Date of Award
2014
Document Type
Dissertation
Publication Status
Version of Record
Submission Date
October 2026
Thesis/Dissertation Advisor [Chair]
Marques, Oge
Abstract
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 concepts associated with sparsity including dictionaries and low rank matrices.
Extent
88 p.
Recommended Citation
Gibson, Joel, "Sparse and low rank constraints on optical flow and trajectories" (2014). Electronic Theses and Dissertations 2010 - 2019. 1098.
https://digitalcommons.fau.edu/etd_general_6/1098
Identifier
FA00004286
Comments
Includes bibliography.|Dissertation (Ph.D.)--Florida Atlantic University, 2014.|FAU Electronic Theses and Dissertations Collection|Includes bibliography.