公开(公告)号：US20210192217A1

公开(公告)日：2021-06-24

申请号：US16892910

申请日：2020-06-04

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Xiaoming Wang ,  Huaifei Xing ,  Wenpeng Ding ,  Huifeng Shen ,  Feifei Cao

IPC: G06K9/00 ,  G06K9/32 ,  G06T7/70 ,  G06K9/62

Abstract: Embodiments of the present disclosure relate to a method and apparatus for processing a video. The method may include: acquiring object regions obtained by performing object detection on a target video frame, a type of an object in each of the object regions being a preset type; determining, for an object region in the acquired object regions, in response to determining that the object region satisfies a preset condition, that the object region is a non-ROI; using an object region other than the non-ROI in the object regions of the target video frame as a ROI; and acquiring a quantization parameter change corresponding to each ROI, and encoding the target video frame based on the quantization parameter change.

公开(公告)号：US11375209B2

公开(公告)日：2022-06-28

申请号：US16895430

申请日：2020-06-08

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Xiaoming Wang ,  Huaifei Xing ,  Wenpeng Ding ,  Huifeng Shen ,  Feifei Cao

IPC: H04N19/172 ,  H04N19/167

Abstract: Embodiments of the present disclosure relate to a method and apparatus for processing a video frame. The method may include: acquiring a sequence of video frames of a video; ascertaining, in the sequence of the video frames, a previous frame, and ascertaining, in the sequence of the video frames, a subsequent frame corresponding to the ascertained previous frame based on acquired number of frames from the previous frame to the subsequent frame. An update step is performed as follows: acquiring object regions detected respectively in the ascertained previous frame and the ascertained subsequent frame, and confidence levels of the object regions; fusing a confidence level of a first object region and a confidence level of a second object region, and updating the confidence level of the second object region based on the fusion result; and updating the ascertained previous frame and the ascertained subsequent frame.

公开(公告)号：US20210195214A1

公开(公告)日：2021-06-24

申请号：US16895430

申请日：2020-06-08

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Xiaoming Wang ,  Huaifei Xing ,  Wenpeng Ding ,  Huifeng Shen ,  Feifei Cao

IPC: H04N19/172 ,  H04N19/167

Abstract: Embodiments of the present disclosure relate to a method and apparatus for processing a video frame. The method may include: acquiring a sequence of video frames of a video; ascertaining, in the sequence of the video frames, a previous frame, and ascertaining, in the sequence of the video frames, a subsequent frame corresponding to the ascertained previous frame based on acquired number of frames from the previous frame to the subsequent frame. An update step is performed as follows: acquiring object regions detected respectively in the ascertained previous frame and the ascertained subsequent frame, and confidence levels of the object regions; fusing a confidence level of a first object region and a confidence level of a second object region, and updating the confidence level of the second object region based on the fusion result; and updating the ascertained previous frame and the ascertained subsequent frame.

公开(公告)号：US10897620B2

公开(公告)日：2021-01-19

申请号：US16567976

申请日：2019-09-11

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Huaifei Xing ,  Jialiang Wang ,  Huifeng Shen ,  Feifei Cao

IPC: H04N19/154 ,  H04N19/14 ,  G06K9/00

Abstract: Embodiments of the present disclosure relate to a method and apparatus for processing a video. The method can include: acquiring a to-be-processed video, and dividing the video into at least one video segment according to a scene; for a video segment of the at least one video segment, extracting a feature of the video segment; inputting the feature and a target video quality into a pre-trained encoding parameter prediction model, to obtain an encoding parameter of the video segment, the encoding parameter prediction model being used to represent a corresponding relationship between the feature of the video segment and the encoding parameter under the target video quality; and performing an encoding process on the video according to the encoding parameter corresponding to the video segment of the at least one video segment, to generate an encoded video.

公开(公告)号：US11659181B2

公开(公告)日：2023-05-23

申请号：US16892910

申请日：2020-06-04

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Xiaoming Wang ,  Huaifei Xing ,  Wenpeng Ding ,  Huifeng Shen ,  Feifei Cao

IPC: G06K9/00 ,  H04N19/124 ,  G06T7/70 ,  G06V20/40 ,  G06V10/25 ,  G06V40/10 ,  G06F18/22 ,  G06V10/80 ,  H04N19/102 ,  H04N19/167 ,  G06V10/22 ,  G06V10/764 ,  H04N19/169 ,  H04N19/115 ,  G06V10/28 ,  H04N19/17

CPC classification number: H04N19/124 ,  G06F18/22 ,  G06T7/70 ,  G06V10/22 ,  G06V10/25 ,  G06V10/28 ,  G06V10/764 ,  G06V10/811 ,  G06V20/41 ,  G06V40/10 ,  H04N19/102 ,  H04N19/115 ,  H04N19/167 ,  H04N19/169 ,  H04N19/17 ,  G06T2207/10016

Abstract: Embodiments of the present disclosure relate to a method and apparatus for processing a video. The method may include: acquiring object regions obtained by performing object detection on a target video frame, a type of an object in each of the object regions being a preset type; determining, for an object region in the acquired object regions, in response to determining that the object region satisfies a preset condition, that the object region is a non-ROI; using an object region other than the non-ROI in the object regions of the target video frame as a ROI; and acquiring a quantization parameter change corresponding to each ROI, and encoding the target video frame based on the quantization parameter change.

公开(公告)号：US11470336B2

公开(公告)日：2022-10-11

申请号：US17129476

申请日：2020-12-21

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Huaifei Xing ,  Yanlong Chang

IPC: H04N19/40 ,  H04N19/119 ,  H04N19/132 ,  H04N19/149 ,  H04N19/172

Abstract: Embodiments of the present disclosure provide a method for transcoding a video. An input attribute of a video is obtained and a target attribute is obtained. A segment transcoding speed of the video is determined based on the input attribute and the target attribute. The segment transcoding speed indicates a transcoding speed of a video segment. The number of video segments of the video is determined based on a preset target transcoding speed and the segment transcoding speed. The video is segmented based on a video length of the video and the number of video segments to obtain the video segments. The video segments are transcoded based on the segment transcoding speed.