中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

93 records (took 0.032 seconds)

    SCALE SPACE NORMALIZATION TECHNIQUE FOR IMPROVED FEATURE DETECTION IN UNIFORM AND NON-UNIFORM ILLUMINATION CHANGES
    53.
    发明公开
    SCALE SPACE NORMALIZATION TECHNIQUE FOR IMPROVED FEATURE DETECTION IN UNIFORM AND NON-UNIFORM ILLUMINATION CHANGES 审中-公开
    秤空间归一化方法对于以均匀的和非均匀的光照变化改进的检测功能

    公开(公告)号：EP2521990A1

    公开(公告)日：2012-11-14

    申请号：EP11700709.6

    申请日：2011-01-08

    Applicant: Qualcomm Incorporated

    Inventor： VADDADI, Sundeep ,  HONG, John H. ,  HAMSICI, Onur C. ,  LEE, Chong U.

    IPC: G06K9/46

    CPC classification number: G06K9/4671

    Abstract: A normalization process is implemented at a difference of scale space to completely or substantially reduce the effect that illumination changes has on feature/keypoint detection in an image. An image may be processed by progressively blurring the image using a smoothening function to generate a smoothened scale space for the image. A difference of scale space may be generated by taking the difference between two different smoothened versions of the image. A normalized difference of scale space image may be generated by dividing the difference of scale space image by a third smoothened version of the image, where the third smoothened version of the image that is as smooth or smoother than the smoothest of the two different smoothened versions of the image. The normalized difference of scale space image may then be used to detect one or more features/keypoints for the image.

    FEATURE MATCHING BY CLUSTERING DETECTED KEYPOINTS IN QUERY AND MODEL IMAGES
    54.
    发明公开
    FEATURE MATCHING BY CLUSTERING DETECTED KEYPOINTS IN QUERY AND MODEL IMAGES 审中-公开
    性能的查明的关键点的集群投票和模型图片的手段平衡

    公开(公告)号：EP2507744A2

    公开(公告)日：2012-10-10

    申请号：EP10788467.8

    申请日：2010-12-02

    Applicant: QUALCOMM Incorporated

    Inventor： VADDADI, Sundeep ,  HONG, John H. ,  HAMSICI, Onur C. ,  REZNIK, Yuriy ,  LEE, Chong U.

    IPC: G06K9/64

    CPC classification number: G06K9/6211

    Abstract: A method for feature matching in image recognition is provided. First, image scaling may be based on a feature distribution across scale spaces for an image to estimate image size/resolution, where peak(s) in the keypoint distribution at different scales is used to track a dominant image scale and roughly track object sizes. Second, instead of using all detected features in an image for feature matching, keypoints may be pruned based on cluster density and/or the scale level in which the keypoints are detected. Keypoints falling within high-density clusters may be preferred over features falling within lower density clusters for purposes of feature matching. Third, inlier-to-outlier keypoint ratios are increased by spatially constraining keypoints into clusters in order to reduce or avoid geometric consistency checking for the image.

    MULTIPLE ACCESS TECHNIQUES FOR A WIRELESS COMMUNICATION MEDIUM
    56.
    发明公开
    MULTIPLE ACCESS TECHNIQUES FOR A WIRELESS COMMUNICATION MEDIUM 有权
    多址方式用于无线通信媒介上

    公开(公告)号：EP2082488A2

    公开(公告)日：2009-07-29

    申请号：EP07864556.1

    申请日：2007-11-16

    Applicant: QUALCOMM Incorporated

    Inventor： EKBAL, Amal ,  LEE, Chong U. ,  JULIAN, David Jonathan

    IPC: H04B1/69

    CPC classification number: H04B1/71632 ,  H04B2201/71636

    Abstract: A multiple access technique for a wireless communication system establishes separate channels by defining different time intervals for different channels. In a transmitted reference system different delay periods may be defined between transmitted reference pulses and associated data pulses for different channels. In addition, a multiple access technique may employ a common reference pulse for multiple channels in a transmitted reference system. Another multiple access technique assigns different pulse repetition periods to different channels. One or more of these techniques may be employed in an ultra-wide band system.

    METHODS AND APPARATUS TO RENDER COLORS TO A BINARY HIGH-DIMENSIONAL OUTPUT DEVICE
    58.
    发明公开
    METHODS AND APPARATUS TO RENDER COLORS TO A BINARY HIGH-DIMENSIONAL OUTPUT DEVICE 审中-公开
    方法和设备来表示颜色上BINARY维输出设备

    公开(公告)号：EP2956924A1

    公开(公告)日：2015-12-23

    申请号：EP14706405.9

    申请日：2014-02-05

    Applicant: Qualcomm Incorporated

    Inventor： ZENG, Huanzhao ,  MA, Jian J. ,  HONG, John H. ,  LEE, Chong U.

    IPC: G09G3/34 ,  G09G3/20 ,  G09G5/06

    CPC classification number: G09G5/06 ,  G09G3/2003 ,  G09G3/2025 ,  G09G3/2044 ,  G09G3/2051 ,  G09G3/2059 ,  G09G3/3466 ,  G09G2340/06

    Abstract: Disclosed are methods and apparatus for color rendering in a binary high-dimensional output device, for example. The methods and apparatus are configured to receive color space data, and then map the received data to an intermediate color space. From this intermediated space, color rendering is performed using a pre-generated number of extended primary colors for temporal modulation. Each of the pre-generated extended primary colors is made up of a combination of at least two subframes with each subframe having a respective primary color. Through use of temporally modulated, pre-generated extended primaries in the color space, the methods and apparatus afford a reduction in the diffusion error for subsequent neighboring pixels yet to be rendered, particularly when using constrained devices such as binary high-dimensional output devices.

    Abstract translation: 本发明公开了在二进制高维输出设备，用于显色性的方法和装置，例如。 这些方法和装置被配置为接收色彩空间的数据，然后在中间颜色空间中的接收到的数据映射。 从该中介空间，显色用的扩展原色时间调制预生成的数目来执行。 所述预生成的扩展基色中的每一个是由至少两个子帧与具有respectivement原色的各子帧的组合。 通过在颜色空间中使用时间调制，预生成的扩展初选的，该方法和装置提供了在扩散误差的减少为后续相邻像素尚未被呈现，特别是当使用受限的设备：诸如二进制高维输出设备。

    ROBUST FEATURE MATCHING FOR VISUAL SEARCH
    60.
    发明公开
    ROBUST FEATURE MATCHING FOR VISUAL SEARCH 审中-公开
    强大的功能平衡可视化搜索

    公开(公告)号：EP2697725A1

    公开(公告)日：2014-02-19

    申请号：EP12718803.5

    申请日：2012-04-13

    Applicant: Qualcomm Incorporated

    Inventor： VADDADI, Sundeep ,  HAMSICI, Onur C. ,  REZNIK, Yuriy ,  HONG, John H. ,  LEE, Chong U.

    IPC: G06F17/30 ,  G06K9/62

    CPC classification number: G06F17/30247 ,  G06K9/62 ,  G06K9/627

    Abstract: Techniques are disclosed for performing robust feature matching for visual search. An apparatus comprising an interface and a feature matching unit may implement these techniques. The interface receives a query feature descriptor. The feature matching unit then computes a distance between a query feature descriptor and reference feature descriptors and determines a first group of the computed distances and a second group of the computed distances in accordance with a clustering algorithm, where this second group of computed distances comprises two or more of the computed distances. The feature matching unit then determines whether the query feature descriptor matches one of the reference feature descriptors associated with a smallest one of the computed distances based on the determined first group and second group of the computed distances.

Patent Agency Ranking