公开(公告)号：US20130130705A1

公开(公告)日：2013-05-23

申请号：US13742765

申请日：2013-01-16

Applicant: QUALCOMM Incorporated

Inventor： Binita GUPTA ,  Linbo LI ,  Raghuraman KRISHNAMOORTHI ,  Ashok MANTRAVADI

IPC: H04W72/04

CPC classification number: H04W72/04 ,  H04W72/005

Abstract: Methods and apparatus for RF channel selection in a multi-frequency network. A method includes identifying selected local operations infrastructures (LOIs) and their neighboring LOIs, generating a neighbor description message (NDM) that identifies the selected LOIs and their neighboring LOIs and associates a descrambling sequence identifier with each RF channel of the selected LOIs and their neighboring LOIs, and distributing the NDM over the selected LOIs. An apparatus includes a message decoder to receive an NDM that identifies RF channels of a first LOI and neighboring LOIs, and wherein each RF channel is associated with a descrambling sequence identifier, and processing logic to detect content acquisition failures, determine a list of RF channels and their associated LOIs that carry desired content, and select a selected RF channel that is associated with a selected LOI that carries the most additional content among the associated LOIs.

Abstract translation: 用于多频网络中RF信道选择的方法和装置。 一种方法包括识别所选择的本地操作基础设施（LOI）及其相邻的LOI，生成识别所选择的LOI及其邻近LOI的邻居描述消息（NDM），并将解扰序列标识符与所选择的LOI的每个RF信道及其相邻的 LOI，并在所选LOI上分发NDM。 一种装置包括：消息解码器，用于接收标识第一LOI和相邻LOI的RF信道的NDM，并且其中每个RF信道与解扰序列标识符相关联，以及用于检测内容获取失败的处理逻辑，确定RF信道列表 以及它们相关联的LOI，其携带期望的内容，并且选择与所关联的LOI中携带最多附加内容的所选LOI相关联的所选RF信道。

公开(公告)号：US20190228311A1

公开(公告)日：2019-07-25

申请号：US15877723

申请日：2018-01-23

Applicant: QUALCOMM Incorporated

Inventor： Anthony SARAH ,  Raghuraman KRISHNAMOORTHI

IPC: G06N3/08 ,  G06N3/04

Abstract: An apparatus of operating a computational network is configured to determine a low-rank approximation for one or more layers of the computational network based at least in part on a set of residual targets. A set of candidate rank vectors corresponding to the set of residual targets may be determined. Each of the candidate rank vectors may be evaluated using an objective function. A candidate rank vector may be selected and used to determine the low rank approximation. The computational network may be compressed based on the low-rank approximation. In turn the computational network may be operated using the one or more compressed layers.

公开(公告)号：US20150213325A1

公开(公告)日：2015-07-30

申请号：US14166620

申请日：2014-01-28

Applicant: QUALCOMM Incorporated

Inventor： Raghuraman KRISHNAMOORTHI ,  Bojan VRCELJ

IPC: G06K9/62 ,  G06K9/46 ,  G06T19/00 ,  G06T7/00 ,  G06F17/30

CPC classification number: G06K9/6211 ,  G06F17/30256 ,  G06F17/30268 ,  G06F17/30277 ,  G06K9/4671 ,  G06K9/6255 ,  G06K9/6262 ,  G06T7/0002 ,  G06T19/006 ,  G06T2200/28 ,  G06T2207/10004 ,  H04N2101/00

Abstract: A method of dynamically updating a feature database that contains features corresponding to a known target object includes providing an image, extracting a first set of features from within the captured image, and comparing the first set of features to the features stored in the feature database. If it is determined that the target object is present in the image then at least one of the extracted features of the first set that are not already included in the feature database are added to the feature database.

Abstract translation: 动态地更新包含与已知目标对象相对应的特征的特征数据库的方法包括提供图像，从捕获的图像中提取第一组特征，以及将第一组特征与存储在特征数据库中的特征进行比较。 如果确定目标对象存在于图像中，那么尚未包括在特征数据库中的第一组提取的特征中的至少一个被添加到特征数据库。

公开(公告)号：US20180018946A1

公开(公告)日：2018-01-18

申请号：US15647034

申请日：2017-07-11

Applicant: QUALCOMM Incorporated

Inventor： Edwin Chongwoo PARK ,  Raghuraman KRISHNAMOORTHI ,  Venkat RANGAN ,  Nelson RASQUINHA

IPC: G09G5/38 ,  G06F3/0346 ,  G06K9/00 ,  G06T3/60

CPC classification number: G09G5/38 ,  G06F3/0346 ,  G06K9/00228 ,  G06T3/606 ,  G06T7/74 ,  G06T2207/30201 ,  G09G2340/0492 ,  G09G2354/00 ,  G09G2360/08 ,  G09G2360/12

Abstract: Methods, systems, computer-readable media, and apparatuses for image processing and utilization are presented. In some embodiments, an image containing at a face of a user may be obtained using a mobile device. An orientation of the face of the user within the image may be determined using the mobile device. The orientation of the face of the user may be determined using multiple stages: (a) a rotation stage for controlling a rotation applied to a portion of the image, to generate a portion of rotated image, and (b) an orientation stage for controlling an orientation applied to orientation-specific feature detection performed on the portion of rotated image. The determined orientation of the face of the user may be utilized as a control input to modify a display rotation of the mobile device.

公开(公告)号：US20150095360A1

公开(公告)日：2015-04-02

申请号：US14492976

申请日：2014-09-22

Applicant: QUALCOMM Incorporated

Inventor： Bojan VRCELJ ,  Raghuraman KRISHNAMOORTHI ,  Qi PAN ,  Wonwoo LEE ,  Emilio MAGGIO

IPC: G06F17/30

CPC classification number: G06F16/24 ,  G06F16/444 ,  G06F16/583 ,  G06F16/5854 ,  G06K9/6211 ,  G06K9/6274

Abstract: A method of building a database for an object recognition system includes acquiring several multi-view images of a target object and then extracting a first set of features from the images. One of these extracted features is then selected and a second set of features is determined based on which of the first set of features include both, descriptors that match and keypoint locations that are proximate to the selected feature. If a repeatability of the selected feature is greater than a repeatability threshold and if a discriminability is greater than a discriminability threshold, then at least one derived feature is stored to the database, where the derived single feature is representative of the second set of features.

Abstract translation: 构建用于对象识别系统的数据库的方法包括获取目标对象的多个多视图图像，然后从图像中提取第一组特征。 然后选择这些提取的特征中的一个，并且基于第一组特征中的哪一个包括与所选择的特征相邻的描述符和匹配关键点的位置来确定第二组特征。 如果所选特征的可重复性大于可重复性阈值，并且如果可辨别性大于可识别阈值，则至少一个导出特征被存储到数据库，其中所导出的单个特征代表第二组特征。

公开(公告)号：US20140270344A1

公开(公告)日：2014-09-18

申请号：US13796444

申请日：2013-03-12

Applicant: QUALCOMM INCORPORATED

Inventor： Raghuraman KRISHNAMOORTHI ,  Gary G. McGRATH ,  Bojan VRCELJ

IPC: G06K9/46

CPC classification number: G06K9/46 ,  G06K9/6211 ,  G06K9/6857

Abstract: In one example, a method for exiting an object detection pipeline includes determining, while in the object detection pipeline, a number of features within a first tile of an image, wherein the image consists of a plurality of tiles, performing a matching procedure using at least a subset of the features within the first tile if the number of features within the first tile meets a threshold value, exiting the object detection pipeline if a result of the matching procedure indicates an object is recognized in the image, and presenting the result of the matching procedure.

Abstract translation: 在一个示例中，用于退出对象检测流水线的方法包括在对象检测流水线中确定图像的第一瓦片内的多个特征，其中所述图像由多个瓦片组成，其中使用 如果所述第一瓦片内的特征数目满足阈值，则在所述第一瓦片内的所述特征的至少一部分，如果所述匹配过程的结果指示对象在所述图像中被识别，则退出所述对象检测流水线， 匹配程序。

公开(公告)号：US20190332941A1

公开(公告)日：2019-10-31

申请号：US15962996

申请日：2018-04-25

Applicant: QUALCOMM Incorporated

Inventor： Regan Blythe TOWAL ,  Raghuraman KRISHNAMOORTHI

IPC: G06N3/08 ,  G06N3/063 ,  G06N3/04

Abstract: An apparatus for learning a rank of an artificial neural network is configured to decompose a weight tensor into a first weight tensor and a second weight tensor. A set of rank selection parameters are applied to the first weight tensor and the second weight tensor to truncate the rank of the first weight tensor and the second weight tensor. The set of rank selection parameters are updated simultaneously with the weight tensors by averaging updates calculated for each rank selection parameter of the set of rank selection parameters.

公开(公告)号：US20180260695A1

公开(公告)日：2018-09-13

申请号：US15452449

申请日：2017-03-07

Applicant: QUALCOMM Incorporated

Inventor： Somdeb MAJUMDAR ,  Raghuraman KRISHNAMOORTHI

IPC: G06N3/08

CPC classification number: G06N3/08 ,  G06N3/0454 ,  G06N3/082 ,  G06N3/084

Abstract: A method, a computer-readable medium, and an apparatus for compressing a neural network with an unlabeled data set are provided. The apparatus may generate a first set of consecutive layers for the neural network. The first set of consecutive layers may share inputs with a second set of consecutive layers of the neural network. The apparatus may adjust weights associated with the first set of consecutive layers based on a function the difference between a first set of output values from the first set of consecutive layers and a second set of output values from the second set of consecutive layers in response to the unlabeled data set. The apparatus may remove the second set of consecutive layers from the neural network when the function of the difference between the first set of output values and the second set of output values satisfies a threshold.