Conference paper
Automatic change detection in RapidEye data using the combined MAD and kernel MAF methods
The IR-MAD components show changes for a large part of the entire subset. Especially phenological changes in the agricultural fields surrounding the open pit are predominant. As opposed to this, kMAF components focus more on changes in the open-cast mine (and changes due to the two clouds and their shadows, not visible in the zoom).
Ground data were available from bucket-wheel excavators on the extraction side (to the northwest in the open pit) in terms of elevation data for both dates. No ground data were available for changes due to backfill (southeastern part of the open pit) or changes due to mining machines other than the bucket-wheels.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2010 |
Pages: | 3078-3081 |
Proceedings: | 30th International Geoscience and Remote Sensing symposium |
ISBN: | 1424495644 , 1424495652 , 1424495660 , 9781424495641 , 9781424495658 and 9781424495665 |
ISSN: | 21537003 and 21536996 |
Types: | Conference paper |
DOI: | 10.1109/IGARSS.2010.5652663 |
ORCIDs: | Nielsen, Allan Aasbjerg |
Correlation Data mining Fuel processing industries IR-MAD components Internet Kernel MAD methods Pixel Principal component analysis RapidEye data agricultural areas automatic change detection brown coal coal correlation methods image processing iterative methods iteratively reweighted multivariate alteration detection kMAF components kernel MAF methods kernel maximum autocorrelation factor material excavation mine minerals spectral signal