Robust Optical Flow Algorithm Based on Spatial Domain Optical Flow
Robust Optical Flow Algorithm Based on Spatial Domain Optical Flow
Files (excerpt)
Published date
Resource type
Publisher
Assumption University
ISBN
ISSN
DOI
Call no.
D227r 2016
Other identifier(s)
Edition
Copyrighted date
Language
eng
File type
application/pdf
Extent
17 pages
Other title(s)
Authors
Advisor
Other Contributor(s)
Citation
Degree name
Degree level
Degree discipline
Degree department
Degree grantor
Abstract
In this paper, we focus on the robustness in noise tolerance of spatial domain optical flow. We
present a performance study of bidirectional confidential with median filter on spatial domain
optical flow (spatial correlation, local based optical flow, and global based optical flow) under
non-Gaussian noise. Several noise tolerance models on spatial domain optical flow are used in
comparison. The experimental results are investigated on robustness under noisy condition by
using non-Gaussian noise (Poisson Noise, Salt & Pepper noise, and Speckle Noise) over several
standard sequences. The experiment concentrates on error vector magnitude (EVM) as
performance indicators for accuracy in the direction and distance of motion vector (MV). In
EVM, the result in MV of each method is used to compare with the ground truth vector in the
experimental performance analysis.
Table of contents
Description
Includes bibliography.
punsarn.dc.description.sponsorship
Spatial Coverage
Subject(s)
Rights
This work is protected by copyright. Reproduction or distribution of the work in any format is prohibited without written permission of the copyright owner.
Access rights
Rights holder(s)
Location
4th Floor (Cathedral of Learning)