中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

12 records (took 0.016 seconds)

    Lane marker recognition
    1.
    发明授权
    Lane marker recognition 有权

    公开(公告)号：US12112552B2

    公开(公告)日：2024-10-08

    申请号：US17655500

    申请日：2022-03-18

    Applicant: QUALCOMM Incorporated

    Inventor： Seungwoo Yoo ,  Heesoo Myeong ,  Hee-Seok Lee

    IPC: G06V20/56 ,  G06T7/73 ,  G06V10/82

    CPC classification number: G06V20/588 ,  G06T7/73 ,  G06V10/82 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30256

    Abstract: Certain aspects of the present disclosure provide techniques for lane marker detection. A set of feature tensors is generated by processing an input image using a convolutional neural network. A set of localizations is generated by processing the set of feature tensors using a localization network, a set of horizontal positions is generated by processing the set of feature tensors using row-wise regression, and a set of end positions is generated by processing the set of feature tensors using y-end regression. A set of lane marker positions is determined based on the set of localizations, the set of horizontal positions, and the set of end positions.

    TEXT-BASED IMAGE RESIZING
    2.
    发明申请
    TEXT-BASED IMAGE RESIZING 有权
    基于文本的图像调整

    公开(公告)号：US20160210768A1

    公开(公告)日：2016-07-21

    申请号：US14597584

    申请日：2015-01-15

    Applicant: QUALCOMM Incorporated

    Inventor： Seungwoo Yoo ,  Hee-Seok Lee ,  Jihoon Kim

    IPC: G06T11/60 ,  G06T3/40

    CPC classification number: G06T11/60 ,  G06K9/3258 ,  G06T3/0012 ,  G06T3/40 ,  G06T2210/22 ,  G09G5/00 ,  G09G2320/0613 ,  G09G2340/04 ,  G09G2340/045 ,  G09G2340/14 ,  H04N1/3875

    Abstract: A method, which is performed by an electronic device, for resizing an image having text is disclosed. The method may include determining layout information of at least one text region in the image. The layout information may include at least one of a number, a size, a location, a shape, or a text density of the at least one text region in the image. The method may also select a seam carving operation, a cropping operation, or a scaling operation for the image based on the layout information, a size of the image, and a target image size. The selected operation may be performed to resize the image to the target image size based at least on one of the layout information, the size of the image, or the target image size. The resized image may include the at least one text region.

    Abstract translation: 公开了一种由电子设备执行的用于调整具有文本的图像的大小的方法。 该方法可以包括确定图像中的至少一个文本区域的布局信息。 布局信息可以包括图像中的至少一个文本区域的数量，大小，位置，形状或文本密度中的至少一个。 该方法还可以基于布局信息，图像的大小和目标图像尺寸来选择图像的缝制操作，裁剪操作或缩放操作。 可以基于布局信息，图像的大小或目标图像尺寸中的至少一个来执行所选择的操作以将图像大小调整为目标图像尺寸。 调整大小的图像可以包括至少一个文本区域。

    Simultaneous object detection and rigid transform estimation using neural network
    3.
    发明授权
    Simultaneous object detection and rigid transform estimation using neural network 有权

    公开(公告)号：US10262218B2

    公开(公告)日：2019-04-16

    申请号：US15441114

    申请日：2017-02-23

    Applicant: QUALCOMM Incorporated

    Inventor： Hee-Seok Lee ,  Duck Hoon Kim

    IPC: G06T7/00 ,  G06K9/00 ,  G06K9/46 ,  G06T7/13 ,  G06T7/168 ,  G06T7/50 ,  G06K9/62

    Abstract: A method, a computer-readable medium, and an apparatus for object detection are provided. The apparatus may determine a regression vector using a neural network based on an input image that contains an object. The object may have a planar surface with a known shape. The apparatus may derive a transform matrix based on the regression vector. The apparatus may identify a precise boundary of the object based on the transform matrix. The precise boundary of the object may include a plurality of vertices of the object. To identify the boundary of the object, the apparatus may apply the transform matrix to a determined shape of the object.

    Efficient dropout inference for bayesian deep learning
    6.
    发明授权
    Efficient dropout inference for bayesian deep learning 有权

    公开(公告)号：US11410040B2

    公开(公告)日：2022-08-09

    申请号：US16168015

    申请日：2018-10-23

    Applicant: QUALCOMM Incorporated

    Inventor： Seungwoo Yoo ,  Heesoo Myeong ,  Hee-Seok Lee ,  Hyun-Mook Cho

    IPC: G06N3/04 ,  G06N3/08 ,  G06N7/00 ,  G06N5/04

    Abstract: Certain aspects of the present disclosure are directed to methods and apparatus for deep learning in an artificial neural network. One example method generally includes receiving input data at an input to a layer of the neural network; replicating a group of neural processing units in the layer to form a superset of neural processing units, the superset comprising n instances of the group of neural processing units; processing the input data using the superset to generate output data for the layer; and determining an uncertainty of the output data. Processing the input data includes performing a dropout function by zeroing out one or more weights of a set of weights for each of the n instances of the superset of neural processing units and convolving, for each of the n instances in parallel, the input data with one or more non-zeroed out weights of the set of weights.

    ACTIVATING FLASH FOR CAPTURING IMAGES WITH TEXT
    9.
    发明申请
    ACTIVATING FLASH FOR CAPTURING IMAGES WITH TEXT 有权
    用文本捕捉图像的激活闪光

    公开(公告)号：US20160057331A1

    公开(公告)日：2016-02-25

    申请号：US14466659

    申请日：2014-08-22

    Applicant: QUALCOMM Incorporated

    Inventor： Seungwoo Yoo ,  Hyun-Mook Cho ,  Hee-Seok Lee ,  Duck Hoon Kim

    IPC: H04N5/235 ,  H04N9/07 ,  H04N5/232

    CPC classification number: H04N5/2354 ,  G06K9/036 ,  G06K9/4661 ,  H04N5/23293 ,  H04N5/2351 ,  H04N9/07

    Abstract: A method, which is performed by an electronic device, of automatically activating a flash for an image sensor of the electronic device is disclosed. The method may include receiving a first image including at least one text region and determining feature data characterizing the at least one text region in the first image. The method may also identify at least one candidate specular reflection region in the first image. Based on the feature data and the at least one candidate specular reflection region, the flash may be activated. Upon activating the flash, a second image including the at least one text region may be captured.

    Abstract translation: 公开了一种由电子设备执行的用于自动激活电子设备的图像传感器的闪光灯的方法。 该方法可以包括接收包括至少一个文本区域的第一图像和确定表征第一图像中的至少一个文本区域的特征数据。 该方法还可以识别第一图像中的至少一个候选镜面反射区域。 基于特征数据和至少一个候选镜面反射区域，可以激活闪光。 在激活闪光灯时，可以捕获包括至少一个文本区域的第二图像。

    Lane marker detection
    10.
    发明授权
    Lane marker detection 有权

    公开(公告)号：US11600080B2

    公开(公告)日：2023-03-07

    申请号：US17200592

    申请日：2021-03-12

    Applicant: QUALCOMM Incorporated

    Inventor： Seungwoo Yoo ,  Heesoo Myeong ,  Hee-Seok Lee

    IPC: G06T7/10 ,  G06V20/56 ,  G06T7/73

    Abstract: Certain aspects of the present disclosure provide a method for lane marker detection, including: receiving an input image; providing the input image to a lane marker detection model; processing the input image with a shared lane marker portion of the lane marker detection model; processing output of the shared lane marker portion of the lane marker detection model with a plurality of lane marker-specific representation layers of the lane marker detection model to generate a plurality of lane marker representations; and outputting a plurality of lane markers based on the plurality of lane marker representations.

Patent Agency Ranking