S
Shaul Oron
Researcher at Tel Aviv University
Publications - 20
Citations - 1129
Shaul Oron is an academic researcher from Tel Aviv University. The author has contributed to research in topics: Template matching & Similarity measure. The author has an hindex of 10, co-authored 19 publications receiving 971 citations. Previous affiliations of Shaul Oron include Intel & General Motors.
Papers
More filters
Journal ArticleDOI
Locally Orderless Tracking
TL;DR: This work provides a probabilistic model of the target variations over time and rigorously shows that this model is a special case of the Earth Mover’s Distance optimization problem where the ground distance is governed by some underlying noise model.
Proceedings ArticleDOI
Locally Orderless Tracking
TL;DR: This work provides a probabilistic model of the object variations over time and shows LOT's tracking capabilities on challenging video sequences, both commonly used and new, demonstrating performance comparable to state-of-the-art methods.
Proceedings ArticleDOI
Best-Buddies Similarity for robust template matching
TL;DR: This work proposes a novel method for template matching in unconstrained environments, based on counting the number of Best-Buddies Pairs—pairs of points in source and target sets, where each point is the nearest neighbor of the other.
Book ChapterDOI
Extended Lucas-Kanade Tracking
TL;DR: Extended Lucas Kanade or ELK casts the original LK algorithm as a maximum likelihood optimization and then extends it by considering pixel object / background likelihoods in the optimization, which is evaluated on two challenging data-sets containing 50 sequences each.
Journal ArticleDOI
Best-Buddies Similarity—Robust Template Matching Using Mutual Nearest Neighbors
TL;DR: The Best-Buddies Similarity (BBS) as mentioned in this paper is a similarity measure based on counting the number of points in source and target sets that are mutual nearest neighbours, i.e., each point is the nearest neighbour of the other.