Ensemble methods for automatic masking of clouds in AVIRIS imagery

Charles M. Bachmann, Eugene E. Clothiaux, John W. Moore, Keith J. Andreano, Dong Q. Luong

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

We describe the first-phase of an investigation into techniques for automatic cloud masking in remote sensing data. BCM Projection Pursuit networks are explored as a method of unsupervised feature extraction from AVIRIS images. Search vectors in this method discover directions in the data in which the projected data is skew or multi-modal, by minimizing a projection index which depends on higher moments of the projected data distribution. Ensemble methods are used to fuse information from extracted BCM features and to smooth the mapping of these features to classification of image pixels. Ensemble hierarchies contain multiple levels of networks, combining BCM at the lowest levels with backward propagation algorithms, based on cross-entropy minimization, at higher levels in the ensembles. Predicted cloud masks are compared against cloud masks derived from human interpretation; ensembles achieve better overall classification accuracy than single BP networks.

Original languageEnglish (US)
Pages394-403
Number of pages10
StatePublished - Dec 1 1994
EventProceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94) - Ermioni, GREECE
Duration: Sep 6 1994Sep 8 1994

Other

OtherProceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94)
CityErmioni, GREECE
Period9/6/949/8/94

Fingerprint

Masks
Electric fuses
Feature extraction
Remote sensing
Entropy
Pixels

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Bachmann, C. M., Clothiaux, E. E., Moore, J. W., Andreano, K. J., & Luong, D. Q. (1994). Ensemble methods for automatic masking of clouds in AVIRIS imagery. 394-403. Paper presented at Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94), Ermioni, GREECE, .
Bachmann, Charles M. ; Clothiaux, Eugene E. ; Moore, John W. ; Andreano, Keith J. ; Luong, Dong Q. / Ensemble methods for automatic masking of clouds in AVIRIS imagery. Paper presented at Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94), Ermioni, GREECE, .10 p.
@conference{37695ee3f6764efa97b34033f42d4035,
title = "Ensemble methods for automatic masking of clouds in AVIRIS imagery",
abstract = "We describe the first-phase of an investigation into techniques for automatic cloud masking in remote sensing data. BCM Projection Pursuit networks are explored as a method of unsupervised feature extraction from AVIRIS images. Search vectors in this method discover directions in the data in which the projected data is skew or multi-modal, by minimizing a projection index which depends on higher moments of the projected data distribution. Ensemble methods are used to fuse information from extracted BCM features and to smooth the mapping of these features to classification of image pixels. Ensemble hierarchies contain multiple levels of networks, combining BCM at the lowest levels with backward propagation algorithms, based on cross-entropy minimization, at higher levels in the ensembles. Predicted cloud masks are compared against cloud masks derived from human interpretation; ensembles achieve better overall classification accuracy than single BP networks.",
author = "Bachmann, {Charles M.} and Clothiaux, {Eugene E.} and Moore, {John W.} and Andreano, {Keith J.} and Luong, {Dong Q.}",
year = "1994",
month = "12",
day = "1",
language = "English (US)",
pages = "394--403",
note = "Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94) ; Conference date: 06-09-1994 Through 08-09-1994",

}

Bachmann, CM, Clothiaux, EE, Moore, JW, Andreano, KJ & Luong, DQ 1994, 'Ensemble methods for automatic masking of clouds in AVIRIS imagery', Paper presented at Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94), Ermioni, GREECE, 9/6/94 - 9/8/94 pp. 394-403.

Ensemble methods for automatic masking of clouds in AVIRIS imagery. / Bachmann, Charles M.; Clothiaux, Eugene E.; Moore, John W.; Andreano, Keith J.; Luong, Dong Q.

1994. 394-403 Paper presented at Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94), Ermioni, GREECE, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Ensemble methods for automatic masking of clouds in AVIRIS imagery

AU - Bachmann, Charles M.

AU - Clothiaux, Eugene E.

AU - Moore, John W.

AU - Andreano, Keith J.

AU - Luong, Dong Q.

PY - 1994/12/1

Y1 - 1994/12/1

N2 - We describe the first-phase of an investigation into techniques for automatic cloud masking in remote sensing data. BCM Projection Pursuit networks are explored as a method of unsupervised feature extraction from AVIRIS images. Search vectors in this method discover directions in the data in which the projected data is skew or multi-modal, by minimizing a projection index which depends on higher moments of the projected data distribution. Ensemble methods are used to fuse information from extracted BCM features and to smooth the mapping of these features to classification of image pixels. Ensemble hierarchies contain multiple levels of networks, combining BCM at the lowest levels with backward propagation algorithms, based on cross-entropy minimization, at higher levels in the ensembles. Predicted cloud masks are compared against cloud masks derived from human interpretation; ensembles achieve better overall classification accuracy than single BP networks.

AB - We describe the first-phase of an investigation into techniques for automatic cloud masking in remote sensing data. BCM Projection Pursuit networks are explored as a method of unsupervised feature extraction from AVIRIS images. Search vectors in this method discover directions in the data in which the projected data is skew or multi-modal, by minimizing a projection index which depends on higher moments of the projected data distribution. Ensemble methods are used to fuse information from extracted BCM features and to smooth the mapping of these features to classification of image pixels. Ensemble hierarchies contain multiple levels of networks, combining BCM at the lowest levels with backward propagation algorithms, based on cross-entropy minimization, at higher levels in the ensembles. Predicted cloud masks are compared against cloud masks derived from human interpretation; ensembles achieve better overall classification accuracy than single BP networks.

UR - http://www.scopus.com/inward/record.url?scp=0028712632&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028712632&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0028712632

SP - 394

EP - 403

ER -

Bachmann CM, Clothiaux EE, Moore JW, Andreano KJ, Luong DQ. Ensemble methods for automatic masking of clouds in AVIRIS imagery. 1994. Paper presented at Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94), Ermioni, GREECE, .