Pruning projection pursuit models for improved cloud detection in AVIRIS imagery

Charles M. Bachmann, Eugene Edmund Clothiaux, John W. Moore, Dong Q. Luong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A Projection Pursuit (PP) method is used to find structure and reduce the complexity of high-dimensional remote sensing data. Individual Projection Pursuit networks extract features from Gray-Level Difference Vector distributions, Sum and Difference Histograms, or simple normalizations of raw pixel intensity from one of four spectral bands used in the study. A PP pruning technique, based on an online perturbation analysis similar to that of (LeCun, Denker, and Solla, 1990), is used to remove parameters of low significance. The four AVIRIS spectral channels studied here were chosen because of their similarity to those which will be available from the Multi-Angle Imaging Spectro-Radiometer, an instrument which will be on EOS satellites. Ensemble models, which combine features extracted from AVIRIS imagery by multiple Projection Pursuit networks, use backward error propagation with a cross-entropy objective function to obtain pixel classifications. Predicted cloud masks are compared against human interpretation masks.

Original languageEnglish (US)
Title of host publicationNeural Networks for Signal Processing - Proceedings of the IEEE Workshop
PublisherIEEE
Pages361-370
Number of pages10
StatePublished - 1995
EventProceedings of the 5th IEEE Workshop on Neural Networks for Signal Processing (NNSP'95) - Cambridge, MA, USA
Duration: Aug 31 1995Sep 2 1995

Other

OtherProceedings of the 5th IEEE Workshop on Neural Networks for Signal Processing (NNSP'95)
CityCambridge, MA, USA
Period8/31/959/2/95

Fingerprint

Masks
Pixels
Radiometers
Remote sensing
Entropy
Satellites
Imaging techniques

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Bachmann, C. M., Clothiaux, E. E., Moore, J. W., & Luong, D. Q. (1995). Pruning projection pursuit models for improved cloud detection in AVIRIS imagery. In Neural Networks for Signal Processing - Proceedings of the IEEE Workshop (pp. 361-370). IEEE.
Bachmann, Charles M. ; Clothiaux, Eugene Edmund ; Moore, John W. ; Luong, Dong Q. / Pruning projection pursuit models for improved cloud detection in AVIRIS imagery. Neural Networks for Signal Processing - Proceedings of the IEEE Workshop. IEEE, 1995. pp. 361-370
@inproceedings{7257d38fdbb04e6999f56d16069b9e62,
title = "Pruning projection pursuit models for improved cloud detection in AVIRIS imagery",
abstract = "A Projection Pursuit (PP) method is used to find structure and reduce the complexity of high-dimensional remote sensing data. Individual Projection Pursuit networks extract features from Gray-Level Difference Vector distributions, Sum and Difference Histograms, or simple normalizations of raw pixel intensity from one of four spectral bands used in the study. A PP pruning technique, based on an online perturbation analysis similar to that of (LeCun, Denker, and Solla, 1990), is used to remove parameters of low significance. The four AVIRIS spectral channels studied here were chosen because of their similarity to those which will be available from the Multi-Angle Imaging Spectro-Radiometer, an instrument which will be on EOS satellites. Ensemble models, which combine features extracted from AVIRIS imagery by multiple Projection Pursuit networks, use backward error propagation with a cross-entropy objective function to obtain pixel classifications. Predicted cloud masks are compared against human interpretation masks.",
author = "Bachmann, {Charles M.} and Clothiaux, {Eugene Edmund} and Moore, {John W.} and Luong, {Dong Q.}",
year = "1995",
language = "English (US)",
pages = "361--370",
booktitle = "Neural Networks for Signal Processing - Proceedings of the IEEE Workshop",
publisher = "IEEE",

}

Bachmann, CM, Clothiaux, EE, Moore, JW & Luong, DQ 1995, Pruning projection pursuit models for improved cloud detection in AVIRIS imagery. in Neural Networks for Signal Processing - Proceedings of the IEEE Workshop. IEEE, pp. 361-370, Proceedings of the 5th IEEE Workshop on Neural Networks for Signal Processing (NNSP'95), Cambridge, MA, USA, 8/31/95.

Pruning projection pursuit models for improved cloud detection in AVIRIS imagery. / Bachmann, Charles M.; Clothiaux, Eugene Edmund; Moore, John W.; Luong, Dong Q.

Neural Networks for Signal Processing - Proceedings of the IEEE Workshop. IEEE, 1995. p. 361-370.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Pruning projection pursuit models for improved cloud detection in AVIRIS imagery

AU - Bachmann, Charles M.

AU - Clothiaux, Eugene Edmund

AU - Moore, John W.

AU - Luong, Dong Q.

PY - 1995

Y1 - 1995

N2 - A Projection Pursuit (PP) method is used to find structure and reduce the complexity of high-dimensional remote sensing data. Individual Projection Pursuit networks extract features from Gray-Level Difference Vector distributions, Sum and Difference Histograms, or simple normalizations of raw pixel intensity from one of four spectral bands used in the study. A PP pruning technique, based on an online perturbation analysis similar to that of (LeCun, Denker, and Solla, 1990), is used to remove parameters of low significance. The four AVIRIS spectral channels studied here were chosen because of their similarity to those which will be available from the Multi-Angle Imaging Spectro-Radiometer, an instrument which will be on EOS satellites. Ensemble models, which combine features extracted from AVIRIS imagery by multiple Projection Pursuit networks, use backward error propagation with a cross-entropy objective function to obtain pixel classifications. Predicted cloud masks are compared against human interpretation masks.

AB - A Projection Pursuit (PP) method is used to find structure and reduce the complexity of high-dimensional remote sensing data. Individual Projection Pursuit networks extract features from Gray-Level Difference Vector distributions, Sum and Difference Histograms, or simple normalizations of raw pixel intensity from one of four spectral bands used in the study. A PP pruning technique, based on an online perturbation analysis similar to that of (LeCun, Denker, and Solla, 1990), is used to remove parameters of low significance. The four AVIRIS spectral channels studied here were chosen because of their similarity to those which will be available from the Multi-Angle Imaging Spectro-Radiometer, an instrument which will be on EOS satellites. Ensemble models, which combine features extracted from AVIRIS imagery by multiple Projection Pursuit networks, use backward error propagation with a cross-entropy objective function to obtain pixel classifications. Predicted cloud masks are compared against human interpretation masks.

UR - http://www.scopus.com/inward/record.url?scp=0029236232&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029236232&partnerID=8YFLogxK

M3 - Conference contribution

SP - 361

EP - 370

BT - Neural Networks for Signal Processing - Proceedings of the IEEE Workshop

PB - IEEE

ER -

Bachmann CM, Clothiaux EE, Moore JW, Luong DQ. Pruning projection pursuit models for improved cloud detection in AVIRIS imagery. In Neural Networks for Signal Processing - Proceedings of the IEEE Workshop. IEEE. 1995. p. 361-370