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:
Jul. 26, 2022

Filed:

Jun. 10, 2020
Applicant:

Ricoh Company, Ltd., Tokyo, JP;

Inventors:

Hector H. Gonzalez-Banos, Mountain View, CA (US);

Ramya Narasimha, Palo Alto, CA (US);

Assignee:

Ricoh Company, Ltd., Tokyo, JP;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G11B 27/031 (2006.01); G06F 16/738 (2019.01); G06F 16/783 (2019.01); G06F 16/78 (2019.01); G06F 16/732 (2019.01); G06V 20/40 (2022.01); G06V 20/52 (2022.01);
U.S. Cl.
CPC ...
G11B 27/031 (2013.01); G06F 16/739 (2019.01); G06F 16/7328 (2019.01); G06F 16/783 (2019.01); G06F 16/785 (2019.01); G06F 16/786 (2019.01); G06F 16/7867 (2019.01); G06V 20/47 (2022.01); G06V 20/52 (2022.01);
Abstract

The disclosure includes a system and method for decomposing a video to salient fragments and synthesizing a video composition based on the salient fragments. A computer-implemented method receives a first set of salient fragments and a first set of clusters extracted from a video, where each cluster includes related salient fragments connected by a connectivity graph. The method determines a weight associated with each of the salient fragments and each of the clusters based on an activity level associated with the respective salient fragment or cluster and determine a permissible zone of activity. The method determines a spatial-temporal distortion to be applied to each salient fragment and cluster and synthesizes a video composition based on the first set of salient fragments, the first set of clusters and non-salient portions of the video using weighted editing.


Find Patent Forward Citations

Loading…