利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

9 条记录 (耗时 0.016 秒)

    Learnable localization using images
    4.
    发明授权
    Learnable localization using images 有权

    公开(公告)号：US12106511B2

    公开(公告)日：2024-10-01

    申请号：US17473466

    申请日：2021-09-13

    申请人： Huawei Technologies Co., Ltd.

    发明人： Onay Urfalioglu ,  Akhil Gurram ,  Fahd Bouzaraa

    IPC分类号： G06K9/00 ,  G06T7/73

    CPC分类号： G06T7/74 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30244

    摘要： An apparatus for generating a model for pose estimation of a system obtains training data for a multiple locations. The training data includes one or more images captured by an image capturing device and the respective poses of the captured images. At least one data sample is generated from the training data for each of the captured images, where a data sample for an image is an assignment of the image and at least one other image selected from the training data to respective poses. A neural network is trained with a data set made up of the data samples to estimate a respective pose of a localization image from: the localization image; at least one additional image from the training data; and a respective pose of each of additional image.

    Method and apparatus for generating high dynamic range image
    5.
    发明授权
    Method and apparatus for generating high dynamic range image 有权

    公开(公告)号：US11017509B2

    公开(公告)日：2021-05-25

    申请号：US16448662

    申请日：2019-06-21

    申请人： Huawei Technologies Co., Ltd.

    发明人： Fahd Bouzaraa ,  Onay Urfalioglu ,  Ibrahim Halfaoui

    IPC分类号： G06T5/00 ,  G06T5/10 ,  G06T5/50

    摘要： A method and an apparatus for generating a High Dynamic Range, HDR, image are proposed. The method comprises obtaining a set of two or more input images, the two or more input images including a reference image and one or more non-reference images; for each of the one or more non-reference images, performing an image analysis which comprises, for each region of a plurality of regions of the non-reference image, assessing whether the region of the non-reference image and a corresponding region of the reference image show the same image content and declaring the region of the non-reference image as valid or as invalid based on the assessment; and generating the HDR image by fusing the reference image and the one or more non-reference images, wherein the fusing comprises, for each of the one or more non-reference images, disregarding the invalid regions of the respective non-reference image.

    Image processing apparatus and method
    6.
    发明授权
    Image processing apparatus and method 有权

    公开(公告)号：US11055827B2

    公开(公告)日：2021-07-06

    申请号：US16729039

    申请日：2019-12-27

    申请人： Huawei Technologies Co., Ltd.

    发明人： Fahd Bouzaraa ,  Onay Urfalioglu ,  Ibrahim Halfaoui

    IPC分类号： G06T5/00 ,  G06T5/50

    摘要： The invention relates to an image processing apparatus for generating an HDR image associated with a first view on the basis of a plurality of LDR images, including a first LDR image and a second LDR image. The first LDR image is associated with the first view and a first exposure, i.e. a first dynamic range, and the second LDR image is associated with a second view and a second exposure, i.e. a second dynamic range. The image processing apparatus comprises a processor configured to provide a neural network having a plurality of neural subnetworks including a first neural subnetwork. The first neural subnetwork is configured to generate the HDR image on the basis of: (i) the first LDR image, (ii) the second LDR image, and (iii) a modified first LDR image. The modified first LDR image is associated with the first view and the second exposure.

    Exposure-related intensity transformation
    7.
    发明授权
    Exposure-related intensity transformation 有权

    公开(公告)号：US10666873B2

    公开(公告)日：2020-05-26

    申请号：US15954941

    申请日：2018-04-17

    申请人： Huawei Technologies Co., Ltd.

    发明人： Fahd Bouzaraa ,  Onay Urfalioglu

    IPC分类号： H04N5/235 ,  H04N5/232 ,  G06K9/62 ,  G06T5/50 ,  G06T5/00

    摘要： An image processing device for generating an output image front an input image of a scene, the input image being the first image and the output image being the second image, the output image corresponds to an exposure that is different from an exposure of the input image, the image processing device comprising an intensity transformer that is configured to determine one or more intensities of an output pixel of the output image based on an input patch around an input pixel of the input image that corresponds to the output pixel.

    System and Method for Processing Input Images Before Generating a High Dynamic Range Image
    9.
    发明申请
    System and Method for Processing Input Images Before Generating a High Dynamic Range Image 有权
    在生成高动态范围图像之前处理输入图像的系统和方法

    公开(公告)号：US20160364847A1

    公开(公告)日：2016-12-15

    申请号：US15245402

    申请日：2016-08-24

    申请人： Huawei Technologies Co., Ltd.

    发明人： Fahd Bouzaraa ,  Giovanni Cordara ,  Onay Urfalioglu

    IPC分类号： G06T5/00 ,  G06T5/40 ,  G06T5/50

    CPC分类号： G06T5/007 ,  G06T5/005 ,  G06T5/40 ,  G06T5/50 ,  G06T2207/10004 ,  G06T2207/10012 ,  G06T2207/10144 ,  G06T2207/20208 ,  G06T2207/20216

    摘要： An image processing system for generating a high dynamic range image from a first image and a second image is presented. The system comprises a first displacement estimator adapted to estimate a displacement of image content between a reference image derived from the first image and an image to be warped derived from the second image. The system comprises a first warping unit that compensates the estimated displacement by warping the image to be warped resulting in a first warped image. The system comprises a first error detector adapted to detect geometric warping errors within the first warped image and a first error compensator adapted to compensate the estimated geometric warping errors within the first warped image resulting in a first error corrected image. The system comprises a high dynamic range calculator adapted to calculate the high-dynamic range image based upon the first error corrected image and the reference image.

    摘要翻译： 提出了一种用于从第一图像和第二图像生成高动态范围图像的图像处理系统。 该系统包括第一位移估计器，其适于估计从第一图像导出的参考图像与从第二图像导出的待扭曲图像之间的图像内容的位移。 该系统包括第一翘曲单元，其通过扭曲扭曲的图像来补偿估计的位移，导致第一翘曲图像。 该系统包括适于检测第一翘曲图像内的几何翘曲误差的第一误差检测器和适于补偿第一翘曲图像内的估计的几何翘曲误差的第一误差补偿器，产生第一误差校正图像。 该系统包括高动态范围计算器，其适于基于第一误差校正图像和参考图像来计算高动态范围图像。