Share Email Print

Proceedings Paper

Nonlinear frame fusion by minimizing divergence magnitude of optical flow
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We define a variational method to perform frame-fusion. The process is in three steps: we first estimate the velocities and occlusions using optical flow and spatial constraint on the velocities based on the L1 norm of the divergence. We then collect non-occluded points from the sequence, and estimate their locations at a chosen time, on which we perform the fusion. From this list of points, we reconstruct the super-frame by minimizing a total variation energy which forces the super-frame to look like each frame of the sequence (after shifting) and select among the least oscillatory solutions. We display some examples.

Paper Details

Date Published: 14 June 1996
PDF: 12 pages
Proc. SPIE 2755, Signal Processing, Sensor Fusion, and Target Recognition V, (14 June 1996); doi: 10.1117/12.243193
Show Author Affiliations
Frederic Guichard, Cognitech, Inc. (United States)
Lenny I. Rudin, Cognitech, Inc. (United States)

Published in SPIE Proceedings Vol. 2755:
Signal Processing, Sensor Fusion, and Target Recognition V
Ivan Kadar; Vibeke Libby, Editor(s)

© SPIE. Terms of Use
Back to Top