-
公开(公告)号：US20050213818A1
公开(公告)日：2005-09-29
申请号：US10517615
申请日：2004-04-22
申请人： Hirotaka Suzuki , Kohtaro Sabe , Masahiro Fujita
发明人： Hirotaka Suzuki , Kohtaro Sabe , Masahiro Fujita
CPC分类号： G06K9/6212 , G06K9/4609 , G06K9/6211 , G06T7/73
摘要： In an image recognition apparatus (1), feature point extraction sections (10a) and (10b) extract feature points from a model image and an object image. Feature quantity retention sections (11a) and (11b) extract a feature quantity for each of the feature points and retain them along with positional information of the feature points. A feature quantity comparison section (12) compares the feature quantities with each other to calculate the similarity or the dissimilarity and generates a candidate-associated feature point pair having a high possibility of correspondence. A model attitude estimation section (13) repeats an operation of projecting an affine transformation parameter determined by three pairs randomly selected from the candidate-associated feature point pair group onto a parameter space. The model attitude estimation section (13) assumes each member in a cluster having the largest number of members formed in the parameter space to be an inlier. The model attitude estimation section (13) finds the affine transformation parameter according to the least squares estimation using the inlier and outputs a model attitude determined by this affine transformation parameter.
摘要翻译： 在图像识别装置（1）中，特征点提取部（10a）和（10b）从模型图像和对象图像中提取特征点。 特征量保留部分（11a）和（11b）提取每个特征点的特征量并将它们与特征点的位置信息一起保留。 特征量比较部分（12）将特征量彼此进行比较，以计算相似度或相似性，并且生成具有高对应可能性的候选关联特征点对。 模型姿态估计部（13）重复将从候选关联特征点对组中随机选择的三对决定的仿射变换参数投影到参数空间的动作。 模型姿态估计部（13）假设具有在参数空间中形成的最大数量的成员的簇中的每个成员是一个较早的。 模型姿态估计部（13）根据使用该误差的最小二乘估计求出仿射变换参数，并输出由该仿射变换参数确定的模型姿态。
-
12.发明申请公开(公告)号：US20130183022A1
公开(公告)日：2013-07-18
申请号：US13814181
申请日：2011-08-02
申请人： Hirotaka Suzuki , Masato Ito
发明人： Hirotaka Suzuki , Masato Ito
IPC分类号： H04N9/87
CPC分类号： H04N9/87 , G06F17/30796 , G06F17/30843 , G06F17/30852 , G06K9/00718 , G06K2209/27
摘要： The present invention relates to an information processing device, an information processing method, and a program capable of easily adding an annotation to content and providing an application, which utilizes the annotation.A learning device 312 extracts an image feature amount of each frame of an image of learning content and extracts word frequency information regarding a frequency of appearance of each word in a description text describing a content of the image of the learning content as a text feature amount of the description text, and learns an annotation model, which is a multi-stream HMM, by using a multi-stream including the image feature amount and the text feature amount. A browsing control device 314 extracts a scene, which is a group of one or more temporally continuous frames, from target content by using the annotation model and displays representative images of the scenes so as to be arranged in chronological order. The present invention may be applied to a case of adding the annotation to the content, for example.
摘要翻译： 本发明涉及一种信息处理设备，信息处理方法以及能够容易地添加注释到内容并提供应用的程序，该应用利用该注释。 学习装置312提取学习内容的图像的每帧的图像特征量，并且将描述学习内容的图像的内容的描述文本中的每个单词的出现频率的词频信息提取为文本特征量 并且通过使用包括图像特征量和文本特征量的多流来学习作为多流HMM的注释模型。 浏览控制装置314通过使用注释模型从目标内容提取作为一个或多个时间上连续的帧的一个场景，并且以时间顺序排列场景的代表性图像。 例如，本发明可以应用于将注释添加到内容的情况。
-
13.发明授权公开(公告)号：US07840508B2
公开(公告)日：2010-11-23
申请号：US11732807
申请日：2007-04-04
CPC分类号： G06N3/02
摘要： An information processing apparatus includes a storage unit configured to store a node holding dynamics; an input-weight-coefficient adjuster configured to adjust input-weight coefficients on a dimension-by-dimension basis, the input-weight coefficients being weight coefficients for individual dimensions of input data input to input units of the node, the input data being observed time-series data having a plurality of dimensions; and an output-weight-coefficient adjuster configured to adjust output-weight coefficients on a dimension-by-dimension basis, the output-weight coefficients being weight coefficients for individual dimensions of output data having a plurality of dimensions and output from output units of the node.
摘要翻译： 一种信息处理装置，包括：存储单元，被配置为存储保存动态的节点; 输入权重系数调整器，其被配置为在逐个维度的基础上调整输入权重系数，输入权重系数是输入到节点的输入单元的输入数据的各个维度的权重系数，观察到的输入数据 具有多个维度的时间序列数据; 以及输出权重系数调整器，其被配置为在逐个维度的基础上调整输出权重系数，所述输出权重系数是具有多个维度的输出数据的各个维度的权重系数，并且从所述输出单元的输出单元输出 节点。
-
公开(公告)号：US20060056678A1
公开(公告)日：2006-03-16
申请号：US11224154
申请日：2005-09-12
申请人： Fumihide Tanaka , Hiroaki Ogawa , Hirotaka Suzuki , Osamu Hanagata , Tsutomu Sawada , Masato Ito
发明人： Fumihide Tanaka , Hiroaki Ogawa , Hirotaka Suzuki , Osamu Hanagata , Tsutomu Sawada , Masato Ito
IPC分类号： G06K9/00
CPC分类号： G06N3/008
摘要： The present invention provides a robot apparatus that can perform appropriate actions in accordance with the ambient conditions, and a method of controlling the behavior of the robot apparatus. The robot apparatus includes a data-acquiring unit that acquires data, externally and/or internally, a subject-identifying unit that identifies a subject performing an action, by using the data externally acquired, a condition-recognizing unit that recognizes external conditions and/or internal conditions, by using the data externally acquired and/or the data internally acquired, an action-pattern acquiring unit that acquires an action pattern of the subject, by using the data externally acquired, a storage unit that stores action data representing the action of the subject, in association with condition data and subject identification data, the condition data representing conditions external and/or internal of the robot apparatus, and the subject identification data identifying the subject, and an action-performing unit that performs actions, wherein the action-performing unit performs an action represented by the action data stored in the storage unit, in accordance with the identification data and the external and/or internal condition data, when the subject-identifying unit identifies the subject.
摘要翻译： 本发明提供一种能够根据环境条件执行适当动作的机器人装置，以及控制机器人装置的动作的方法。 机器人装置包括数据获取单元，其通过使用外部获取的数据来获取识别执行动作的对象的对象识别单元的外部和/或内部的数据，识别外部条件的条件识别单元和/ 或内部条件，通过使用外部获取的数据和/或内部获取的数据，动作模式获取单元，通过使用外部获取的数据来获取对象的动作模式;存储单元，存储表示动作的动作数据 与条件数据和对象识别数据相关联的条件数据表示机器人装置的外部和/或内部的条件以及标识对象的对象识别数据，以及执行动作的动作执行单元，其中， 动作执行单元根据识别符执行由存储在存储单元中的动作数据表示的动作 阳性数据和外部和/或内部条件数据，当主体识别单元识别对象时。
-
15.发明授权公开(公告)号：US09232205B2
公开(公告)日：2016-01-05
申请号：US13814181
申请日：2011-08-02
申请人： Hirotaka Suzuki , Masato Ito
发明人： Hirotaka Suzuki , Masato Ito
CPC分类号： H04N9/87 , G06F17/30796 , G06F17/30843 , G06F17/30852 , G06K9/00718 , G06K2209/27
摘要： An information processing device, method and a program adds an annotation to content and provides an application which utilizes the annotation. A learning module extracts an image feature amount of each frame of an image of learning content and extracts word frequency information regarding a frequency of appearance of each word in a description text, and learns an annotation models which is a multi-stream Hidden Markov Model (HMM) by using a multi-stream including the image feature amount and the text feature amount. A browsing controller extracts a scene which is a group of one or more temporally continuous frames from target content by using the annotation model and displays representative images of the scenes so as to be arranged in chronological order.
摘要翻译： 信息处理设备，方法和程序向内容添加注释并提供利用注释的应用。 学习模块提取学习内容的图像的每帧的图像特征量，并提取关于描述文本中的每个单词的出现频率的单词频率信息，并且学习作为多流隐马尔可夫模型的注释模型（ HMM）通过使用包括图像特征量和文本特征量的多流。 浏览控制器通过使用注释模型从目标内容中提取作为一个或多个时间上连续的帧的组的场景，并且以时间顺序排列场景的代表性图像。
-
16.发明授权Apparatus and method for embedding recurrent neural networks into the nodes of a self-organizing map 有权将循环神经网络嵌入到自组织图的节点中的装置和方法公开(公告)号：US07672920B2
公开(公告)日：2010-03-02
申请号：US11699428
申请日：2007-01-30
IPC分类号： G06N5/00
CPC分类号： G06K9/00536 , G06K9/00335 , G06N3/0445 , G06N99/005
摘要： A learning system is provided, which includes network storage means for storing a network including a plurality of nodes, each of which holds a dynamics; and learning means for self-organizationally updating the dynamics of the network on the basis of measured time-series data.
摘要翻译： 提供了一种学习系统，其包括用于存储包括多个节点的网络的网络存储装置，每个节点保持动态; 以及基于测量的时间序列数据自组织地更新网络动态的学习手段。
-
公开(公告)号：US20070239644A1
公开(公告)日：2007-10-11
申请号：US11732773
申请日：2007-04-04
IPC分类号： G06N3/00
CPC分类号： G06N99/005 , G06N3/0445 , G06N3/0454 , G06N3/084
摘要： A learning apparatus includes a storage unit configured to store a network formed by a plurality of nodes each holding dynamics; a learning unit configured to learn the dynamics of the network in a self-organizing manner on the basis of observed time-series data; a winner-node determiner configured to determine a winner node, the winner node being a node having dynamics that best match the time-series data; and a weight determiner configured to determine learning weights for the dynamics held by the individual nodes according to distances of the individual nodes from the winner node. The learning unit is configured to learn the dynamics of the network in a self-organizing manner by degrees corresponding to the learning weights.
摘要翻译： 学习装置包括：存储单元，被配置为存储由保持动态的多个节点形成的网络; 学习单元，被配置为基于观察到的时间序列数据以自组织的方式学习网络的动态; 获胜者节点确定器，被配置为确定胜者节点，胜者节点是具有与时间序列数据最佳匹配的动态的节点; 以及权重确定器，被配置为根据各个节点与胜利者节点的距离来确定由各个节点保持的动态的学习权重。 学习单元被配置为以自组织的方式以对应于学习权重的度学习网络的动态。
-
18.发明授权公开(公告)号：US09280709B2
公开(公告)日：2016-03-08
申请号：US13814170
申请日：2011-08-02
申请人： Hirotaka Suzuki , Masato Ito
发明人： Hirotaka Suzuki , Masato Ito
CPC分类号： G06K9/00718 , G06F17/30796 , G06F17/30843 , G06F17/30852 , G06K9/18 , G06K2209/27
摘要： The present invention relates to an information processing device, an information processing method, and a program capable of easily adding an annotation to content.A feature amount extracting unit 21 extracts an image feature amount of each frame of an image of learning content and extracts word frequency information regarding frequency of appearance of each word in a description text describing a content of the image of the learning content (for example, a text of a caption) as a text feature amount of the description text. A model learning unit 22 learns an annotation model, which is a multi-stream HMM, by using an annotation sequence for annotation, which is a multi-stream including the image feature amount of each frame and the text feature amount. The present invention may be applied when adding the annotation to the content such as a television broadcast program, for example.
摘要翻译： 本发明涉及一种信息处理设备，信息处理方法和能够容易地向内容添加注释的程序。 特征量提取单元21提取学习内容的图像的每帧的图像特征量，并且提取关于描述学习内容的图像的内容的描述文本中的每个单词的出现频率的词频信息（例如， 文字的文本）作为描述文本的文本特征量。 模型学习单元22通过使用注释的注释序列来学习作为多流HMM的注释模型，注释序列是包括每个帧的图像特征量和文本特征量的多流。 例如，当将注释添加到诸如电视广播节目的内容时，可以应用本发明。
-
19.发明申请公开(公告)号：US20070239635A1
公开(公告)日：2007-10-11
申请号：US11732807
申请日：2007-04-04
IPC分类号： G06N3/02
CPC分类号： G06N3/02
摘要： An information processing apparatus includes a storage unit configured to store a node holding dynamics; an input-weight-coefficient adjuster configured to adjust input-weight coefficients on a dimension-by-dimension basis, the input-weight coefficients being weight coefficients for individual dimensions of input data input to input units of the node, the input data being observed time-series data having a plurality of dimensions; and an output-weight-coefficient adjuster configured to adjust output-weight coefficients on a dimension-by-dimension basis, the output-weight coefficients being weight coefficients for individual dimensions of output data having a plurality of dimensions and output from output units of the node.
摘要翻译： 一种信息处理装置，包括：存储单元，被配置为存储保存动态的节点; 输入权重系数调整器，其被配置为在逐个维度的基础上调整输入权重系数，输入权重系数是输入到节点的输入单元的输入数据的各个维度的权重系数，观察到的输入数据 具有多个维度的时间序列数据; 以及输出权重系数调整器，其被配置为在逐个维度的基础上调整输出权重系数，所述输出权重系数是具有多个维度的输出数据的各个维度的权重系数，并且从所述输出单元的输出单元输出 节点。
-
20.发明申请公开(公告)号：US20130163860A1
公开(公告)日：2013-06-27
申请号：US13814170
申请日：2011-08-02
申请人： Hirotaka Suzuki , Masato Ito
发明人： Hirotaka Suzuki , Masato Ito
IPC分类号： G06K9/18
CPC分类号： G06K9/00718 , G06F17/30796 , G06F17/30843 , G06F17/30852 , G06K9/18 , G06K2209/27
摘要： The present invention relates to an information processing device, an information processing method, and a program capable of easily adding an annotation to content.A feature amount extracting unit 21 extracts an image feature amount of each frame of an image of learning content and extracts word frequency information regarding frequency of appearance of each word in a description text describing a content of the image of the learning content (for example, a text of a caption) as a text feature amount of the description text. A model learning unit 22 learns an annotation model, which is a multi-stream HMM, by using an annotation sequence for annotation, which is a multi-stream including the image feature amount of each frame and the text feature amount. The present invention may be applied when adding the annotation to the content such as a television broadcast program, for example.
摘要翻译： 本发明涉及一种信息处理设备，信息处理方法和能够容易地向内容添加注释的程序。 特征量提取单元21提取学习内容的图像的每帧的图像特征量，并且提取关于描述学习内容的图像的内容的描述文本中的每个单词的出现频率的词频信息（例如， 文字的文本）作为描述文本的文本特征量。 模型学习单元22通过使用注释的注释序列来学习作为多流HMM的注释模型，注释序列是包括每个帧的图像特征量和文本特征量的多流。 例如，当将注释添加到诸如电视广播节目的内容时，可以应用本发明。
-
-
-
-
-
-
-
-
-
搜索结果
69 条记录 (耗时 0.028 秒)
