Show simple item record

dc.contributor.advisorAnderson, Derek T.
dc.contributor.advisorBethel, Cindy L.
dc.contributor.authorSmith, Ryan Elliott.
dc.date2017
dc.date.accessioned2020-04-07T20:12:17Z
dc.date.available2020-04-07T20:12:17Z
dc.identifier.urihttps://hdl.handle.net/11668/16610
dc.description.abstractThermal cameras are used in numerous computer vision applications, such as human detection and scene understanding. However, the cost of high quality and high resolution thermal sensors is often a limiting factor. Conversely, high resolution visual spectrum cameras are readily available and generally inexpensive. Herein, we explore the creation of higher quality upsampled thermal imagery using a high resolution visual spectrum camera and Markov random fields theory. This paper also presents a discussion of the tradeoffs from this approach and the effects of upsampling, both from quantitative and qualitative perspectives. Our results demonstrate the successful application of this approach for human detection and the accurate propagation of thermal measurements within images for more general tasks like scene understanding. A tradeoff analysis of the costs related to performance as the resolution of the thermal camera decreases are also provided.
dc.publisherMississippi State University
dc.subject.otherUpsampling
dc.subject.otherThreat Detection
dc.subject.otherThermal Imaging
dc.subject.otherMarkov Random Fields
dcterms.titleFusion of RGB and Thermal Data for Improved Scene Understanding
dcterms.typeThesis
dc.publisher.departmentDepartment of Electrical and Computer Engineering
dc.publisher.collegeBagley College of Engineering
dc.subject.degreeMaster of Science
dc.subject.majorElectrical and Computer Engineering
dc.contributor.committeeArchibald, Christopher.
dc.contributor.committeeBall, John E.
dc.date.defense2016-12-05


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record