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. 发明公开

EP3337163A1 METHOD AND APPARATUS FOR OPTIMAL HOME AMBIENT LIGHTING SELECTION FOR STUDIO GRADED CONTENT 审中-公开
公开(公告)号：EP3337163A1
公开(公告)日：2018-06-20
申请号：EP16306673.1
申请日：2016-12-13
申请人： Thomson Licensing
发明人： ZEPEDA SALVATIERRA, Joaquin , REINHARD, Erik , GUILLOTEL, Philippe
IPC分类号： H04N5/58 , H04N21/84 , H04N21/43 , H04N21/47
CPC分类号： H04N21/84 , H04L12/2816 , H04N5/58 , H04N21/43 , H04N21/47
摘要： Reference lighting data is based on a reference lighting setup from a studio environment, such as a color-grading studio. The reference lighting data is synchronized with video content being processed at the studio. The reference lighting data is available at a viewer location, for example, through concurrent transmission or stored on a disk. The viewer location uses cameras to capture illumination data that is compared to the reference lighting data and a control signal is generated to control lighting at the viewer location. The control signal is synchronized with the video because the reference lighting data is synchronized with the video. In one embodiment, the reference lighting data is also synchronized with events of a game, so that a user playing games in a gaming environment will have his lighting synchronized with video and events of the game. In another embodiment, the reference lighting data is embedded on a disk.

2. 发明公开

EP3301917A1 METHOD AND APPARATUS FOR SPATIAL GUIDED PREDICTION 审中-公开
标题翻译：用于空间引导预测的方法和设备
公开(公告)号：EP3301917A1
公开(公告)日：2018-04-04
申请号：EP16306279.7
申请日：2016-09-30
申请人： Thomson Licensing
发明人： THOREAU, Dominique , TURKAN, Mehmet , ALAIN, Martin , ZEPEDA SALVATIERRA, Joaquin
IPC分类号： H04N19/11 , H04N19/157 , H04N19/186 , H04N19/174 , H04N19/192 , H04N19/593
CPC分类号： H04N19/11 , H04N19/157 , H04N19/174 , H04N19/186 , H04N19/192 , H04N19/593
摘要： A spatial guided prediction technique uses reconstructed pixels of a first component of a digital video image block to determine prediction modes used to recursively build prediction blocks for the other components of the same digital video image block. The technique builds improved predictions resulting in smaller prediction residuals and less bits to code for a given image quality. In one embodiment, the prediction blocks for the subsequent digital video component blocks are built recursively line by line. In another embodiment, the prediction blocks for subsequent digital video component blocks are built recursively column by column.
摘要翻译：空间引导预测技术使用数字视频图像块的第一分量的重建像素来确定用于递归地为同一数字视频图像块的其他分量建立预测块的预测模式。该技术可以提高预测效果，从而减少预测残差，减少编码给定图像质量的比特数。在一个实施例中，用于后续数字视频分量块的预测块是逐行递增地构建的。在另一个实施例中，用于后续数字视频分量块的预测块被逐列递归地构建。

3. 发明公开

EP2859505A1 IMAGE DESCRIPTOR FOR MEDIA CONTENT 审中-公开
标题翻译：图片描述媒体内容
公开(公告)号：EP2859505A1
公开(公告)日：2015-04-15
申请号：EP12726123.8
申请日：2012-06-07
申请人： Thomson Licensing
发明人： ZEPEDA SALVATIERRA, Joaquin , PEREZ, Patrick
IPC分类号： G06K9/46 , G06F17/30
CPC分类号： G06F17/30247 , G06F17/30259 , G06F17/30271 , G06F17/3028 , G06K9/4676
摘要： A method for generating image descriptors for media content of images represented by a set of key-points, fn, is recommended which determines for each key-point of the image, designated as a central key-point, a neighbourhood of other key-points, fml, whose features are expressed relative to those of the central key-point. A sparse photo- geometric descriptor, SPGD, of each key-point in the image being a representation of the geometry and intensity content of a feature and its neighbourhood is provided to perform an efficient image querying for efficient searches. The approach demonstrates that incorporating geometrical constraints in image registration applications does not need to be a computationally demanding operation carried out to refine a query response short-list.

4. 发明公开

EP3166022A1 METHOD AND APPARATUS FOR IMAGE SEARCH USING SPARSIFYING ANALYSIS OPERATORS 审中-公开
标题翻译：使用分散分析算子进行图像搜索的方法和设备
公开(公告)号：EP3166022A1
公开(公告)日：2017-05-10
申请号：EP15306771.5
申请日：2015-11-06
申请人： Thomson Licensing
发明人： BILEN, Cagdas , ZEPEDA SALVATIERRA, Joaquin , PEREZ, Patrick
IPC分类号： G06F17/30
CPC分类号： G06F17/30247
摘要： In a particular implementation, images are represented by feature vectors, whose sparse representations are computed using an analysis operator. The sparse representations of the images are then used to efficiently compute similarity metrics between the images. Using pair-wise constraints where each pair of images is indicated as similar or dissimilar, the analysis operator can be trained for the task of image matching. Using triplet constraints wherein a first image and a second image are indicated as more similar than the first image and a third image are, the analysis operator can be trained for the task of image ranking. The analysis operator can be computed using an optimization problem based on a penalty function and sparsity constraints, or using a multiple layer neural network. The analysis operator can also be used to compute a Mahalanobis metric transformation matrix.
摘要翻译：在特定实现中，图像由特征向量表示，其稀疏表示使用分析操作符来计算。然后使用图像的稀疏表示来有效地计算图像之间的相似性度量。在每对图像被指示为相似或不相似的情况下，使用成对约束，分析操作员可以被训练用于图像匹配的任务。使用三重约束，其中第一图像和第二图像被指示为比第一图像和第三图像更相似，分析操作员可以被训练用于图像排序的任务。可以使用基于惩罚函数和稀疏性约束的优化问题或使用多层神经网络来计算分析算子。分析运算符也可用于计算Mahalanobis度量转换矩阵。

5. 发明公开

EP3166021A1 METHOD AND APPARATUS FOR IMAGE SEARCH USING SPARSIFYING ANALYSIS AND SYNTHESIS OPERATORS 审中-公开
标题翻译：方法和设备图片搜索BY LICHTUNGSANALYSE-和-SYNTHESEOPERATOREN
公开(公告)号：EP3166021A1
公开(公告)日：2017-05-10
申请号：EP15306770.7
申请日：2015-11-06
申请人： Thomson Licensing
发明人： BILEN, Cagdas , ZEPEDA SALVATIERRA, Joaquin , PEREZ, Patrick
IPC分类号： G06F17/30
CPC分类号： G06F17/30247
摘要： In a particular implementation, images are represented by feature vectors, whose sparse representations are computed using an analysis operator. The sparse representations of the images and a synthesis operator are used to efficiently compute similarity metrics between the images. When the sparse representation of the query image is readily available, a symmetric similarity metric is calculated using the sparse representation of the query image and database images. Otherwise, when the sparse representation of the query image is not available, an asymmetric similarity metric can be calculated using the feature vector of the query image and sparse representations of the database images. Given pair-wise constraints or triplet constraints on similarity, the synthesis operator can be computed using an optimization problem based on a penalty function. Also, the synthesis operator can be learned jointly with the analysis operator.
摘要翻译：在具体实施时，图像是由特征向量，谁稀疏表示使用在分析运营商计算为代表。图像和合成操作者的稀疏表示被用于有效地计算图像之间的相似性的指标。当查询图像的稀疏表示是现成的，对称相似性度量是使用查询图像和数据库图像的稀疏表示计算。否则，当查询图像的稀疏表示不可用于非对称相似性量度可以使用查询图像和数据库图像的稀疏表示的特征向量进行计算。基于问题上的罚函数给定的成对约束或约束三重上的相似性，在合成操作者可以利用在优化计算。因此，综合运营商可以共同与分析运营商的经验教训。

6. 发明公开

EP3096243A1 METHODS, SYSTEMS AND APPARATUS FOR AUTOMATIC VIDEO QUERY EXPANSION 审中-公开
标题翻译： VERFAHREN，SYSTEME UND VORRICHTUNG ZUR AUTOMATISCHEN VIDEOABFRAGEERWEITERUNG
公开(公告)号：EP3096243A1
公开(公告)日：2016-11-23
申请号：EP15305780.7
申请日：2015-05-22
申请人： Thomson Licensing
发明人： ZEPEDA SALVATIERRA, Joaquin , BABON, Frédéric
IPC分类号： G06F17/30 , G06K9/62
CPC分类号： G06F17/30784 , G06K9/00711 , G06K9/6254 , G06K9/6293
摘要： The present principles provide methods and systems for searching a plurality of videos, including determing a first classifier based on a search query, a first scored plurality of videos based on the first classifier and a plurality of videos; determining at least a second plurality of features based on the first scored plurality of videos; determining at least a second classifier; determining a fused classifier based on the first classifier and the at least a second classifier; determining a second scored plurality of videos based on the fused classifier and the plurality of videos; where the first plurality of features are determined based on a first search utilizing the search query, the first plurality of features are each of a first type video feature and the at least second plurality of features are each of at least a second type video features; wherein the first type video feature is different than the at least a second type of video feature.
摘要翻译：本原理提供了用于搜索多个视频的方法和系统，包括基于搜索查询来确定第一分类器，基于第一分类器和多个视频确定第一划分的多个视频; 基于所述第一划分的多个视频确定至少第二多个特征; 确定至少第二分类器; 基于所述第一分类器和所述至少第二分类器确定融合分类器; 基于所述融合分类器和所述多个视频确定第二划分的多个视频; 其中基于使用所述搜索查询的第一搜索来确定所述第一多个特征，所述第一多个特征中的每一个都是第一类型视频特征，并且所述至少第二多个特征中的每一个都至少是第二类型的视频特征; 其中所述第一类型视频特征不同于所述至少第二类型的视频特征。

7. 发明公开

EP3029606A3 METHOD AND APPARATUS FOR IMAGE CLASSIFICATION WITH JOINT FEATURE ADAPTATION AND CLASSIFIER LEARNING 审中-公开
标题翻译：方法和装置具有相同特征与调整KLASSIFIZIERERLERNEN图像分类
公开(公告)号：EP3029606A3
公开(公告)日：2016-09-14
申请号：EP15183185.6
申请日：2015-08-31
申请人： Thomson Licensing
发明人： KULKARNI, Praveen Anil , ZEPEDA SALVATIERRA, Joaquin , JURIE, Frédéric
IPC分类号： G06K9/46 , G06K9/62
CPC分类号： G06K9/66 , G06K9/46 , G06K9/4628 , G06K9/6256 , G06K9/6262 , G06K9/6269
摘要： A technique for improving the performance of image classification systems is proposed which consists of learning an adaptation architecture on top of the input features jointly with linear classifiers, e.g., SVM. This adaptation method is agnostic to the type of input feature and applies either to features built using aggregators, e.g., BoW, FV, or to features obtained from the activations or outputs from DCNN layers. The adaptation architecture may be single (shallow) or multi-layered (deep). This technique achieves a higher performance compared to current state of the art classification systems.

8. 发明公开

EP3331325A1 METHOD AND APPARATUS FOR CREATING, DISTRIBUTING AND DYNAMICALLY REPRODUCING ROOM ILLUMINATION EFFECTS 审中-公开
公开(公告)号：EP3331325A1
公开(公告)日：2018-06-06
申请号：EP16306579.0
申请日：2016-11-30
申请人： Thomson Licensing
发明人： GUILLOTEL, Philippe , ALAIN, Martin , REINHARD, Erik , BEGAINT, Jean , THOREAU, Dominique , ZEPEDA SALVATIERRA, Joaquin
IPC分类号： H05B37/02 , H04N9/73
CPC分类号： H05B37/029 , H04N9/73
摘要： A content stream comprising video and synchronized illumination data is based on a reference lighting setup from, for example, the site of the content creation. The content stream is received at a user location where the illumination data controls user lighting that is synchronized with the video data, so that when the video data is displayed the user's lighting is in synchronization with the video. In one embodiment, the illumination data is also synchronized with events of a game, so that a user playing games in a gaming environment will have his lighting synchronized with video and events of the game. In another embodiment, the content stream is embedded on a disk.

9. 发明公开

EP3316578A1 METHOD AND APPARATUS FOR ENCODING AND DECODING A PICTURE 审中-公开
标题翻译：用于编码和解码图片的方法和设备
公开(公告)号：EP3316578A1
公开(公告)日：2018-05-02
申请号：EP16306398.5
申请日：2016-10-25
申请人： Thomson Licensing
发明人： THOREAU, Dominique , ALAIN, Martin , ZEPEDA SALVATIERRA, Joaquin , TURKAN, Mehmet
IPC分类号： H04N19/105 , H04N19/50 , H04N19/147 , H04N19/186 , H04N19/593
CPC分类号： H04N19/147 , H04N19/105 , H04N19/186 , H04N19/50 , H04N19/593
摘要： A method and an apparatus for encoding a picture are disclosed. For at least one block of a picture to encode, a block predictor is determined (22) for a decoded first component (21) of said at least one block, from a reconstructed region of a first component of said picture. At least one second component of said at least one block is then encoded (23) by predicting said at least one second component from a second component of said block predictor. Corresponding decoding method and apparatus are disclosed.
摘要翻译：公开了一种用于对图片进行编码的方法和设备。对于要编码的图片的至少一个块，从所述图片的第一分量的重构区域为所述至少一个块的解码的第一分量（21）确定（22）块预测器。然后通过从所述块预测器的第二分量预测所述至少一个第二分量来编码（23）所述至少一个块的至少一个第二分量。公开了相应的解码方法和设备。

10. 发明公开

EP3251366A1 METHODS, SYSTEMS AND APPARATUS FOR ELECTRO-OPTICAL AND OPTO-ELECTRICAL CONVERSION OF IMAGES AND VIDEO 有权转让
标题翻译：用于图像和视频的电光和光电转换的方法，系统和设备
公开(公告)号：EP3251366A1
公开(公告)日：2017-12-06
申请号：EP16701752.4
申请日：2016-01-26
申请人： Thomson Licensing
发明人： REINHARD, Erik , ANDRIVON, Pierre , BORDES, Philippe , FRANCOIS, Edouard , ZEPEDA SALVATIERRA, Joaquin , CHEVANCE, Christophe , STAUDER, Jürgen , MORVAN, Patrick
IPC分类号： H04N19/70 , H04N19/85 , H04N19/98
CPC分类号： H04N19/98 , G09G2320/0271 , G09G2320/0276 , G09G2370/04 , G09G2370/12 , H04N19/186 , H04N19/70 , H04N19/85
摘要： The present principles are directed to a parameterized OETF/EOTF for processing images and video. The present principles provide a method for encoding a picture, comprising: applying a parameterized transfer function to a luminance (L) signal of the picture to determine a resulting V(L) transformed signal; encoding the resulting V(L); wherein the parameterized transfer function is adjusted based on a plurality of parameters to model one of a plurality of transfer functions. The present principles also provide for a method for decoding a digital picture, the method comprising: receiving the digital picture; applying a parameterized transfer function to the digital picture to determine a luminance (L) signal of the digital picture, the parameterized transfer function being based on a plurality of parameters; wherein the parameterized transfer function is adjusted based on a plurality of parameters to model one of a plurality of transfer functions.

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