公开(公告)号：US20070269107A1

公开(公告)日：2007-11-22

申请号：US11693614

申请日：2007-03-29

申请人： Yoshiaki IWAI ,  Akira Nakamura ,  Weiguo Wu ,  Takayuki Yoshigahara

发明人： Yoshiaki IWAI ,  Akira Nakamura ,  Weiguo Wu ,  Takayuki Yoshigahara

IPC分类号： G06K9/00 ,  G06K9/48

CPC分类号： G06K9/50 ,  G06K9/6211

摘要： Disclosed herein is an object recognition device for recognition of an object that exists in an image, the device including: an edge image creator configured to create an edge image from a target image; a local feature extractor configured to extract a feature of each edge point on an edge image, and determine a base point and a support point from edge points in a local area defined for the edge image; a feature matching unit configured to implement, with reference to a memory, feature matching of a base point and a support point to thereby acquire a matching pair; and a matching pair determiner configured to determine final matching pairs by employing matching pairs having a highest matching cost among matching pairs obtained by the feature matching unit, wherein an object in a target image is identified based on matching pairs determined by the matching pair determiner.

摘要翻译： 这里公开了一种用于识别存在于图像中的对象的对象识别装置，该装置包括：边缘图像创建器，被配置为从目标图像创建边缘图像; 局部特征提取器，被配置为提取边缘图像上的每个边缘点的特征，并且从为边缘图像定义的局部区域中的边缘点确定基点和支持点; 特征匹配单元，被配置为参照存储器实现基点和支持点的特征匹配，从而获取匹配对; 以及匹配对确定器，被配置为通过使用由所述特征匹配单元获得的匹配对中具有最高匹配成本的匹配对来确定最终匹配对，其中，基于由所述匹配对确定器确定的匹配对来识别目标图像中的对象。

公开(公告)号：US20090103814A1

公开(公告)日：2009-04-23

申请号：US12234777

申请日：2008-09-22

申请人： Akira NAKAMURA ,  Yoshiaki IWAI ,  Takayuki YOSHIGAHARA

发明人： Akira NAKAMURA ,  Yoshiaki IWAI ,  Takayuki YOSHIGAHARA

IPC分类号： G06K9/46

CPC分类号： G06K9/4671 ,  G06K9/6203

摘要： An information processing apparatus that compares a query image and a model image and provides support information for discriminating a subject of the model image from a subject of the query image is disclosed. The information processing apparatus includes: a feature point extracting means extracting one or more feature points from the model image; a feature describing means describing features of the one or more feature points extracted by the feature point extracting means; and a discrimination capability value calculating means generating correlation images among the features described by the feature describing means, the extracted model image, and one or more other model images for the one or more feature points extracted by the feature point extracting means, and calculating a discrimination capability value indicating the degree of contribution to discriminating the subject of the model image on the basis of the correlation images.

摘要翻译： 公开了一种信息处理装置，其将查询图像和模型图像进行比较，并且提供用于从所述查询图像的对象识别所述模型图像的对象的支持信息。 该信息处理装置包括：特征点提取装置，从模型图像提取一个或多个特征点; 特征描述用于描述由特征点提取装置提取的一个或多个特征点的特征的装置; 以及识别能力值计算装置，在由特征描述装置描述的特征，提取的模型图像和由特征点提取装置提取的一个或多个特征点的一个或多个其他模型图像之间产生相关图像，并且计算 识别能力值，其指示基于相关图像来区分模型图像的被摄体的贡献程度。

公开(公告)号：US20100208983A1

公开(公告)日：2010-08-19

申请号：US12704001

申请日：2010-02-11

申请人： Yoshiaki IWAI ,  Akira NAKAMURA ,  Takayuki YOSHIGAHARA

发明人： Yoshiaki IWAI ,  Akira NAKAMURA ,  Takayuki YOSHIGAHARA

IPC分类号： G06K9/62 ,  G06K9/46

CPC分类号： G06K9/4671 ,  G06K9/00228

摘要： A learning device includes a feature-point extracting section extracting feature points from a generation image, a feature-point feature-quantity extracting section extracting feature-point feature-quantities representing features of the feature points, a total-feature-quantity generating section generating a total feature quantity represented by a multi-dimensional vector, and an identifier generating section generating an identifier using the total feature quantity and a true label indicating whether or not the generation image is a positive image or a negative image.

摘要翻译： 学习装置包括从生成图像提取特征点的特征点提取部，特征点特征量提取部，提取表示特征点的特征的特征量特征量，生成全部特征量生成部 由多维向量表示的总特征量，以及使用总特征量生成标识符的标识符生成部以及指示生成图像是正图像还是负图像的真实标签。

公开(公告)号：US20110182516A1

公开(公告)日：2011-07-28

申请号：US12963031

申请日：2010-12-08

申请人： Yoshiaki IWAI ,  Shunichi Homma ,  Takayuki Yoshigahara

发明人： Yoshiaki IWAI ,  Shunichi Homma ,  Takayuki Yoshigahara

IPC分类号： G06K9/46

CPC分类号： G06K9/6256 ,  G06K9/4671

摘要： A learning device includes: a feature point extracting unit for extracting a feature point from each of multiple generated images made up of a positive image including an identified object, and a negative image excluding the identified object; a feature point feature amount extracting unit for extracting feature point feature amount representing the feature of the feature point from the generated image; a whole feature amount calculating unit for calculating the whole feature amount representing the feature of the whole generated image based on the feature point feature amount of a feature point existing on a feature point selection range determined based on the multiple generated images, of the generated image range; and an identifier generating unit for generating an identifier based on the whole feature amount of the generated image, and a correct answer label representing whether the generated image is the positive image or the negative image.

摘要翻译： 一种学习装置，包括：特征点提取单元，用于从由包括识别对象的正图像构成的多个生成图像中的每一个提取特征点，以及不包括所识别的对象的负图像; 特征点特征量提取单元，用于从所生成的图像中提取表示特征点的特征的特征点特征量; 整个特征量计算单元，用于基于生成的图像的基于多个生成图像确定的特征点选择范围上存在的特征点的特征点特征量来计算表示整个生成图像的特征的整体特征量 范围; 以及标识符生成单元，用于基于所生成的图像的整体特征量来生成标识符，以及正确的应答标签，其表示生成的图像是正图像还是负像。

公开(公告)号：US20110295778A1

公开(公告)日：2011-12-01

申请号：US13048309

申请日：2011-03-15

申请人： Shunichi HOMMA ,  Yoshiaki IWAI ,  Takayuki YOSHIGAHARA

发明人： Shunichi HOMMA ,  Yoshiaki IWAI ,  Takayuki YOSHIGAHARA

IPC分类号： G06F15/18

CPC分类号： G06K9/6259

摘要： There is provided an information processing apparatus including a data pool generation section which generates an unknown data pool, a learning sample collection section which randomly collects a plurality of learning samples from the unknown data pool, a classifier generation section which generates a plurality of classifiers using the learning samples, an output feature quantity acquisition section which associates with the data, for each piece of the data, a plurality of output values, which are obtained by inputting the data into the plurality of classifiers to identify the data, as an output feature quantity represented in an output feature quantity space different from the feature quantity space, and a classification section which classifies each piece of the data into any one of a predetermined number of the classes based on the output feature quantity.

摘要翻译： 提供了一种信息处理装置，包括：生成未知数据池的数据池生成部，从未知数据池中随机收集多个学习样本的学习样本收集部，生成多个分类器的分类器生成部， 学习样本，与每个数据相关联的输出特征量获取部分，通过将数据输入到多个分类器中以识别数据而获得的多个输出值作为输出特征 在与特征量空间不同的输出特征量空间中表示的数量，以及分类部，其根据输出特征量，将各条数据分类为规定数量的任意一个。

公开(公告)号：US20120215805A1

公开(公告)日：2012-08-23

申请号：US13396911

申请日：2012-02-15

申请人： Shunichi HOMMA ,  Yoshiaki IWAI ,  Jianing WU

发明人： Shunichi HOMMA ,  Yoshiaki IWAI ,  Jianing WU

IPC分类号： G06F17/30

CPC分类号： G06Q30/0625 ,  G06F17/30029 ,  G06F17/30061 ,  G06F17/30864 ,  G06F17/30867 ,  G06Q30/0601 ,  G06Q30/0643

摘要： An information processing apparatus may include a control unit to control display of parts information of a plurality of items, to generate search information according to feedback from a user for the parts information, and to control display of a search result according to the search information.

摘要翻译： 信息处理装置可以包括控制单元，用于控制多个项目的零件信息的显示，根据来自用户对零件信息的反馈生成搜索信息，并且根据搜索信息来控制搜索结果的显示。

公开(公告)号：US20110249899A1

公开(公告)日：2011-10-13

申请号：US13046184

申请日：2011-03-11

申请人： Jianing WU ,  Yoshiaki IWAI ,  Shunichi HOMMA

发明人： Jianing WU ,  Yoshiaki IWAI ,  Shunichi HOMMA

IPC分类号： G06K9/46

CPC分类号： G06K9/6218 ,  G06K9/6211

摘要： A recognition device includes storage unit that stores information of a cluster to which a model feature point belongs; extracting unit that extracts a feature amount of a query feature point; generating unit that determines a first set of the query feature point including a reference point and a dependent point, and generates geometric information; clustering unit that clusters the query feature point; correcting unit that sets up the model feature point as a nearest candidate of the reference point, sets up the model feature point as a nearest candidate of the dependent point, determines whether or not the nearest candidate of the reference point is present, and corrects the model feature point; and similarity degree calculating unit that calculates a similarity degree of the first set and a second set and determines the second set nearest to the first set.

摘要翻译： 识别装置包括存储模型特征点所属的集群的信息的存储单元; 提取单元，其提取查询特征点的特征量; 生成单元，其确定包括参考点和从属点的所述查询特征点的第一组，并生成几何信息; 聚类查询特征点的聚类单元; 将模型特征点设置为参考点的最近候选的校正单元，将模型特征点设置为从属点的最近候选，确定参考点的最近候选是否存在，并校正 模特点; 以及相似度计算单元，其计算第一组和第二组的相似度，并确定最接近第一组的第二组。

公开(公告)号：US20110238212A1

公开(公告)日：2011-09-29

申请号：US13070138

申请日：2011-03-23

申请人： Hirokazu SHIRADO ,  Masakuni NAGANO ,  Wataru KOKUBO ,  Yoshiaki IWAI ,  Satoru SHIMIZU

发明人： Hirokazu SHIRADO ,  Masakuni NAGANO ,  Wataru KOKUBO ,  Yoshiaki IWAI ,  Satoru SHIMIZU

IPC分类号： B25J13/00

CPC分类号： G05D1/0274 ,  A61B5/1112 ,  A61B5/1113 ,  A61H3/06 ,  B25J11/009 ,  G01S19/14 ,  G05D1/0238 ,  G05D1/0246 ,  G05D2201/0206 ,  G06K9/00335 ,  G06K9/00771

摘要： A robot apparatus, method and computer program storage device use a memory that stores cueing point information and user information to assist a user in an external environment. The cueing points are distributed within an environmental map held by the robot apparatus, and when the user is detected by the robot apparatus as approaching a predetermined region within the external environment classified as a cueing point, the robot apparatus reacts by providing a cue to the user. The cue may user-specific, or optionally provided based on a level of care required by the user.

摘要翻译： 机器人装置，方法和计算机程序存储装置使用存储提示点信息和用户信息以在外部环境中帮助用户的存储器。 提示点分布在由机器人装置保持的环境地图中，并且当机器人装置检测到用户接近分类为提示点的外部环境中的预定区域时，机器人装置通过向机器人装置提供提示来进行反应 用户。 提示可以是用户特定的，或者可选地基于用户所要求的关注级别来提供。

公开(公告)号：US20110231018A1

公开(公告)日：2011-09-22

申请号：US13042707

申请日：2011-03-08

申请人： Yoshiaki IWAI ,  Yasuhiro SUTO ,  Kenichiro NAGASAKA ,  Akichika TANAKA ,  Takashi KITO

发明人： Yoshiaki IWAI ,  Yasuhiro SUTO ,  Kenichiro NAGASAKA ,  Akichika TANAKA ,  Takashi KITO

IPC分类号： G05B19/04

CPC分类号： B25J9/1694 ,  B25J9/1664 ,  G05B2219/40393

摘要： Provided is a control apparatus comprising an executing unit for allowing a movable body to perform a predetermined process, a storage unit for storing an environment map of a movable area of the movable body, a detection unit for detecting information on the surroundings of the movable body, an update unit for updating the environment map based on the information on the surroundings of the movable body, which is detected by the detection unit, and an acquisition unit for acquiring instruction information representing an instruction of a user according to user input, wherein the executing unit allows the movable body to perform the process based on the instruction information with reference to the environment map, and the update unit updates the environment map based on the instruction information and the process performed by the movable body based on the instruction information.

摘要翻译： 本发明提供一种控制装置，包括：执行单元，用于允许可移动体执行预定处理;存储单元，用于存储可移动体的可移动区域的环境图;检测单元，用于检测关于可移动体的周围的信息; 更新单元，用于基于由检测单元检测到的关于可移动体周围的信息来更新环境地图;以及获取单元，用于根据用户输入获取表示用户的指令的指示信息，其中， 执行单元允许可移动体基于参考环境图的指令信息执行处理，并且更新单元基于指令信息和基于指令信息的可移动体执行的处理来更新环境地图。