Impact of spatial complexity preprocessing on hyperspectral data unmixing

Stefan Robila, Kimberly Pirate, Terrance Hall

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

2 Citations (Scopus)

Abstract

For most of the success, hyperspectral image processing techniques have their origins in multidimensional signal processing with a special emphasis on optimization based on objective functions. Many of these techniques (ICA, PCA, NMF, OSP, etc.) have their basis on collections of single dimensional data and do not take in consideration any spatial based characteristics (such as the shape of objects in the scene). Recently, in an effort to improve the processing results, several approaches that characterize spatial complexity (based on the neighborhood information) were introduced. Our goal is to investigate how spatial complexity based approaches can be employed as preprocessing techniques for other previously established methods. First, we designed for each spatial complexity based technique a step that generates a hyperspectral cube scaled based on spatial information. Next we feed the new cubes to a group of processing techniques such as ICA and PCA. We compare the results between processing the original and the scaled data. We compared the results on the scaled data with the results on the full data. We built upon these initial results by employing additional spatial complexity approaches. We also introduced new hybrid approaches that would embed the spatial complexity step into the main processing stage.

Original languageEnglish
Title of host publicationAlgorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX
Volume8743
DOIs
StatePublished - 12 Aug 2013
EventAlgorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX - Baltimore, MD, United States
Duration: 29 Apr 20132 May 2013

Other

OtherAlgorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX
CountryUnited States
CityBaltimore, MD
Period29/04/132/05/13

Fingerprint

Hyperspectral Data
preprocessing
Preprocessing
Independent component analysis
Processing
Multidimensional Signal Processing
Cube
Signal processing
Image processing
Hyperspectral Image
Spatial Information
image processing
Hybrid Approach
signal processing
Regular hexahedron
Image Processing
Objective function
optimization
Optimization

Keywords

  • Bilateral filtering
  • Hyperspectral data
  • Linear unmixing
  • Spatial complexity

Cite this

Robila, S., Pirate, K., & Hall, T. (2013). Impact of spatial complexity preprocessing on hyperspectral data unmixing. In Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX (Vol. 8743). [874323] https://doi.org/10.1117/12.2015585
Robila, Stefan ; Pirate, Kimberly ; Hall, Terrance. / Impact of spatial complexity preprocessing on hyperspectral data unmixing. Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX. Vol. 8743 2013.
@inproceedings{9cb24566eff549849fbd6bcc55021470,
title = "Impact of spatial complexity preprocessing on hyperspectral data unmixing",
abstract = "For most of the success, hyperspectral image processing techniques have their origins in multidimensional signal processing with a special emphasis on optimization based on objective functions. Many of these techniques (ICA, PCA, NMF, OSP, etc.) have their basis on collections of single dimensional data and do not take in consideration any spatial based characteristics (such as the shape of objects in the scene). Recently, in an effort to improve the processing results, several approaches that characterize spatial complexity (based on the neighborhood information) were introduced. Our goal is to investigate how spatial complexity based approaches can be employed as preprocessing techniques for other previously established methods. First, we designed for each spatial complexity based technique a step that generates a hyperspectral cube scaled based on spatial information. Next we feed the new cubes to a group of processing techniques such as ICA and PCA. We compare the results between processing the original and the scaled data. We compared the results on the scaled data with the results on the full data. We built upon these initial results by employing additional spatial complexity approaches. We also introduced new hybrid approaches that would embed the spatial complexity step into the main processing stage.",
keywords = "Bilateral filtering, Hyperspectral data, Linear unmixing, Spatial complexity",
author = "Stefan Robila and Kimberly Pirate and Terrance Hall",
year = "2013",
month = "8",
day = "12",
doi = "10.1117/12.2015585",
language = "English",
isbn = "9780819495341",
volume = "8743",
booktitle = "Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX",

}

Robila, S, Pirate, K & Hall, T 2013, Impact of spatial complexity preprocessing on hyperspectral data unmixing. in Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX. vol. 8743, 874323, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX, Baltimore, MD, United States, 29/04/13. https://doi.org/10.1117/12.2015585

Impact of spatial complexity preprocessing on hyperspectral data unmixing. / Robila, Stefan; Pirate, Kimberly; Hall, Terrance.

Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX. Vol. 8743 2013. 874323.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

TY - GEN

T1 - Impact of spatial complexity preprocessing on hyperspectral data unmixing

AU - Robila, Stefan

AU - Pirate, Kimberly

AU - Hall, Terrance

PY - 2013/8/12

Y1 - 2013/8/12

N2 - For most of the success, hyperspectral image processing techniques have their origins in multidimensional signal processing with a special emphasis on optimization based on objective functions. Many of these techniques (ICA, PCA, NMF, OSP, etc.) have their basis on collections of single dimensional data and do not take in consideration any spatial based characteristics (such as the shape of objects in the scene). Recently, in an effort to improve the processing results, several approaches that characterize spatial complexity (based on the neighborhood information) were introduced. Our goal is to investigate how spatial complexity based approaches can be employed as preprocessing techniques for other previously established methods. First, we designed for each spatial complexity based technique a step that generates a hyperspectral cube scaled based on spatial information. Next we feed the new cubes to a group of processing techniques such as ICA and PCA. We compare the results between processing the original and the scaled data. We compared the results on the scaled data with the results on the full data. We built upon these initial results by employing additional spatial complexity approaches. We also introduced new hybrid approaches that would embed the spatial complexity step into the main processing stage.

AB - For most of the success, hyperspectral image processing techniques have their origins in multidimensional signal processing with a special emphasis on optimization based on objective functions. Many of these techniques (ICA, PCA, NMF, OSP, etc.) have their basis on collections of single dimensional data and do not take in consideration any spatial based characteristics (such as the shape of objects in the scene). Recently, in an effort to improve the processing results, several approaches that characterize spatial complexity (based on the neighborhood information) were introduced. Our goal is to investigate how spatial complexity based approaches can be employed as preprocessing techniques for other previously established methods. First, we designed for each spatial complexity based technique a step that generates a hyperspectral cube scaled based on spatial information. Next we feed the new cubes to a group of processing techniques such as ICA and PCA. We compare the results between processing the original and the scaled data. We compared the results on the scaled data with the results on the full data. We built upon these initial results by employing additional spatial complexity approaches. We also introduced new hybrid approaches that would embed the spatial complexity step into the main processing stage.

KW - Bilateral filtering

KW - Hyperspectral data

KW - Linear unmixing

KW - Spatial complexity

UR - http://www.scopus.com/inward/record.url?scp=84881189409&partnerID=8YFLogxK

U2 - 10.1117/12.2015585

DO - 10.1117/12.2015585

M3 - Conference contribution

SN - 9780819495341

VL - 8743

BT - Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX

ER -

Robila S, Pirate K, Hall T. Impact of spatial complexity preprocessing on hyperspectral data unmixing. In Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX. Vol. 8743. 2013. 874323 https://doi.org/10.1117/12.2015585