JOURNAL ARTICLE

Unsupervised classification of changes in multispectral satellite imagery

Morton John CantyAllan Aasbjerg Nielsen

Year: 2004 Journal:   Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE Vol: 5573 Pages: 356-356   Publisher: SPIE

Abstract

The statistical techniques of multivariate alteration detection, maximum autocorrelation factor transformation, expectation maximization, fuzzy maximum likelihood estimation and probabilistic label relaxation are combined in a unified scheme to classify changes in multispectral satellite data. An example involving bitemporal LANDSAT TM imagery is given.

Keywords:
Multispectral image Probabilistic logic Computer science Autocorrelation Transformation (genetics) Multivariate statistics Expectation–maximization algorithm Multispectral pattern recognition Artificial intelligence Satellite Pattern recognition (psychology) Statistical model Maximum likelihood Remote sensing Change detection Maximization Mathematics Geology Statistics Machine learning

Metrics

10
Cited By
3.22
FWCI (Field Weighted Citation Impact)
9
Refs
0.92
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Citation History

Topics

Remote-Sensing Image Classification
Physical Sciences →  Engineering →  Media Technology
Geochemistry and Geologic Mapping
Physical Sciences →  Computer Science →  Artificial Intelligence
Spectroscopy and Chemometric Analyses
Physical Sciences →  Chemistry →  Analytical Chemistry
© 2026 ScienceGate Book Chapters — All rights reserved.