-
1.发明授权Image analysis using coefficient distributions with selective basis feature representation 有权使用具有选择性基函数表示的系数分布的图像分析公开(公告)号：US08861872B2
公开(公告)日：2014-10-14
申请号：US13668886
申请日：2012-11-05
Applicant: Raytheon BBN Technologies Corp.
Inventor： Shiv N. Vitaladevuni , Pradeep Natarajan , Rohit Prasad , Premkumar Natarajan
CPC classification number: G06K9/6267 , G06K9/4671 , G06K9/6249 , G06K2009/4695
Abstract: Distributional information for a set of α vectors is determined using a sparse basis selection approach to representing an input image or video. In some examples, this distributional information is used for a classification task.
Abstract translation: 使用稀疏基础选择方法来确定一组α向量的分布信息来表示输入图像或视频。 在一些示例中，该分配信息用于分类任务。
-
公开(公告)号：US09471886B2
公开(公告)日：2016-10-18
申请号：US14459242
申请日：2014-08-13
Applicant: Raytheon BBN Technologies Corp.
Inventor： Manasvi Tickoo , Devansh Arpit , Xiaodan Zhuang , Walter Andrews , Pradeep Natarajan
CPC classification number: G06N99/005 , G06K9/6235 , G06K2009/6236
Abstract: A method for feature transformation of a data set includes: receiving a data set including original feature samples with corresponding class labels; splitting the data set into a direction optimization set and a training set; using the direction optimization set to calculate an optimum transformation vector that maximizes inter-class separability and minimizes intra-class variance of the feature samples with respect to corresponding class labels; using the optimum transformation vector to transform the rest of the original feature samples of the data set to new feature samples with enhanced discriminative characteristics; and training a classifier using the new feature samples, wherein the method is performed by one or more processors.
Abstract translation: 一种用于数据集的特征变换的方法包括：接收包括具有相应类别标签的原始特征样本的数据集; 将数据集分为方向优化集和训练集; 使用方向优化集来计算最大化类间分离性并使特征样本相对于相应类标签的类内方差最小化的最佳变换向量; 使用最佳变换向量将数据集的其余原始特征样本变换为具有增强的鉴别特征的新特征样本; 并使用新的特征样本训练分类器，其中该方法由一个或多个处理器执行。
-
公开(公告)号：US20140099033A1
公开(公告)日：2014-04-10
申请号：US14046194
申请日：2013-10-04
Applicant: Raytheon BBN Technologies Corp.
Inventor： Pradeep Natarajan , Shuang Wu , Rohit Prasad , Premkumar Natarajan
IPC: G06K9/46
CPC classification number: G06K9/4633 , G06K9/6247
Abstract: An approach to computation of kernel descriptors is accelerated using precomputed tables. In one aspect, a fast algorithm for kernel descriptor computation that takes O(1) operations per pixel in each patch, based on pre-computed kernel values. This speeds up the kernel descriptor features under consideration, to levels that are comparable with D-SIFT and color SIFT, and two orders of magnitude faster than STIP and HoG3D. In some examples, kernel descriptors are applied to extract gradient, flow and texture based features for video analysis. In tests of the approach on a large database of internet videos used in the TRECVID MED 2011 evaluations, the flow based kernel descriptors are up to two orders of magnitude faster than STIP and HoG3D, and also produce significant performance improvements. Further, using features from multiple color planes produces small but consistent gains.
Abstract translation: 使用预先计算的表加速了内核描述符的计算方法。 在一个方面，一种用于内核描述符计算的快速算法，其基于预先计算的内核值在每个补丁中每像素执行O（1）个操作。 这将加速考虑的内核描述符功能，达到与D-SIFT和颜色SIFT相当的水平，比STIP和HoG3D快两个数量级。 在一些示例中，内核描述符被应用于提取用于视频分析的梯度，流和纹理的特征。 在对TRECVID MED 2011评估中使用的大量互联网视频数据库的方法进行测试时，基于流的内核描述符比STIP和HoG3D快两个数量级，并且还可以显着提高性能。 此外，使用来自多个颜色平面的特征产生小但恒定的增益。
-
Patent Agency Ranking
公开(公告)号：US20140126824A1
公开(公告)日：2014-05-08
申请号：US13668582
申请日：2012-11-05
Applicant: Raytheon BBN Technologies Corp.
Inventor： Shiv N. Vitaladevuni , Pradeep Natarajan , Rohit Prasad , Premkumar Natarajan
IPC: G06K9/46
CPC classification number: G06F17/10 , G06F17/16 , G06K9/00711 , G06K9/6247
Abstract: A computationally efficient approach to determining inner products between feature vectors is provided that eliminates or reduces the need for multiplication, and more specifically, provides an efficient and accurate basis selection for techniques such as Orthogonal Matching Pursuit.
Abstract translation: 提供了一种计算有效的方法来确定特征向量之间的内积，消除或减少对乘法的需要，更具体地说，为诸如正交匹配追求的技术提供了有效和准确的基础选择。
-
5.发明申请IMAGE ANALYSIS USING COEFFICIENT DISTRIBUTIONS WITH SELECTIVE BASIS FEATURE REPRESENTATION 有权使用具有选择性基础特征表示的系数分布的图像分析公开(公告)号：US20140126817A1
公开(公告)日：2014-05-08
申请号：US13668886
申请日：2012-11-05
Applicant: Raytheon BBN Technologies Corp.
Inventor： Shiv N. Vitaladevuni , Pradeep Natarajan , Rohit Prasad , Premkumar Natarajan
IPC: G06K9/62
CPC classification number: G06K9/6267 , G06K9/4671 , G06K9/6249 , G06K2009/4695
Abstract: Distributional information for a set of α vectors is determined using a sparse basis selection approach to representing an input image or video. In some examples, this distributional information is used for a classification task.
Abstract translation: 使用稀疏基础选择方法来确定一组α向量的分布信息来表示输入图像或视频。 在一些示例中，该分配信息用于分类任务。
-
公开(公告)号：US09330332B2
公开(公告)日：2016-05-03
申请号：US14046194
申请日：2013-10-04
Applicant: Raytheon BBN Technologies Corp.
Inventor： Pradeep Natarajan , Shuang Wu , Rohit Prasad , Premkumar Natarajan
CPC classification number: G06K9/4633 , G06K9/6247
Abstract: An approach to computation of kernel descriptors is accelerated using precomputed tables. In one aspect, a fast algorithm for kernel descriptor computation that takes O(1) operations per pixel in each patch, based on pre-computed kernel values. This speeds up the kernel descriptor features under consideration, to levels that are comparable with D-SIFT and color SIFT, and two orders of magnitude faster than STIP and HoG3D. In some examples, kernel descriptors are applied to extract gradient, flow and texture based features for video analysis. In tests of the approach on a large database of internet videos used in the TRECVID MED 2011 evaluations, the flow based kernel descriptors are up to two orders of magnitude faster than STIP and HoG3D, and also produce significant performance improvements. Further, using features from multiple color planes produces small but consistent gains.
Abstract translation: 使用预先计算的表加速了内核描述符的计算方法。 在一个方面，一种用于内核描述符计算的快速算法，其基于预先计算的内核值在每个补丁中每像素执行O（1）个操作。 这将加速考虑的内核描述符功能，达到与D-SIFT和颜色SIFT相当的水平，比STIP和HoG3D快两个数量级。 在一些示例中，内核描述符被应用于提取用于视频分析的梯度，流和纹理的特征。 在对TRECVID MED 2011评估中使用的大量互联网视频数据库的方法进行测试时，基于流的内核描述符比STIP和HoG3D快两个数量级，并且还可以显着提高性能。 此外，使用来自多个颜色平面的特征产生小但恒定的增益。
-
公开(公告)号：US20150117766A1
公开(公告)日：2015-04-30
申请号：US14459242
申请日：2014-08-13
Applicant: Raytheon BBN Technologies Corp.
Inventor： Manasvi Tickoo , Devansh Arpit , Xiaodan Zhuang , Walter Andrews , Pradeep Natarajan
CPC classification number: G06N99/005 , G06K9/6235 , G06K2009/6236
Abstract: A method for feature transformation of a data set includes: receiving a data set including original feature samples with corresponding class labels; splitting the data set into a direction optimization set and a training set; using the direction optimization set to calculate an optimum transformation vector that maximizes inter-class separability and minimizes intra-class variance of the feature samples with respect to corresponding class labels; using the optimum transformation vector to transform the rest of the original feature samples of the data set to new feature samples with enhanced discriminative characteristics; and training a classifier using the new feature samples, wherein the method is performed by one or more processors.
Abstract translation: 一种用于数据集的特征变换的方法包括：接收包括具有相应类别标签的原始特征样本的数据集; 将数据集分为方向优化集和训练集; 使用方向优化集来计算最大化类间分离性并使特征样本相对于相应类标签的类内方差最小化的最佳变换向量; 使用最佳变换向量将数据集的其余原始特征样本变换为具有增强的鉴别特征的新特征样本; 并使用新的特征样本训练分类器，其中该方法由一个或多个处理器执行。
-
公开(公告)号：US08953892B2
公开(公告)日：2015-02-10
申请号：US13668582
申请日：2012-11-05
Applicant: Raytheon BBN Technologies Corp.
Inventor： Shiv N. Vitaladevuni , Pradeep Natarajan , Rohit Prasad , Premkumar Natarajan
CPC classification number: G06F17/10 , G06F17/16 , G06K9/00711 , G06K9/6247
Abstract: A computationally efficient approach to determining inner products between feature vectors is provided that eliminates or reduces the need for multiplication, and more specifically, provides an efficient and accurate basis selection for techniques such as Orthogonal Matching Pursuit.
Abstract translation: 提供了一种计算有效的方法来确定特征向量之间的内积，消除或减少对乘法的需要，更具体地说，为诸如正交匹配追求的技术提供了有效和准确的基础选择。
-
-
-
-
-
-
-
Search Results
8
records
(took 0.015 seconds)
