公开(公告)号：US12231645B2

公开(公告)日：2025-02-18

申请号：US17830062

申请日：2022-06-01

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Jun Ji ,  Changcai Lai

IPC: H04N19/132 ,  H04N19/105 ,  H04N19/137 ,  H04N19/172

Abstract: This application provides a video encoding/decoding method, a corresponding video encoding/decoding apparatus. The video encoding method includes: obtaining a to-be-encoded video; encoding the to-be-encoded video to obtain a first bitstream and a second bitstream before outputting the first and second bitstreams. The first bitstream is obtained by performing frame skipping and encoding on the to-be-encoded video, and the second bitstream is obtained by encoding video frames in a second frame sequence by using video frames in a first frame sequence as key frames. The first frame sequence includes video frames obtained by downsampling video frames in the to-be-encoded video that are encoded into the first bitstream, and the second frame sequence includes video frames obtained by downsampling video frames in the to-be-encoded video that are not encoded into the first bitstream. The technical solutions provided in this application help improve video image prediction accuracy.

公开(公告)号：US20250037242A1

公开(公告)日：2025-01-30

申请号：US18591631

申请日：2024-02-29

Applicant: Huawei Technologies Co., Ltd.

Inventor： Huazhen Wu ,  Jun Ji ,  Pengchao Zhan

IPC: G06T5/60 ,  G06T5/50 ,  G06T7/70 ,  G06V10/25 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82

Abstract: A data processing method includes obtaining first frame data, where the first frame data is one frame in raw data collected by an image sensor; obtaining data corresponding to a compact box, to obtain first data, where coverage of the compact box in the first frame data includes a target object detected from the first frame data; obtaining data corresponding to a loose box, to obtain second data, where coverage of the loose box in the first frame data includes and is larger than the coverage of the compact box in the first frame data; and using the first data and the second data as inputs of a target network, to obtain an output image, where the target network is used to extract information about a plurality of channels in the input data, and obtain the output image based on the information about the channels.