公开(公告)号：US20120201468A1

公开(公告)日：2012-08-09

申请号：US13501647

申请日：2010-10-13

申请人： Ryoma Oami ,  Yasufumi Hirakawa ,  Yusuke Takahashi

发明人： Ryoma Oami ,  Yasufumi Hirakawa ,  Yusuke Takahashi

IPC分类号： G06K9/48 ,  G06K9/46

CPC分类号： G06T7/0081 ,  G06F17/30244 ,  G06K9/00228 ,  G06K9/00362 ,  G06K9/00771 ,  G06K9/3241 ,  G06K9/4652 ,  G06K9/52 ,  G06K9/527 ,  G06K9/6215 ,  G06T7/248 ,  G06T2207/30124 ,  G06T2207/30196 ,  G06T2210/16

摘要： A person's region is detected from input video of a surveillance camera; a person's direction in the person's region is determined; the separability of person's clothes is determined to generate clothing segment separation information; furthermore, clothing features representing visual features of person's clothes in the person's region are extracted in consideration of the person's direction and the clothing segment separation information. The person's direction is determined based on a person's face direction, person's motion, and clothing symmetry. The clothing segment separation information is generated based on analysis information regarding a geometrical shape of the person's region and visual segment information representing person's clothing segments which are visible based on the person's region and background prior information. A person is searched out based on a result of matching between a clothing query text, representing a type and a color of person's clothes, and the extracted person's clothing features.

摘要翻译： 从监视摄像机的输入视频中检测到人的区域; 一个人在该地区的方向是确定的; 确定人的衣服的分离性，以产生服装段分离信息; 此外，考虑到该人的方向和服装段分离信息，提取表示该人区域中的衣服的视觉特征的服装特征。 该人的方向是根据人的面部方向，人的动作和衣服的对称性来确定的。 基于关于人的区域的几何形状的分析信息和表示基于该人的区域和背景事先信息可见的人的服装区段的视觉区段信息生成服装区段分离信息。 基于表示人的衣服的类型和颜色的服装查询文本与提取的人的服装特征之间的匹配结果，搜索出人物。

公开(公告)号：US09495754B2

公开(公告)日：2016-11-15

申请号：US14508477

申请日：2014-10-07

申请人： Ryoma Oami ,  Yasufumi Hirakawa ,  Yusuke Takahashi

发明人： Ryoma Oami ,  Yasufumi Hirakawa ,  Yusuke Takahashi

IPC分类号： G06K9/46 ,  G06T7/00 ,  G06K9/00 ,  G06F17/30

CPC分类号： G06T7/0081 ,  G06F17/30244 ,  G06K9/00228 ,  G06K9/00362 ,  G06K9/00771 ,  G06K9/3241 ,  G06K9/4652 ,  G06K9/52 ,  G06K9/527 ,  G06K9/6215 ,  G06T7/248 ,  G06T2207/30124 ,  G06T2207/30196 ,  G06T2210/16

摘要： A person's region is detected from input video of a surveillance camera; a person's direction in the person's region is determined; the separability of person's clothes is determined to generate clothing segment separation information; furthermore, clothing features representing visual features of person's clothes in the person's region are extracted in consideration of the person's direction and the clothing segment separation information. The person's direction is determined based on a person's face direction, person's motion, and clothing symmetry. The clothing segment separation information is generated based on analysis information regarding a geometrical shape of the person's region and visual segment information representing person's clothing segments which are visible based on the person's region and background prior information. A person is searched out based on a result of matching between a clothing query text, representing a type and a color of person's clothes, and the extracted person's clothing features.

摘要翻译： 从监视摄像机的输入视频中检测到人的区域; 一个人在该地区的方向是确定的; 确定人的衣服的分离性，以产生服装段分离信息; 此外，考虑到该人的方向和服装段分离信息，提取表示该人区域中的衣服的视觉特征的服装特征。 该人的方向是根据人的面部方向，人的动作和衣服的对称性来确定的。 基于关于人的区域的几何形状的分析信息和表示基于该人的区域和背景事先信息可见的人的服装区段的视觉区段信息生成服装区段分离信息。 基于表示人的衣服的类型和颜色的服装查询文本与提取的人的服装特征之间的匹配结果，搜索出人物。

公开(公告)号：US08891880B2

公开(公告)日：2014-11-18

申请号：US13501647

申请日：2010-10-13

申请人： Ryoma Oami ,  Yasufumi Hirakawa ,  Yusuke Takahashi

发明人： Ryoma Oami ,  Yasufumi Hirakawa ,  Yusuke Takahashi

IPC分类号： G06K9/34 ,  G06K9/46 ,  G06K9/00

CPC分类号： G06T7/0081 ,  G06F17/30244 ,  G06K9/00228 ,  G06K9/00362 ,  G06K9/00771 ,  G06K9/3241 ,  G06K9/4652 ,  G06K9/52 ,  G06K9/527 ,  G06K9/6215 ,  G06T7/248 ,  G06T2207/30124 ,  G06T2207/30196 ,  G06T2210/16

摘要： A person's region is detected from input video of a surveillance camera; a person's direction in the person's region is determined; the separability of person's clothes is determined to generate clothing segment separation information; furthermore, clothing features representing visual features of person's clothes in the person's region are extracted in consideration of the person's direction and the clothing segment separation information. The person's direction is determined based on a person's face direction, person's motion, and clothing symmetry. The clothing segment separation information is generated based on analysis information regarding a geometrical shape of the person's region and visual segment information representing person's clothing segments which are visible based on the person's region and background prior information. A person is searched out based on a result of matching between a clothing query text, representing a type and a color of person's clothes, and the extracted person's clothing features.

摘要翻译： 从监视摄像机的输入视频中检测到人的区域; 一个人在该地区的方向是确定的; 确定人的衣服的分离性，以产生服装段分离信息; 此外，考虑到该人的方向和服装段分离信息，提取表示该人区域中的衣服的视觉特征的服装特征。 该人的方向是根据人的面部方向，人的动作和衣服的对称性来确定的。 基于关于人的区域的几何形状的分析信息和表示基于该人的区域和背景事先信息可见的人的服装区段的视觉区段信息生成服装区段分离信息。 基于表示人的衣服的类型和颜色的服装查询文本与提取的人的服装特征之间的匹配结果，搜索出人物。

公开(公告)号：US08913873B2

公开(公告)日：2014-12-16

申请号：US13001398

申请日：2009-06-22

申请人： Kota Iwamoto ,  Ryoma Oami ,  Yuzo Senda ,  Takahiro Kimoto ,  Takami Sato ,  Yasufumi Hirakawa

发明人： Kota Iwamoto ,  Ryoma Oami ,  Yuzo Senda ,  Takahiro Kimoto ,  Takami Sato ,  Yasufumi Hirakawa

IPC分类号： H04N9/80 ,  H04N5/93 ,  H04N5/76 ,  G11B27/034 ,  G11B27/28 ,  H04N21/432 ,  H04N19/30 ,  H04N21/44 ,  G11B27/32

CPC分类号： G11B27/28 ,  G11B27/034 ,  G11B27/329 ,  H04N5/76 ,  H04N19/15 ,  H04N19/30 ,  H04N21/4325 ,  H04N21/44008

摘要： Provided is a content reproduction control system equipped with: a signal characterizing quantity sequence extraction means that, for each content item stored in a content group storage unit that stores at least more than one content item, extracts a signal characterizing quantity sequence which is the sequence of the signal characterizing quantities associated with the content positions on the time axis; a common section group detection means that detects, as a common section group in the signal characterizing quantity sequence for each content item, a common section group for which the signal characterizing quantities for different content items are similar to each other; a content reproduction quality information collection means that, for each common section group, collects content reproduction quality information which indicates the reproduction quality of the content to which each common section of a common section group belongs; and a content reproduction control means that, when the content contained in the content group storage unit is reproduced, switches the content reproduced for the content to be reproduced for the sections included in the common section group and performs reproduction such that the reproduction quality of the content will be higher, based on the content reproduction quality information for the content to which each common section of a common section group belongs.

摘要翻译： 提供一种内容再现控制系统，其具备：信号特征量序列提取装置，对于存储在存储至少多于一个内容项目的内容组存储单元中的每个内容项目，提取作为所述序列的信号表征量序列 与时间轴上的内容位置相关联的信号表征量; 公共部分组检测装置，检测用于每个内容项目的信号特征量序列中的公共部分组，用于不同内容项目的信号特征量彼此相似的公共部分组; 内容再现质量信息收集意味着，对于每个公共部分组，收集指示公共部分组的每个公共部分所属的内容的再现质量的内容再现质量信息; 并且内容再现控制装置，当再现包含在内容组存储单元中的内容时，切换为包含在共同部分组中的部分将被再现的内容再现的内容，并进行再现，使得再现 基于公共部分组的每个公共部分所属的内容的内容再现质量信息，内容将更高。

公开(公告)号：US20110153609A1

公开(公告)日：2011-06-23

申请号：US13001369

申请日：2009-06-16

申请人： Ryoma Oami ,  Kota Iwamoto ,  Takami Sato ,  Yasufumi Hirakawa ,  Yuzo Senda ,  Takahiro Kimoto

发明人： Ryoma Oami ,  Kota Iwamoto ,  Takami Sato ,  Yasufumi Hirakawa ,  Yuzo Senda ,  Takahiro Kimoto

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06Q30/02 ,  G10L15/02

摘要： A system for determining content topicality comprises a feature value extracting means which extracts feature values of a plurality of contents from the contents; a content grouping means which compares the feature values of the plurality of contents extracted by the feature value extracting means, obtains identical contents and derived contents created using the contents, both of which are included in the plurality of contents, and groups the identical/derived contents, thereby computing identical/derived content grouping information; and a topicality determining means which totals viewing frequencies of the contents determined to be the identical/derived contents from viewing history information and the identical/derived content grouping information relating to the plurality of contents, computes total viewing frequencies of each of the identical/derived contents, and determines the topicality of the identical/derived contents according to the total viewing frequency.

摘要翻译： 一种用于确定内容话题的系统，包括从内容中提取多个内容的特征值的特征值提取装置; 一种内容分组装置，其比较由特征值提取装置提取的多个内容的特征值，获得使用内容创建的相同内容和派生内容，两者都包括在多个内容中，并将相同/派生的 内容，从而计算相同/派生的内容分组信息; 以及主题确定装置，其从观看历史信息和与多个内容相关的相同/导出的内容分组信息总计确定为相同/派生内容的内容的观看频率，计算每个相同/派生的总观看频率 内容，并根据总观看频率确定相同/派生内容的主题。

公开(公告)号：US20110149169A1

公开(公告)日：2011-06-23

申请号：US13001378

申请日：2009-06-16

申请人： Ryoma Oami ,  Kota Iwamoto ,  Takami Sato ,  Yasufumi Hirakawa ,  Yuzo Senda ,  Takahiro Kimoto

发明人： Ryoma Oami ,  Kota Iwamoto ,  Takami Sato ,  Yasufumi Hirakawa ,  Yuzo Senda ,  Takahiro Kimoto

IPC分类号： H04N5/38

CPC分类号： H04N5/91 ,  G11B27/034 ,  G11B27/036 ,  G11B27/105 ,  G11B2220/2516 ,  H04N7/17318 ,  H04N9/7921 ,  H04N9/8205 ,  H04N21/4622 ,  H04N21/482 ,  H04N21/4828 ,  H04N21/6125 ,  H04N21/8456

摘要： A high-quality content generating system provided with a feature amount extracting means for extracting the feature amounts of a plurality of pieces of content therefrom, a content grouping means for performing matching between the feature amounts of the plurality of pieces of content extracted by the feature amount extracting means, grouping the same content included in the plurality of pieces of content and the derived content produced by using the same content, and calculating same/derived content grouping information, and a high-quality content generating means for selecting pieces of content to be grouped by the same/derived content grouping information from the plurality of pieces of content and generating content with higher quality by using the selected content.

摘要翻译： 一种高质量的内容生成系统，具备提取多条内容的特征量的特征量提取单元，其特征在于，具有从特征量提取的多条内容的特征量之间进行匹配的内容分组单元， 数量提取​​装置，对包含在多条内容中的相同内容和通过使用相同内容产生的导出内容进行分组，并计算相同/导出的内容分组信息;以及高质量内容生成装置，用于选择内容的片段 通过来自多条内容的相同/派生内容分组信息进行分组，并通过使用所选择的内容来产生具有较高质量的内容。

公开(公告)号：US08655147B2

公开(公告)日：2014-02-18

申请号：US13001399

申请日：2009-06-22

申请人： Kota Iwamoto ,  Ryoma Oami ,  Yuzo Senda ,  Takahiro Kimoto ,  Takami Sato ,  Yasufumi Hirakawa

发明人： Kota Iwamoto ,  Ryoma Oami ,  Yuzo Senda ,  Takahiro Kimoto ,  Takami Sato ,  Yasufumi Hirakawa

IPC分类号： H04N9/80

CPC分类号： G11B27/28 ,  G11B27/105 ,  H04N21/4325 ,  H04N21/44008 ,  H04N21/4825 ,  H04N21/858

摘要： A system comprising: a extraction unit that extracts from each content a signal feature series, being a series of signal features caused to correspond to positions on a time axis of the content; a generator for detects mutual similarity sections, being sections in which the signal features for different contents are similar to each other, from said signal feature series for each content, and generates the content to which each mutual similarity section belongs, information for specifying the position of the above mutual similarity section on the time axis of the content, and a link indicative of a correspondence relation of the mutual similarity section as mutual similarity section link information; and a determination unit that determines a reproduction order of the content based upon a relationship of the position of the mutual similarity section on the time axis of the content that said mutual similarity section link information indicates.

摘要翻译： 一种系统，包括：提取单元，从每个内容提取信号特征序列，所述信号特征序列是与所述内容的时间轴上的位置相对应地引起的一系列信号特征; 用于检测相互相似部分的发生器，作为用于不同内容的信号特征的部分彼此相似，用于每个内容的所述信号特征序列，并且生成每个相互相关部分所属的内容，用于指定位置的信息 以及指示相互相似部分作为相互相似性部分链接信息的对应关系的链接; 以及确定单元，其基于所述互相似部分链接信息指示的内容的时间轴上的相互相似部分的位置的关系来确定内容的再现顺序。

公开(公告)号：US08306992B2

公开(公告)日：2012-11-06

申请号：US13001369

申请日：2009-06-16

申请人： Ryoma Oami ,  Kota Iwamoto ,  Takami Sato ,  Yasufumi Hirakawa ,  Yuzo Senda ,  Takahiro Kimoto

发明人： Ryoma Oami ,  Kota Iwamoto ,  Takami Sato ,  Yasufumi Hirakawa ,  Yuzo Senda ,  Takahiro Kimoto

IPC分类号： G06F17/30

CPC分类号： G06Q30/02 ,  G10L15/02

摘要： A system for determining content topicality comprises a feature value extracting means which extracts feature values of a plurality of contents from the contents; a content grouping means which compares the feature values of the plurality of contents extracted by the feature value extracting means, obtains identical contents and derived contents created using the contents, both of which are included in the plurality of contents, and groups the identical/derived contents, thereby computing identical/derived content grouping information; and a topicality determining means which totals viewing frequencies of the contents determined to be the identical/derived contents from viewing history information and the identical/derived content grouping information relating to the plurality of contents, computes total viewing frequencies of each of the identical/derived contents, and determines the topicality of the identical/derived contents according to the total viewing frequency.

摘要翻译： 一种用于确定内容话题的系统，包括从内容中提取多个内容的特征值的特征值提取装置; 一种内容分组装置，其比较由特征值提取装置提取的多个内容的特征值，获得使用内容创建的相同内容和派生内容，两者都包括在多个内容中，并将相同/派生的 内容，从而计算相同/派生的内容分组信息; 以及主题确定装置，其从观看历史信息和与多个内容相关的相同/导出的内容分组信息总计确定为相同/派生内容的内容的观看频率，计算每个相同/派生的总观看频率 内容，并根据总观看频率确定相同/派生内容的主题。

公开(公告)号：US20140193034A1

公开(公告)日：2014-07-10

申请号：US14127872

申请日：2012-05-21

申请人： Ryoma Oami ,  Yasufumi Hirakawa

发明人： Ryoma Oami ,  Yasufumi Hirakawa

IPC分类号： G06K9/46 ,  G06K9/00

CPC分类号： G06K9/46 ,  G06K9/00362 ,  G06K9/209 ,  G06K9/3233 ,  G06T7/73 ,  G06T2207/30196 ,  H04N5/23238

摘要： The present invention accurately detects an object from a video image where large distortion of an image may be generated for covering a wide field of view. An object detection device 1 that detects an object from a camera image captured by a camera having a wide field of view and causing distortion varying according to a position in an image includes: a candidate area selection unit 10 configured to select candidate areas for detecting the object from the camera image, and generate candidate area information identifying the candidate areas, and positional parameter information indicating distances from the center of the camera image to the candidate areas; and an object detection unit 20 configured to select, on the basis of the positional parameter information corresponding to the candidate areas, an object detection system used when detecting the object from the candidate areas, rotate the candidate areas with respect to the center of the camera image in order to unify directions from the candidate areas to the center of the camera image to the same direction, and detect whether or not the object exists in each of the candidate areas, the directions of which being unified.

摘要翻译： 本发明可以从可能产生图像的大失真以覆盖宽视野的视频图像中精确地检测对象。 一种物体检测装置1，其从具有宽视野的摄像机拍摄的摄像机图像中检测出物体，并使根据图像中的位置变化的畸变包括：候选区域选择单元10，被配置为选择用于检测 生成识别候选区域的候补区域信息，以及表示从摄像机图像的中心到候补区域的距离的位置参数信息; 以及对象检测单元20，被配置为基于与候选区域相对应的位置参数信息来选择当从候选区域检测对象时使用的对象检测系统，相对于照相机的中心旋转候选区域 图像，以将从相机图像的候选区域到中心的方向统一到相同方向，并且检测对象是否存在于每个候选区域中，其方向是统一的。

公开(公告)号：US20110123171A1

公开(公告)日：2011-05-26

申请号：US13001398

申请日：2009-06-22

申请人： Kota Iwamoto ,  Ryoma Oami ,  Yuzo Senda ,  Takahiro Kimoto ,  Takami Sato ,  Yasufumi Hirakawa

发明人： Kota Iwamoto ,  Ryoma Oami ,  Yuzo Senda ,  Takahiro Kimoto ,  Takami Sato ,  Yasufumi Hirakawa

IPC分类号： H04N9/80

CPC分类号： G11B27/28 ,  G11B27/034 ,  G11B27/329 ,  H04N5/76 ,  H04N19/15 ,  H04N19/30 ,  H04N21/4325 ,  H04N21/44008

摘要： Provided is a content reproduction control system equipped with: a signal characterizing quantity sequence extraction means that, for each content item stored in a content group storage unit that stores at least more than one content item, extracts a signal characterizing quantity sequence which is the sequence of the signal characterizing quantities associated with the content positions on the time axis; a common section group detection means that detects, as a common section group in the signal characterizing quantity sequence for each content item, a common section group for which the signal characterizing quantities for different content items are similar to each other; a content reproduction quality information collection means that, for each common section group, collects content reproduction quality information which indicates the reproduction quality of the content to which each common section of a common section group belongs; and a content reproduction control means that, when the content contained in the content group storage unit is reproduced, switches the content reproduced for the content to be reproduced for the sections included in the common section group and performs reproduction such that the reproduction quality of the content will be higher, based on the content reproduction quality information for the content to which each common section of a common section group belongs.

摘要翻译： 提供一种内容再现控制系统，其具备：信号特征量序列提取装置，对于存储在存储至少多于一个内容项目的内容组存储单元中的每个内容项目，提取作为所述序列的信号表征量序列 与时间轴上的内容位置相关联的信号表征量; 公共部分组检测装置，检测用于每个内容项目的信号特征量序列中的公共部分组，用于不同内容项目的信号特征量彼此相似的公共部分组; 内容再现质量信息收集意味着，对于每个公共部分组，收集指示公共部分组的每个公共部分所属的内容的再现质量的内容再现质量信息; 并且内容再现控制装置，当再现包含在内容组存储单元中的内容时，切换为包含在共同部分组中的部分将被再现的内容再现的内容，并进行再现，使得再现 基于公共部分组的每个公共部分所属的内容的内容再现质量信息，内容将更高。