Current Search: Approximation theory -- Mathematical models (x)
-
-
Title
-
Sparse and low rank constraints on optical flow and trajectories.
-
Creator
-
Gibson, Joel, Marques, Oge, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
-
Abstract/Description
-
In this dissertation we apply sparse constraints to improve optical flow and trajectories. We apply sparsity in two ways. First, with 2-frame optical flow, we enforce a sparse representation of flow patches using a learned overcomplete dictionary. Second, we apply a low rank constraint to trajectories via robust coupling. We begin with a review of optical flow fundamentals. We discuss the commonly used flow estimation strategies and the advantages and shortcomings of each. We introduce the...
Show moreIn this dissertation we apply sparse constraints to improve optical flow and trajectories. We apply sparsity in two ways. First, with 2-frame optical flow, we enforce a sparse representation of flow patches using a learned overcomplete dictionary. Second, we apply a low rank constraint to trajectories via robust coupling. We begin with a review of optical flow fundamentals. We discuss the commonly used flow estimation strategies and the advantages and shortcomings of each. We introduce the concepts associated with sparsity including dictionaries and low rank matrices.
Show less
-
Date Issued
-
2014
-
PURL
-
http://purl.flvc.org/fau/fd/FA00004286, http://purl.flvc.org/fau/fd/FA00004286
-
Subject Headings
-
Approximation theory -- Mathematical models, Computer vision, Image processing -- Digital techniques, Information visualization
-
Format
-
Document (PDF)
