公开(公告)号：US10567299B2

公开(公告)日：2020-02-18

申请号：US16127649

申请日：2018-09-11

Applicant: HUAWEI TECHNOLOGIES CO.,LTD.

Inventor： Zhitang Chen ,  Yanhui Geng ,  Hong Zhang ,  Kai Chen

IPC: H04L29/06 ,  H04L12/891 ,  G06F16/00 ,  G06N7/00 ,  G06N20/00 ,  H04L12/851 ,  H04L12/927

Abstract: A coflow identification method includes: obtaining a weighted matrix by means of learning according to historical data in the network, where the weighted matrix is used to minimize a feature distance between data streams belonging to a same coflow and maximize a feature distance between data streams belonging to different coflows; computing a feature distance between any two data streams in the network according to metrics in the data stream layer data feature, the application layer data stream feature distance, the terminal aspect data feature distance, and the weighted matrix; and dividing the data streams in the network into several cluster sets by using a clustering algorithm and according to the feature distance between the any two data streams in the network, where each of the several cluster sets is a coflow.

公开(公告)号：US20190335196A1

公开(公告)日：2019-10-31

申请号：US16505182

申请日：2019-07-08

Applicant: Huawei Technologies Co., Ltd.

Inventor： Hong Zhang ,  Haitao Yang

IPC: H04N19/513 ,  H04N19/54 ,  H04N19/53 ,  H04N19/119 ,  H04N19/196 ,  H04N19/52 ,  H04N19/176 ,  H04N19/139 ,  H04N19/573 ,  H04N19/57

Abstract: The present invention provides a video picture coding method, a video picture decoding method, a coding device, and a decoding device. The method includes: determining a motion vector difference of an affine picture block; determining motion vector precision of the affine picture block; determining a size of an affine motion compensation picture subblock in the affine picture block according to the motion vector difference, the motion vector precision, and a distance between control points in the affine picture block, where the control points are pixels used to determine the motion vector difference; and performing coding processing on the affine picture block according to the size of the affine motion compensation picture subblock. In this way, a picture subblock of an appropriate size is selected, so that coding complexity can be reduced, and coding efficiency can be improved.

公开(公告)号：US20170180727A1

公开(公告)日：2017-06-22

申请号：US15454356

申请日：2017-03-09

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xin Huang ,  Hong Zhang ,  Haitao Yang

IPC: H04N19/105 ,  H04N19/513 ,  H04N19/182

CPC classification number: H04N19/105 ,  H04N19/182 ,  H04N19/44 ,  H04N19/51 ,  H04N19/513 ,  H04N19/567

Abstract: A picture prediction method and a related apparatus are disclosed, which includes: determining N templates whose degrees of matching with a current template meet a preset condition, where the current template is a template corresponding to a current picture block, and the M templates are obtained by searching reference pictures of the current picture block; determining a weight of a pixel area in a picture block corresponding to each template in the N templates, where weights of at least two pixel areas in a picture block corresponding to at least one template in the N templates are different; and calculating a predicted pixel value of a pixel area in the current picture block based on the weight and a pixel value of the pixel area in the picture block corresponding to each template in the N templates, where the pixel area includes at least one pixel.