The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Apr. 18, 2017

Filed:

Apr. 28, 2010
Applicants:

Tao Mei, Beijing, CN;

Xian-sheng Hua, Beijing, CN;

Shipeng LI, Palo Alto, CA (US);

Lin-xie Tang, Hefei, CN;

Inventors:

Tao Mei, Beijing, CN;

Xian-Sheng Hua, Beijing, CN;

Shipeng Li, Palo Alto, CA (US);

Lin-Xie Tang, Hefei, CN;

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
H04N 5/14 (2006.01); G06K 9/00 (2006.01); G11B 27/034 (2006.01); G11B 27/10 (2006.01); G11B 27/28 (2006.01); H04N 21/81 (2011.01); H04N 21/84 (2011.01); H04N 21/845 (2011.01); H04N 21/8549 (2011.01); H04N 19/159 (2014.01); H04N 19/61 (2014.01); H04N 19/25 (2014.01);
U.S. Cl.
CPC ...
H04N 5/144 (2013.01); G06K 9/00751 (2013.01); G11B 27/034 (2013.01); G11B 27/105 (2013.01); G11B 27/28 (2013.01); H04N 19/159 (2014.11); H04N 19/25 (2014.11); H04N 19/61 (2014.11); H04N 21/816 (2013.01); H04N 21/84 (2013.01); H04N 21/8453 (2013.01); H04N 21/8455 (2013.01); H04N 21/8456 (2013.01); H04N 21/8549 (2013.01);
Abstract

Described is perceptually near-lossless video summarization for use in maintaining video summaries, which operates to substantially reconstruct an original video in a generally perceptually near-lossless manner. A video stream is summarized with little information loss by using a relatively very small piece of summary metadata. The summary metadata comprises an image set of synthesized mosaics and representative keyframes, audio data, and the metadata about video structure and motion. In one implementation, the metadata is computed and maintained (e.g., as a file) to summarize a relatively large video sequence, by segmenting a video shot into subshots, and selecting keyframes and mosaics based upon motion data corresponding to those subshots. The motion data is maintained as a semantic description associated with the image set. To reconstruct the video, the metadata is processed, including simulating motion using the image set and the semantic description, which recovers the audiovisual content without any significant information loss.


Find Patent Forward Citations

Loading…