模板匹配以找到与指尖位置相对应的匹配点; 并根据指尖位置和匹配点计算实际空间中的指尖位置。

公开(公告)号：US20150055836A1

公开(公告)日：2015-02-26

申请号：US14285826

申请日：2014-05-23

Applicant: FUJITSU LIMITED

Inventor： Atsunori MOTEKI ,  Koichiro NIINUMA ,  Takahiro MATSUDA

IPC: G06K9/00

CPC classification number: G06K9/00375 ,  G06K9/00355

Abstract: An image processing device includes, a processor; and a memory which stores a plurality of instructions, which when executed by the processor, cause the processor to execute, acquiring an image including a first region of a user; extracting a color feature quantity or an intensity gradient feature quantity from the image; detecting the first region based on the color feature quantity or the intensity gradient feature quantity; and selecting whether the detecting is detecting the first region using either the color feature quantity or the intensity gradient feature quantity, based on first information related to the speed of movement of the first region calculated from a comparison of the first regions in a plurality of images acquired at different times.

Abstract translation: 图像处理装置包括：处理器; 以及存储器，其存储多个指令，所述指令在由所述处理器执行时使所述处理器执行，获取包括用户的第一区域的图像; 从图像中提取颜色特征量或强度梯度特征量; 基于颜色特征量或强度梯度特征量检测第一区域; 以及基于与从多个图像中的第一区域的比较计算出的第一区域的移动速度相关的第一信息来选择检测是使用颜色特征量还是强度梯度特征量来检测第一区域 在不同时间获得

公开(公告)号：US20160224191A1

公开(公告)日：2016-08-04

申请号：US15005146

申请日：2016-01-25

Applicant: FUJITSU LIMITED

Inventor： Kazuki Osamura ,  Taichi Murase ,  Takahiro MATSUDA

IPC: G06F3/042 ,  G06K9/52 ,  G06K9/62 ,  G06K9/00 ,  G06T7/00 ,  G06T7/40 ,  G06K9/46 ,  G06T7/60 ,  G06T5/00

CPC classification number: G06F3/0425 ,  G06K9/00355 ,  G06K9/4652

Abstract: A fingertip position estimation apparatus includes a processor that executes a process. The process includes: identifying a first fingertip position of a finger included in an image, based on a color area model that defines a color of a finger; calculating dimensions of an area that is different from a background of the image, within an area of a prescribed size that is in contact with the first fingertip position and that is positioned in a direction in which a fingertip is pointing; and when the dimensions are larger than a prescribed threshold, estimating a second fingertip position that is positioned away from the first fingertip position in the direction in which the fingertip is pointing.

Abstract translation: 指尖位置估计装置包括执行处理的处理器。 该过程包括：基于定义手指颜色的颜色区域模型来识别包括在图像中的手指的第一指尖位置; 在与第一指尖位置接触并且位于指尖指向方向上的规定尺寸的区域内计算与图像背景不同的区域的尺寸; 并且当所述尺寸大于规定的阈值时，估计在所述指尖指向的方向上位于远离所述第一指尖位置的第二指尖位置。

公开(公告)号：US20130148850A1

公开(公告)日：2013-06-13

申请号：US13667494

申请日：2012-11-02

Applicant: FUJITSU LIMITED

Inventor： Takahiro MATSUDA ,  Koichiro Niinuma

IPC: G06K9/62

CPC classification number: G06F21/32 ,  G06F2221/2139 ,  G06K9/00295 ,  G06K9/00362 ,  G06K9/4642 ,  G06K9/6212 ,  G06K9/66 ,  G06K2009/3291 ,  G06K2009/6213

Abstract: A user detecting apparatus includes: a memory; and a processor that executes a procedure, the procedure including: obtaining a first image and a second image, extracting a user-associated area from the first image according to a given condition, dividing the user-associated area into a plurality of areas, storing a histogram of each of the plurality of areas in the memory, detecting from the second image a corresponding area that corresponds to an area that is one of the plurality of areas and has a first reference histogram according to similarity, and changing a reference histogram used for a third image from the first reference histogram to a second reference histogram.

Abstract translation: 用户检测装置包括：存储器; 以及执行过程的处理器，所述过程包括：获得第一图像和第二图像，根据给定条件从所述第一图像提取用户相关区域，将所述用户相关区域划分为多个区域，存储 所述存储器中的所述多个区域中的每一个的直方图，从所述第二图像检测与所述多个区域中的一个区域对应的对应区域，并且根据相似度具有第一参考直方图，并且改变使用的参考直方图 对于从第一参考直方图到第二参考直方图的第三图像。

公开(公告)号：US20160004386A1

公开(公告)日：2016-01-07

申请号：US14737695

申请日：2015-06-12

Applicant: FUJITSU LIMITED

Inventor： Kazuki OSAMURA ,  Taichi MURASE ,  Takahiro MATSUDA

IPC: G06F3/042 ,  G06T19/00 ,  G06K9/00 ,  G06F3/01

Abstract: A gesture recognition device includes a processor; and a memory which stores a plurality of instructions, which when executed by the processor, cause the processor to execute: acquiring, on a basis of an image of an irradiation region irradiated with projector light, the image being picked up by an image pickup device, first color information representative of color information of a hand region when the projector light is not irradiated on the hand region and second color information representative of color information of the hand region when the projector light is irradiated on the hand region; and extracting, from the image picked up by the image pickup device, a portion of the hand region at which the hand region does not overlap with a touch region irradiated with the projector light on a basis of the first color information and extracting a portion of the hand region.

Abstract translation: 手势识别装置包括处理器; 以及存储器，其存储多个指令，所述指令在由所述处理器执行时使所述处理器执行：基于由投影仪光照射的照射区域的图像，获取由图像拾取装置拾取的图像 当投影仪光不被照射在手区域上时，代表手区域的颜色信息的第一颜色信息和表示投影机光照射在手区域时的手区域的颜色信息的第二颜色信息; 以及根据所述第一颜色信息，从由所述图像拾取装置拾取的图像提取所述手区域的与所述投影仪光照射的触摸区域不重叠的手部区域的一部分，并且提取所述第一颜色信息的一部分 手区。