知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

15 records (took 0.02 seconds)

    Multi-stage neural network process for keypoint detection in an image
    1.
    发明授权
    Multi-stage neural network process for keypoint detection in an image 有权

    公开(公告)号：US11256956B2

    公开(公告)日：2022-02-22

    申请号：US16700219

    申请日：2019-12-02

    Applicant: QUALCOMM Incorporated

    Inventor： Upal Mahbub ,  Rakesh Nattoji Rajaram ,  Vasudev Bhaskaran

    IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06K9/00

    Abstract: Embodiments include systems and methods for keypoint detection in an image. In embodiments, a processor of a computing device may apply to an image a first neural network that has been trained to define and output a plurality of regions. The processor may apply to each of the plurality of regions a respective second neural network to that has been trained to output a plurality of keypoints in each of the plurality of regions. The processor may apply to the plurality of keypoints a third neural network that has been trained to determine a correction for each of the plurality of keypoints to provide corrected keypoints suitable for the execution of an image processing function.

    METHOD AND APPARATUS OF REDUCING COMPRESSION NOISE IN DIGITAL VIDEO STREAMS
    3.
    发明申请
    METHOD AND APPARATUS OF REDUCING COMPRESSION NOISE IN DIGITAL VIDEO STREAMS 审中-公开
    减少压缩噪声在数字视频流中的方法和装置

    公开(公告)号：US20140192266A1

    公开(公告)日：2014-07-10

    申请号：US13734667

    申请日：2013-01-04

    Applicant: Qualcomm Incorporated

    Inventor： Mainak Biswas ,  Vasudev Bhaskaran ,  Sujith Srinivasan

    IPC: H04N5/21

    CPC classification number: H04N5/21 ,  H04N19/117 ,  H04N19/14 ,  H04N19/176 ,  H04N19/86 ,  H04N19/865

    Abstract: Method and apparatus for reducing random noise in digital video streams are described. In one innovative aspect, a device for reducing noise of a video stream is provided. The device includes a ringing noise detector configured to identify ringing noise in an image included in the video stream. The device further includes a block detector configured to identify a block pattern in the image included in the video stream, the block detector configured to identify block patterns of a predetermined size and block patterns of an arbitrary size. The device also includes a noise reducer configured to filter the image based on the identified ringing noise and the block pattern.

    Abstract translation: 描述了用于减少数字视频流中随机噪声的方法和装置。 在一个创新的方面，提供了用于降低视频流的噪声的设备。 该装置包括配置成识别包含在视频流中的图像中的振铃噪声的振铃噪声检测器。 该装置还包括块检测器，其被配置为识别包括在视频流中的图像中的块图案，块检测器被配置为识别预定大小的块图案和任意大小的块图案。 该装置还包括被配置为基于所识别的振铃噪声和块图案来对图像进行滤波的降噪器。

    MULTIVIEW SYNTHESIS AND PROCESSING SYSTEMS AND METHODS
    4.
    发明申请
    MULTIVIEW SYNTHESIS AND PROCESSING SYSTEMS AND METHODS 审中-公开
    综合与处理系统与方法

    公开(公告)号：US20140098100A1

    公开(公告)日：2014-04-10

    申请号：US14046858

    申请日：2013-10-04

    Applicant: Qualcomm Incorporated

    Inventor： Gokce Dane ,  Vasudev Bhaskaran

    IPC: G06T15/20 ,  H04N13/04 ,  H04N13/00

    CPC classification number: G06T15/20 ,  H04N13/111 ,  H04N13/271 ,  H04N13/282 ,  H04N13/302 ,  H04N2213/005

    Abstract: Certain embodiments relate to systems and methods for presenting an autostereoscopic, 3-dimensional image to a user. The system may comprise a view rendering module to generate multi-view autostereoscopic images from a limited number of reference views, enabling users to view the content from different angles without the need of glasses. Some embodiments may employ two or more reference views to generate virtual reference views and provide high quality stereoscopic images. Certain embodiments may use a combination of disparity-based depth map processing, view interpolation and smart blending of virtual views, artifact reduction, depth cluster guided hole filling, and post-processing of synthesized views.

    Abstract translation: 某些实施例涉及用于向用户呈现自动立体3维图像的系统和方法。 该系统可以包括视图呈现模块，用于从有限数量的参考视图生成多视图自动立体图像，使得用户能够从不同角度观看内容而不需要眼镜。 一些实施例可以采用两个或更多个参考视图来生成虚拟参考视图并提供高质量的立体图像。 某些实施例可以使用基于视差的深度图处理，视图插值和虚拟视图的智能混合，伪像减少，深度簇引导孔填充和合成视图的后处理的组合。

    Systems and methods for non-obstacle area detection
    5.
    发明授权
    Systems and methods for non-obstacle area detection 有权

    公开(公告)号：US10395377B2

    公开(公告)日：2019-08-27

    申请号：US15872672

    申请日：2018-01-16

    Applicant: QUALCOMM Incorporated

    Inventor： Gokce Dane ,  Vasudev Bhaskaran

    IPC: G06K9/00 ,  G06K9/62 ,  G06T7/11 ,  G06T7/20 ,  G06T7/50 ,  G06T7/507

    Abstract: A method performed by an electronic device is described. The method includes generating a depth map of a scene external to a vehicle. The method also includes performing first processing in a first direction of a depth map to determine a first non-obstacle estimation of the scene. The method also includes performing second processing in a second direction of the depth map to determine a second non-obstacle estimation of the scene. The method further includes combining the first non-obstacle estimation and the second non-obstacle estimation to determine a non-obstacle map of the scene. The combining includes combining comprises selectively using a first reliability map of the first processing and/or a second reliability map of the second processing The method additionally includes navigating the vehicle using the non-obstacle map.

    CONSTRAINED RANDOM DECISION FOREST FOR OBJECT DETECTION
    7.
    发明申请
    CONSTRAINED RANDOM DECISION FOREST FOR OBJECT DETECTION 审中-公开

    公开(公告)号：US20190266429A1

    公开(公告)日：2019-08-29

    申请号：US15903981

    申请日：2018-02-23

    Applicant: QUALCOMM Incorporated

    Inventor： Sujith Srinivasan ,  Rakesh Nattoji Rajaram ,  Gokce Dane ,  Vasudev Bhaskaran

    IPC: G06K9/32 ,  G06K9/62 ,  G06K9/46

    Abstract: A classifier for detecting objects in images can be configured to receive features of an image from a feature extractor. The classifier can determine a feature window based on the received features, and allows access by each decision tree of the classifier to only a predetermined area of the feature window. Each decision tree of the classifier can compare a corresponding predetermined area of the feature window with one or more thresholds. The classifier can determine an object in the image based on the comparisons. In some examples, the classifier can determine objects in a feature window based on received features, where the received features are based on color information for an image.

    SYSTEMS AND METHODS FOR NON-OBSTACLE AREA DETECTION
    9.
    发明申请
    SYSTEMS AND METHODS FOR NON-OBSTACLE AREA DETECTION 有权

    公开(公告)号：US20180012367A1

    公开(公告)日：2018-01-11

    申请号：US15685390

    申请日：2017-08-24

    Applicant: QUALCOMM Incorporated

    Inventor： Gokce Dane ,  Vasudev Bhaskaran

    IPC: G06T7/20 ,  G06K9/00 ,  G06K9/62

    CPC classification number: G06T7/20 ,  G06K9/00791 ,  G06K9/00798 ,  G06K9/6292 ,  G06T7/11 ,  G06T7/50 ,  G06T7/507 ,  G06T2207/10028 ,  G06T2207/30256

    Abstract: A method performed by an electronic device is described. The method includes generating a depth map of a scene external to a vehicle. The method also includes performing first processing in a first direction of a depth map to determine a first non-obstacle estimation of the scene. The method also includes performing second processing in a second direction of the depth map to determine a second non-obstacle estimation of the scene. The method further includes combining the first non-obstacle estimation and the second non-obstacle estimation to determine a non-obstacle map of the scene. The combining includes combining comprises selectively using a first reliability map of the first processing and/or a second reliability map of the second processing The method additionally includes navigating the vehicle using the non-obstacle map.

Patent Agency Ranking