Title:
METHOD AND SYSTEM FOR VIDEO SEGMENTATION
Document Type and Number:
WIPO Patent Application WO/2021/047532
Kind Code:
A1
Abstract:
Methods and systems for video segmentation and scene recognition are described. A video having a plurality of frames and a subtitle file associated with the video are received. Segmentation is performed on the video to generate a first set video frames comprising one or more video frames based on a frame-by-frame comparison of features in the frames of the video. Each video frame in the first includes a frame indicator which indicates at least a first start frame of the video frame. The subtitle file associated with the video is parsed to generate one or more subtitle segments based on a start and an end time of each dialogue in the subtitle file. A second set of video frames comprising one or more second video frames are generated based on the video frames of the first set of video frames and the one or more subtitle segments. The second set of video segments includes at least one merged video segment generated by merging two or more video segments of the first set of video segments that correspond to a common subtitle segment.
Inventors:
LI RUIWEN (CA)
DAI PENG (CA)
RAO VARSHANTH RAVINDRA (CA)
LU JUWEI (CA)
LI WEI (CA)
XU JIANPENG (CA)
DAI PENG (CA)
RAO VARSHANTH RAVINDRA (CA)
LU JUWEI (CA)
LI WEI (CA)
XU JIANPENG (CA)
Application Number:
PCT/CN2020/114153
Publication Date:
March 18, 2021
Filing Date:
September 09, 2020
Export Citation:
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
H04N5/262; G06V10/764
Foreign References:
| CN105744356A | 2016-07-06 | |||
| CN105744356A | 2016-07-06 | |||
| CN101021857A | 2007-08-22 | |||
| CN108347643A | 2018-07-31 | |||
| CN109803180A | 2019-05-24 | |||
| US20070253678A1 | 2007-11-01 |
Download PDF: