专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08437543B2 Method and device of determining a saliency map for an image 有权
标题翻译：确定图像的显着性图的方法和装置
公开(公告)号：US08437543B2
公开(公告)日：2013-05-07
申请号：US13199303
申请日：2011-08-25
申请人： Christel Chamaret , Fabrice Urban , Brice Follet
发明人： Christel Chamaret , Fabrice Urban , Brice Follet
IPC分类号： G06K9/00
CPC分类号： G06K9/629 , G06K9/00664 , G06K9/4628 , G06K9/4671 , G06K9/726
摘要： The invention proposes a method and a device of determining a saliency map for an image.The proposed method uses a processing device for executing the steps of: selecting one of at least two different predetermined weight sets each associated with the predetermined scene category by determining to which of the predetermined scene categories a scene depicted in the image belongs, each predetermined weight sets comprising weights for color dependent subbands, splitting the image into color dependent frequency subbands and orientation subbands by splitting the image into color components and applying wavelet transformation to each color component, determining early feature maps for the subbands by extracting visual features from the wavelet transforms by a center-surround mechanism based on a Difference of Gaussian, weighting the early feature maps using the selected weight set and fusing the weighted feature maps.
摘要翻译：本发明提出了一种确定图像的显着图的方法和装置。所提出的方法使用处理装置来执行以下步骤：通过确定图像中描绘的场景中的哪个预定场景类别属于哪个预定权重，来选择与预定场景类别相关联的至少两个不同的预定权重集中的一个通过将图像分割成颜色分量并将小波变换应用于每个颜色分量，通过从小波变换中提取视觉特征来确定子带的早期特征图，从而将图像分解为色彩相关的频率子带和取向子带通过基于高斯差的中心环绕机制，使用所选权重集来加权早期特征图并融合加权特征图。

2. 发明申请

US20130028511A1 Method and device of determining a saliency map for an image 有权
标题翻译：确定图像的显着性图的方法和装置
公开(公告)号：US20130028511A1
公开(公告)日：2013-01-31
申请号：US13199303
申请日：2011-08-25
申请人： Christel Chamaret , Fabrice Urban , Brice Follet
发明人： Christel Chamaret , Fabrice Urban , Brice Follet
IPC分类号： G06K9/62
CPC分类号： G06K9/629 , G06K9/00664 , G06K9/4628 , G06K9/4671 , G06K9/726
摘要： The invention proposes a method and a device of determining a saliency map for an image.The proposed method uses a processing device for executing the steps of: selecting one of at least two different predetermined weight sets each associated with the predetermined scene category by determining to which of the predetermined scene categories a scene depicted in the image belongs, each predetermined weight sets comprising weights for colour dependent subbands, splitting the image into colour dependent frequency subbands and orientation subbands by splitting the image into colour components and applying wavelet transformation to each colour component, determining early feature maps for the subbands by extracting visual features from the wavelet transforms by a center-surround mechanism based on a Difference of Gaussian, weighting the early feature maps using the selected weight set and fusing the weighted feature maps.
摘要翻译：本发明提出了一种确定图像的显着图的方法和装置。所提出的方法使用处理装置来执行以下步骤：通过确定图像中描绘的场景中的哪个预定场景类别属于哪个预定权重，来选择与预定场景类别相关联的至少两个不同的预定权重集中的一个通过将图像分割成颜色分量并将小波变换应用于每个颜色分量，通过从小波变换中提取视觉特征来确定子带的早期特征图，从而将图像分解为色彩相关的频率子带和取向子带通过基于高斯差的中心环绕机制，使用所选权重集来加权早期特征图并融合加权特征图。

3. 发明申请

US20100188430A1 Method for image format conversion with insertion of an information banner 有权
标题翻译：插入信息横幅的图像格式转换方法
公开(公告)号：US20100188430A1
公开(公告)日：2010-07-29
申请号：US12586931
申请日：2009-09-30
申请人： Christel Chamaret , Olivier Le Meur , Alexandre Ninassi , Fabrice Urban
发明人： Christel Chamaret , Olivier Le Meur , Alexandre Ninassi , Fabrice Urban
IPC分类号： G09G5/00
CPC分类号： H04N5/44591 , G06T3/40 , H04N5/445 , H04N5/57 , H04N7/0102 , H04N7/0122 , H04N7/165 , H04N21/4312 , H04N21/4314 , H04N21/440272 , H04N21/4728 , H04N21/4886 , H04N21/812
摘要： The present invention relates to a method for image processing to generate, from a source image having a predefined width to height ratio, called initial ratio, and an information banner having predefined width to height ratio, called banner ratio, a final image having a width called final and a height called final and for which the width to height ratio, called final ratio, is different from said initial ratio, comprising the following steps: determine a ratio called useful according to said final ratio and said banner ratio, extract from the source image a part of the image having a width to height ratio equal to the useful ratio, and generate, from the part of the image extracted and the information banner, a final image comprising in juxtaposition an image representative of said extracted image part having a width to height ratio equal to the useful ratio and an image representative of said information banner having a width to height ratio equal to the banner ratio.
摘要翻译：本发明涉及一种用于图像处理的方法，用于从具有预定宽度与高度比的称为初始比的源图像以及称为横幅比的预定宽度与高度比的信息横幅生成具有宽度的最终图像称为最终和称为最终的高度，称为最终比率的宽度与高度之比与所述初始比不同，包括以下步骤：确定根据所述最终比率和所述横幅比率称为有用的比率，从源图像具有与有用比率相等的宽高比的图像的一部分，并且从提取的图像的一部分和信息横幅中生成最终图像，该最终图像包括表示所述提取的图像部分的图像，其具有宽度与高度之比等于有用比率，以及代表所述信息横幅的图像，其宽高比等于横幅比。

4. 发明申请

US20120150849A1 METHOD FOR SELECTING VERSIONS OF A DOCUMENT FROM A PLURALITY OF VERSIONS RECEIVED AFTER A SEARCH, AND RELATED RECEIVER 有权
标题翻译：从搜索后收到的多个版本中选择文档的版本的方法和相关的接收者
公开(公告)号：US20120150849A1
公开(公告)日：2012-06-14
申请号：US13378726
申请日：2010-06-15
申请人： Fabrice Urban , Olivier Le Meur , Christel Chamaret , Alexandre Ninassi , Jean-Claude Chevet
发明人： Fabrice Urban , Olivier Le Meur , Christel Chamaret , Alexandre Ninassi , Jean-Claude Chevet
IPC分类号： G06F17/30
CPC分类号： G06F17/3002 , G06F17/30799 , G06F17/30864 , H04N21/23439
摘要： The present invention pertains to a method for selecting a version of a document. The user inputs an identifier of a document at the level of his receiver connected to at least one communication network, and initiates a search request to receive versions of at least one part of this document. The receiver then receives a plurality of versions of the said document. Each version received is analysed by a plurality of evaluation modules so as to calculate an evaluation value for each version received according to a predetermined criterion. The receiver selects for each of the evaluation modules a version of the document having the best evaluation in respect of this criterion, and displays the identifiers of versions having the best evaluations according to each criterion. The user can then easily select the version for reproduction thereof which best meets a criterion. The invention also relates to a receiver implementing the said method.
摘要翻译：本发明涉及用于选择文档的版本的方法。用户在连接到至少一个通信网络的他的接收者的级别输入文档的标识符，并发起搜索请求以接收该文档的至少一部分的版本。然后，接收器接收所述文档的多个版本。通过多个评估模块分析接收的每个版本，以便根据预定标准计算接收的每个版本的评估值。接收机为每个评估模块选择关于该标准具有最佳评估的文档的版本，并且根据每个标准显示具有最佳评估的版本的标识符。用户可以容易地选择最符合标准的用于再现的版本。本发明还涉及实现所述方法的接收机。

5. 发明申请

US20140232821A1 METHOD AND DEVICE FOR RETARGETING A 3D CONTENT 有权
标题翻译：用于重新设计3D内容的方法和装置
公开(公告)号：US20140232821A1
公开(公告)日：2014-08-21
申请号：US14123213
申请日：2012-05-23
申请人： Christel Chamaret , Fabrice Urban , Thai Quan Huynh-Thu , Jean-Claude Chevet
发明人： Christel Chamaret , Fabrice Urban , Thai Quan Huynh-Thu , Jean-Claude Chevet
IPC分类号： H04N13/00
CPC分类号： H04N13/122 , G06T3/0012 , G06T2207/20132 , H04N13/139
摘要： A method of cropping a 3D content comprising at least a first view and a second view is disclosed that comprises: determining a first saliency map from the first view and a second saliency map from the second view; determining a final cropping window from the first and second saliency maps; and cropping the first view and the second view according to the final cropping window.
摘要翻译：公开了一种裁剪包含至少第一视图和第二视图的3D内容的方法，其包括：从第一视图确定第一显着图和从第二视图确定第二显着图; 从第一和第二显着图确定最终裁剪窗口; 并根据最终裁剪窗口裁剪第一个视图和第二个视图。

6. 发明授权

US09743062B2 Method and device for retargeting a 3D content 有权
公开(公告)号：US09743062B2
公开(公告)日：2017-08-22
申请号：US14123213
申请日：2012-05-23
申请人： Christel Chamaret , Fabrice Urban , Thai Quan Huynh-Thu , Jean-Claude Chevet
发明人： Christel Chamaret , Fabrice Urban , Thai Quan Huynh-Thu , Jean-Claude Chevet
IPC分类号： H04N13/00 , G06T3/00
CPC分类号： H04N13/122 , G06T3/0012 , G06T2207/20132 , H04N13/139
摘要： A method of cropping a 3D content comprising at least a first view and a second view is disclosed that comprises: determining a first saliency map from the first view and a second saliency map from the second view; determining a final cropping window from the first and second saliency maps; and cropping the first view and the second view according to the final cropping window.

7. 发明授权

US09678959B2 Method of selecting versions of a document from a plurality of versions received after a search, and related receiver 有权
公开(公告)号：US09678959B2
公开(公告)日：2017-06-13
申请号：US13378726
申请日：2010-06-15
申请人： Fabrice Urban , Olivier Le Meur , Christel Chamaret , Alexandre Ninassi , Jean-Claude Chevet
发明人： Fabrice Urban , Olivier Le Meur , Christel Chamaret , Alexandre Ninassi , Jean-Claude Chevet
IPC分类号： G06F17/30 , H04N21/2343
CPC分类号： G06F17/3002 , G06F17/30799 , G06F17/30864 , H04N21/23439
摘要： The present invention pertains to a method for selecting a version of a document. The user inputs an identifier of a document at the level of his receiver connected to at least one communication network, and initiates a search request to receive versions of at least one part of this document. The receiver then receives a plurality of versions of the said document. Each version received is analysed by a plurality of evaluation modules so as to calculate an evaluation value for each version received according to a predetermined criterion. The receiver selects for each of the evaluation modules a version of the document having the best evaluation in respect of this criterion, and displays the identifiers of versions having the best evaluations according to each criterion. The user can then easily select the version for reproduction thereof which best meets a criterion. The invention also relates to a receiver implementing the said method.

8. 发明授权

US09641795B2 Method and apparatus for reframing and encoding a video signal 有权
公开(公告)号：US09641795B2
公开(公告)日：2017-05-02
申请号：US14233556
申请日：2012-06-25
申请人： Fabrice Urban , Christel Chamaret , Philippe Guillotel
发明人： Fabrice Urban , Christel Chamaret , Philippe Guillotel
IPC分类号： H04N7/12 , G06F3/00 , H04N7/01 , H04N19/176 , H04N19/196 , H04N19/115 , H04N19/14 , H04N19/154 , H04N19/17 , H04N19/85
CPC分类号： H04N7/01 , H04N19/115 , H04N19/14 , H04N19/154 , H04N19/17 , H04N19/176 , H04N19/196 , H04N19/85
摘要： Reframing is used to re-size an image or video content, e.g. for displaying video signals with a given aspect ratio on a display having a different aspect ratio. Window cropping parameters (position and size over time) are constrained in order to optimise the rate/distortion of the encoded output video signal. Initial reframing is improved by computing a saliency map representing a user attention map which considers the video coding context and by providing a macroblock coding efficiency cost map and then taking the saliency map or a combined saliency/coding cost map into account so that the coding cost for said reframed video signal is smaller than the coding cost for other candidate reframing windows' sizes and positions.

9. 发明授权

US08264602B2 Method for image format conversion with insertion of an information banner 有权
标题翻译：插入信息横幅的图像格式转换方法
公开(公告)号：US08264602B2
公开(公告)日：2012-09-11
申请号：US12586931
申请日：2009-09-30
申请人： Christel Chamaret , Olivier Le Meur , Alexandre Ninassi , Fabrice Urban
发明人： Christel Chamaret , Olivier Le Meur , Alexandre Ninassi , Fabrice Urban
IPC分类号： H04N7/01 , H04N9/74
CPC分类号： H04N5/44591 , G06T3/40 , H04N5/445 , H04N5/57 , H04N7/0102 , H04N7/0122 , H04N7/165 , H04N21/4312 , H04N21/4314 , H04N21/440272 , H04N21/4728 , H04N21/4886 , H04N21/812
摘要： The present invention relates to a method for image processing to generate, from a source image having a predefined width to height ratio, called initial ratio, and an information banner having predefined width to height ratio, called banner ratio, a final image having a width called final and a height called final and for which the width to height ratio, called final ratio, is different from the initial ratio, comprising the following steps: determine a ratio called useful according to the final ratio and the banner ratio, extract from the source image a part of the image having a width to height ratio equal to the useful ratio, and generate, from the part of the image extracted and the information banner, a final image comprising in juxtaposition an image representative of the extracted image part having a width to height ratio equal to the useful ratio and an image representative of the information banner having a width to height ratio equal to the banner ratio.
摘要翻译：本发明涉及一种用于图像处理的方法，用于从具有预定宽度与高度比的称为初始比的源图像以及称为横幅比的预定宽度与高度比的信息横幅生成具有宽度的最终图像称为最终和称为最终的高度，称为最终比率的宽度与高度之比不同于初始比例，包括以下步骤：根据最终比例和横幅比确定称为有用的比例，从源图像具有与有用比率相等的宽高比的图像的一部分，并且从提取的图像的一部分和信息横幅中生成最终图像，该最终图像包括并排表示所提取的图像部分的图像，其具有宽高比等于有用比例，以及表示宽度与高度之比等于横幅比的信息横幅的图像。

10. 发明授权

US08813119B2 Method for inserting an advertising clip into a video sequence and corresponding device 有权
标题翻译：将广告剪辑插入视频序列和相应设备的方法
公开(公告)号：US08813119B2
公开(公告)日：2014-08-19
申请号：US12586422
申请日：2009-09-22
申请人： Olivier Le Meur , Alexandre Ninassi , Fabrice Urban
发明人： Olivier Le Meur , Alexandre Ninassi , Fabrice Urban
IPC分类号： H04N7/10 , H04N7/025
CPC分类号： G11B27/036 , H04N21/23418 , H04N21/23424 , H04N21/44016 , H04N21/812 , H04N21/8455
摘要： The present invention relates to a method for processing pictures intended to insert an advertising clip at a point, called insertion, between two pictures of a sequence of video pictures, called video sequence, comprising the following steps: generating a salience map representing the salience of the video sequence preceding the insertion point, generating, for each advertising clip of a set of advertising clips, a salience map, determining, for each advertising clip of said set of advertising clips, a degree of similarity between the salience map of the video sequence and the salience map of said advertising clip, said degree of similarity being representative of the comparison between the location of the salience zones on both said maps, selecting, among said set of advertising clips, the advertising clip having the highest degree of similarity, and inserting the advertising clip selected into the video sequence at the insertion point.
摘要翻译：本发明涉及一种用于处理图像的方法，所述图像旨在在称为视频序列的视频图像序列的两个图像之间的称为插入的点处插入广告剪辑，包括以下步骤：产生表示显着性的显着性的显着图在插入点之前的视频序列，针对一组广告片段的每个广告片段生成突出图，对于所述一组广告片段的每个广告片段，确定视频序列的显着图之间的相似度以及所述广告剪辑的显示图，所述相似度表示两个所述地图上的显着区域的位置之间的比较，在所述一组广告剪辑中选择具有最高相似度的广告剪辑，以及将所选择的广告剪辑插入到插入点处的视频序列中。

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