Application of Abundance Map Reference Data for Spectral Unmixing
Reference data (“ground truth”) maps have traditionally been used to assess the accuracy of classification algorithms. These maps typically classify pixels or areas of imagery as belonging to a finite number of ground cover classes, but do not include sub-pixel abundance estimates; therefore, they a...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-08-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/9/8/793 |
_version_ | 1798018433080623104 |
---|---|
author | McKay D. Williams John P. Kerekes Jan van Aardt |
author_facet | McKay D. Williams John P. Kerekes Jan van Aardt |
author_sort | McKay D. Williams |
collection | DOAJ |
description | Reference data (“ground truth”) maps have traditionally been used to assess the accuracy of classification algorithms. These maps typically classify pixels or areas of imagery as belonging to a finite number of ground cover classes, but do not include sub-pixel abundance estimates; therefore, they are not sufficiently detailed to directly assess the performance of spectral unmixing algorithms. Our research aims to efficiently generate, validate, and apply abundance map reference data (AMRD) to airborne remote sensing scenes. Scene-wide AMRD for this study were generated using the remotely sensed reference data (RSRD) technique, which spatially aggregates classification or unmixing results from fine scale imagery (e.g., 1-m GSD) to co-located coarse scale imagery (e.g., 10-m GSD or larger). Validation of the accuracy of these methods was previously performed for generic 10 m × 10 m coarse scale imagery, resulting in AMRD with known accuracy. The purpose of this paper was to apply this previously validated AMRD to specific examples of airborne coarse scale imagery. Application of AMRD involved three main parts: (1) spatial alignment of coarse and fine scale imagery; (2) aggregation of fine scale abundances to produce coarse scale imagery specific AMRD; and (3) demonstration of comparisons between coarse scale unmixing abundances and AMRD. Spatial alignment was performed using our new scene-wide spectral comparison (SWSC) algorithm, which aligned imagery with accuracy approaching the distance of a single fine scale pixel. We compared simple rectangular aggregation to coarse sensor point-spread function (PSF) aggregation, and found that PSF returned lower error, but that rectangular aggregation more accurately estimated true AMRD at ground level. We demonstrated various metrics for comparing unmixing results to AMRD, including several new techniques which adjust for known error in the reference data itself. These metrics indicated that fully constrained linear unmixing of AVIRIS imagery across all three scenes returned an average error of 10.83% per class and pixel. Our reference data research has demonstrated a viable methodology to efficiently generate, validate, and apply AMRD to specific examples of airborne remote sensing imagery, thereby enabling direct quantitative assessment of spectral unmixing performance. |
first_indexed | 2024-04-11T16:24:03Z |
format | Article |
id | doaj.art-03169082615440f3a9cb457d2e89511d |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-04-11T16:24:03Z |
publishDate | 2017-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-03169082615440f3a9cb457d2e89511d2022-12-22T04:14:14ZengMDPI AGRemote Sensing2072-42922017-08-019879310.3390/rs9080793rs9080793Application of Abundance Map Reference Data for Spectral UnmixingMcKay D. Williams0John P. Kerekes1Jan van Aardt2Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, Rochester, NY 14623, USAChester F. Carlson Center for Imaging Science, Rochester Institute of Technology, Rochester, NY 14623, USAChester F. Carlson Center for Imaging Science, Rochester Institute of Technology, Rochester, NY 14623, USAReference data (“ground truth”) maps have traditionally been used to assess the accuracy of classification algorithms. These maps typically classify pixels or areas of imagery as belonging to a finite number of ground cover classes, but do not include sub-pixel abundance estimates; therefore, they are not sufficiently detailed to directly assess the performance of spectral unmixing algorithms. Our research aims to efficiently generate, validate, and apply abundance map reference data (AMRD) to airborne remote sensing scenes. Scene-wide AMRD for this study were generated using the remotely sensed reference data (RSRD) technique, which spatially aggregates classification or unmixing results from fine scale imagery (e.g., 1-m GSD) to co-located coarse scale imagery (e.g., 10-m GSD or larger). Validation of the accuracy of these methods was previously performed for generic 10 m × 10 m coarse scale imagery, resulting in AMRD with known accuracy. The purpose of this paper was to apply this previously validated AMRD to specific examples of airborne coarse scale imagery. Application of AMRD involved three main parts: (1) spatial alignment of coarse and fine scale imagery; (2) aggregation of fine scale abundances to produce coarse scale imagery specific AMRD; and (3) demonstration of comparisons between coarse scale unmixing abundances and AMRD. Spatial alignment was performed using our new scene-wide spectral comparison (SWSC) algorithm, which aligned imagery with accuracy approaching the distance of a single fine scale pixel. We compared simple rectangular aggregation to coarse sensor point-spread function (PSF) aggregation, and found that PSF returned lower error, but that rectangular aggregation more accurately estimated true AMRD at ground level. We demonstrated various metrics for comparing unmixing results to AMRD, including several new techniques which adjust for known error in the reference data itself. These metrics indicated that fully constrained linear unmixing of AVIRIS imagery across all three scenes returned an average error of 10.83% per class and pixel. Our reference data research has demonstrated a viable methodology to efficiently generate, validate, and apply AMRD to specific examples of airborne remote sensing imagery, thereby enabling direct quantitative assessment of spectral unmixing performance.https://www.mdpi.com/2072-4292/9/8/793reference dataground truthimaging spectroscopyhyperspectralunmixingclassificationabundance mapsubpixel |
spellingShingle | McKay D. Williams John P. Kerekes Jan van Aardt Application of Abundance Map Reference Data for Spectral Unmixing Remote Sensing reference data ground truth imaging spectroscopy hyperspectral unmixing classification abundance map subpixel |
title | Application of Abundance Map Reference Data for Spectral Unmixing |
title_full | Application of Abundance Map Reference Data for Spectral Unmixing |
title_fullStr | Application of Abundance Map Reference Data for Spectral Unmixing |
title_full_unstemmed | Application of Abundance Map Reference Data for Spectral Unmixing |
title_short | Application of Abundance Map Reference Data for Spectral Unmixing |
title_sort | application of abundance map reference data for spectral unmixing |
topic | reference data ground truth imaging spectroscopy hyperspectral unmixing classification abundance map subpixel |
url | https://www.mdpi.com/2072-4292/9/8/793 |
work_keys_str_mv | AT mckaydwilliams applicationofabundancemapreferencedataforspectralunmixing AT johnpkerekes applicationofabundancemapreferencedataforspectralunmixing AT janvanaardt applicationofabundancemapreferencedataforspectralunmixing |