Vitenskapelig Kapittel/Artikkel/Konferanseartikkel   2011

Salberg, Arnt-Børre; Trier, Øivind Due

Publikasjonsdetaljer

Sider:

2322–2325

År:

2011

Lenker:

FULLTEKST: http://dx.doi.org/10.1109/IGARSS.2011.6049674
DOI: doi.org/10.1109/igarss.2011.6049674

Del av: Geoscience and Remote Sensing Symposium (IGARSS), 2011 IEEE International (IEEE Press, 2011)

Remote sensing plays a key role in monitoring the quality and coverage of the tropical forests, and for early warning of il legal logging and forest degradation. We propose a hidden Markov model based methodology for analyzing time series of remote sensing images of tropical forests with the aim of detecting changes in the spatial coverage of the forest. Two different methods are investigated; the most likely state sequence and the minimum probability of state error. The pro posed methodology is demonstrated on a time series of Land sat TM images covering tropical forest in Brazil. The results are evaluated by visual inspection, and show that for change detection the most likely state sequence method is recommended.