公开(公告)号：WO2012158361A1

公开(公告)日：2012-11-22

申请号：PCT/US2012/036362

申请日：2012-05-03

Applicant: QUALCOMM Incorporated ,  SHARMA, Piyush ,  SWAMINATHAN, Ashwin ,  REZAIIFAR, Ramin ,  XUE, Qi

Inventor： SHARMA, Piyush ,  SWAMINATHAN, Ashwin ,  REZAIIFAR, Ramin ,  XUE, Qi

IPC: G06T7/00 ,  G06K9/00

CPC classification number: G06K9/00234 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/30201

Abstract: A three-dimensional pose of the head of a subject is determined based on depth data captured in multiple images. The multiple images of the head are captured, e.g., by an RGBD camera. A rotation matrix and translation vector of the pose of the head relative to a reference pose is determined using the depth data. For example, arbitrary feature points on the head may be extracted in each of the multiple images and provided along with corresponding depth data to an Extended Kalman filter with states including a rotation matrix and a translation vector associated with the reference pose for the head and a current orientation and a current position. The three-dimensional pose of the head with respect to the reference pose is then determined based on the rotation matrix and the translation vector.

Abstract translation: 基于在多个图像中捕获的深度数据确定被摄体头部的三维姿态。 头部的多个图像例如通过RGBD照相机被捕获。 使用深度数据确定头部相对于参考姿势的姿态的旋转矩阵和平移向量。 例如，可以在多个图像的每一个中提取头上的任意特征点，并将其与相应的深度数据一起提供给扩展卡尔曼滤波器，该扩展卡尔曼滤波器的状态包括旋转矩阵和与头部的参考姿势相关联的平移向量 当前方向和当前位置。 然后基于旋转矩阵和平移向量来确定头部相对于参考姿势的三维姿态。

公开(公告)号：WO2012034092A8

公开(公告)日：2012-03-15

申请号：PCT/US2011/051109

申请日：2011-09-09

Applicant: QUALCOMM INCORPORATED ,  JIANG, Bolan ,  SWAMINATHAN, Ashwin ,  SPINDOLA, Serafin Diaz ,  AHUJA, Dheeraj ,  SWEET, III, Charles Wheeler

Inventor： JIANG, Bolan ,  SWAMINATHAN, Ashwin ,  SPINDOLA, Serafin Diaz ,  AHUJA, Dheeraj ,  SWEET, III, Charles Wheeler

IPC: G06T7/00

Abstract: A multi-user augmented reality (AR) system operates without a previously acquired common reference by generating a reference image on the fly. The reference image is produced by capturing at least two images of a planar object and using the images to determine a pose (position and orientation) of a first mobile platform with respect to the planar object. Based on the orientation of the mobile platform, an image of the planar object, which may be one of the initial images or a subsequently captured image, is warped to produce the reference image of a front view of the planar object. The reference image may be produced by the mobile platform or by, e.g., a server. Other mobile platforms may determine their pose with respect to the planar object using the reference image to perform a multi-user augmented reality application.

公开(公告)号：WO2012006580A1

公开(公告)日：2012-01-12

申请号：PCT/US2011/043441

申请日：2011-07-08

Applicant: QUALCOMM INCORPORATED ,  BAHETI, Pawan K. ,  SWAMINATHAN, Ashwin ,  SPINDOLA, Serafin Diaz ,  CHARI, Murali Ramaswamy

Inventor： BAHETI, Pawan K. ,  SWAMINATHAN, Ashwin ,  SPINDOLA, Serafin Diaz ,  CHARI, Murali Ramaswamy

IPC: G06K9/46 ,  G06F17/30

CPC classification number: G06K9/4671

Abstract: A database for object recognition is modified based on feedback information received from a mobile platform. The feedback information includes information with respect to an image of an object captured by the mobile platform. The feedback information, for example, may include the image, features extracted from the image, a confidence level for the features, posterior probabilities of the features belonging to an object in the database, GPS information, and heading orientation information. The feedback information may be used to improve the database pruning, add content to the database or update the database compression efficiency. The information feedback to the server by the mobile platform may be determined based on a search of a portion of the database performed by the mobile platform using features extracted from a captured query image.

Abstract translation: 基于从移动平台接收的反馈信息修改用于对象识别的数据库。 反馈信息包括关于由移动平台捕获的对象的图像的信息。 例如，反馈信息可以包括图像，从图像提取的特征，特征的置信水平，属于数据库中的对象的特征的后验概率，GPS信息和航向方向信息。 反馈信息可用于改进数据库修剪，向数据库添加内容或更新数据库压缩效率。 可以基于由移动平台使用从捕获的查询图像提取的特征来执行的数据库的一部分的搜索来确定由移动平台向服务器反馈的信息。

公开(公告)号：WO2011008887A3

公开(公告)日：2011-05-12

申请号：PCT/US2010042019

申请日：2010-07-14

Applicant: QUALCOMM INC ,  SWAMINATHAN ASHWIN ,  NARAYANAN VIDYA ,  JAYARAM RANJITH S

Inventor： SWAMINATHAN ASHWIN ,  NARAYANAN VIDYA ,  JAYARAM RANJITH S

IPC: G06F15/16

CPC classification number: H04L67/16 ,  G06F17/30616 ,  H04L67/104 ,  H04L67/1044

Abstract: Systems and methods are described herein for updating documents in a distributed network. When a new document needs to be added to the network, or when changes are to be made to an existing document, keywords are extracted from the document and used to generate update messages for each keyword. The nodes responsible for each keyword are determined. The individual update messages are consolidated into a composite update messages that is sent to a first node in the network. The first node extracts those portions of the composite message associated with it, and forwards the composite message to a second node in the network.

Abstract translation: 这里描述了用于更新分布式网络中的文档的系统和方法。 当需要将新文档添加到网络中时，或者当对现有文档进行更改时，将从文档中提取关键字，并用于为每个关键字生成更新消息。 确定负责每个关键字的节点。 单独的更新消息被合并到发送到网络中的第一个节点的组合更新消息中。 第一节点提取与其相关联的复合消息的那些部分，并将该复合消息转发到网络中的第二节点。

公开(公告)号：WO2012006579A1

公开(公告)日：2012-01-12

申请号：PCT/US2011/043440

申请日：2011-07-08

Applicant: QUALCOMM INCORPORATED ,  BAHETI, Pawan K. ,  SWAMINATHAN, Ashwin ,  SPINDOLA, Serafin Diaz ,  NING, Xia

Inventor： BAHETI, Pawan K. ,  SWAMINATHAN, Ashwin ,  SPINDOLA, Serafin Diaz ,  NING, Xia

IPC: G06F17/30 ,  G06K9/64 ,  G06K9/62 ,  G06K9/46

CPC classification number: G06F17/30247 ,  G06K9/4676 ,  G06K9/6226 ,  G06K9/6228

Abstract: A database for object recognition is generated by performing at least one of intra-object pruning and inter-object pruning, as well as keypoint clustering and selection. Intra-object pruning removes similar and redundant keypoints within an object and different views of the same object, and may be used to generate and associate a significance value, such as a weight, with respect to remaining keypoint descriptors. Inter-object pruning retains the most informative set of descriptors across different objects, by characterizing the discriminability of the keypoint descriptors for all of the objects and removing keypoint descriptors with a discriminability that is less than a threshold. Additionally, a mobile platform may download a geographically relevant portion of the database and perform object recognition by extracting features from the query image and using determined confidence levels for each query feature during outlier removal.

Abstract translation: 通过执行对象内修剪和对象间修剪以及关键点聚类和选择中的至少一个来生成用于对象识别的数据库。 对象内修剪删除对象内的相似和冗余的关键点以及相同对象的不同视图，并且可以用于生成关联剩余关键点描述符的重要值（例如权重）并将其相关联。 对象间修剪通过表征所有对象的关键点描述符的可区分性并且以小于阈值的区分性去除关键点描述符来保留跨越不同对象的最有用的描述符集合。 此外，移动平台可以下载数据库的地理上相关的部分并且通过从查询图像中提取特征并且在异常值去除期间使用确定的每个查询特征的置信水平来执行对象识别。

公开(公告)号：WO2011008889A2

公开(公告)日：2011-01-20

申请号：PCT/US2010/042021

申请日：2010-07-14

Applicant: QUALCOMM INCORPORATED ,  SWAMINATHAN, Ashwin ,  JAYARAM, Ranjith, S. ,  NARAYANAN, Vidya

Inventor： SWAMINATHAN, Ashwin ,  JAYARAM, Ranjith, S. ,  NARAYANAN, Vidya

CPC classification number: G06F17/30699 ,  G06F17/30675 ,  G06F17/30864 ,  G06F17/30867 ,  H04L67/104 ,  H04L67/1068 ,  H04L67/16

Abstract: Methods and apparatus are described herein for performing AND/OR searching using multiple keywords. A query is received at a first node in a network having multiple keywords. The first node determines a set of documents matching a first of the multiple keywords, and computes an ideal Bloom filter representing those keywords. The first node sends the query and the Bloom filter to a second node, which determines its search results for a second of the multiple keywords in accordance with the Bloom filter.

Abstract translation: 这里描述了使用多个关键字执行AND / OR搜索的方法和设备。 在具有多个关键字的网络中的第一节点处接收查询。 第一节点确定与多个关键字中的第一个相匹配的一组文档，并且计算表示这些关键字的理想布隆过滤器。 第一个节点将查询和Bloom过滤器发送到第二个节点，该节点根据Bloom过滤器确定其多个关键字中的第二个的搜索结果。

公开(公告)号：WO2011008887A2

公开(公告)日：2011-01-20

申请号：PCT/US2010/042019

申请日：2010-07-14

Applicant: QUALCOMM INCORPORATED ,  SWAMINATHAN, Ashwin ,  NARAYANAN, Vidya ,  JAYARAM, Ranjith, S.

Inventor： SWAMINATHAN, Ashwin ,  NARAYANAN, Vidya ,  JAYARAM, Ranjith, S.

CPC classification number: H04L67/16 ,  G06F17/30616 ,  H04L67/104 ,  H04L67/1044

Abstract: Systems and methods are described herein for updating documents in a distributed network. When a new document needs to be added to the network, or when changes are to be made to an existing document, keywords are extracted from the document and used to generate update messages for each keyword. The nodes responsible for each keyword are determined. The individual update messages are consolidated into a composite update messages that is sent to a first node in the network. The first node extracts those portions of the composite message associated with it, and forwards the composite message to a second node in the network.

Abstract translation: 这里描述了用于更新分布式网络中的文档的系统和方法。 当需要将新文档添加到网络中或对现有文档进行更改时，会从文档中提取关键字并用于为每个关键字生成更新消息。 负责每个关键字的节点被确定。 单独的更新消息被合并到复合更新消息中，并发送到网络中的第一个节点。 第一个节点提取与其关联的复合消息的那些部分，并将复合消息转发到网络中的第二个节点。

公开(公告)号：WO2013048641A1

公开(公告)日：2013-04-04

申请号：PCT/US2012/051739

申请日：2012-08-21

Applicant: QUALCOMM INCORPORATED ,  RAMACHANDRAN, Mahesh ,  SWAMINATHAN, Ashwin ,  CHARI, Murali R. ,  DIAZ SPINDOLA, Serafin

Inventor： RAMACHANDRAN, Mahesh ,  SWAMINATHAN, Ashwin ,  CHARI, Murali R. ,  DIAZ SPINDOLA, Serafin

IPC: G06T7/20

CPC classification number: G06T7/2066 ,  G06T7/207 ,  G06T7/269 ,  G06T2207/10016 ,  G06T2207/20016 ,  G06T2207/30244

Abstract: Reference free tracking of position by a mobile platform is performed using images of a planar surface. Tracking is performed optical flow techniques, such as pyramidal Lucas-Kanade optical flow with multiple levels of resolution, where displacement is determined with pixel accuracy at lower resolutions and at sub-pixel accuracy at full resolution, which improves computation time for real time performance. Periodic drift correction is performed by matching features between a current frame and a keyframe. The keyframe may be replaced with the drift corrected current image.

Abstract translation: 使用平面表面的图像来执行移动平台对位置的自由跟踪。 跟踪采用光流技术，如具有多级分辨率的锥形Lucas-Kanade光流，其中以较低分辨率的像素精度和全分辨率的亚像素精度确定位移，从而提高实时性能的计算时间。 通过匹配当前帧和关键帧之间的特征来执行周期漂移校正。 关键帧可以用漂移校正的当前图像代替。

公开(公告)号：WO2012016168A3

公开(公告)日：2012-02-02

申请号：PCT/US2011/045942

申请日：2011-07-29

Applicant: QUALCOMM INCORPORATED ,  BAHETI, Pawan, Kumar ,  VADDADI, Sundeep ,  SWAMINATHAN, Ashwin ,  REZNIK, Yuriy ,  HAMSICI, Onur, C. ,  CHARI, Murali, Ramaswamy ,  HONG, John, H. ,  LEE, Chong, Uk

Inventor： BAHETI, Pawan, Kumar ,  VADDADI, Sundeep ,  SWAMINATHAN, Ashwin ,  REZNIK, Yuriy ,  HAMSICI, Onur, C. ,  CHARI, Murali, Ramaswamy ,  HONG, John, H. ,  LEE, Chong, Uk

IPC: G06K9/46 ,  G06K9/68

Abstract: In one example, an apparatus includes a processor configured to extract a first set of one or more keypoints from a first set of blurred images of a first octave of a received image, calculate a first set of one or more descriptors for the first set of keypoints, receive a confidence value for a result produced by querying a feature descriptor database with the first set of descriptors, wherein the result comprises information describing an identity of an object in the received image, and extract a second set of one or more keypoints from a second set of blurred images of a second octave of the received image when the confidence value does not exceed a confidence threshold. In this manner, the processor may perform incremental feature descriptor extraction, which may improve computational efficiency of object recognition in digital images.

公开(公告)号：WO2011130423A1

公开(公告)日：2011-10-20

申请号：PCT/US2011/032344

申请日：2011-04-13

Applicant: CISCO TECHNOLOGY, INC. ,  SRINIVASAN, Udayakumar ,  SARDAR, Srinivas ,  SWAMINATHAN, Joseph Michaelsamy ,  SWAMINATHAN, Ashwin Deepak

Inventor： SRINIVASAN, Udayakumar ,  SARDAR, Srinivas ,  SWAMINATHAN, Joseph Michaelsamy ,  SWAMINATHAN, Ashwin Deepak

IPC: H04L12/56

CPC classification number: H04L41/0893 ,  H04L49/25 ,  H04L49/65 ,  H04L49/70

Abstract: Techniques are described for specifying a destination of a network policy, such as redirect or span policy, to be a logical set of ports (i.e., ports belonging to a port-profile or a port group) where the members of the set of ports may be added/removed dynamically without requiring any changes to the network policy. Further, a network administrator (or other user) may predefine the destinations for a network policy even before some or all of the destinations are active on a given virtualized system. In such cases, the network policies may go into effect when the required entities become available.

Abstract translation: 描述了用于将网络策略的目的地（例如重定向或跨度策略）指定为逻辑端口集合（即，属于端口简档或端口组的端口）的技术，其中端口组的成员可以 动态添加/删除，而不需要对网络策略进行任何更改。 此外，网络管理员（或其他用户）可以在给定的虚拟化系统上的一些或所有目的地活动之前预定义网络策略的目的地。 在这种情况下，当所需实体可用时，网络策略可能会生效。