A classifier is described that makes use of multitemporal data to produce an accurate ground cover thematic classification map. Ground cover types are considered as stochastic systems having nonstationary Gaussian processes as input and temporal variation of reflected and emitted electromagnetic energy as output. Then, by assumption that the behavior of these stochastic systems are governed by first-order Markov processes, multitemporal information is utilized. As a result of this approach for characterizing multitemporal data, a new processor, the Markov classifier, is developed. Experimental results from Landsat Multispectral Scanner (MSS) data are included which show significantly better performance than the maximum likelihood and cascade pixel classifiers.
Utilizing multitemporal data by a stochastic model
Verwendung multitemporaler Daten durch ein stochastisches Modell
IEEE Transactions on Geoscience and Remote Sensing ; GE-24 , 5 ; 792-795
1986
4 Seiten, 8 Quellen
Aufsatz (Zeitschrift)
Englisch
Estimation with Multitemporal Measurements
Online Contents | 2010
|Multitemporal SAR Data in Hydrological and Agro-Environmental Applications
British Library Online Contents | 1996
|Cloud Screening and Multitemporal Unmixing of MERIS FR Data
British Library Conference Proceedings | 2007
|Multitemporal change detection for SAR imagery
SPIE | 1999
|