CLUSTER-BASED SPECTRAL-SPATIAL SEGMENTATION OF HYPERSPECTRAL IMAGERY
Loading...
Authors
Kennedy, Sean M.
Subjects
hyperspectral
image
segmentation
clustering
k-means
hierarchical agglomerative clustering
community detection
SLIC
Ward’s method
energy distance
modularity
spectral
spatial
image
segmentation
clustering
k-means
hierarchical agglomerative clustering
community detection
SLIC
Ward’s method
energy distance
modularity
spectral
spatial
Advisors
Scrofani, James W.
Roth, John D.
Thulasiraman, Preetha
Date of Issue
2019-09
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
In this thesis, a three-stage algorithm for performing unsupervised segmentation of hyperspectral imagery is developed and tested. Based on a data-model derived from common sources of error inherent in all imaging spectrometers, each stage of the algorithm leverages modified clustering methods that incorporate both the spatial and spectral information present within the hyperspectral scene. The ultimate output of the process is a classification map that groups spatially adjoining pixels into a number of distinct regions, each of which can be well approximated by a multivariate normal distribution. This output is expected to be useful in various target detection scenarios that require accurate estimates of background statistics; an anecdotal example of improved subpixel target detection is provided at the end of the thesis. Execution time and memory metrics are provided for each stage of the algorithm, along with segmentation proficiency scores as measured against random synthetic data sets. Segmentation results of real-world hyperspectral images are also provided for qualitative analysis. We conclude from the experiments that the algorithm usually performs well in typical overhead views with multiple, spectrally diverse objects to segment, but suffers from reduced accuracy in scenarios where individual regions are exceptionally large or small. Future improvements to the algorithm are recommended to potentially overcome these drawbacks.
Type
Thesis
Description
Series/Report No
Department
Electrical and Computer Engineering (ECE), Electrical and Computer Engineering (ECE)
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Approved for public release; distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.