Repository logo
 

Theory and applications of optimized correlation output filters

Simple item page
dc.contributor.authorBolme, David Scott, author
dc.contributor.authorBeveridge, J. Ross, 1957-, advisor
dc.contributor.authorDraper, Bruce A. (Bruce Austin), 1962-, committee member
dc.contributor.authorStrout, Michelle Mills, committee member
dc.contributor.authorKirby, Michael J., committee member
dc.date.accessioned2007-01-03T05:13:17Z
dc.date.available2007-01-03T05:13:17Z
dc.date.issued2011
dc.description.abstractCorrelation filters are a standard way to solve many problems in signal processing, image processing, and computer vision. This research introduces two new filter training techniques, called Average of Synthetic Exact Filters (ASEF) and Minimum Output Sum of Squared Error (MOSSE), which have produced filters that perform well on many object detection problems. Typically, correlation filters are created by cropping templates out of training images; however, these templates fail to adequately discriminate between targets and background in difficult detection scenarios. More advanced methods such as Synthetic Discriminant Functions (SDF), Minimum Average Correlation Energy (MACE), Unconstrained Minimum Average Correlation Energy (UMACE), and Optimal Tradeoff Filters (OTF) improve performance by controlling the response of the correlation peak, but they only loosely control the effect of the filters on the rest of the image. This research introduces a new approach to correlation filter training, which considers the entire image to image mapping known as cross-correlation. ASEF and MOSSE find filters that optimally map the input training images to user specified outputs. The goal is to produce strong correlation peaks for targets while suppressing the responses to background. Results in eye localization, person detection, and visual tracking indicate that these new filters outperform other advanced correlation filter training methods and even produce better results than much more complicated non-filter algorithms.
dc.format.mediumborn digital
dc.format.mediumdoctoral dissertations
dc.identifierBolme_colostate_0053A_10249.pdf
dc.identifier.urihttp://hdl.handle.net/10217/47326
dc.languageEnglish
dc.language.isoeng
dc.publisherColorado State University. Libraries
dc.relation.ispartof2000-2019
dc.rightsCopyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright.
dc.subjectcomputer vision
dc.subjectobject detection
dc.subjectcorrelation filters
dc.titleTheory and applications of optimized correlation output filters
dc.typeText
dcterms.rights.dplaThis Item is protected by copyright and/or related rights (https://rightsstatements.org/vocab/InC/1.0/). You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
thesis.degree.disciplineComputer Science
thesis.degree.grantorColorado State University
thesis.degree.levelDoctoral
thesis.degree.nameDoctor of Philosophy (Ph.D.)

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Bolme_colostate_0053A_10249.pdf
Size:
14.49 MB
Format:
Adobe Portable Document Format
Description:
Download

Collections

2000-2019
Theses and Dissertations