US 11,057,635 B2
Methods and systems for video synopsis
Jianhua Xiang, Hangzhou (CN); Wenkai Zhou, Hangzhou (CN); Yan Xu, Hangzhou (CN); Lili Chen, Hangzhou (CN); and Li Yang, Hangzhou (CN)
Assigned to ZHEJIANG DAHUA TECHNOLOGY CO., LTD., Hangzhou (CN)
Filed by ZHEJIANG DAHUA TECHNOLOGY CO., LTD., Zhejiang (CN)
Filed on Jun. 7, 2019, as Appl. No. 16/434,305.
Application 16/434,305 is a continuation of application No. PCT/CN2016/109015, filed on Dec. 8, 2016.
Prior Publication US 2019/0289311 A1, Sep. 19, 2019
Int. Cl. H04N 7/18 (2006.01); H04N 19/46 (2014.01); H04N 19/40 (2014.01); G06K 9/00 (2006.01); G06T 7/20 (2017.01); H04N 21/44 (2011.01); H04N 21/8549 (2011.01); H04N 21/234 (2011.01); H04N 21/845 (2011.01)
CPC H04N 19/46 (2014.11) [G06K 9/00751 (2013.01); G06K 9/00765 (2013.01); G06T 7/20 (2013.01); H04N 7/18 (2013.01); H04N 19/40 (2014.11); H04N 21/23418 (2013.01); H04N 21/44008 (2013.01); H04N 21/8456 (2013.01); H04N 21/8549 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/30232 (2013.01); G06T 2207/30241 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for generating a video synopsis comprising:
segmenting a video file into a plurality of video fragments;
extracting moving object information from the plurality of video fragments based on a distributed computing method;
determining a plurality of index files corresponding to the plurality of video fragments based on the moving object information;
combining the plurality of index files; and
generating a video synopsis by:
arranging the moving object information based on the combined index file;
generating video data of a plurality of frames based on the arranged moving object information; and
encoding the video data into the video synopsis.