专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明专利

JP2013109389A Image dictionary generation device, image dictionary generation method and image dictionary generation program 有权
标题翻译：图像词典生成装置，图像词典生成方法和图像词典生成程序
公开(公告)号：JP2013109389A
公开(公告)日：2013-06-06
申请号：JP2011251525
申请日：2011-11-17
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： SUN YONGQING , IRIE TAKESHI , SATO TAKASHI , KOJIMA AKIRA , MORIMOTO MASASHI , SUDO KYOKO
IPC分类号： G06T7/00
摘要： PROBLEM TO BE SOLVED: To accurately generate an image dictionary required when recognizing contents of an image.SOLUTION: An image dictionary generation device includes: means for performing image collection of target domain which is learning data related to a semantic concept which is a word indicating a concept and image collection of origin domain; means for calculating each topic in images of the target domain and the origin domain and outputting image information belonging to information of the calculated topic and the topic; means for associating the topic of the outputted origin domain with the topic of the target domain and outputting information of the associated topic and the image information belonging to the topic; means for synthesizing by fitting image information related to the topic of origin domain for each topic to a feature distribution of image related to the topic of target domain, and outputting the topic information of the target domain and the origin domain and the image information for each topic; means for generating an image dictionary representing the semantic concept from the image information for each topic, and the topic information of the target domain and the origin domain.
摘要翻译：要解决的问题：准确生成识别图像内容时所需的图像字典。图像字典生成装置包括：用于执行目标域的图像采集的装置，该目标域是学习与语义概念相关的数据，该语义概念是指示原始域的概念和图像收集的单词; 用于计算目标域和原始域的图像中的每个主题并输出属于所计算的主题和主题的信息的图像信息的装置; 用于将所输出的原始域的主题与目标域的主题相关联并输出关联的主题的信息和属于该主题的图像信息的装置; 用于通过将与每个主题的原始域的主题相关的图像信息拟合到与目标域的主题相关的图像的特征分布并且输出目标域和源域的主题信息以及每个主题的图像信息来合成的装置话题; 用于从每个主题的图像信息生成表示语义概念的图像字典的装置，以及目标域和原始域的主题信息。版权所有（C）2013，JPO＆INPIT

32. 发明专利

JP2013085156A Video encoding method, video decoding method, video encoder, video decoder, and program of video encoder and video decoder 有权
标题翻译：视频编码方法，视频解码方法，视频编码器，视频解码器和视频编码器和视频解码器的程序
公开(公告)号：JP2013085156A
公开(公告)日：2013-05-09
申请号：JP2011224505
申请日：2011-10-12
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： SHIMIZU SHINYA , KIMATA HIDEAKI , SUGIMOTO SHIORI , KOJIMA AKIRA
IPC分类号： H04N13/00 , H04N19/105 , H04N19/134 , H04N19/136 , H04N19/146 , H04N19/167 , H04N19/176 , H04N19/182 , H04N19/19 , H04N19/196 , H04N19/423 , H04N19/50 , H04N19/503 , H04N19/597 , H04N19/80
摘要： PROBLEM TO BE SOLVED: To improve prediction efficiency when a video is prediction-encoded and to reduce a code amount required for encoding a predictive residual when a depth map to the video of an encoding object can be obtained even in a decoding side.SOLUTION: A reference region setting section 105 sets a plurality of reference regions to a processing region of an encoding object from previously encoded regions. A weight calculation section 106 calculates similarity of the reference region to a processing region for each pixel or a pixel group in the reference region by using a depth map to the processing region and a depth map to the reference region, and sets a weighting coefficient for each pixel or the pixel group in the reference region by using the calculated similarity. A prediction image generation section 107 generates a prediction image by linearly coupling the video signals to the reference region in accordance with the weighting coefficient which is set.
摘要翻译：要解决的问题：为了提高视频被预测编码时的预测效率，并且即使在解码侧也可以获得与编码对象的视频的深度图相关的编码预测残差所需的编码量。解决方案：参考区域设置部分105将多个参考区域设置为来自先前编码区域的编码对象的处理区域。权重计算部分106通过使用到处理区域的深度图和参考区域的深度图来计算参考区域对于参考区域中的每个像素或像素组的处理区域的相似度，并且为通过使用所计算的相似度，参考区域中的每个像素或像素组。预测图像生成部107根据设定的加权系数，将视频信号线性地耦合到基准区域，生成预测图像。版权所有（C）2013，JPO＆INPIT

33. 发明专利

JP2013027025A Arrangement information generator and operation method thereof 审中-公开
标题翻译：装置信息发生器及其操作方法
公开(公告)号：JP2013027025A
公开(公告)日：2013-02-04
申请号：JP2011163279
申请日：2011-07-26
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： SHIMADA SATOSHI , MIYASHITA HIROMU , KOJIMA AKIRA
IPC分类号： H04N7/173 , G06T3/00 , H04N1/387 , H04N5/44
摘要： PROBLEM TO BE SOLVED: To provide an arrangement information generator that generates arrangement information indicating a state in which a plurality of component images are arranged to constitute an entire image, allows a positional relationship between subjects reflected in the individual component images to coincide with an actual positional relationship, and allows the size of each of the component images to coincide with a size according to the importance thereof.SOLUTION: An arrangement information generator 1 includes: a positional relationship calculation section 13 to find a positional relationship when an instructor and material are viewed from the same position; an importance calculation section 14 to calculate importance of each of an instructor image and a material image; and an arrangement information generation section 15 to generate arrangement information indicating a state in which the instructor image and the material image having the size corresponding to the importance are arranged to constitute an entire image, and the instructor image and the material image are arranged to allow the positional relationship between the instructor image and the material image when the entre image is viewed to coincide with the positional relationship between the instructor and the material.
摘要翻译：要解决的问题：为了提供一种布置信息发生器，其产生指示多个分量图像被布置成构成整个图像的状态的布置信息，允许反映在各个分量图像中的被摄体的位置关系一致具有实际的位置关系，并且允许每个分量图像的大小与根据其重要性的大小一致。解决方案：布置信息生成器1包括：位置关系计算部13，用于在从同一位置观看教师和材料时找到位置关系; 重要性计算部分14，用于计算每个教练图像和素材图像的重要性; 以及布置信息生成部15，其生成表示指示者图像和具有与重要性对应的尺寸的素材图像配置为构成整体图像的状态的布置信息，并且指导者图像和素材图像被布置为允许当视觉图像被视为与指导者和材料之间的位置关系一致时，指导者图像与素材图像之间的位置关系。版权所有（C）2013，JPO＆INPIT

34. 发明专利

JP2012256280A Dynamic image processing method, dynamic image processor and dynamic image processing program 有权
标题翻译：动态图像处理方法，动态图像处理器和动态图像处理程序
公开(公告)号：JP2012256280A
公开(公告)日：2012-12-27
申请号：JP2011130010
申请日：2011-06-10
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： TSUTSUGUCHI KEN , KONISHI HIROSHI , MIYASHITA HIROMU , KOJIMA AKIRA
IPC分类号： G06T19/00 , G06T11/20 , G06T17/30
摘要： PROBLEM TO BE SOLVED: To present a dynamic image with vector data.SOLUTION: A dynamic image processing method includes steps of: dividing a closed region with similar color values within a start frame image of dynamic image data into quadrangular curved-surface patches; tracing peaks and control points of the curved-surface patches in chronological order with reference to a frame of the dynamic image data; approximating a locus of the peaks and the control points in a time axis direction by a parametric curve; acquiring each color value corresponding to the peak and the control point of the parametric curve from the frame image of the dynamic image data; and outputting the color value corresponding to each spatiotemporal coordinate value of the peak and the control point of the parametric curve. Accordingly, the dynamic image data can be presented with vector data.
摘要翻译：要解决的问题：使用向量数据呈现动态图像。动态图像处理方法包括以下步骤：将动态图像数据的起始帧图像内的类似颜色值的闭合区域划分为四边形曲面贴片; 参考动态图像数据的帧，按照时间顺序跟踪曲面贴片的峰值和控制点; 通过参数曲线在时间轴方向近似峰值和控制点的轨迹; 从动态图像数据的帧图像获取对应于参数曲线的峰值和控制点的每个颜色值; 并输出与峰值的时空坐标值和参数曲线的控制点对应的颜色值。因此，动态图像数据可以用矢量数据呈现。版权所有（C）2013，JPO＆INPIT

35. 发明专利

JP2012169809A Information presentation device, information presentation method, and information presentation program 审中-公开
标题翻译：信息陈述设备，信息呈现方法和信息呈现程序
公开(公告)号：JP2012169809A
公开(公告)日：2012-09-06
申请号：JP2011028362
申请日：2011-02-14
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： MIYASHITA HIROMU , AZUMA SHOZO , SHIMADA SATOSHI , KOJIMA AKIRA
IPC分类号： H04N5/91 , H04N5/225 , H04N5/232
摘要： PROBLEM TO BE SOLVED: To intelligibly present content information to a user by controlling presentation of the content information in accordance with the state of the user.SOLUTION: An information presentation device 1 for presenting content information comprises: storage means 18 which stores comment information and control information relating to the content information; user state detection means 11 which detects the state of a user; control means 15 which acquires from the storage means 18 the control information corresponding to the state of the user detected by the user state detection means 11 and controls the presentation of the comment information and the content information in accordance with the acquired control information; and presentation means 13 which presents the comment information and the content information in accordance with control by the control means 15.
摘要翻译：要解决的问题：通过根据用户的状态控制内容信息的呈现，可以将内容信息清晰地呈现给用户。解决方案：用于呈现内容信息的信息呈现装置1包括：存储装置18，其存储关于内容信息的注释信息和控制信息; 用户状态检测装置11，其检测用户的状态; 从存储装置18获取与由用户状态检测装置11检测到的用户的状态对应的控制信息的控制装置15，根据获取的控制信息控制评论信息和内容信息的呈现; 以及呈现装置13，其根据控制装置15的控制呈现评论信息和内容信息。版权所有：（C）2012，JPO＆INPIT

36. 发明专利

JP2012019305A Video summarization device, video summarization method and video summarization program 有权
标题翻译：视频总体设计，视频总体方法和视频总结程序
公开(公告)号：JP2012019305A
公开(公告)日：2012-01-26
申请号：JP2010154406
申请日：2010-07-07
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： IRIE TAKESHI , SATO TAKASHI , KOJIMA AKIRA
IPC分类号： H04N5/91 , H04N5/76
摘要： PROBLEM TO BE SOLVED: To provide a video summarization technique for generating a summary video from a plurality of videos.SOLUTION: A video section division part 102 divides an individual video included in a video group as a summary video generation target into video sections. A video section feature amount extraction part 103 extracts a feature amount for each video section. A video section group selection part 104 selects one or more video sections corresponding to a summary generation request accepted. An evaluation function optimization part 105 selects one or more video sections using metadata of the video to which the video section included in a group of the selected video sections belongs or information of the extracted feature amount to find an ordered video sections set, in which a time order of the selected video sections is defined, such that an evaluation value calculated by a predetermined evaluation function with respect to the ordered video sections set is to be maximum. A summary video generation part 106 combines the ordered video sections set to generate a summary video 3.
摘要翻译：要解决的问题：提供用于从多个视频生成摘要视频的视频摘要技术。解决方案：视频部分分割部分102将包括在视频组中的单个视频作为概要视频产生目标划分成视频部分。视频部分特征量提取部分103提取每个视频部分的特征量。视频部分组选择部分104选择对应于接受的摘要生成请求的一个或多个视频部分。评价函数优化部105使用所选择的视频部分的组中包括的视频部分所属的视频的元数据或者提取的特征量的信息来选择一个或多个视频部分，以找到有序的视频部分集合，其中，定义所选择的视频部分的时间顺序，使得通过预定评估函数计算的相对于有序视频部分集合的评估值最大。概要视频生成部分106组合设置的有序视频部分以生成摘要视频3.版权所有（C）2012，JPO和INPIT

37. 发明专利

JP2011254342A Method for editing video, device for editing video, and program for editing video 审中-公开
标题翻译：编辑视频的方法，编辑视频的设备和编辑视频的程序
公开(公告)号：JP2011254342A
公开(公告)日：2011-12-15
申请号：JP2010127416
申请日：2010-06-03
申请人： Nippon Telegr & Teleph Corp , Univ Of Tokyo , 国立大学法人東京大学 , 日本電信電話株式会社
发明人： IRIE TAKESHI , SATO TAKASHI , KOJIMA AKIRA , AIZAWA KIYOHARU , YAMAZAKI TOSHIHIKO
IPC分类号： H04N5/91
摘要： PROBLEM TO BE SOLVED: To automatically create edited video suitable for advertisement video to advertise video of a processing target.SOLUTION: In a method for editing video, a symbol extraction processing part 13 extracts symbols (titles, music) to define video from video 10 of a processing target. Also, an impressive speech interval extraction processing part 14 extracts impressive speech intervals, of which not fitting in the standard speech, from the video 10. An impressive video section extraction processing part 15 extracts impressive video sections from the video 10. A reconstitution processing part 16 combines the symbols, the impressive speech intervals, and the impressive video sections extracted from the video 10, and outputs the combined video as edited video 17.
摘要翻译：要解决的问题：自动创建适合广告视频的编辑视频，以广告处理对象的视频。解决方案：在编辑视频的方法中，符号提取处理部分13从处理对象的视频10中提取用于定义视频的符号（标题，音乐）。此外，令人印象深刻的语音间隔提取处理部分14从视频10中提取不符合标准语音的令人印象深刻的语音间隔。令人印象深刻的视频部分提取处理部分15从视频10中提取令人印象深刻的视频片段。重构处理部分 16组合符号，令人印象深刻的语音间隔和从视频10提取的令人印象深刻的视频部分，并输出作为编辑视频17的组合视频。版权所有（C）2012，JPO＆INPIT

38. 发明专利

JP2011124681A Video editing device, video editing method, and video editing program 有权
标题翻译：视频编辑设备，视频编辑方法和视频编辑程序
公开(公告)号：JP2011124681A
公开(公告)日：2011-06-23
申请号：JP2009279253
申请日：2009-12-09
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： IRIE TAKESHI , SATO TAKASHI , KOJIMA AKIRA
IPC分类号： H04N5/91
摘要： PROBLEM TO BE SOLVED: To automatically generate edited video while taking into consideration context of video to be generated.
SOLUTION: Video is divided into video sections (S202), the likelihood of each semantic content is given from the video feature of each video section and a likelihood model of a semantic content category dictionary (S204). The semantic likelihood is used to cluster the video sections (S205). A semantic change degree of the video is calculated from a connecting relationship as the video is calculated about a representative video section selected from each cluster (S206), a representative video section group to be used for edited video is selected from the semantic change degree of the entire candidate representative video sections (S207), and the edited video is generated (S209).
COPYRIGHT: (C)2011,JPO&INPIT
摘要翻译：要解决的问题：在考虑要生成的视频的上下文的同时自动生成编辑的视频。解决方案：将视频分为视频部分（S202），每个视频部分的视频特征和语义内容类别字典的似然模型给出每个语义内容的可能性（S204）。语义可能性用于对视频片段进行聚类（S205）。从关于从每个集群中选择的代表性视频部分计算视频的连接关系计算视频的语义变化度（S206），从编辑视频中使用的代表性视频部分组从语义变化度生成整个候选代表视频部分（S207）和编辑的视频（S209）。版权所有（C）2011，JPO＆INPIT

39. 发明专利

JP2010186358A Video classification method, device and program 有权
标题翻译：视频分类方法，设备和程序
公开(公告)号：JP2010186358A
公开(公告)日：2010-08-26
申请号：JP2009030659
申请日：2009-02-13
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： HIDAKA KOTA , KOJIMA AKIRA , IRIE TAKESHI
IPC分类号： G06F17/30 , H04N5/76
摘要： PROBLEM TO BE SOLVED: To provide new video classification technology allowing classification of a type of a video without viewing the video. SOLUTION: A viewpoint is placed to "a rising position" of the video and "a rising degree", and a trend indicated by the video of a classification target is classified in point of view of the rising of the video without requesting the viewing of the video of the classification target to classify the type of the video. Specifically, first, a rising portion included in the input video is extracted according to a decision criterion of video portion extraction used for creation of a summary video. Next, by detecting the position of a video main story wherein the extracted rising portion of the video is present, a video feature pattern indicated by the input video is specified. Next, by deciding a preset representative video feature pattern to which the specified video feature pattern corresponds, a class to which the input video belongs is decided. COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：提供新的视频分类技术，允许对视频类型进行分类，而不观看视频。解决方案：将视点置于视频的“上升位置”和“上升度”，并且由分类目标的视频指示的趋势被分类为视频上升的观点，而不请求观看分类目标的视频以对视频的类型进行分类。具体地，首先，根据用于创建概要视频的视频部分提取的判定标准，提取包含在输入视频中的上升部分。接下来，通过检测视频主要故事的位置，其中存在提取的视频的上升部分，由输入视频指示的视频特征图案被指定。接下来，通过确定指定的视频特征图案对应的预设的代表性视频特征图案，确定输入视频所属的类别。版权所有（C）2010，JPO＆INPIT

40. 发明专利

JP2010015469A Still area detection method, and apparatus, program and recording medium therefor 有权
标题翻译：静态区域检测方法及其装置，程序和记录介质
公开(公告)号：JP2010015469A
公开(公告)日：2010-01-21
申请号：JP2008176262
申请日：2008-07-04
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： YAMASHITA KATSUYA , ARAI HIROYUKI , ISO KAZUYUKI , SHINSENJI HISAMI , KOJIMA AKIRA , NAKAZAWA HITOSHI , SUDO KYOKO , KOIKE HIDEKI
IPC分类号： G06T7/20
摘要： PROBLEM TO BE SOLVED: To robustly detect a still area even under conditions with various disturbance factors.
SOLUTION: An initial background creation unit 2 in a still area detection apparatus 10 creates a background image by calculating a weighted mean image by using images acquired from an image input means and creates a threshold image by modeling steady fluctuation by normal distribution. A foreground portion extraction unit 3 calculates a foreground by performing differential calculation between the acquired image and the created background image based on a threshold image. Then, the foreground portion extraction unit 3 calculates a foreground by differential calculation for comparing the acquired image with the created background image by calculating an index value based on the created background image, and then calculates a foreground area by calculating a logical AND of the two foregrounds. A sequential background updating processing unit 5 newly creates background models for an area which is not determined as a foreground by the foreground extraction unit 3 and an area determined as a still area by a still portion evaluation unit 4 by using the acquired images and the created background model.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：即使在各种扰动因素的条件下，也可以强健地检测静止区域。解决方案：静止区域检测装置10中的初始背景创建单元2通过使用从图像输入装置获取的图像计算加权平均图像来创建背景图像，并通过通过正态分布建模稳定波动来创建阈值图像。前景部分提取单元3通过基于阈值图像在所获取的图像和创建的背景图像之间进行差分计算来计算前景。然后，前景部分提取单元3通过差分计算来计算前景，用于通过基于所创建的背景图像计算索引值来比较所获取的图像与创建的背景图像，然后通过计算两者的逻辑AND来计算前景区域重点讲。顺序背景更新处理单元5通过使用所获取的图像新创建由前景提取单元3未被确定为前景的区域的背景模型和由静止部分评估单元4确定为静止区域的区域的背景模型，并且创建背景模型。版权所有（C）2010，JPO＆INPIT

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式