IP Library Granted Patent US 10,217,187
Granted Patent B2
US 10,217,187 · App. 15/579,924 · Granted Feb 26, 2019

Method for dynamic video magnification

Inventors: Mohamed Abdelaziz A. Mohamed Elgharib (Doha, QA); Mohamed M. Hefeeda (Doha, QA); William T. Freeman (Acton, MA); Frederic Durand (Somerville, MA)
Assignees: QATAR FOUNDATION FOR EDUCATION, SCIENCE AND IMMUNITY DEVELOPMENT; MASSACHUSETTS INSTITUTE OF TECHNOLOGY
G06T3/40G06T5/005G06T7/33H04N5/23248H04N5/2628G06T2207/10016G06T2207/20104
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,217,187
App. No.
15/579,924
Granted
Feb 26, 2019
Kind
B2
Abstract

The method for dynamic video magnification magnifies small motions occurring simultaneously within large motions. The method involves selecting a region of interest from a video for magnification. The region of interest is warped to obtain a stabilized sequence of frames that discounts large motions. Each frame of the stabilized sequence is decomposed to a foreground layer, a background layer, and an alpha matte layer, and each of the foreground and alpha matte layers is magnified. Then a magnified sequence is generated from the magnified layers using matte inversion. Any image holes in the magnified sequence are filled in using texture synthesis. Finally, the magnified sequence is de-warped to the original space-time coordinates.

Claims (9)

1. A method for dynamic video magnification of small motions occurring simultaneously within large motions, comprising the steps of:

selecting the small motions as a region of interest (ROI) from a video for magnification;

warping the region of interest to discount the large motions, thereby obtaining a stabilized sequence of the small motion input video frames, wherein the warping technique is selected from the group consisting of a Kanade-Lucas-Tomasi (KLT) feature tracker, an optical flow, and parametric modeling;

for each of the input video frames in the stabilized sequence:

decomposing the frame into a foreground layer, a background layer, and an alpha matte layer;

magnifying each of the foreground and alpha matte layers, wherein the magnification includes applying phase-based magnification;

generating a magnified sequence of the magnified foreground and alpha matte layers by matte inversion, wherein the generated magnified sequence includes superimposing the magnified foreground layer over the background layer to reconstruct remaining unmagnified sites;

filling in holes in the magnified sequence by texture synthesis; and

de-warping the magnified sequence to original space-time coordinates after filling in the image holes to obtain dynamic video magnification of the region of interest.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 22, 2019
From: ELGHARIB, MOHAMED ABDELAZIZ A. MOHAMED, DR.; HEFEEDA, MOHAMED M., DR.
To: QATAR FOUNDATION FOR EDUCATION, SCIENCE AND COMMUNITY DEVELOPMENT
Reel/Frame 048095/0234 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 22, 2019
From: FREEMAN, WILLIAM T., DR.; DURAND, FREDERIC, DR.
To: MASSACHUSETTS INSTITUTE OF TECHNOLOGY
Reel/Frame 048095/0584 →
Continuity (2)
Provisional Application 62171816 · Jun 5, 2015
Related Publication 20180225803A1 · Aug 9, 2018