Graduate Thesis Or Dissertation

 

Multi-dimensional parametric estimation: two-dimensional sharpening by predictive bandwidth extrapolation and fast algorithms for three dimensional autoregressive estimation Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/ks65hg00z

Descriptions

Attribute NameValues
Creator
Abstract
  • Achieving sharpened (enhanced detail) features of a multi-dimensional data source using the linear prediction (LP) bandwidth extrapolation (BWE) technique in the transform domain is the main objective of this research. The evolution of sensor technology has provided acquisition scenarios in which the data format is inherently multi-dimensional, including hyperspectral imaging (HSI), interferometric synthetic aperture radar (IF-SAR) imaging, and radar space-time adaptive processing (STAP). In all these applications, fully multi-dimensional signal processing that has the capability (1) to enhance the resolution of the final multi-dimensional analysis result, and (2) to provide reduced-dimension parametric features of the multi-dimensional data for purposes of data encoding/compression is highly desirable. This thesis provides algorithmic techniques that achieve both capabilities using a novel 2-D BWE approach and its associated fast computational algorithms. Furthermore, 3-D LP fast algorithms were developed, as part of this research, that estimate 3-D AR parameters of the original 3-D sensor domain data, which are then used to produce high resolution 3-D AR spectral estimates. These new 3-D algorithms will become components of future research in 3-D BWE algorithms that sharpen features in 3-D data sources.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Keyword
Subject
Rights Statement
Language
File Format
File Extent
  • 2400518 bytes
Replaces
Additional Information
  • description.provenance : Made available in DSpace on 2006-08-02T22:01:53Z (GMT). No. of bitstreams: 1 liew_thesis_final.pdf: 2400518 bytes, checksum: 6228c8582f39865c1ffaf69df193874f (MD5)
  • description.provenance : Submitted by Ji-Seok Liew (liewj@onid.orst.edu) on 2006-07-13T18:28:45Z No. of bitstreams: 1 liew_thesis_final.pdf: 2400518 bytes, checksum: 6228c8582f39865c1ffaf69df193874f (MD5)
  • description.provenance : Approved for entry into archive by Julie Kurtz(julie.kurtz@oregonstate.edu) on 2006-07-26T16:01:21Z (GMT) No. of bitstreams: 1 liew_thesis_final.pdf: 2400518 bytes, checksum: 6228c8582f39865c1ffaf69df193874f (MD5)

Relationships

Parents:

This work has no parents.

Items