Show simple item record

dc.contributor.advisorManian, Vidya
dc.contributor.authorAlarcon-Ramirez, Andres
dc.date.accessioned2019-05-14T18:22:48Z
dc.date.available2019-05-14T18:22:48Z
dc.date.issued2009
dc.identifier.urihttps://hdl.handle.net/20.500.11801/2215
dc.description.abstractA novel variational method using level sets that incorporate spectral angle distance in the model for automatic target detection is presented. Algorithms are presented for detecting both spatial and pixel targets. The new method is tested in tasks of unsupervised target detection in hyperspectral images with more than 100 bands, and the results are compared with a widely used region-based level sets algorithm. In addition Texture and spectral information are incorporated into level set equation for extracting large targets placed on images The proposed method is also adapted for supervised target detection and its performance is compared with traditional orthogonal subspace projection and constrained signal detector for the detection of pixel targets. The method is evaluated with different complexity such as noise levels and target sizes.en_US
dc.description.abstractUn novedoso método que utiliza Level set y que incorpora distancia espectral angular en la detección automática de objetivos es presentado. Distintos algoritmos fueron desarrollados para la detección de objetivos que tienen tamaño de pocos pixeles y otros de mayor tamaño. El nuevo método es probado en tareas de detección de objetivos no-supervisados en imágenes hiperespectrales con más de 100 bandas, y los resultados son comparados con otras técnicas de level set basadas en regiones que han sido ampliamente utilizadas. Adicionalmente información espectral y de textura es incorporada en la ecuación de level set para la extracción de objetos grandes situados en una imagen. El método propuesto es también adaptado para la detección supervisada de objetivos, y su rendimiento es comparado con algoritmos de proyección del sub-espacio ortogonal y detección de señales restringidas para la detección de objetivos de pocos pixeles. El método es evaluado con diferentes niveles de ruido y tamaño de objetos.en_US
dc.description.sponsorshipFunded primarily by the Bernard M. Gordon Center for Subsurface Sensing and Imaging Systems, under the Engineering Research Centers Program of the National Science Foundation (Award Number EEC-9986821).en_US
dc.language.isoEnglishen_US
dc.titleAutomatic target detection in hyperspectral images using level setsen_US
dc.typeThesisen_US
dc.rights.licenseAll rights reserveden_US
dc.rights.holder(c) 2009 Andres Alarcon-Ramirezen_US
dc.contributor.committeeVélez-Reyes, Miguel
dc.contributor.committeeRodríguez, Domingo
dc.contributor.representativeBollman, Dorothy
thesis.degree.levelM.S.en_US
thesis.degree.disciplineComputer Engineeringen_US
dc.contributor.collegeCollege of Engineeringen_US
dc.contributor.departmentDepartment of Electrical and Computer Engineeringen_US
dc.description.graduationYear2009en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

  • Theses & Dissertations
    Items included under this collection are theses, dissertations, and project reports submitted as a requirement for completing a degree at UPR-Mayagüez.

Show simple item record

All rights reserved
Except where otherwise noted, this item's license is described as All Rights Reserved